Training in progress, epoch 1, checkpoint
Browse files- checkpoint-305280/config.json +28 -0
- checkpoint-305280/generation_config.json +7 -0
- checkpoint-305280/optimizer.pt +3 -0
- checkpoint-305280/pytorch_model.bin +3 -0
- checkpoint-305280/rng_state.pth +3 -0
- checkpoint-305280/scheduler.pt +3 -0
- checkpoint-305280/special_tokens_map.json +5 -0
- checkpoint-305280/tokenizer.json +0 -0
- checkpoint-305280/tokenizer_config.json +12 -0
- checkpoint-305280/trainer_state.json +3633 -0
- checkpoint-305280/training_args.bin +3 -0
    	
        checkpoint-305280/config.json
    ADDED
    
    | @@ -0,0 +1,28 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_remove_final_layer_norm": false,
         | 
| 3 | 
            +
              "activation_function": "relu",
         | 
| 4 | 
            +
              "architectures": [
         | 
| 5 | 
            +
                "OPTForCausalLM"
         | 
| 6 | 
            +
              ],
         | 
| 7 | 
            +
              "attention_dropout": 0.0,
         | 
| 8 | 
            +
              "bos_token_id": 2,
         | 
| 9 | 
            +
              "do_layer_norm_before": true,
         | 
| 10 | 
            +
              "dropout": 0.1,
         | 
| 11 | 
            +
              "enable_bias": true,
         | 
| 12 | 
            +
              "eos_token_id": 2,
         | 
| 13 | 
            +
              "ffn_dim": 768,
         | 
| 14 | 
            +
              "hidden_size": 768,
         | 
| 15 | 
            +
              "init_std": 0.02,
         | 
| 16 | 
            +
              "layer_norm_elementwise_affine": true,
         | 
| 17 | 
            +
              "layerdrop": 0.0,
         | 
| 18 | 
            +
              "max_position_embeddings": 512,
         | 
| 19 | 
            +
              "model_type": "opt",
         | 
| 20 | 
            +
              "num_attention_heads": 8,
         | 
| 21 | 
            +
              "num_hidden_layers": 8,
         | 
| 22 | 
            +
              "pad_token_id": 1,
         | 
| 23 | 
            +
              "torch_dtype": "float32",
         | 
| 24 | 
            +
              "transformers_version": "4.33.3",
         | 
| 25 | 
            +
              "use_cache": true,
         | 
| 26 | 
            +
              "vocab_size": 50002,
         | 
| 27 | 
            +
              "word_embed_proj_dim": 768
         | 
| 28 | 
            +
            }
         | 
    	
        checkpoint-305280/generation_config.json
    ADDED
    
    | @@ -0,0 +1,7 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "_from_model_config": true,
         | 
| 3 | 
            +
              "bos_token_id": 2,
         | 
| 4 | 
            +
              "eos_token_id": 2,
         | 
| 5 | 
            +
              "pad_token_id": 1,
         | 
| 6 | 
            +
              "transformers_version": "4.33.3"
         | 
| 7 | 
            +
            }
         | 
    	
        checkpoint-305280/optimizer.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:f9d0d40b588fc893e6ce7bacd785cd87f93f095c489535a7d88bf2de78187fc2
         | 
| 3 | 
            +
            size 537476677
         | 
    	
        checkpoint-305280/pytorch_model.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:b5d6a3e34c8357e7748d06c22256e14b444dfd6f8f83d363d4220ecdd548af61
         | 
| 3 | 
            +
            size 268727709
         | 
    	
        checkpoint-305280/rng_state.pth
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:a7b0f5174890e56089982e430202b1560c33db3ea32e0b705101badf72e01344
         | 
| 3 | 
            +
            size 14575
         | 
    	
        checkpoint-305280/scheduler.pt
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:6a291a88b367329231482d0e7a7640f0fb5380bbda194b41ad69d8b3c4ef90d9
         | 
| 3 | 
            +
            size 627
         | 
    	
        checkpoint-305280/special_tokens_map.json
    ADDED
    
    | @@ -0,0 +1,5 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "eos_token": "<eos>",
         | 
| 3 | 
            +
              "pad_token": "<pad>",
         | 
| 4 | 
            +
              "unk_token": "<unk>"
         | 
| 5 | 
            +
            }
         | 
    	
        checkpoint-305280/tokenizer.json
    ADDED
    
    | The diff for this file is too large to render. 
		See raw diff | 
|  | 
    	
        checkpoint-305280/tokenizer_config.json
    ADDED
    
    | @@ -0,0 +1,12 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "clean_up_tokenization_spaces": true,
         | 
| 3 | 
            +
              "eos_token": "<eos>",
         | 
| 4 | 
            +
              "max_length": null,
         | 
| 5 | 
            +
              "model_max_length": 512,
         | 
| 6 | 
            +
              "pad_to_multiple_of": null,
         | 
| 7 | 
            +
              "pad_token": "<pad>",
         | 
| 8 | 
            +
              "pad_token_type_id": 0,
         | 
| 9 | 
            +
              "padding_side": "right",
         | 
| 10 | 
            +
              "tokenizer_class": "PreTrainedTokenizerFast",
         | 
| 11 | 
            +
              "unk_token": "<unk>"
         | 
| 12 | 
            +
            }
         | 
    	
        checkpoint-305280/trainer_state.json
    ADDED
    
    | @@ -0,0 +1,3633 @@ | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            {
         | 
| 2 | 
            +
              "best_metric": 3.9126405715942383,
         | 
| 3 | 
            +
              "best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/existential-there-quantifier/transformer/4/checkpoints/checkpoint-305280",
         | 
| 4 | 
            +
              "epoch": 1.0250006060157382,
         | 
| 5 | 
            +
              "eval_steps": 10,
         | 
| 6 | 
            +
              "global_step": 305280,
         | 
| 7 | 
            +
              "is_hyper_param_search": false,
         | 
| 8 | 
            +
              "is_local_process_zero": true,
         | 
| 9 | 
            +
              "is_world_process_zero": true,
         | 
| 10 | 
            +
              "log_history": [
         | 
| 11 | 
            +
                {
         | 
| 12 | 
            +
                  "epoch": 0.0,
         | 
| 13 | 
            +
                  "learning_rate": 4.999998362119627e-05,
         | 
| 14 | 
            +
                  "loss": 11.0368,
         | 
| 15 | 
            +
                  "step": 1
         | 
| 16 | 
            +
                },
         | 
| 17 | 
            +
                {
         | 
| 18 | 
            +
                  "epoch": 0.0,
         | 
| 19 | 
            +
                  "learning_rate": 4.999161405248948e-05,
         | 
| 20 | 
            +
                  "loss": 6.8134,
         | 
| 21 | 
            +
                  "step": 512
         | 
| 22 | 
            +
                },
         | 
| 23 | 
            +
                {
         | 
| 24 | 
            +
                  "epoch": 0.0,
         | 
| 25 | 
            +
                  "learning_rate": 4.998322810497896e-05,
         | 
| 26 | 
            +
                  "loss": 6.1877,
         | 
| 27 | 
            +
                  "step": 1024
         | 
| 28 | 
            +
                },
         | 
| 29 | 
            +
                {
         | 
| 30 | 
            +
                  "epoch": 0.0,
         | 
| 31 | 
            +
                  "learning_rate": 4.997484215746844e-05,
         | 
| 32 | 
            +
                  "loss": 5.9788,
         | 
| 33 | 
            +
                  "step": 1536
         | 
| 34 | 
            +
                },
         | 
| 35 | 
            +
                {
         | 
| 36 | 
            +
                  "epoch": 0.0,
         | 
| 37 | 
            +
                  "learning_rate": 4.996645620995792e-05,
         | 
| 38 | 
            +
                  "loss": 5.8108,
         | 
| 39 | 
            +
                  "step": 2048
         | 
| 40 | 
            +
                },
         | 
| 41 | 
            +
                {
         | 
| 42 | 
            +
                  "epoch": 0.0,
         | 
| 43 | 
            +
                  "learning_rate": 4.99580702624474e-05,
         | 
| 44 | 
            +
                  "loss": 5.7032,
         | 
| 45 | 
            +
                  "step": 2560
         | 
| 46 | 
            +
                },
         | 
| 47 | 
            +
                {
         | 
| 48 | 
            +
                  "epoch": 0.0,
         | 
| 49 | 
            +
                  "learning_rate": 4.994968431493688e-05,
         | 
| 50 | 
            +
                  "loss": 5.5999,
         | 
| 51 | 
            +
                  "step": 3072
         | 
| 52 | 
            +
                },
         | 
| 53 | 
            +
                {
         | 
| 54 | 
            +
                  "epoch": 0.0,
         | 
| 55 | 
            +
                  "learning_rate": 4.994129836742636e-05,
         | 
| 56 | 
            +
                  "loss": 5.5361,
         | 
| 57 | 
            +
                  "step": 3584
         | 
| 58 | 
            +
                },
         | 
| 59 | 
            +
                {
         | 
| 60 | 
            +
                  "epoch": 0.0,
         | 
| 61 | 
            +
                  "learning_rate": 4.993291241991584e-05,
         | 
| 62 | 
            +
                  "loss": 5.4453,
         | 
| 63 | 
            +
                  "step": 4096
         | 
| 64 | 
            +
                },
         | 
| 65 | 
            +
                {
         | 
| 66 | 
            +
                  "epoch": 0.0,
         | 
| 67 | 
            +
                  "learning_rate": 4.992452647240532e-05,
         | 
| 68 | 
            +
                  "loss": 5.4008,
         | 
| 69 | 
            +
                  "step": 4608
         | 
| 70 | 
            +
                },
         | 
| 71 | 
            +
                {
         | 
| 72 | 
            +
                  "epoch": 0.0,
         | 
| 73 | 
            +
                  "learning_rate": 4.99161405248948e-05,
         | 
| 74 | 
            +
                  "loss": 5.3507,
         | 
| 75 | 
            +
                  "step": 5120
         | 
| 76 | 
            +
                },
         | 
| 77 | 
            +
                {
         | 
| 78 | 
            +
                  "epoch": 0.0,
         | 
| 79 | 
            +
                  "learning_rate": 4.990775457738428e-05,
         | 
| 80 | 
            +
                  "loss": 5.3098,
         | 
| 81 | 
            +
                  "step": 5632
         | 
| 82 | 
            +
                },
         | 
| 83 | 
            +
                {
         | 
| 84 | 
            +
                  "epoch": 0.0,
         | 
| 85 | 
            +
                  "learning_rate": 4.989936862987376e-05,
         | 
| 86 | 
            +
                  "loss": 5.2582,
         | 
| 87 | 
            +
                  "step": 6144
         | 
| 88 | 
            +
                },
         | 
| 89 | 
            +
                {
         | 
| 90 | 
            +
                  "epoch": 0.0,
         | 
| 91 | 
            +
                  "learning_rate": 4.989099906116697e-05,
         | 
| 92 | 
            +
                  "loss": 5.2103,
         | 
| 93 | 
            +
                  "step": 6656
         | 
| 94 | 
            +
                },
         | 
| 95 | 
            +
                {
         | 
| 96 | 
            +
                  "epoch": 0.0,
         | 
| 97 | 
            +
                  "learning_rate": 4.988261311365645e-05,
         | 
| 98 | 
            +
                  "loss": 5.1687,
         | 
| 99 | 
            +
                  "step": 7168
         | 
| 100 | 
            +
                },
         | 
| 101 | 
            +
                {
         | 
| 102 | 
            +
                  "epoch": 0.0,
         | 
| 103 | 
            +
                  "learning_rate": 4.987422716614593e-05,
         | 
| 104 | 
            +
                  "loss": 5.1357,
         | 
| 105 | 
            +
                  "step": 7680
         | 
| 106 | 
            +
                },
         | 
| 107 | 
            +
                {
         | 
| 108 | 
            +
                  "epoch": 0.0,
         | 
| 109 | 
            +
                  "learning_rate": 4.986584121863541e-05,
         | 
| 110 | 
            +
                  "loss": 5.1055,
         | 
| 111 | 
            +
                  "step": 8192
         | 
| 112 | 
            +
                },
         | 
| 113 | 
            +
                {
         | 
| 114 | 
            +
                  "epoch": 0.0,
         | 
| 115 | 
            +
                  "learning_rate": 4.985745527112489e-05,
         | 
| 116 | 
            +
                  "loss": 5.0901,
         | 
| 117 | 
            +
                  "step": 8704
         | 
| 118 | 
            +
                },
         | 
| 119 | 
            +
                {
         | 
| 120 | 
            +
                  "epoch": 0.0,
         | 
| 121 | 
            +
                  "learning_rate": 4.984906932361437e-05,
         | 
| 122 | 
            +
                  "loss": 5.0477,
         | 
| 123 | 
            +
                  "step": 9216
         | 
| 124 | 
            +
                },
         | 
| 125 | 
            +
                {
         | 
| 126 | 
            +
                  "epoch": 0.0,
         | 
| 127 | 
            +
                  "learning_rate": 4.984068337610385e-05,
         | 
| 128 | 
            +
                  "loss": 5.0274,
         | 
| 129 | 
            +
                  "step": 9728
         | 
| 130 | 
            +
                },
         | 
| 131 | 
            +
                {
         | 
| 132 | 
            +
                  "epoch": 0.0,
         | 
| 133 | 
            +
                  "learning_rate": 4.983229742859333e-05,
         | 
| 134 | 
            +
                  "loss": 5.0154,
         | 
| 135 | 
            +
                  "step": 10240
         | 
| 136 | 
            +
                },
         | 
| 137 | 
            +
                {
         | 
| 138 | 
            +
                  "epoch": 0.0,
         | 
| 139 | 
            +
                  "learning_rate": 4.9823927859886547e-05,
         | 
| 140 | 
            +
                  "loss": 4.9707,
         | 
| 141 | 
            +
                  "step": 10752
         | 
| 142 | 
            +
                },
         | 
| 143 | 
            +
                {
         | 
| 144 | 
            +
                  "epoch": 0.0,
         | 
| 145 | 
            +
                  "learning_rate": 4.9815541912376026e-05,
         | 
| 146 | 
            +
                  "loss": 4.9456,
         | 
| 147 | 
            +
                  "step": 11264
         | 
| 148 | 
            +
                },
         | 
| 149 | 
            +
                {
         | 
| 150 | 
            +
                  "epoch": 0.0,
         | 
| 151 | 
            +
                  "learning_rate": 4.9807155964865506e-05,
         | 
| 152 | 
            +
                  "loss": 4.9307,
         | 
| 153 | 
            +
                  "step": 11776
         | 
| 154 | 
            +
                },
         | 
| 155 | 
            +
                {
         | 
| 156 | 
            +
                  "epoch": 0.0,
         | 
| 157 | 
            +
                  "learning_rate": 4.9798770017354986e-05,
         | 
| 158 | 
            +
                  "loss": 4.9209,
         | 
| 159 | 
            +
                  "step": 12288
         | 
| 160 | 
            +
                },
         | 
| 161 | 
            +
                {
         | 
| 162 | 
            +
                  "epoch": 0.0,
         | 
| 163 | 
            +
                  "learning_rate": 4.9790400448648195e-05,
         | 
| 164 | 
            +
                  "loss": 4.8868,
         | 
| 165 | 
            +
                  "step": 12800
         | 
| 166 | 
            +
                },
         | 
| 167 | 
            +
                {
         | 
| 168 | 
            +
                  "epoch": 0.0,
         | 
| 169 | 
            +
                  "learning_rate": 4.9782030879941405e-05,
         | 
| 170 | 
            +
                  "loss": 4.8669,
         | 
| 171 | 
            +
                  "step": 13312
         | 
| 172 | 
            +
                },
         | 
| 173 | 
            +
                {
         | 
| 174 | 
            +
                  "epoch": 0.0,
         | 
| 175 | 
            +
                  "learning_rate": 4.9773644932430885e-05,
         | 
| 176 | 
            +
                  "loss": 4.8606,
         | 
| 177 | 
            +
                  "step": 13824
         | 
| 178 | 
            +
                },
         | 
| 179 | 
            +
                {
         | 
| 180 | 
            +
                  "epoch": 0.0,
         | 
| 181 | 
            +
                  "learning_rate": 4.9765258984920364e-05,
         | 
| 182 | 
            +
                  "loss": 4.8385,
         | 
| 183 | 
            +
                  "step": 14336
         | 
| 184 | 
            +
                },
         | 
| 185 | 
            +
                {
         | 
| 186 | 
            +
                  "epoch": 0.0,
         | 
| 187 | 
            +
                  "learning_rate": 4.9756873037409844e-05,
         | 
| 188 | 
            +
                  "loss": 4.8117,
         | 
| 189 | 
            +
                  "step": 14848
         | 
| 190 | 
            +
                },
         | 
| 191 | 
            +
                {
         | 
| 192 | 
            +
                  "epoch": 0.01,
         | 
| 193 | 
            +
                  "learning_rate": 4.9748487089899324e-05,
         | 
| 194 | 
            +
                  "loss": 4.7945,
         | 
| 195 | 
            +
                  "step": 15360
         | 
| 196 | 
            +
                },
         | 
| 197 | 
            +
                {
         | 
| 198 | 
            +
                  "epoch": 0.01,
         | 
| 199 | 
            +
                  "learning_rate": 4.9740117521192533e-05,
         | 
| 200 | 
            +
                  "loss": 4.7903,
         | 
| 201 | 
            +
                  "step": 15872
         | 
| 202 | 
            +
                },
         | 
| 203 | 
            +
                {
         | 
| 204 | 
            +
                  "epoch": 0.01,
         | 
| 205 | 
            +
                  "learning_rate": 4.9731731573682013e-05,
         | 
| 206 | 
            +
                  "loss": 4.7787,
         | 
| 207 | 
            +
                  "step": 16384
         | 
| 208 | 
            +
                },
         | 
| 209 | 
            +
                {
         | 
| 210 | 
            +
                  "epoch": 0.01,
         | 
| 211 | 
            +
                  "learning_rate": 4.97233456261715e-05,
         | 
| 212 | 
            +
                  "loss": 4.7747,
         | 
| 213 | 
            +
                  "step": 16896
         | 
| 214 | 
            +
                },
         | 
| 215 | 
            +
                {
         | 
| 216 | 
            +
                  "epoch": 0.01,
         | 
| 217 | 
            +
                  "learning_rate": 4.971495967866098e-05,
         | 
| 218 | 
            +
                  "loss": 4.7513,
         | 
| 219 | 
            +
                  "step": 17408
         | 
| 220 | 
            +
                },
         | 
| 221 | 
            +
                {
         | 
| 222 | 
            +
                  "epoch": 0.01,
         | 
| 223 | 
            +
                  "learning_rate": 4.970657373115046e-05,
         | 
| 224 | 
            +
                  "loss": 4.736,
         | 
| 225 | 
            +
                  "step": 17920
         | 
| 226 | 
            +
                },
         | 
| 227 | 
            +
                {
         | 
| 228 | 
            +
                  "epoch": 0.01,
         | 
| 229 | 
            +
                  "learning_rate": 4.969820416244367e-05,
         | 
| 230 | 
            +
                  "loss": 4.7379,
         | 
| 231 | 
            +
                  "step": 18432
         | 
| 232 | 
            +
                },
         | 
| 233 | 
            +
                {
         | 
| 234 | 
            +
                  "epoch": 0.01,
         | 
| 235 | 
            +
                  "learning_rate": 4.968981821493315e-05,
         | 
| 236 | 
            +
                  "loss": 4.7031,
         | 
| 237 | 
            +
                  "step": 18944
         | 
| 238 | 
            +
                },
         | 
| 239 | 
            +
                {
         | 
| 240 | 
            +
                  "epoch": 0.01,
         | 
| 241 | 
            +
                  "learning_rate": 4.968143226742263e-05,
         | 
| 242 | 
            +
                  "loss": 4.6961,
         | 
| 243 | 
            +
                  "step": 19456
         | 
| 244 | 
            +
                },
         | 
| 245 | 
            +
                {
         | 
| 246 | 
            +
                  "epoch": 0.01,
         | 
| 247 | 
            +
                  "learning_rate": 4.967304631991211e-05,
         | 
| 248 | 
            +
                  "loss": 4.6831,
         | 
| 249 | 
            +
                  "step": 19968
         | 
| 250 | 
            +
                },
         | 
| 251 | 
            +
                {
         | 
| 252 | 
            +
                  "epoch": 0.01,
         | 
| 253 | 
            +
                  "learning_rate": 4.966466037240159e-05,
         | 
| 254 | 
            +
                  "loss": 4.6832,
         | 
| 255 | 
            +
                  "step": 20480
         | 
| 256 | 
            +
                },
         | 
| 257 | 
            +
                {
         | 
| 258 | 
            +
                  "epoch": 0.01,
         | 
| 259 | 
            +
                  "learning_rate": 4.965627442489107e-05,
         | 
| 260 | 
            +
                  "loss": 4.6604,
         | 
| 261 | 
            +
                  "step": 20992
         | 
| 262 | 
            +
                },
         | 
| 263 | 
            +
                {
         | 
| 264 | 
            +
                  "epoch": 0.01,
         | 
| 265 | 
            +
                  "learning_rate": 4.964788847738054e-05,
         | 
| 266 | 
            +
                  "loss": 4.672,
         | 
| 267 | 
            +
                  "step": 21504
         | 
| 268 | 
            +
                },
         | 
| 269 | 
            +
                {
         | 
| 270 | 
            +
                  "epoch": 0.01,
         | 
| 271 | 
            +
                  "learning_rate": 4.963950252987002e-05,
         | 
| 272 | 
            +
                  "loss": 4.6425,
         | 
| 273 | 
            +
                  "step": 22016
         | 
| 274 | 
            +
                },
         | 
| 275 | 
            +
                {
         | 
| 276 | 
            +
                  "epoch": 0.01,
         | 
| 277 | 
            +
                  "learning_rate": 4.963113296116324e-05,
         | 
| 278 | 
            +
                  "loss": 4.6463,
         | 
| 279 | 
            +
                  "step": 22528
         | 
| 280 | 
            +
                },
         | 
| 281 | 
            +
                {
         | 
| 282 | 
            +
                  "epoch": 0.01,
         | 
| 283 | 
            +
                  "learning_rate": 4.962274701365272e-05,
         | 
| 284 | 
            +
                  "loss": 4.6366,
         | 
| 285 | 
            +
                  "step": 23040
         | 
| 286 | 
            +
                },
         | 
| 287 | 
            +
                {
         | 
| 288 | 
            +
                  "epoch": 0.01,
         | 
| 289 | 
            +
                  "learning_rate": 4.96143610661422e-05,
         | 
| 290 | 
            +
                  "loss": 4.6276,
         | 
| 291 | 
            +
                  "step": 23552
         | 
| 292 | 
            +
                },
         | 
| 293 | 
            +
                {
         | 
| 294 | 
            +
                  "epoch": 0.01,
         | 
| 295 | 
            +
                  "learning_rate": 4.960597511863168e-05,
         | 
| 296 | 
            +
                  "loss": 4.6242,
         | 
| 297 | 
            +
                  "step": 24064
         | 
| 298 | 
            +
                },
         | 
| 299 | 
            +
                {
         | 
| 300 | 
            +
                  "epoch": 0.01,
         | 
| 301 | 
            +
                  "learning_rate": 4.959758917112116e-05,
         | 
| 302 | 
            +
                  "loss": 4.5995,
         | 
| 303 | 
            +
                  "step": 24576
         | 
| 304 | 
            +
                },
         | 
| 305 | 
            +
                {
         | 
| 306 | 
            +
                  "epoch": 0.01,
         | 
| 307 | 
            +
                  "learning_rate": 4.9589219602414374e-05,
         | 
| 308 | 
            +
                  "loss": 4.587,
         | 
| 309 | 
            +
                  "step": 25088
         | 
| 310 | 
            +
                },
         | 
| 311 | 
            +
                {
         | 
| 312 | 
            +
                  "epoch": 0.01,
         | 
| 313 | 
            +
                  "learning_rate": 4.958085003370758e-05,
         | 
| 314 | 
            +
                  "loss": 4.6012,
         | 
| 315 | 
            +
                  "step": 25600
         | 
| 316 | 
            +
                },
         | 
| 317 | 
            +
                {
         | 
| 318 | 
            +
                  "epoch": 0.01,
         | 
| 319 | 
            +
                  "learning_rate": 4.957246408619706e-05,
         | 
| 320 | 
            +
                  "loss": 4.5854,
         | 
| 321 | 
            +
                  "step": 26112
         | 
| 322 | 
            +
                },
         | 
| 323 | 
            +
                {
         | 
| 324 | 
            +
                  "epoch": 0.01,
         | 
| 325 | 
            +
                  "learning_rate": 4.956407813868654e-05,
         | 
| 326 | 
            +
                  "loss": 4.5687,
         | 
| 327 | 
            +
                  "step": 26624
         | 
| 328 | 
            +
                },
         | 
| 329 | 
            +
                {
         | 
| 330 | 
            +
                  "epoch": 0.01,
         | 
| 331 | 
            +
                  "learning_rate": 4.9555692191176016e-05,
         | 
| 332 | 
            +
                  "loss": 4.5577,
         | 
| 333 | 
            +
                  "step": 27136
         | 
| 334 | 
            +
                },
         | 
| 335 | 
            +
                {
         | 
| 336 | 
            +
                  "epoch": 0.01,
         | 
| 337 | 
            +
                  "learning_rate": 4.954732262246923e-05,
         | 
| 338 | 
            +
                  "loss": 4.5648,
         | 
| 339 | 
            +
                  "step": 27648
         | 
| 340 | 
            +
                },
         | 
| 341 | 
            +
                {
         | 
| 342 | 
            +
                  "epoch": 0.01,
         | 
| 343 | 
            +
                  "learning_rate": 4.953893667495871e-05,
         | 
| 344 | 
            +
                  "loss": 4.5469,
         | 
| 345 | 
            +
                  "step": 28160
         | 
| 346 | 
            +
                },
         | 
| 347 | 
            +
                {
         | 
| 348 | 
            +
                  "epoch": 0.01,
         | 
| 349 | 
            +
                  "learning_rate": 4.953055072744819e-05,
         | 
| 350 | 
            +
                  "loss": 4.5599,
         | 
| 351 | 
            +
                  "step": 28672
         | 
| 352 | 
            +
                },
         | 
| 353 | 
            +
                {
         | 
| 354 | 
            +
                  "epoch": 0.01,
         | 
| 355 | 
            +
                  "learning_rate": 4.952216477993767e-05,
         | 
| 356 | 
            +
                  "loss": 4.5342,
         | 
| 357 | 
            +
                  "step": 29184
         | 
| 358 | 
            +
                },
         | 
| 359 | 
            +
                {
         | 
| 360 | 
            +
                  "epoch": 0.01,
         | 
| 361 | 
            +
                  "learning_rate": 4.951377883242715e-05,
         | 
| 362 | 
            +
                  "loss": 4.5313,
         | 
| 363 | 
            +
                  "step": 29696
         | 
| 364 | 
            +
                },
         | 
| 365 | 
            +
                {
         | 
| 366 | 
            +
                  "epoch": 0.01,
         | 
| 367 | 
            +
                  "learning_rate": 4.950539288491663e-05,
         | 
| 368 | 
            +
                  "loss": 4.535,
         | 
| 369 | 
            +
                  "step": 30208
         | 
| 370 | 
            +
                },
         | 
| 371 | 
            +
                {
         | 
| 372 | 
            +
                  "epoch": 0.01,
         | 
| 373 | 
            +
                  "learning_rate": 4.949700693740611e-05,
         | 
| 374 | 
            +
                  "loss": 4.5165,
         | 
| 375 | 
            +
                  "step": 30720
         | 
| 376 | 
            +
                },
         | 
| 377 | 
            +
                {
         | 
| 378 | 
            +
                  "epoch": 0.01,
         | 
| 379 | 
            +
                  "learning_rate": 4.948862098989559e-05,
         | 
| 380 | 
            +
                  "loss": 4.4989,
         | 
| 381 | 
            +
                  "step": 31232
         | 
| 382 | 
            +
                },
         | 
| 383 | 
            +
                {
         | 
| 384 | 
            +
                  "epoch": 0.01,
         | 
| 385 | 
            +
                  "learning_rate": 4.94802514211888e-05,
         | 
| 386 | 
            +
                  "loss": 4.5047,
         | 
| 387 | 
            +
                  "step": 31744
         | 
| 388 | 
            +
                },
         | 
| 389 | 
            +
                {
         | 
| 390 | 
            +
                  "epoch": 0.01,
         | 
| 391 | 
            +
                  "learning_rate": 4.947186547367828e-05,
         | 
| 392 | 
            +
                  "loss": 4.488,
         | 
| 393 | 
            +
                  "step": 32256
         | 
| 394 | 
            +
                },
         | 
| 395 | 
            +
                {
         | 
| 396 | 
            +
                  "epoch": 0.01,
         | 
| 397 | 
            +
                  "learning_rate": 4.946347952616776e-05,
         | 
| 398 | 
            +
                  "loss": 4.4898,
         | 
| 399 | 
            +
                  "step": 32768
         | 
| 400 | 
            +
                },
         | 
| 401 | 
            +
                {
         | 
| 402 | 
            +
                  "epoch": 0.01,
         | 
| 403 | 
            +
                  "learning_rate": 4.945509357865724e-05,
         | 
| 404 | 
            +
                  "loss": 4.4974,
         | 
| 405 | 
            +
                  "step": 33280
         | 
| 406 | 
            +
                },
         | 
| 407 | 
            +
                {
         | 
| 408 | 
            +
                  "epoch": 0.01,
         | 
| 409 | 
            +
                  "learning_rate": 4.944670763114672e-05,
         | 
| 410 | 
            +
                  "loss": 4.4911,
         | 
| 411 | 
            +
                  "step": 33792
         | 
| 412 | 
            +
                },
         | 
| 413 | 
            +
                {
         | 
| 414 | 
            +
                  "epoch": 0.01,
         | 
| 415 | 
            +
                  "learning_rate": 4.943833806243993e-05,
         | 
| 416 | 
            +
                  "loss": 4.4782,
         | 
| 417 | 
            +
                  "step": 34304
         | 
| 418 | 
            +
                },
         | 
| 419 | 
            +
                {
         | 
| 420 | 
            +
                  "epoch": 0.01,
         | 
| 421 | 
            +
                  "learning_rate": 4.942995211492941e-05,
         | 
| 422 | 
            +
                  "loss": 4.4663,
         | 
| 423 | 
            +
                  "step": 34816
         | 
| 424 | 
            +
                },
         | 
| 425 | 
            +
                {
         | 
| 426 | 
            +
                  "epoch": 0.01,
         | 
| 427 | 
            +
                  "learning_rate": 4.942156616741889e-05,
         | 
| 428 | 
            +
                  "loss": 4.4584,
         | 
| 429 | 
            +
                  "step": 35328
         | 
| 430 | 
            +
                },
         | 
| 431 | 
            +
                {
         | 
| 432 | 
            +
                  "epoch": 0.01,
         | 
| 433 | 
            +
                  "learning_rate": 4.941318021990837e-05,
         | 
| 434 | 
            +
                  "loss": 4.4699,
         | 
| 435 | 
            +
                  "step": 35840
         | 
| 436 | 
            +
                },
         | 
| 437 | 
            +
                {
         | 
| 438 | 
            +
                  "epoch": 0.01,
         | 
| 439 | 
            +
                  "learning_rate": 4.9404810651201585e-05,
         | 
| 440 | 
            +
                  "loss": 4.466,
         | 
| 441 | 
            +
                  "step": 36352
         | 
| 442 | 
            +
                },
         | 
| 443 | 
            +
                {
         | 
| 444 | 
            +
                  "epoch": 0.01,
         | 
| 445 | 
            +
                  "learning_rate": 4.9396441082494794e-05,
         | 
| 446 | 
            +
                  "loss": 4.4578,
         | 
| 447 | 
            +
                  "step": 36864
         | 
| 448 | 
            +
                },
         | 
| 449 | 
            +
                {
         | 
| 450 | 
            +
                  "epoch": 0.01,
         | 
| 451 | 
            +
                  "learning_rate": 4.9388055134984274e-05,
         | 
| 452 | 
            +
                  "loss": 4.456,
         | 
| 453 | 
            +
                  "step": 37376
         | 
| 454 | 
            +
                },
         | 
| 455 | 
            +
                {
         | 
| 456 | 
            +
                  "epoch": 0.01,
         | 
| 457 | 
            +
                  "learning_rate": 4.9379669187473754e-05,
         | 
| 458 | 
            +
                  "loss": 4.4582,
         | 
| 459 | 
            +
                  "step": 37888
         | 
| 460 | 
            +
                },
         | 
| 461 | 
            +
                {
         | 
| 462 | 
            +
                  "epoch": 0.01,
         | 
| 463 | 
            +
                  "learning_rate": 4.9371283239963234e-05,
         | 
| 464 | 
            +
                  "loss": 4.4521,
         | 
| 465 | 
            +
                  "step": 38400
         | 
| 466 | 
            +
                },
         | 
| 467 | 
            +
                {
         | 
| 468 | 
            +
                  "epoch": 0.01,
         | 
| 469 | 
            +
                  "learning_rate": 4.936291367125644e-05,
         | 
| 470 | 
            +
                  "loss": 4.4261,
         | 
| 471 | 
            +
                  "step": 38912
         | 
| 472 | 
            +
                },
         | 
| 473 | 
            +
                {
         | 
| 474 | 
            +
                  "epoch": 0.01,
         | 
| 475 | 
            +
                  "learning_rate": 4.935452772374592e-05,
         | 
| 476 | 
            +
                  "loss": 4.4359,
         | 
| 477 | 
            +
                  "step": 39424
         | 
| 478 | 
            +
                },
         | 
| 479 | 
            +
                {
         | 
| 480 | 
            +
                  "epoch": 0.01,
         | 
| 481 | 
            +
                  "learning_rate": 4.93461417762354e-05,
         | 
| 482 | 
            +
                  "loss": 4.4321,
         | 
| 483 | 
            +
                  "step": 39936
         | 
| 484 | 
            +
                },
         | 
| 485 | 
            +
                {
         | 
| 486 | 
            +
                  "epoch": 0.01,
         | 
| 487 | 
            +
                  "learning_rate": 4.933775582872488e-05,
         | 
| 488 | 
            +
                  "loss": 4.4188,
         | 
| 489 | 
            +
                  "step": 40448
         | 
| 490 | 
            +
                },
         | 
| 491 | 
            +
                {
         | 
| 492 | 
            +
                  "epoch": 0.01,
         | 
| 493 | 
            +
                  "learning_rate": 4.932936988121436e-05,
         | 
| 494 | 
            +
                  "loss": 4.4303,
         | 
| 495 | 
            +
                  "step": 40960
         | 
| 496 | 
            +
                },
         | 
| 497 | 
            +
                {
         | 
| 498 | 
            +
                  "epoch": 0.01,
         | 
| 499 | 
            +
                  "learning_rate": 4.932098393370384e-05,
         | 
| 500 | 
            +
                  "loss": 4.4199,
         | 
| 501 | 
            +
                  "step": 41472
         | 
| 502 | 
            +
                },
         | 
| 503 | 
            +
                {
         | 
| 504 | 
            +
                  "epoch": 0.01,
         | 
| 505 | 
            +
                  "learning_rate": 4.931259798619332e-05,
         | 
| 506 | 
            +
                  "loss": 4.4254,
         | 
| 507 | 
            +
                  "step": 41984
         | 
| 508 | 
            +
                },
         | 
| 509 | 
            +
                {
         | 
| 510 | 
            +
                  "epoch": 0.01,
         | 
| 511 | 
            +
                  "learning_rate": 4.930422841748654e-05,
         | 
| 512 | 
            +
                  "loss": 4.4167,
         | 
| 513 | 
            +
                  "step": 42496
         | 
| 514 | 
            +
                },
         | 
| 515 | 
            +
                {
         | 
| 516 | 
            +
                  "epoch": 0.01,
         | 
| 517 | 
            +
                  "learning_rate": 4.929584246997602e-05,
         | 
| 518 | 
            +
                  "loss": 4.3887,
         | 
| 519 | 
            +
                  "step": 43008
         | 
| 520 | 
            +
                },
         | 
| 521 | 
            +
                {
         | 
| 522 | 
            +
                  "epoch": 0.01,
         | 
| 523 | 
            +
                  "learning_rate": 4.92874565224655e-05,
         | 
| 524 | 
            +
                  "loss": 4.3998,
         | 
| 525 | 
            +
                  "step": 43520
         | 
| 526 | 
            +
                },
         | 
| 527 | 
            +
                {
         | 
| 528 | 
            +
                  "epoch": 0.01,
         | 
| 529 | 
            +
                  "learning_rate": 4.927907057495498e-05,
         | 
| 530 | 
            +
                  "loss": 4.3993,
         | 
| 531 | 
            +
                  "step": 44032
         | 
| 532 | 
            +
                },
         | 
| 533 | 
            +
                {
         | 
| 534 | 
            +
                  "epoch": 0.01,
         | 
| 535 | 
            +
                  "learning_rate": 4.927068462744446e-05,
         | 
| 536 | 
            +
                  "loss": 4.3994,
         | 
| 537 | 
            +
                  "step": 44544
         | 
| 538 | 
            +
                },
         | 
| 539 | 
            +
                {
         | 
| 540 | 
            +
                  "epoch": 0.01,
         | 
| 541 | 
            +
                  "learning_rate": 4.926229867993394e-05,
         | 
| 542 | 
            +
                  "loss": 4.3916,
         | 
| 543 | 
            +
                  "step": 45056
         | 
| 544 | 
            +
                },
         | 
| 545 | 
            +
                {
         | 
| 546 | 
            +
                  "epoch": 0.01,
         | 
| 547 | 
            +
                  "learning_rate": 4.925392911122715e-05,
         | 
| 548 | 
            +
                  "loss": 4.3838,
         | 
| 549 | 
            +
                  "step": 45568
         | 
| 550 | 
            +
                },
         | 
| 551 | 
            +
                {
         | 
| 552 | 
            +
                  "epoch": 0.02,
         | 
| 553 | 
            +
                  "learning_rate": 4.924554316371663e-05,
         | 
| 554 | 
            +
                  "loss": 4.3862,
         | 
| 555 | 
            +
                  "step": 46080
         | 
| 556 | 
            +
                },
         | 
| 557 | 
            +
                {
         | 
| 558 | 
            +
                  "epoch": 0.02,
         | 
| 559 | 
            +
                  "learning_rate": 4.923715721620611e-05,
         | 
| 560 | 
            +
                  "loss": 4.375,
         | 
| 561 | 
            +
                  "step": 46592
         | 
| 562 | 
            +
                },
         | 
| 563 | 
            +
                {
         | 
| 564 | 
            +
                  "epoch": 0.02,
         | 
| 565 | 
            +
                  "learning_rate": 4.922878764749932e-05,
         | 
| 566 | 
            +
                  "loss": 4.368,
         | 
| 567 | 
            +
                  "step": 47104
         | 
| 568 | 
            +
                },
         | 
| 569 | 
            +
                {
         | 
| 570 | 
            +
                  "epoch": 0.02,
         | 
| 571 | 
            +
                  "learning_rate": 4.92204016999888e-05,
         | 
| 572 | 
            +
                  "loss": 4.3685,
         | 
| 573 | 
            +
                  "step": 47616
         | 
| 574 | 
            +
                },
         | 
| 575 | 
            +
                {
         | 
| 576 | 
            +
                  "epoch": 0.02,
         | 
| 577 | 
            +
                  "learning_rate": 4.921201575247828e-05,
         | 
| 578 | 
            +
                  "loss": 4.3654,
         | 
| 579 | 
            +
                  "step": 48128
         | 
| 580 | 
            +
                },
         | 
| 581 | 
            +
                {
         | 
| 582 | 
            +
                  "epoch": 0.02,
         | 
| 583 | 
            +
                  "learning_rate": 4.920362980496776e-05,
         | 
| 584 | 
            +
                  "loss": 4.3794,
         | 
| 585 | 
            +
                  "step": 48640
         | 
| 586 | 
            +
                },
         | 
| 587 | 
            +
                {
         | 
| 588 | 
            +
                  "epoch": 0.02,
         | 
| 589 | 
            +
                  "learning_rate": 4.919524385745724e-05,
         | 
| 590 | 
            +
                  "loss": 4.3545,
         | 
| 591 | 
            +
                  "step": 49152
         | 
| 592 | 
            +
                },
         | 
| 593 | 
            +
                {
         | 
| 594 | 
            +
                  "epoch": 0.02,
         | 
| 595 | 
            +
                  "learning_rate": 4.918685790994672e-05,
         | 
| 596 | 
            +
                  "loss": 4.3487,
         | 
| 597 | 
            +
                  "step": 49664
         | 
| 598 | 
            +
                },
         | 
| 599 | 
            +
                {
         | 
| 600 | 
            +
                  "epoch": 0.02,
         | 
| 601 | 
            +
                  "learning_rate": 4.91784719624362e-05,
         | 
| 602 | 
            +
                  "loss": 4.347,
         | 
| 603 | 
            +
                  "step": 50176
         | 
| 604 | 
            +
                },
         | 
| 605 | 
            +
                {
         | 
| 606 | 
            +
                  "epoch": 0.02,
         | 
| 607 | 
            +
                  "learning_rate": 4.9170086014925676e-05,
         | 
| 608 | 
            +
                  "loss": 4.3576,
         | 
| 609 | 
            +
                  "step": 50688
         | 
| 610 | 
            +
                },
         | 
| 611 | 
            +
                {
         | 
| 612 | 
            +
                  "epoch": 0.02,
         | 
| 613 | 
            +
                  "learning_rate": 4.9161700067415156e-05,
         | 
| 614 | 
            +
                  "loss": 4.3531,
         | 
| 615 | 
            +
                  "step": 51200
         | 
| 616 | 
            +
                },
         | 
| 617 | 
            +
                {
         | 
| 618 | 
            +
                  "epoch": 0.02,
         | 
| 619 | 
            +
                  "learning_rate": 4.9153314119904636e-05,
         | 
| 620 | 
            +
                  "loss": 4.3398,
         | 
| 621 | 
            +
                  "step": 51712
         | 
| 622 | 
            +
                },
         | 
| 623 | 
            +
                {
         | 
| 624 | 
            +
                  "epoch": 0.02,
         | 
| 625 | 
            +
                  "learning_rate": 4.9144928172394116e-05,
         | 
| 626 | 
            +
                  "loss": 4.3393,
         | 
| 627 | 
            +
                  "step": 52224
         | 
| 628 | 
            +
                },
         | 
| 629 | 
            +
                {
         | 
| 630 | 
            +
                  "epoch": 0.02,
         | 
| 631 | 
            +
                  "learning_rate": 4.9136542224883596e-05,
         | 
| 632 | 
            +
                  "loss": 4.3214,
         | 
| 633 | 
            +
                  "step": 52736
         | 
| 634 | 
            +
                },
         | 
| 635 | 
            +
                {
         | 
| 636 | 
            +
                  "epoch": 0.02,
         | 
| 637 | 
            +
                  "learning_rate": 4.9128172656176805e-05,
         | 
| 638 | 
            +
                  "loss": 4.3374,
         | 
| 639 | 
            +
                  "step": 53248
         | 
| 640 | 
            +
                },
         | 
| 641 | 
            +
                {
         | 
| 642 | 
            +
                  "epoch": 0.02,
         | 
| 643 | 
            +
                  "learning_rate": 4.9119786708666285e-05,
         | 
| 644 | 
            +
                  "loss": 4.322,
         | 
| 645 | 
            +
                  "step": 53760
         | 
| 646 | 
            +
                },
         | 
| 647 | 
            +
                {
         | 
| 648 | 
            +
                  "epoch": 0.02,
         | 
| 649 | 
            +
                  "learning_rate": 4.9111400761155765e-05,
         | 
| 650 | 
            +
                  "loss": 4.3206,
         | 
| 651 | 
            +
                  "step": 54272
         | 
| 652 | 
            +
                },
         | 
| 653 | 
            +
                {
         | 
| 654 | 
            +
                  "epoch": 0.02,
         | 
| 655 | 
            +
                  "learning_rate": 4.910303119244898e-05,
         | 
| 656 | 
            +
                  "loss": 4.3238,
         | 
| 657 | 
            +
                  "step": 54784
         | 
| 658 | 
            +
                },
         | 
| 659 | 
            +
                {
         | 
| 660 | 
            +
                  "epoch": 0.02,
         | 
| 661 | 
            +
                  "learning_rate": 4.909464524493846e-05,
         | 
| 662 | 
            +
                  "loss": 4.3228,
         | 
| 663 | 
            +
                  "step": 55296
         | 
| 664 | 
            +
                },
         | 
| 665 | 
            +
                {
         | 
| 666 | 
            +
                  "epoch": 0.02,
         | 
| 667 | 
            +
                  "learning_rate": 4.908625929742794e-05,
         | 
| 668 | 
            +
                  "loss": 4.3172,
         | 
| 669 | 
            +
                  "step": 55808
         | 
| 670 | 
            +
                },
         | 
| 671 | 
            +
                {
         | 
| 672 | 
            +
                  "epoch": 0.02,
         | 
| 673 | 
            +
                  "learning_rate": 4.907787334991742e-05,
         | 
| 674 | 
            +
                  "loss": 4.3153,
         | 
| 675 | 
            +
                  "step": 56320
         | 
| 676 | 
            +
                },
         | 
| 677 | 
            +
                {
         | 
| 678 | 
            +
                  "epoch": 0.02,
         | 
| 679 | 
            +
                  "learning_rate": 4.90694874024069e-05,
         | 
| 680 | 
            +
                  "loss": 4.3074,
         | 
| 681 | 
            +
                  "step": 56832
         | 
| 682 | 
            +
                },
         | 
| 683 | 
            +
                {
         | 
| 684 | 
            +
                  "epoch": 0.02,
         | 
| 685 | 
            +
                  "learning_rate": 4.906110145489638e-05,
         | 
| 686 | 
            +
                  "loss": 4.3136,
         | 
| 687 | 
            +
                  "step": 57344
         | 
| 688 | 
            +
                },
         | 
| 689 | 
            +
                {
         | 
| 690 | 
            +
                  "epoch": 0.02,
         | 
| 691 | 
            +
                  "learning_rate": 4.905273188618959e-05,
         | 
| 692 | 
            +
                  "loss": 4.3028,
         | 
| 693 | 
            +
                  "step": 57856
         | 
| 694 | 
            +
                },
         | 
| 695 | 
            +
                {
         | 
| 696 | 
            +
                  "epoch": 0.02,
         | 
| 697 | 
            +
                  "learning_rate": 4.904434593867907e-05,
         | 
| 698 | 
            +
                  "loss": 4.3023,
         | 
| 699 | 
            +
                  "step": 58368
         | 
| 700 | 
            +
                },
         | 
| 701 | 
            +
                {
         | 
| 702 | 
            +
                  "epoch": 0.02,
         | 
| 703 | 
            +
                  "learning_rate": 4.903595999116855e-05,
         | 
| 704 | 
            +
                  "loss": 4.3076,
         | 
| 705 | 
            +
                  "step": 58880
         | 
| 706 | 
            +
                },
         | 
| 707 | 
            +
                {
         | 
| 708 | 
            +
                  "epoch": 0.02,
         | 
| 709 | 
            +
                  "learning_rate": 4.902757404365803e-05,
         | 
| 710 | 
            +
                  "loss": 4.3048,
         | 
| 711 | 
            +
                  "step": 59392
         | 
| 712 | 
            +
                },
         | 
| 713 | 
            +
                {
         | 
| 714 | 
            +
                  "epoch": 0.02,
         | 
| 715 | 
            +
                  "learning_rate": 4.901920447495124e-05,
         | 
| 716 | 
            +
                  "loss": 4.3025,
         | 
| 717 | 
            +
                  "step": 59904
         | 
| 718 | 
            +
                },
         | 
| 719 | 
            +
                {
         | 
| 720 | 
            +
                  "epoch": 0.02,
         | 
| 721 | 
            +
                  "learning_rate": 4.901081852744072e-05,
         | 
| 722 | 
            +
                  "loss": 4.2937,
         | 
| 723 | 
            +
                  "step": 60416
         | 
| 724 | 
            +
                },
         | 
| 725 | 
            +
                {
         | 
| 726 | 
            +
                  "epoch": 0.02,
         | 
| 727 | 
            +
                  "learning_rate": 4.90024325799302e-05,
         | 
| 728 | 
            +
                  "loss": 4.2983,
         | 
| 729 | 
            +
                  "step": 60928
         | 
| 730 | 
            +
                },
         | 
| 731 | 
            +
                {
         | 
| 732 | 
            +
                  "epoch": 0.02,
         | 
| 733 | 
            +
                  "learning_rate": 4.8994046632419686e-05,
         | 
| 734 | 
            +
                  "loss": 4.2932,
         | 
| 735 | 
            +
                  "step": 61440
         | 
| 736 | 
            +
                },
         | 
| 737 | 
            +
                {
         | 
| 738 | 
            +
                  "epoch": 0.02,
         | 
| 739 | 
            +
                  "learning_rate": 4.8985660684909166e-05,
         | 
| 740 | 
            +
                  "loss": 4.2793,
         | 
| 741 | 
            +
                  "step": 61952
         | 
| 742 | 
            +
                },
         | 
| 743 | 
            +
                {
         | 
| 744 | 
            +
                  "epoch": 0.02,
         | 
| 745 | 
            +
                  "learning_rate": 4.8977274737398646e-05,
         | 
| 746 | 
            +
                  "loss": 4.2973,
         | 
| 747 | 
            +
                  "step": 62464
         | 
| 748 | 
            +
                },
         | 
| 749 | 
            +
                {
         | 
| 750 | 
            +
                  "epoch": 0.02,
         | 
| 751 | 
            +
                  "learning_rate": 4.8968888789888125e-05,
         | 
| 752 | 
            +
                  "loss": 4.2813,
         | 
| 753 | 
            +
                  "step": 62976
         | 
| 754 | 
            +
                },
         | 
| 755 | 
            +
                {
         | 
| 756 | 
            +
                  "epoch": 0.02,
         | 
| 757 | 
            +
                  "learning_rate": 4.8960502842377605e-05,
         | 
| 758 | 
            +
                  "loss": 4.2894,
         | 
| 759 | 
            +
                  "step": 63488
         | 
| 760 | 
            +
                },
         | 
| 761 | 
            +
                {
         | 
| 762 | 
            +
                  "epoch": 0.02,
         | 
| 763 | 
            +
                  "learning_rate": 4.8952133273670815e-05,
         | 
| 764 | 
            +
                  "loss": 4.2709,
         | 
| 765 | 
            +
                  "step": 64000
         | 
| 766 | 
            +
                },
         | 
| 767 | 
            +
                {
         | 
| 768 | 
            +
                  "epoch": 0.02,
         | 
| 769 | 
            +
                  "learning_rate": 4.8943747326160294e-05,
         | 
| 770 | 
            +
                  "loss": 4.2661,
         | 
| 771 | 
            +
                  "step": 64512
         | 
| 772 | 
            +
                },
         | 
| 773 | 
            +
                {
         | 
| 774 | 
            +
                  "epoch": 0.02,
         | 
| 775 | 
            +
                  "learning_rate": 4.8935361378649774e-05,
         | 
| 776 | 
            +
                  "loss": 4.2649,
         | 
| 777 | 
            +
                  "step": 65024
         | 
| 778 | 
            +
                },
         | 
| 779 | 
            +
                {
         | 
| 780 | 
            +
                  "epoch": 0.02,
         | 
| 781 | 
            +
                  "learning_rate": 4.8926991809942984e-05,
         | 
| 782 | 
            +
                  "loss": 4.2682,
         | 
| 783 | 
            +
                  "step": 65536
         | 
| 784 | 
            +
                },
         | 
| 785 | 
            +
                {
         | 
| 786 | 
            +
                  "epoch": 0.02,
         | 
| 787 | 
            +
                  "learning_rate": 4.8918605862432463e-05,
         | 
| 788 | 
            +
                  "loss": 4.258,
         | 
| 789 | 
            +
                  "step": 66048
         | 
| 790 | 
            +
                },
         | 
| 791 | 
            +
                {
         | 
| 792 | 
            +
                  "epoch": 0.02,
         | 
| 793 | 
            +
                  "learning_rate": 4.8910219914921943e-05,
         | 
| 794 | 
            +
                  "loss": 4.2754,
         | 
| 795 | 
            +
                  "step": 66560
         | 
| 796 | 
            +
                },
         | 
| 797 | 
            +
                {
         | 
| 798 | 
            +
                  "epoch": 0.02,
         | 
| 799 | 
            +
                  "learning_rate": 4.8901833967411423e-05,
         | 
| 800 | 
            +
                  "loss": 4.272,
         | 
| 801 | 
            +
                  "step": 67072
         | 
| 802 | 
            +
                },
         | 
| 803 | 
            +
                {
         | 
| 804 | 
            +
                  "epoch": 0.02,
         | 
| 805 | 
            +
                  "learning_rate": 4.88934480199009e-05,
         | 
| 806 | 
            +
                  "loss": 4.2555,
         | 
| 807 | 
            +
                  "step": 67584
         | 
| 808 | 
            +
                },
         | 
| 809 | 
            +
                {
         | 
| 810 | 
            +
                  "epoch": 0.02,
         | 
| 811 | 
            +
                  "learning_rate": 4.888506207239038e-05,
         | 
| 812 | 
            +
                  "loss": 4.2596,
         | 
| 813 | 
            +
                  "step": 68096
         | 
| 814 | 
            +
                },
         | 
| 815 | 
            +
                {
         | 
| 816 | 
            +
                  "epoch": 0.02,
         | 
| 817 | 
            +
                  "learning_rate": 4.887667612487986e-05,
         | 
| 818 | 
            +
                  "loss": 4.2631,
         | 
| 819 | 
            +
                  "step": 68608
         | 
| 820 | 
            +
                },
         | 
| 821 | 
            +
                {
         | 
| 822 | 
            +
                  "epoch": 0.02,
         | 
| 823 | 
            +
                  "learning_rate": 4.886829017736934e-05,
         | 
| 824 | 
            +
                  "loss": 4.2597,
         | 
| 825 | 
            +
                  "step": 69120
         | 
| 826 | 
            +
                },
         | 
| 827 | 
            +
                {
         | 
| 828 | 
            +
                  "epoch": 0.02,
         | 
| 829 | 
            +
                  "learning_rate": 4.885992060866256e-05,
         | 
| 830 | 
            +
                  "loss": 4.2637,
         | 
| 831 | 
            +
                  "step": 69632
         | 
| 832 | 
            +
                },
         | 
| 833 | 
            +
                {
         | 
| 834 | 
            +
                  "epoch": 0.02,
         | 
| 835 | 
            +
                  "learning_rate": 4.885155103995577e-05,
         | 
| 836 | 
            +
                  "loss": 4.2595,
         | 
| 837 | 
            +
                  "step": 70144
         | 
| 838 | 
            +
                },
         | 
| 839 | 
            +
                {
         | 
| 840 | 
            +
                  "epoch": 0.02,
         | 
| 841 | 
            +
                  "learning_rate": 4.884316509244525e-05,
         | 
| 842 | 
            +
                  "loss": 4.2466,
         | 
| 843 | 
            +
                  "step": 70656
         | 
| 844 | 
            +
                },
         | 
| 845 | 
            +
                {
         | 
| 846 | 
            +
                  "epoch": 0.02,
         | 
| 847 | 
            +
                  "learning_rate": 4.883477914493473e-05,
         | 
| 848 | 
            +
                  "loss": 4.2528,
         | 
| 849 | 
            +
                  "step": 71168
         | 
| 850 | 
            +
                },
         | 
| 851 | 
            +
                {
         | 
| 852 | 
            +
                  "epoch": 0.02,
         | 
| 853 | 
            +
                  "learning_rate": 4.882639319742421e-05,
         | 
| 854 | 
            +
                  "loss": 4.2464,
         | 
| 855 | 
            +
                  "step": 71680
         | 
| 856 | 
            +
                },
         | 
| 857 | 
            +
                {
         | 
| 858 | 
            +
                  "epoch": 0.02,
         | 
| 859 | 
            +
                  "learning_rate": 4.881800724991369e-05,
         | 
| 860 | 
            +
                  "loss": 4.24,
         | 
| 861 | 
            +
                  "step": 72192
         | 
| 862 | 
            +
                },
         | 
| 863 | 
            +
                {
         | 
| 864 | 
            +
                  "epoch": 0.02,
         | 
| 865 | 
            +
                  "learning_rate": 4.880962130240316e-05,
         | 
| 866 | 
            +
                  "loss": 4.2503,
         | 
| 867 | 
            +
                  "step": 72704
         | 
| 868 | 
            +
                },
         | 
| 869 | 
            +
                {
         | 
| 870 | 
            +
                  "epoch": 0.02,
         | 
| 871 | 
            +
                  "learning_rate": 4.880123535489264e-05,
         | 
| 872 | 
            +
                  "loss": 4.2374,
         | 
| 873 | 
            +
                  "step": 73216
         | 
| 874 | 
            +
                },
         | 
| 875 | 
            +
                {
         | 
| 876 | 
            +
                  "epoch": 0.02,
         | 
| 877 | 
            +
                  "learning_rate": 4.879286578618586e-05,
         | 
| 878 | 
            +
                  "loss": 4.2263,
         | 
| 879 | 
            +
                  "step": 73728
         | 
| 880 | 
            +
                },
         | 
| 881 | 
            +
                {
         | 
| 882 | 
            +
                  "epoch": 0.02,
         | 
| 883 | 
            +
                  "learning_rate": 4.878447983867534e-05,
         | 
| 884 | 
            +
                  "loss": 4.2481,
         | 
| 885 | 
            +
                  "step": 74240
         | 
| 886 | 
            +
                },
         | 
| 887 | 
            +
                {
         | 
| 888 | 
            +
                  "epoch": 0.02,
         | 
| 889 | 
            +
                  "learning_rate": 4.877609389116482e-05,
         | 
| 890 | 
            +
                  "loss": 4.2278,
         | 
| 891 | 
            +
                  "step": 74752
         | 
| 892 | 
            +
                },
         | 
| 893 | 
            +
                {
         | 
| 894 | 
            +
                  "epoch": 0.02,
         | 
| 895 | 
            +
                  "learning_rate": 4.87677079436543e-05,
         | 
| 896 | 
            +
                  "loss": 4.228,
         | 
| 897 | 
            +
                  "step": 75264
         | 
| 898 | 
            +
                },
         | 
| 899 | 
            +
                {
         | 
| 900 | 
            +
                  "epoch": 0.02,
         | 
| 901 | 
            +
                  "learning_rate": 4.875932199614378e-05,
         | 
| 902 | 
            +
                  "loss": 4.2307,
         | 
| 903 | 
            +
                  "step": 75776
         | 
| 904 | 
            +
                },
         | 
| 905 | 
            +
                {
         | 
| 906 | 
            +
                  "epoch": 0.02,
         | 
| 907 | 
            +
                  "learning_rate": 4.875093604863326e-05,
         | 
| 908 | 
            +
                  "loss": 4.2235,
         | 
| 909 | 
            +
                  "step": 76288
         | 
| 910 | 
            +
                },
         | 
| 911 | 
            +
                {
         | 
| 912 | 
            +
                  "epoch": 0.03,
         | 
| 913 | 
            +
                  "eval_loss": 4.195763111114502,
         | 
| 914 | 
            +
                  "eval_runtime": 304.3449,
         | 
| 915 | 
            +
                  "eval_samples_per_second": 1253.811,
         | 
| 916 | 
            +
                  "eval_steps_per_second": 39.183,
         | 
| 917 | 
            +
                  "step": 76320
         | 
| 918 | 
            +
                },
         | 
| 919 | 
            +
                {
         | 
| 920 | 
            +
                  "epoch": 1.0,
         | 
| 921 | 
            +
                  "learning_rate": 4.874255010112274e-05,
         | 
| 922 | 
            +
                  "loss": 4.2068,
         | 
| 923 | 
            +
                  "step": 76800
         | 
| 924 | 
            +
                },
         | 
| 925 | 
            +
                {
         | 
| 926 | 
            +
                  "epoch": 1.0,
         | 
| 927 | 
            +
                  "learning_rate": 4.873416415361222e-05,
         | 
| 928 | 
            +
                  "loss": 4.2199,
         | 
| 929 | 
            +
                  "step": 77312
         | 
| 930 | 
            +
                },
         | 
| 931 | 
            +
                {
         | 
| 932 | 
            +
                  "epoch": 1.0,
         | 
| 933 | 
            +
                  "learning_rate": 4.8725794584905426e-05,
         | 
| 934 | 
            +
                  "loss": 4.2339,
         | 
| 935 | 
            +
                  "step": 77824
         | 
| 936 | 
            +
                },
         | 
| 937 | 
            +
                {
         | 
| 938 | 
            +
                  "epoch": 1.0,
         | 
| 939 | 
            +
                  "learning_rate": 4.8717408637394906e-05,
         | 
| 940 | 
            +
                  "loss": 4.2115,
         | 
| 941 | 
            +
                  "step": 78336
         | 
| 942 | 
            +
                },
         | 
| 943 | 
            +
                {
         | 
| 944 | 
            +
                  "epoch": 1.0,
         | 
| 945 | 
            +
                  "learning_rate": 4.8709022689884386e-05,
         | 
| 946 | 
            +
                  "loss": 4.2262,
         | 
| 947 | 
            +
                  "step": 78848
         | 
| 948 | 
            +
                },
         | 
| 949 | 
            +
                {
         | 
| 950 | 
            +
                  "epoch": 1.0,
         | 
| 951 | 
            +
                  "learning_rate": 4.8700636742373866e-05,
         | 
| 952 | 
            +
                  "loss": 4.2001,
         | 
| 953 | 
            +
                  "step": 79360
         | 
| 954 | 
            +
                },
         | 
| 955 | 
            +
                {
         | 
| 956 | 
            +
                  "epoch": 1.0,
         | 
| 957 | 
            +
                  "learning_rate": 4.8692267173667075e-05,
         | 
| 958 | 
            +
                  "loss": 4.2133,
         | 
| 959 | 
            +
                  "step": 79872
         | 
| 960 | 
            +
                },
         | 
| 961 | 
            +
                {
         | 
| 962 | 
            +
                  "epoch": 1.0,
         | 
| 963 | 
            +
                  "learning_rate": 4.8683881226156555e-05,
         | 
| 964 | 
            +
                  "loss": 4.1979,
         | 
| 965 | 
            +
                  "step": 80384
         | 
| 966 | 
            +
                },
         | 
| 967 | 
            +
                {
         | 
| 968 | 
            +
                  "epoch": 1.0,
         | 
| 969 | 
            +
                  "learning_rate": 4.867551165744977e-05,
         | 
| 970 | 
            +
                  "loss": 4.2083,
         | 
| 971 | 
            +
                  "step": 80896
         | 
| 972 | 
            +
                },
         | 
| 973 | 
            +
                {
         | 
| 974 | 
            +
                  "epoch": 1.0,
         | 
| 975 | 
            +
                  "learning_rate": 4.866712570993925e-05,
         | 
| 976 | 
            +
                  "loss": 4.2035,
         | 
| 977 | 
            +
                  "step": 81408
         | 
| 978 | 
            +
                },
         | 
| 979 | 
            +
                {
         | 
| 980 | 
            +
                  "epoch": 1.0,
         | 
| 981 | 
            +
                  "learning_rate": 4.865873976242873e-05,
         | 
| 982 | 
            +
                  "loss": 4.209,
         | 
| 983 | 
            +
                  "step": 81920
         | 
| 984 | 
            +
                },
         | 
| 985 | 
            +
                {
         | 
| 986 | 
            +
                  "epoch": 1.0,
         | 
| 987 | 
            +
                  "learning_rate": 4.865035381491821e-05,
         | 
| 988 | 
            +
                  "loss": 4.2051,
         | 
| 989 | 
            +
                  "step": 82432
         | 
| 990 | 
            +
                },
         | 
| 991 | 
            +
                {
         | 
| 992 | 
            +
                  "epoch": 1.0,
         | 
| 993 | 
            +
                  "learning_rate": 4.864198424621142e-05,
         | 
| 994 | 
            +
                  "loss": 4.1916,
         | 
| 995 | 
            +
                  "step": 82944
         | 
| 996 | 
            +
                },
         | 
| 997 | 
            +
                {
         | 
| 998 | 
            +
                  "epoch": 1.0,
         | 
| 999 | 
            +
                  "learning_rate": 4.86335982987009e-05,
         | 
| 1000 | 
            +
                  "loss": 4.1833,
         | 
| 1001 | 
            +
                  "step": 83456
         | 
| 1002 | 
            +
                },
         | 
| 1003 | 
            +
                {
         | 
| 1004 | 
            +
                  "epoch": 1.0,
         | 
| 1005 | 
            +
                  "learning_rate": 4.862521235119038e-05,
         | 
| 1006 | 
            +
                  "loss": 4.1845,
         | 
| 1007 | 
            +
                  "step": 83968
         | 
| 1008 | 
            +
                },
         | 
| 1009 | 
            +
                {
         | 
| 1010 | 
            +
                  "epoch": 1.0,
         | 
| 1011 | 
            +
                  "learning_rate": 4.861682640367986e-05,
         | 
| 1012 | 
            +
                  "loss": 4.1852,
         | 
| 1013 | 
            +
                  "step": 84480
         | 
| 1014 | 
            +
                },
         | 
| 1015 | 
            +
                {
         | 
| 1016 | 
            +
                  "epoch": 1.0,
         | 
| 1017 | 
            +
                  "learning_rate": 4.860844045616934e-05,
         | 
| 1018 | 
            +
                  "loss": 4.1949,
         | 
| 1019 | 
            +
                  "step": 84992
         | 
| 1020 | 
            +
                },
         | 
| 1021 | 
            +
                {
         | 
| 1022 | 
            +
                  "epoch": 1.0,
         | 
| 1023 | 
            +
                  "learning_rate": 4.860005450865882e-05,
         | 
| 1024 | 
            +
                  "loss": 4.1823,
         | 
| 1025 | 
            +
                  "step": 85504
         | 
| 1026 | 
            +
                },
         | 
| 1027 | 
            +
                {
         | 
| 1028 | 
            +
                  "epoch": 1.0,
         | 
| 1029 | 
            +
                  "learning_rate": 4.85916685611483e-05,
         | 
| 1030 | 
            +
                  "loss": 4.1885,
         | 
| 1031 | 
            +
                  "step": 86016
         | 
| 1032 | 
            +
                },
         | 
| 1033 | 
            +
                {
         | 
| 1034 | 
            +
                  "epoch": 1.0,
         | 
| 1035 | 
            +
                  "learning_rate": 4.858328261363778e-05,
         | 
| 1036 | 
            +
                  "loss": 4.205,
         | 
| 1037 | 
            +
                  "step": 86528
         | 
| 1038 | 
            +
                },
         | 
| 1039 | 
            +
                {
         | 
| 1040 | 
            +
                  "epoch": 1.0,
         | 
| 1041 | 
            +
                  "learning_rate": 4.857489666612726e-05,
         | 
| 1042 | 
            +
                  "loss": 4.179,
         | 
| 1043 | 
            +
                  "step": 87040
         | 
| 1044 | 
            +
                },
         | 
| 1045 | 
            +
                {
         | 
| 1046 | 
            +
                  "epoch": 1.0,
         | 
| 1047 | 
            +
                  "learning_rate": 4.856651071861674e-05,
         | 
| 1048 | 
            +
                  "loss": 4.1732,
         | 
| 1049 | 
            +
                  "step": 87552
         | 
| 1050 | 
            +
                },
         | 
| 1051 | 
            +
                {
         | 
| 1052 | 
            +
                  "epoch": 1.0,
         | 
| 1053 | 
            +
                  "learning_rate": 4.8558124771106226e-05,
         | 
| 1054 | 
            +
                  "loss": 4.1771,
         | 
| 1055 | 
            +
                  "step": 88064
         | 
| 1056 | 
            +
                },
         | 
| 1057 | 
            +
                {
         | 
| 1058 | 
            +
                  "epoch": 1.0,
         | 
| 1059 | 
            +
                  "learning_rate": 4.8549755202399435e-05,
         | 
| 1060 | 
            +
                  "loss": 4.186,
         | 
| 1061 | 
            +
                  "step": 88576
         | 
| 1062 | 
            +
                },
         | 
| 1063 | 
            +
                {
         | 
| 1064 | 
            +
                  "epoch": 1.0,
         | 
| 1065 | 
            +
                  "learning_rate": 4.8541385633692644e-05,
         | 
| 1066 | 
            +
                  "loss": 4.1671,
         | 
| 1067 | 
            +
                  "step": 89088
         | 
| 1068 | 
            +
                },
         | 
| 1069 | 
            +
                {
         | 
| 1070 | 
            +
                  "epoch": 1.0,
         | 
| 1071 | 
            +
                  "learning_rate": 4.8532999686182124e-05,
         | 
| 1072 | 
            +
                  "loss": 4.171,
         | 
| 1073 | 
            +
                  "step": 89600
         | 
| 1074 | 
            +
                },
         | 
| 1075 | 
            +
                {
         | 
| 1076 | 
            +
                  "epoch": 1.0,
         | 
| 1077 | 
            +
                  "learning_rate": 4.8524613738671604e-05,
         | 
| 1078 | 
            +
                  "loss": 4.1727,
         | 
| 1079 | 
            +
                  "step": 90112
         | 
| 1080 | 
            +
                },
         | 
| 1081 | 
            +
                {
         | 
| 1082 | 
            +
                  "epoch": 1.0,
         | 
| 1083 | 
            +
                  "learning_rate": 4.8516227791161084e-05,
         | 
| 1084 | 
            +
                  "loss": 4.1665,
         | 
| 1085 | 
            +
                  "step": 90624
         | 
| 1086 | 
            +
                },
         | 
| 1087 | 
            +
                {
         | 
| 1088 | 
            +
                  "epoch": 1.0,
         | 
| 1089 | 
            +
                  "learning_rate": 4.8507841843650564e-05,
         | 
| 1090 | 
            +
                  "loss": 4.1514,
         | 
| 1091 | 
            +
                  "step": 91136
         | 
| 1092 | 
            +
                },
         | 
| 1093 | 
            +
                {
         | 
| 1094 | 
            +
                  "epoch": 1.01,
         | 
| 1095 | 
            +
                  "learning_rate": 4.8499455896140044e-05,
         | 
| 1096 | 
            +
                  "loss": 4.1567,
         | 
| 1097 | 
            +
                  "step": 91648
         | 
| 1098 | 
            +
                },
         | 
| 1099 | 
            +
                {
         | 
| 1100 | 
            +
                  "epoch": 1.01,
         | 
| 1101 | 
            +
                  "learning_rate": 4.8491069948629524e-05,
         | 
| 1102 | 
            +
                  "loss": 4.1553,
         | 
| 1103 | 
            +
                  "step": 92160
         | 
| 1104 | 
            +
                },
         | 
| 1105 | 
            +
                {
         | 
| 1106 | 
            +
                  "epoch": 1.01,
         | 
| 1107 | 
            +
                  "learning_rate": 4.848270037992273e-05,
         | 
| 1108 | 
            +
                  "loss": 4.1666,
         | 
| 1109 | 
            +
                  "step": 92672
         | 
| 1110 | 
            +
                },
         | 
| 1111 | 
            +
                {
         | 
| 1112 | 
            +
                  "epoch": 1.01,
         | 
| 1113 | 
            +
                  "learning_rate": 4.847431443241221e-05,
         | 
| 1114 | 
            +
                  "loss": 4.1708,
         | 
| 1115 | 
            +
                  "step": 93184
         | 
| 1116 | 
            +
                },
         | 
| 1117 | 
            +
                {
         | 
| 1118 | 
            +
                  "epoch": 1.01,
         | 
| 1119 | 
            +
                  "learning_rate": 4.846592848490169e-05,
         | 
| 1120 | 
            +
                  "loss": 4.1529,
         | 
| 1121 | 
            +
                  "step": 93696
         | 
| 1122 | 
            +
                },
         | 
| 1123 | 
            +
                {
         | 
| 1124 | 
            +
                  "epoch": 1.01,
         | 
| 1125 | 
            +
                  "learning_rate": 4.845754253739117e-05,
         | 
| 1126 | 
            +
                  "loss": 4.1501,
         | 
| 1127 | 
            +
                  "step": 94208
         | 
| 1128 | 
            +
                },
         | 
| 1129 | 
            +
                {
         | 
| 1130 | 
            +
                  "epoch": 1.01,
         | 
| 1131 | 
            +
                  "learning_rate": 4.844915658988065e-05,
         | 
| 1132 | 
            +
                  "loss": 4.1648,
         | 
| 1133 | 
            +
                  "step": 94720
         | 
| 1134 | 
            +
                },
         | 
| 1135 | 
            +
                {
         | 
| 1136 | 
            +
                  "epoch": 1.01,
         | 
| 1137 | 
            +
                  "learning_rate": 4.844077064237013e-05,
         | 
| 1138 | 
            +
                  "loss": 4.1387,
         | 
| 1139 | 
            +
                  "step": 95232
         | 
| 1140 | 
            +
                },
         | 
| 1141 | 
            +
                {
         | 
| 1142 | 
            +
                  "epoch": 1.01,
         | 
| 1143 | 
            +
                  "learning_rate": 4.843238469485961e-05,
         | 
| 1144 | 
            +
                  "loss": 4.1448,
         | 
| 1145 | 
            +
                  "step": 95744
         | 
| 1146 | 
            +
                },
         | 
| 1147 | 
            +
                {
         | 
| 1148 | 
            +
                  "epoch": 1.01,
         | 
| 1149 | 
            +
                  "learning_rate": 4.842401512615282e-05,
         | 
| 1150 | 
            +
                  "loss": 4.1371,
         | 
| 1151 | 
            +
                  "step": 96256
         | 
| 1152 | 
            +
                },
         | 
| 1153 | 
            +
                {
         | 
| 1154 | 
            +
                  "epoch": 1.01,
         | 
| 1155 | 
            +
                  "learning_rate": 4.84156291786423e-05,
         | 
| 1156 | 
            +
                  "loss": 4.1433,
         | 
| 1157 | 
            +
                  "step": 96768
         | 
| 1158 | 
            +
                },
         | 
| 1159 | 
            +
                {
         | 
| 1160 | 
            +
                  "epoch": 1.01,
         | 
| 1161 | 
            +
                  "learning_rate": 4.840724323113178e-05,
         | 
| 1162 | 
            +
                  "loss": 4.1352,
         | 
| 1163 | 
            +
                  "step": 97280
         | 
| 1164 | 
            +
                },
         | 
| 1165 | 
            +
                {
         | 
| 1166 | 
            +
                  "epoch": 1.01,
         | 
| 1167 | 
            +
                  "learning_rate": 4.839885728362126e-05,
         | 
| 1168 | 
            +
                  "loss": 4.1532,
         | 
| 1169 | 
            +
                  "step": 97792
         | 
| 1170 | 
            +
                },
         | 
| 1171 | 
            +
                {
         | 
| 1172 | 
            +
                  "epoch": 1.01,
         | 
| 1173 | 
            +
                  "learning_rate": 4.839048771491447e-05,
         | 
| 1174 | 
            +
                  "loss": 4.1375,
         | 
| 1175 | 
            +
                  "step": 98304
         | 
| 1176 | 
            +
                },
         | 
| 1177 | 
            +
                {
         | 
| 1178 | 
            +
                  "epoch": 1.01,
         | 
| 1179 | 
            +
                  "learning_rate": 4.838210176740395e-05,
         | 
| 1180 | 
            +
                  "loss": 4.1386,
         | 
| 1181 | 
            +
                  "step": 98816
         | 
| 1182 | 
            +
                },
         | 
| 1183 | 
            +
                {
         | 
| 1184 | 
            +
                  "epoch": 1.01,
         | 
| 1185 | 
            +
                  "learning_rate": 4.837371581989343e-05,
         | 
| 1186 | 
            +
                  "loss": 4.1346,
         | 
| 1187 | 
            +
                  "step": 99328
         | 
| 1188 | 
            +
                },
         | 
| 1189 | 
            +
                {
         | 
| 1190 | 
            +
                  "epoch": 1.01,
         | 
| 1191 | 
            +
                  "learning_rate": 4.836532987238292e-05,
         | 
| 1192 | 
            +
                  "loss": 4.1408,
         | 
| 1193 | 
            +
                  "step": 99840
         | 
| 1194 | 
            +
                },
         | 
| 1195 | 
            +
                {
         | 
| 1196 | 
            +
                  "epoch": 1.01,
         | 
| 1197 | 
            +
                  "learning_rate": 4.83569439248724e-05,
         | 
| 1198 | 
            +
                  "loss": 4.133,
         | 
| 1199 | 
            +
                  "step": 100352
         | 
| 1200 | 
            +
                },
         | 
| 1201 | 
            +
                {
         | 
| 1202 | 
            +
                  "epoch": 1.01,
         | 
| 1203 | 
            +
                  "learning_rate": 4.834855797736188e-05,
         | 
| 1204 | 
            +
                  "loss": 4.1239,
         | 
| 1205 | 
            +
                  "step": 100864
         | 
| 1206 | 
            +
                },
         | 
| 1207 | 
            +
                {
         | 
| 1208 | 
            +
                  "epoch": 1.01,
         | 
| 1209 | 
            +
                  "learning_rate": 4.834017202985136e-05,
         | 
| 1210 | 
            +
                  "loss": 4.117,
         | 
| 1211 | 
            +
                  "step": 101376
         | 
| 1212 | 
            +
                },
         | 
| 1213 | 
            +
                {
         | 
| 1214 | 
            +
                  "epoch": 1.01,
         | 
| 1215 | 
            +
                  "learning_rate": 4.8331802461144566e-05,
         | 
| 1216 | 
            +
                  "loss": 4.1385,
         | 
| 1217 | 
            +
                  "step": 101888
         | 
| 1218 | 
            +
                },
         | 
| 1219 | 
            +
                {
         | 
| 1220 | 
            +
                  "epoch": 1.01,
         | 
| 1221 | 
            +
                  "learning_rate": 4.8323416513634046e-05,
         | 
| 1222 | 
            +
                  "loss": 4.1267,
         | 
| 1223 | 
            +
                  "step": 102400
         | 
| 1224 | 
            +
                },
         | 
| 1225 | 
            +
                {
         | 
| 1226 | 
            +
                  "epoch": 1.01,
         | 
| 1227 | 
            +
                  "learning_rate": 4.8315030566123526e-05,
         | 
| 1228 | 
            +
                  "loss": 4.1169,
         | 
| 1229 | 
            +
                  "step": 102912
         | 
| 1230 | 
            +
                },
         | 
| 1231 | 
            +
                {
         | 
| 1232 | 
            +
                  "epoch": 1.01,
         | 
| 1233 | 
            +
                  "learning_rate": 4.8306644618613006e-05,
         | 
| 1234 | 
            +
                  "loss": 4.1171,
         | 
| 1235 | 
            +
                  "step": 103424
         | 
| 1236 | 
            +
                },
         | 
| 1237 | 
            +
                {
         | 
| 1238 | 
            +
                  "epoch": 1.01,
         | 
| 1239 | 
            +
                  "learning_rate": 4.8298275049906215e-05,
         | 
| 1240 | 
            +
                  "loss": 4.1231,
         | 
| 1241 | 
            +
                  "step": 103936
         | 
| 1242 | 
            +
                },
         | 
| 1243 | 
            +
                {
         | 
| 1244 | 
            +
                  "epoch": 1.01,
         | 
| 1245 | 
            +
                  "learning_rate": 4.8289889102395695e-05,
         | 
| 1246 | 
            +
                  "loss": 4.112,
         | 
| 1247 | 
            +
                  "step": 104448
         | 
| 1248 | 
            +
                },
         | 
| 1249 | 
            +
                {
         | 
| 1250 | 
            +
                  "epoch": 1.01,
         | 
| 1251 | 
            +
                  "learning_rate": 4.8281503154885175e-05,
         | 
| 1252 | 
            +
                  "loss": 4.13,
         | 
| 1253 | 
            +
                  "step": 104960
         | 
| 1254 | 
            +
                },
         | 
| 1255 | 
            +
                {
         | 
| 1256 | 
            +
                  "epoch": 1.01,
         | 
| 1257 | 
            +
                  "learning_rate": 4.8273117207374655e-05,
         | 
| 1258 | 
            +
                  "loss": 4.113,
         | 
| 1259 | 
            +
                  "step": 105472
         | 
| 1260 | 
            +
                },
         | 
| 1261 | 
            +
                {
         | 
| 1262 | 
            +
                  "epoch": 1.01,
         | 
| 1263 | 
            +
                  "learning_rate": 4.8264731259864135e-05,
         | 
| 1264 | 
            +
                  "loss": 4.1149,
         | 
| 1265 | 
            +
                  "step": 105984
         | 
| 1266 | 
            +
                },
         | 
| 1267 | 
            +
                {
         | 
| 1268 | 
            +
                  "epoch": 1.01,
         | 
| 1269 | 
            +
                  "learning_rate": 4.8256345312353615e-05,
         | 
| 1270 | 
            +
                  "loss": 4.124,
         | 
| 1271 | 
            +
                  "step": 106496
         | 
| 1272 | 
            +
                },
         | 
| 1273 | 
            +
                {
         | 
| 1274 | 
            +
                  "epoch": 1.01,
         | 
| 1275 | 
            +
                  "learning_rate": 4.8247959364843095e-05,
         | 
| 1276 | 
            +
                  "loss": 4.1038,
         | 
| 1277 | 
            +
                  "step": 107008
         | 
| 1278 | 
            +
                },
         | 
| 1279 | 
            +
                {
         | 
| 1280 | 
            +
                  "epoch": 1.01,
         | 
| 1281 | 
            +
                  "learning_rate": 4.823957341733258e-05,
         | 
| 1282 | 
            +
                  "loss": 4.1002,
         | 
| 1283 | 
            +
                  "step": 107520
         | 
| 1284 | 
            +
                },
         | 
| 1285 | 
            +
                {
         | 
| 1286 | 
            +
                  "epoch": 1.01,
         | 
| 1287 | 
            +
                  "learning_rate": 4.823120384862579e-05,
         | 
| 1288 | 
            +
                  "loss": 4.1103,
         | 
| 1289 | 
            +
                  "step": 108032
         | 
| 1290 | 
            +
                },
         | 
| 1291 | 
            +
                {
         | 
| 1292 | 
            +
                  "epoch": 1.01,
         | 
| 1293 | 
            +
                  "learning_rate": 4.822281790111527e-05,
         | 
| 1294 | 
            +
                  "loss": 4.0924,
         | 
| 1295 | 
            +
                  "step": 108544
         | 
| 1296 | 
            +
                },
         | 
| 1297 | 
            +
                {
         | 
| 1298 | 
            +
                  "epoch": 1.01,
         | 
| 1299 | 
            +
                  "learning_rate": 4.821443195360475e-05,
         | 
| 1300 | 
            +
                  "loss": 4.0985,
         | 
| 1301 | 
            +
                  "step": 109056
         | 
| 1302 | 
            +
                },
         | 
| 1303 | 
            +
                {
         | 
| 1304 | 
            +
                  "epoch": 1.01,
         | 
| 1305 | 
            +
                  "learning_rate": 4.820604600609423e-05,
         | 
| 1306 | 
            +
                  "loss": 4.1096,
         | 
| 1307 | 
            +
                  "step": 109568
         | 
| 1308 | 
            +
                },
         | 
| 1309 | 
            +
                {
         | 
| 1310 | 
            +
                  "epoch": 1.01,
         | 
| 1311 | 
            +
                  "learning_rate": 4.819766005858371e-05,
         | 
| 1312 | 
            +
                  "loss": 4.1122,
         | 
| 1313 | 
            +
                  "step": 110080
         | 
| 1314 | 
            +
                },
         | 
| 1315 | 
            +
                {
         | 
| 1316 | 
            +
                  "epoch": 1.01,
         | 
| 1317 | 
            +
                  "learning_rate": 4.8189274111073184e-05,
         | 
| 1318 | 
            +
                  "loss": 4.1009,
         | 
| 1319 | 
            +
                  "step": 110592
         | 
| 1320 | 
            +
                },
         | 
| 1321 | 
            +
                {
         | 
| 1322 | 
            +
                  "epoch": 1.01,
         | 
| 1323 | 
            +
                  "learning_rate": 4.8180888163562664e-05,
         | 
| 1324 | 
            +
                  "loss": 4.0957,
         | 
| 1325 | 
            +
                  "step": 111104
         | 
| 1326 | 
            +
                },
         | 
| 1327 | 
            +
                {
         | 
| 1328 | 
            +
                  "epoch": 1.01,
         | 
| 1329 | 
            +
                  "learning_rate": 4.817253497365961e-05,
         | 
| 1330 | 
            +
                  "loss": 4.0861,
         | 
| 1331 | 
            +
                  "step": 111616
         | 
| 1332 | 
            +
                },
         | 
| 1333 | 
            +
                {
         | 
| 1334 | 
            +
                  "epoch": 1.01,
         | 
| 1335 | 
            +
                  "learning_rate": 4.816414902614909e-05,
         | 
| 1336 | 
            +
                  "loss": 4.1051,
         | 
| 1337 | 
            +
                  "step": 112128
         | 
| 1338 | 
            +
                },
         | 
| 1339 | 
            +
                {
         | 
| 1340 | 
            +
                  "epoch": 1.01,
         | 
| 1341 | 
            +
                  "learning_rate": 4.815576307863857e-05,
         | 
| 1342 | 
            +
                  "loss": 4.1013,
         | 
| 1343 | 
            +
                  "step": 112640
         | 
| 1344 | 
            +
                },
         | 
| 1345 | 
            +
                {
         | 
| 1346 | 
            +
                  "epoch": 1.01,
         | 
| 1347 | 
            +
                  "learning_rate": 4.814737713112805e-05,
         | 
| 1348 | 
            +
                  "loss": 4.1016,
         | 
| 1349 | 
            +
                  "step": 113152
         | 
| 1350 | 
            +
                },
         | 
| 1351 | 
            +
                {
         | 
| 1352 | 
            +
                  "epoch": 1.01,
         | 
| 1353 | 
            +
                  "learning_rate": 4.8138991183617535e-05,
         | 
| 1354 | 
            +
                  "loss": 4.102,
         | 
| 1355 | 
            +
                  "step": 113664
         | 
| 1356 | 
            +
                },
         | 
| 1357 | 
            +
                {
         | 
| 1358 | 
            +
                  "epoch": 1.01,
         | 
| 1359 | 
            +
                  "learning_rate": 4.813060523610701e-05,
         | 
| 1360 | 
            +
                  "loss": 4.1048,
         | 
| 1361 | 
            +
                  "step": 114176
         | 
| 1362 | 
            +
                },
         | 
| 1363 | 
            +
                {
         | 
| 1364 | 
            +
                  "epoch": 1.01,
         | 
| 1365 | 
            +
                  "learning_rate": 4.8122235667400224e-05,
         | 
| 1366 | 
            +
                  "loss": 4.1031,
         | 
| 1367 | 
            +
                  "step": 114688
         | 
| 1368 | 
            +
                },
         | 
| 1369 | 
            +
                {
         | 
| 1370 | 
            +
                  "epoch": 1.01,
         | 
| 1371 | 
            +
                  "learning_rate": 4.8113849719889704e-05,
         | 
| 1372 | 
            +
                  "loss": 4.0819,
         | 
| 1373 | 
            +
                  "step": 115200
         | 
| 1374 | 
            +
                },
         | 
| 1375 | 
            +
                {
         | 
| 1376 | 
            +
                  "epoch": 1.01,
         | 
| 1377 | 
            +
                  "learning_rate": 4.8105480151182914e-05,
         | 
| 1378 | 
            +
                  "loss": 4.0935,
         | 
| 1379 | 
            +
                  "step": 115712
         | 
| 1380 | 
            +
                },
         | 
| 1381 | 
            +
                {
         | 
| 1382 | 
            +
                  "epoch": 1.01,
         | 
| 1383 | 
            +
                  "learning_rate": 4.8097094203672393e-05,
         | 
| 1384 | 
            +
                  "loss": 4.095,
         | 
| 1385 | 
            +
                  "step": 116224
         | 
| 1386 | 
            +
                },
         | 
| 1387 | 
            +
                {
         | 
| 1388 | 
            +
                  "epoch": 1.01,
         | 
| 1389 | 
            +
                  "learning_rate": 4.8088708256161873e-05,
         | 
| 1390 | 
            +
                  "loss": 4.0788,
         | 
| 1391 | 
            +
                  "step": 116736
         | 
| 1392 | 
            +
                },
         | 
| 1393 | 
            +
                {
         | 
| 1394 | 
            +
                  "epoch": 1.01,
         | 
| 1395 | 
            +
                  "learning_rate": 4.808032230865135e-05,
         | 
| 1396 | 
            +
                  "loss": 4.1021,
         | 
| 1397 | 
            +
                  "step": 117248
         | 
| 1398 | 
            +
                },
         | 
| 1399 | 
            +
                {
         | 
| 1400 | 
            +
                  "epoch": 1.01,
         | 
| 1401 | 
            +
                  "learning_rate": 4.8071936361140827e-05,
         | 
| 1402 | 
            +
                  "loss": 4.0938,
         | 
| 1403 | 
            +
                  "step": 117760
         | 
| 1404 | 
            +
                },
         | 
| 1405 | 
            +
                {
         | 
| 1406 | 
            +
                  "epoch": 1.01,
         | 
| 1407 | 
            +
                  "learning_rate": 4.8063550413630307e-05,
         | 
| 1408 | 
            +
                  "loss": 4.0971,
         | 
| 1409 | 
            +
                  "step": 118272
         | 
| 1410 | 
            +
                },
         | 
| 1411 | 
            +
                {
         | 
| 1412 | 
            +
                  "epoch": 1.01,
         | 
| 1413 | 
            +
                  "learning_rate": 4.8055164466119786e-05,
         | 
| 1414 | 
            +
                  "loss": 4.0954,
         | 
| 1415 | 
            +
                  "step": 118784
         | 
| 1416 | 
            +
                },
         | 
| 1417 | 
            +
                {
         | 
| 1418 | 
            +
                  "epoch": 1.01,
         | 
| 1419 | 
            +
                  "learning_rate": 4.804677851860927e-05,
         | 
| 1420 | 
            +
                  "loss": 4.071,
         | 
| 1421 | 
            +
                  "step": 119296
         | 
| 1422 | 
            +
                },
         | 
| 1423 | 
            +
                {
         | 
| 1424 | 
            +
                  "epoch": 1.01,
         | 
| 1425 | 
            +
                  "learning_rate": 4.803840894990248e-05,
         | 
| 1426 | 
            +
                  "loss": 4.0829,
         | 
| 1427 | 
            +
                  "step": 119808
         | 
| 1428 | 
            +
                },
         | 
| 1429 | 
            +
                {
         | 
| 1430 | 
            +
                  "epoch": 1.01,
         | 
| 1431 | 
            +
                  "learning_rate": 4.803002300239196e-05,
         | 
| 1432 | 
            +
                  "loss": 4.0819,
         | 
| 1433 | 
            +
                  "step": 120320
         | 
| 1434 | 
            +
                },
         | 
| 1435 | 
            +
                {
         | 
| 1436 | 
            +
                  "epoch": 1.01,
         | 
| 1437 | 
            +
                  "learning_rate": 4.802163705488144e-05,
         | 
| 1438 | 
            +
                  "loss": 4.0849,
         | 
| 1439 | 
            +
                  "step": 120832
         | 
| 1440 | 
            +
                },
         | 
| 1441 | 
            +
                {
         | 
| 1442 | 
            +
                  "epoch": 1.01,
         | 
| 1443 | 
            +
                  "learning_rate": 4.801325110737092e-05,
         | 
| 1444 | 
            +
                  "loss": 4.0833,
         | 
| 1445 | 
            +
                  "step": 121344
         | 
| 1446 | 
            +
                },
         | 
| 1447 | 
            +
                {
         | 
| 1448 | 
            +
                  "epoch": 1.01,
         | 
| 1449 | 
            +
                  "learning_rate": 4.800488153866413e-05,
         | 
| 1450 | 
            +
                  "loss": 4.0746,
         | 
| 1451 | 
            +
                  "step": 121856
         | 
| 1452 | 
            +
                },
         | 
| 1453 | 
            +
                {
         | 
| 1454 | 
            +
                  "epoch": 1.02,
         | 
| 1455 | 
            +
                  "learning_rate": 4.799649559115361e-05,
         | 
| 1456 | 
            +
                  "loss": 4.084,
         | 
| 1457 | 
            +
                  "step": 122368
         | 
| 1458 | 
            +
                },
         | 
| 1459 | 
            +
                {
         | 
| 1460 | 
            +
                  "epoch": 1.02,
         | 
| 1461 | 
            +
                  "learning_rate": 4.798810964364309e-05,
         | 
| 1462 | 
            +
                  "loss": 4.0771,
         | 
| 1463 | 
            +
                  "step": 122880
         | 
| 1464 | 
            +
                },
         | 
| 1465 | 
            +
                {
         | 
| 1466 | 
            +
                  "epoch": 1.02,
         | 
| 1467 | 
            +
                  "learning_rate": 4.797972369613257e-05,
         | 
| 1468 | 
            +
                  "loss": 4.0647,
         | 
| 1469 | 
            +
                  "step": 123392
         | 
| 1470 | 
            +
                },
         | 
| 1471 | 
            +
                {
         | 
| 1472 | 
            +
                  "epoch": 1.02,
         | 
| 1473 | 
            +
                  "learning_rate": 4.797133774862205e-05,
         | 
| 1474 | 
            +
                  "loss": 4.0716,
         | 
| 1475 | 
            +
                  "step": 123904
         | 
| 1476 | 
            +
                },
         | 
| 1477 | 
            +
                {
         | 
| 1478 | 
            +
                  "epoch": 1.02,
         | 
| 1479 | 
            +
                  "learning_rate": 4.796295180111153e-05,
         | 
| 1480 | 
            +
                  "loss": 4.0769,
         | 
| 1481 | 
            +
                  "step": 124416
         | 
| 1482 | 
            +
                },
         | 
| 1483 | 
            +
                {
         | 
| 1484 | 
            +
                  "epoch": 1.02,
         | 
| 1485 | 
            +
                  "learning_rate": 4.795458223240474e-05,
         | 
| 1486 | 
            +
                  "loss": 4.0869,
         | 
| 1487 | 
            +
                  "step": 124928
         | 
| 1488 | 
            +
                },
         | 
| 1489 | 
            +
                {
         | 
| 1490 | 
            +
                  "epoch": 1.02,
         | 
| 1491 | 
            +
                  "learning_rate": 4.794619628489423e-05,
         | 
| 1492 | 
            +
                  "loss": 4.0682,
         | 
| 1493 | 
            +
                  "step": 125440
         | 
| 1494 | 
            +
                },
         | 
| 1495 | 
            +
                {
         | 
| 1496 | 
            +
                  "epoch": 1.02,
         | 
| 1497 | 
            +
                  "learning_rate": 4.793781033738371e-05,
         | 
| 1498 | 
            +
                  "loss": 4.0545,
         | 
| 1499 | 
            +
                  "step": 125952
         | 
| 1500 | 
            +
                },
         | 
| 1501 | 
            +
                {
         | 
| 1502 | 
            +
                  "epoch": 1.02,
         | 
| 1503 | 
            +
                  "learning_rate": 4.792942438987319e-05,
         | 
| 1504 | 
            +
                  "loss": 4.0634,
         | 
| 1505 | 
            +
                  "step": 126464
         | 
| 1506 | 
            +
                },
         | 
| 1507 | 
            +
                {
         | 
| 1508 | 
            +
                  "epoch": 1.02,
         | 
| 1509 | 
            +
                  "learning_rate": 4.792103844236267e-05,
         | 
| 1510 | 
            +
                  "loss": 4.074,
         | 
| 1511 | 
            +
                  "step": 126976
         | 
| 1512 | 
            +
                },
         | 
| 1513 | 
            +
                {
         | 
| 1514 | 
            +
                  "epoch": 1.02,
         | 
| 1515 | 
            +
                  "learning_rate": 4.791265249485215e-05,
         | 
| 1516 | 
            +
                  "loss": 4.071,
         | 
| 1517 | 
            +
                  "step": 127488
         | 
| 1518 | 
            +
                },
         | 
| 1519 | 
            +
                {
         | 
| 1520 | 
            +
                  "epoch": 1.02,
         | 
| 1521 | 
            +
                  "learning_rate": 4.790426654734163e-05,
         | 
| 1522 | 
            +
                  "loss": 4.0658,
         | 
| 1523 | 
            +
                  "step": 128000
         | 
| 1524 | 
            +
                },
         | 
| 1525 | 
            +
                {
         | 
| 1526 | 
            +
                  "epoch": 1.02,
         | 
| 1527 | 
            +
                  "learning_rate": 4.7895880599831107e-05,
         | 
| 1528 | 
            +
                  "loss": 4.0598,
         | 
| 1529 | 
            +
                  "step": 128512
         | 
| 1530 | 
            +
                },
         | 
| 1531 | 
            +
                {
         | 
| 1532 | 
            +
                  "epoch": 1.02,
         | 
| 1533 | 
            +
                  "learning_rate": 4.7887494652320587e-05,
         | 
| 1534 | 
            +
                  "loss": 4.0503,
         | 
| 1535 | 
            +
                  "step": 129024
         | 
| 1536 | 
            +
                },
         | 
| 1537 | 
            +
                {
         | 
| 1538 | 
            +
                  "epoch": 1.02,
         | 
| 1539 | 
            +
                  "learning_rate": 4.7879125083613796e-05,
         | 
| 1540 | 
            +
                  "loss": 4.0659,
         | 
| 1541 | 
            +
                  "step": 129536
         | 
| 1542 | 
            +
                },
         | 
| 1543 | 
            +
                {
         | 
| 1544 | 
            +
                  "epoch": 1.02,
         | 
| 1545 | 
            +
                  "learning_rate": 4.7870739136103276e-05,
         | 
| 1546 | 
            +
                  "loss": 4.0511,
         | 
| 1547 | 
            +
                  "step": 130048
         | 
| 1548 | 
            +
                },
         | 
| 1549 | 
            +
                {
         | 
| 1550 | 
            +
                  "epoch": 1.02,
         | 
| 1551 | 
            +
                  "learning_rate": 4.7862353188592756e-05,
         | 
| 1552 | 
            +
                  "loss": 4.0559,
         | 
| 1553 | 
            +
                  "step": 130560
         | 
| 1554 | 
            +
                },
         | 
| 1555 | 
            +
                {
         | 
| 1556 | 
            +
                  "epoch": 1.02,
         | 
| 1557 | 
            +
                  "learning_rate": 4.7853983619885965e-05,
         | 
| 1558 | 
            +
                  "loss": 4.0591,
         | 
| 1559 | 
            +
                  "step": 131072
         | 
| 1560 | 
            +
                },
         | 
| 1561 | 
            +
                {
         | 
| 1562 | 
            +
                  "epoch": 1.02,
         | 
| 1563 | 
            +
                  "learning_rate": 4.7845597672375445e-05,
         | 
| 1564 | 
            +
                  "loss": 4.0593,
         | 
| 1565 | 
            +
                  "step": 131584
         | 
| 1566 | 
            +
                },
         | 
| 1567 | 
            +
                {
         | 
| 1568 | 
            +
                  "epoch": 1.02,
         | 
| 1569 | 
            +
                  "learning_rate": 4.7837211724864925e-05,
         | 
| 1570 | 
            +
                  "loss": 4.0524,
         | 
| 1571 | 
            +
                  "step": 132096
         | 
| 1572 | 
            +
                },
         | 
| 1573 | 
            +
                {
         | 
| 1574 | 
            +
                  "epoch": 1.02,
         | 
| 1575 | 
            +
                  "learning_rate": 4.782882577735441e-05,
         | 
| 1576 | 
            +
                  "loss": 4.0583,
         | 
| 1577 | 
            +
                  "step": 132608
         | 
| 1578 | 
            +
                },
         | 
| 1579 | 
            +
                {
         | 
| 1580 | 
            +
                  "epoch": 1.02,
         | 
| 1581 | 
            +
                  "learning_rate": 4.782043982984389e-05,
         | 
| 1582 | 
            +
                  "loss": 4.0494,
         | 
| 1583 | 
            +
                  "step": 133120
         | 
| 1584 | 
            +
                },
         | 
| 1585 | 
            +
                {
         | 
| 1586 | 
            +
                  "epoch": 1.02,
         | 
| 1587 | 
            +
                  "learning_rate": 4.781205388233337e-05,
         | 
| 1588 | 
            +
                  "loss": 4.0549,
         | 
| 1589 | 
            +
                  "step": 133632
         | 
| 1590 | 
            +
                },
         | 
| 1591 | 
            +
                {
         | 
| 1592 | 
            +
                  "epoch": 1.02,
         | 
| 1593 | 
            +
                  "learning_rate": 4.7803667934822844e-05,
         | 
| 1594 | 
            +
                  "loss": 4.0477,
         | 
| 1595 | 
            +
                  "step": 134144
         | 
| 1596 | 
            +
                },
         | 
| 1597 | 
            +
                {
         | 
| 1598 | 
            +
                  "epoch": 1.02,
         | 
| 1599 | 
            +
                  "learning_rate": 4.7795281987312324e-05,
         | 
| 1600 | 
            +
                  "loss": 4.0458,
         | 
| 1601 | 
            +
                  "step": 134656
         | 
| 1602 | 
            +
                },
         | 
| 1603 | 
            +
                {
         | 
| 1604 | 
            +
                  "epoch": 1.02,
         | 
| 1605 | 
            +
                  "learning_rate": 4.778691241860554e-05,
         | 
| 1606 | 
            +
                  "loss": 4.0589,
         | 
| 1607 | 
            +
                  "step": 135168
         | 
| 1608 | 
            +
                },
         | 
| 1609 | 
            +
                {
         | 
| 1610 | 
            +
                  "epoch": 1.02,
         | 
| 1611 | 
            +
                  "learning_rate": 4.777852647109502e-05,
         | 
| 1612 | 
            +
                  "loss": 4.0574,
         | 
| 1613 | 
            +
                  "step": 135680
         | 
| 1614 | 
            +
                },
         | 
| 1615 | 
            +
                {
         | 
| 1616 | 
            +
                  "epoch": 1.02,
         | 
| 1617 | 
            +
                  "learning_rate": 4.777015690238823e-05,
         | 
| 1618 | 
            +
                  "loss": 4.053,
         | 
| 1619 | 
            +
                  "step": 136192
         | 
| 1620 | 
            +
                },
         | 
| 1621 | 
            +
                {
         | 
| 1622 | 
            +
                  "epoch": 1.02,
         | 
| 1623 | 
            +
                  "learning_rate": 4.776177095487771e-05,
         | 
| 1624 | 
            +
                  "loss": 4.0468,
         | 
| 1625 | 
            +
                  "step": 136704
         | 
| 1626 | 
            +
                },
         | 
| 1627 | 
            +
                {
         | 
| 1628 | 
            +
                  "epoch": 1.02,
         | 
| 1629 | 
            +
                  "learning_rate": 4.775338500736719e-05,
         | 
| 1630 | 
            +
                  "loss": 4.0515,
         | 
| 1631 | 
            +
                  "step": 137216
         | 
| 1632 | 
            +
                },
         | 
| 1633 | 
            +
                {
         | 
| 1634 | 
            +
                  "epoch": 1.02,
         | 
| 1635 | 
            +
                  "learning_rate": 4.774499905985666e-05,
         | 
| 1636 | 
            +
                  "loss": 4.0501,
         | 
| 1637 | 
            +
                  "step": 137728
         | 
| 1638 | 
            +
                },
         | 
| 1639 | 
            +
                {
         | 
| 1640 | 
            +
                  "epoch": 1.02,
         | 
| 1641 | 
            +
                  "learning_rate": 4.773661311234615e-05,
         | 
| 1642 | 
            +
                  "loss": 4.0367,
         | 
| 1643 | 
            +
                  "step": 138240
         | 
| 1644 | 
            +
                },
         | 
| 1645 | 
            +
                {
         | 
| 1646 | 
            +
                  "epoch": 1.02,
         | 
| 1647 | 
            +
                  "learning_rate": 4.772822716483563e-05,
         | 
| 1648 | 
            +
                  "loss": 4.057,
         | 
| 1649 | 
            +
                  "step": 138752
         | 
| 1650 | 
            +
                },
         | 
| 1651 | 
            +
                {
         | 
| 1652 | 
            +
                  "epoch": 1.02,
         | 
| 1653 | 
            +
                  "learning_rate": 4.771984121732511e-05,
         | 
| 1654 | 
            +
                  "loss": 4.041,
         | 
| 1655 | 
            +
                  "step": 139264
         | 
| 1656 | 
            +
                },
         | 
| 1657 | 
            +
                {
         | 
| 1658 | 
            +
                  "epoch": 1.02,
         | 
| 1659 | 
            +
                  "learning_rate": 4.771145526981459e-05,
         | 
| 1660 | 
            +
                  "loss": 4.0523,
         | 
| 1661 | 
            +
                  "step": 139776
         | 
| 1662 | 
            +
                },
         | 
| 1663 | 
            +
                {
         | 
| 1664 | 
            +
                  "epoch": 1.02,
         | 
| 1665 | 
            +
                  "learning_rate": 4.77030857011078e-05,
         | 
| 1666 | 
            +
                  "loss": 4.0341,
         | 
| 1667 | 
            +
                  "step": 140288
         | 
| 1668 | 
            +
                },
         | 
| 1669 | 
            +
                {
         | 
| 1670 | 
            +
                  "epoch": 1.02,
         | 
| 1671 | 
            +
                  "learning_rate": 4.769469975359728e-05,
         | 
| 1672 | 
            +
                  "loss": 4.0357,
         | 
| 1673 | 
            +
                  "step": 140800
         | 
| 1674 | 
            +
                },
         | 
| 1675 | 
            +
                {
         | 
| 1676 | 
            +
                  "epoch": 1.02,
         | 
| 1677 | 
            +
                  "learning_rate": 4.768631380608676e-05,
         | 
| 1678 | 
            +
                  "loss": 4.0319,
         | 
| 1679 | 
            +
                  "step": 141312
         | 
| 1680 | 
            +
                },
         | 
| 1681 | 
            +
                {
         | 
| 1682 | 
            +
                  "epoch": 1.02,
         | 
| 1683 | 
            +
                  "learning_rate": 4.767792785857624e-05,
         | 
| 1684 | 
            +
                  "loss": 4.0344,
         | 
| 1685 | 
            +
                  "step": 141824
         | 
| 1686 | 
            +
                },
         | 
| 1687 | 
            +
                {
         | 
| 1688 | 
            +
                  "epoch": 1.02,
         | 
| 1689 | 
            +
                  "learning_rate": 4.766955828986945e-05,
         | 
| 1690 | 
            +
                  "loss": 4.0316,
         | 
| 1691 | 
            +
                  "step": 142336
         | 
| 1692 | 
            +
                },
         | 
| 1693 | 
            +
                {
         | 
| 1694 | 
            +
                  "epoch": 1.02,
         | 
| 1695 | 
            +
                  "learning_rate": 4.766117234235893e-05,
         | 
| 1696 | 
            +
                  "loss": 4.0465,
         | 
| 1697 | 
            +
                  "step": 142848
         | 
| 1698 | 
            +
                },
         | 
| 1699 | 
            +
                {
         | 
| 1700 | 
            +
                  "epoch": 1.02,
         | 
| 1701 | 
            +
                  "learning_rate": 4.765278639484841e-05,
         | 
| 1702 | 
            +
                  "loss": 4.0479,
         | 
| 1703 | 
            +
                  "step": 143360
         | 
| 1704 | 
            +
                },
         | 
| 1705 | 
            +
                {
         | 
| 1706 | 
            +
                  "epoch": 1.02,
         | 
| 1707 | 
            +
                  "learning_rate": 4.764440044733789e-05,
         | 
| 1708 | 
            +
                  "loss": 4.0357,
         | 
| 1709 | 
            +
                  "step": 143872
         | 
| 1710 | 
            +
                },
         | 
| 1711 | 
            +
                {
         | 
| 1712 | 
            +
                  "epoch": 1.02,
         | 
| 1713 | 
            +
                  "learning_rate": 4.763601449982737e-05,
         | 
| 1714 | 
            +
                  "loss": 4.0289,
         | 
| 1715 | 
            +
                  "step": 144384
         | 
| 1716 | 
            +
                },
         | 
| 1717 | 
            +
                {
         | 
| 1718 | 
            +
                  "epoch": 1.02,
         | 
| 1719 | 
            +
                  "learning_rate": 4.762764493112058e-05,
         | 
| 1720 | 
            +
                  "loss": 4.0387,
         | 
| 1721 | 
            +
                  "step": 144896
         | 
| 1722 | 
            +
                },
         | 
| 1723 | 
            +
                {
         | 
| 1724 | 
            +
                  "epoch": 1.02,
         | 
| 1725 | 
            +
                  "learning_rate": 4.761925898361006e-05,
         | 
| 1726 | 
            +
                  "loss": 4.0371,
         | 
| 1727 | 
            +
                  "step": 145408
         | 
| 1728 | 
            +
                },
         | 
| 1729 | 
            +
                {
         | 
| 1730 | 
            +
                  "epoch": 1.02,
         | 
| 1731 | 
            +
                  "learning_rate": 4.761087303609954e-05,
         | 
| 1732 | 
            +
                  "loss": 4.0461,
         | 
| 1733 | 
            +
                  "step": 145920
         | 
| 1734 | 
            +
                },
         | 
| 1735 | 
            +
                {
         | 
| 1736 | 
            +
                  "epoch": 1.02,
         | 
| 1737 | 
            +
                  "learning_rate": 4.760248708858902e-05,
         | 
| 1738 | 
            +
                  "loss": 4.0374,
         | 
| 1739 | 
            +
                  "step": 146432
         | 
| 1740 | 
            +
                },
         | 
| 1741 | 
            +
                {
         | 
| 1742 | 
            +
                  "epoch": 1.02,
         | 
| 1743 | 
            +
                  "learning_rate": 4.759411751988223e-05,
         | 
| 1744 | 
            +
                  "loss": 4.0331,
         | 
| 1745 | 
            +
                  "step": 146944
         | 
| 1746 | 
            +
                },
         | 
| 1747 | 
            +
                {
         | 
| 1748 | 
            +
                  "epoch": 1.02,
         | 
| 1749 | 
            +
                  "learning_rate": 4.758573157237171e-05,
         | 
| 1750 | 
            +
                  "loss": 4.0284,
         | 
| 1751 | 
            +
                  "step": 147456
         | 
| 1752 | 
            +
                },
         | 
| 1753 | 
            +
                {
         | 
| 1754 | 
            +
                  "epoch": 1.02,
         | 
| 1755 | 
            +
                  "learning_rate": 4.757734562486119e-05,
         | 
| 1756 | 
            +
                  "loss": 4.0381,
         | 
| 1757 | 
            +
                  "step": 147968
         | 
| 1758 | 
            +
                },
         | 
| 1759 | 
            +
                {
         | 
| 1760 | 
            +
                  "epoch": 1.02,
         | 
| 1761 | 
            +
                  "learning_rate": 4.756895967735067e-05,
         | 
| 1762 | 
            +
                  "loss": 4.0264,
         | 
| 1763 | 
            +
                  "step": 148480
         | 
| 1764 | 
            +
                },
         | 
| 1765 | 
            +
                {
         | 
| 1766 | 
            +
                  "epoch": 1.02,
         | 
| 1767 | 
            +
                  "learning_rate": 4.756059010864388e-05,
         | 
| 1768 | 
            +
                  "loss": 4.0306,
         | 
| 1769 | 
            +
                  "step": 148992
         | 
| 1770 | 
            +
                },
         | 
| 1771 | 
            +
                {
         | 
| 1772 | 
            +
                  "epoch": 1.02,
         | 
| 1773 | 
            +
                  "learning_rate": 4.755220416113336e-05,
         | 
| 1774 | 
            +
                  "loss": 4.0283,
         | 
| 1775 | 
            +
                  "step": 149504
         | 
| 1776 | 
            +
                },
         | 
| 1777 | 
            +
                {
         | 
| 1778 | 
            +
                  "epoch": 1.02,
         | 
| 1779 | 
            +
                  "learning_rate": 4.754381821362284e-05,
         | 
| 1780 | 
            +
                  "loss": 4.0197,
         | 
| 1781 | 
            +
                  "step": 150016
         | 
| 1782 | 
            +
                },
         | 
| 1783 | 
            +
                {
         | 
| 1784 | 
            +
                  "epoch": 1.02,
         | 
| 1785 | 
            +
                  "learning_rate": 4.753544864491605e-05,
         | 
| 1786 | 
            +
                  "loss": 4.0409,
         | 
| 1787 | 
            +
                  "step": 150528
         | 
| 1788 | 
            +
                },
         | 
| 1789 | 
            +
                {
         | 
| 1790 | 
            +
                  "epoch": 1.02,
         | 
| 1791 | 
            +
                  "learning_rate": 4.7527062697405536e-05,
         | 
| 1792 | 
            +
                  "loss": 4.0207,
         | 
| 1793 | 
            +
                  "step": 151040
         | 
| 1794 | 
            +
                },
         | 
| 1795 | 
            +
                {
         | 
| 1796 | 
            +
                  "epoch": 1.02,
         | 
| 1797 | 
            +
                  "learning_rate": 4.7518676749895016e-05,
         | 
| 1798 | 
            +
                  "loss": 4.0199,
         | 
| 1799 | 
            +
                  "step": 151552
         | 
| 1800 | 
            +
                },
         | 
| 1801 | 
            +
                {
         | 
| 1802 | 
            +
                  "epoch": 1.02,
         | 
| 1803 | 
            +
                  "learning_rate": 4.7510290802384496e-05,
         | 
| 1804 | 
            +
                  "loss": 4.0233,
         | 
| 1805 | 
            +
                  "step": 152064
         | 
| 1806 | 
            +
                },
         | 
| 1807 | 
            +
                {
         | 
| 1808 | 
            +
                  "epoch": 1.02,
         | 
| 1809 | 
            +
                  "learning_rate": 4.7501904854873976e-05,
         | 
| 1810 | 
            +
                  "loss": 4.0188,
         | 
| 1811 | 
            +
                  "step": 152576
         | 
| 1812 | 
            +
                },
         | 
| 1813 | 
            +
                {
         | 
| 1814 | 
            +
                  "epoch": 1.03,
         | 
| 1815 | 
            +
                  "eval_loss": 4.028048515319824,
         | 
| 1816 | 
            +
                  "eval_runtime": 306.2895,
         | 
| 1817 | 
            +
                  "eval_samples_per_second": 1245.851,
         | 
| 1818 | 
            +
                  "eval_steps_per_second": 38.934,
         | 
| 1819 | 
            +
                  "step": 152640
         | 
| 1820 | 
            +
                },
         | 
| 1821 | 
            +
                {
         | 
| 1822 | 
            +
                  "epoch": 0.0,
         | 
| 1823 | 
            +
                  "learning_rate": 4.7493518907363456e-05,
         | 
| 1824 | 
            +
                  "loss": 4.0033,
         | 
| 1825 | 
            +
                  "step": 153088
         | 
| 1826 | 
            +
                },
         | 
| 1827 | 
            +
                {
         | 
| 1828 | 
            +
                  "epoch": 0.0,
         | 
| 1829 | 
            +
                  "learning_rate": 4.7485132959852936e-05,
         | 
| 1830 | 
            +
                  "loss": 4.0187,
         | 
| 1831 | 
            +
                  "step": 153600
         | 
| 1832 | 
            +
                },
         | 
| 1833 | 
            +
                {
         | 
| 1834 | 
            +
                  "epoch": 0.0,
         | 
| 1835 | 
            +
                  "learning_rate": 4.7476747012342416e-05,
         | 
| 1836 | 
            +
                  "loss": 4.0332,
         | 
| 1837 | 
            +
                  "step": 154112
         | 
| 1838 | 
            +
                },
         | 
| 1839 | 
            +
                {
         | 
| 1840 | 
            +
                  "epoch": 0.0,
         | 
| 1841 | 
            +
                  "learning_rate": 4.7468361064831896e-05,
         | 
| 1842 | 
            +
                  "loss": 4.0153,
         | 
| 1843 | 
            +
                  "step": 154624
         | 
| 1844 | 
            +
                },
         | 
| 1845 | 
            +
                {
         | 
| 1846 | 
            +
                  "epoch": 0.0,
         | 
| 1847 | 
            +
                  "learning_rate": 4.7459975117321376e-05,
         | 
| 1848 | 
            +
                  "loss": 4.0297,
         | 
| 1849 | 
            +
                  "step": 155136
         | 
| 1850 | 
            +
                },
         | 
| 1851 | 
            +
                {
         | 
| 1852 | 
            +
                  "epoch": 0.0,
         | 
| 1853 | 
            +
                  "learning_rate": 4.745158916981085e-05,
         | 
| 1854 | 
            +
                  "loss": 4.0079,
         | 
| 1855 | 
            +
                  "step": 155648
         | 
| 1856 | 
            +
                },
         | 
| 1857 | 
            +
                {
         | 
| 1858 | 
            +
                  "epoch": 0.0,
         | 
| 1859 | 
            +
                  "learning_rate": 4.744320322230033e-05,
         | 
| 1860 | 
            +
                  "loss": 4.021,
         | 
| 1861 | 
            +
                  "step": 156160
         | 
| 1862 | 
            +
                },
         | 
| 1863 | 
            +
                {
         | 
| 1864 | 
            +
                  "epoch": 0.0,
         | 
| 1865 | 
            +
                  "learning_rate": 4.743481727478981e-05,
         | 
| 1866 | 
            +
                  "loss": 3.9999,
         | 
| 1867 | 
            +
                  "step": 156672
         | 
| 1868 | 
            +
                },
         | 
| 1869 | 
            +
                {
         | 
| 1870 | 
            +
                  "epoch": 0.0,
         | 
| 1871 | 
            +
                  "learning_rate": 4.742643132727929e-05,
         | 
| 1872 | 
            +
                  "loss": 4.017,
         | 
| 1873 | 
            +
                  "step": 157184
         | 
| 1874 | 
            +
                },
         | 
| 1875 | 
            +
                {
         | 
| 1876 | 
            +
                  "epoch": 0.0,
         | 
| 1877 | 
            +
                  "learning_rate": 4.741804537976877e-05,
         | 
| 1878 | 
            +
                  "loss": 4.0142,
         | 
| 1879 | 
            +
                  "step": 157696
         | 
| 1880 | 
            +
                },
         | 
| 1881 | 
            +
                {
         | 
| 1882 | 
            +
                  "epoch": 0.0,
         | 
| 1883 | 
            +
                  "learning_rate": 4.740965943225825e-05,
         | 
| 1884 | 
            +
                  "loss": 4.0125,
         | 
| 1885 | 
            +
                  "step": 158208
         | 
| 1886 | 
            +
                },
         | 
| 1887 | 
            +
                {
         | 
| 1888 | 
            +
                  "epoch": 0.0,
         | 
| 1889 | 
            +
                  "learning_rate": 4.7401289863551465e-05,
         | 
| 1890 | 
            +
                  "loss": 4.0213,
         | 
| 1891 | 
            +
                  "step": 158720
         | 
| 1892 | 
            +
                },
         | 
| 1893 | 
            +
                {
         | 
| 1894 | 
            +
                  "epoch": 0.0,
         | 
| 1895 | 
            +
                  "learning_rate": 4.739292029484468e-05,
         | 
| 1896 | 
            +
                  "loss": 4.0019,
         | 
| 1897 | 
            +
                  "step": 159232
         | 
| 1898 | 
            +
                },
         | 
| 1899 | 
            +
                {
         | 
| 1900 | 
            +
                  "epoch": 0.0,
         | 
| 1901 | 
            +
                  "learning_rate": 4.7384534347334154e-05,
         | 
| 1902 | 
            +
                  "loss": 3.9977,
         | 
| 1903 | 
            +
                  "step": 159744
         | 
| 1904 | 
            +
                },
         | 
| 1905 | 
            +
                {
         | 
| 1906 | 
            +
                  "epoch": 0.0,
         | 
| 1907 | 
            +
                  "learning_rate": 4.7376148399823634e-05,
         | 
| 1908 | 
            +
                  "loss": 3.996,
         | 
| 1909 | 
            +
                  "step": 160256
         | 
| 1910 | 
            +
                },
         | 
| 1911 | 
            +
                {
         | 
| 1912 | 
            +
                  "epoch": 0.0,
         | 
| 1913 | 
            +
                  "learning_rate": 4.7367762452313114e-05,
         | 
| 1914 | 
            +
                  "loss": 4.004,
         | 
| 1915 | 
            +
                  "step": 160768
         | 
| 1916 | 
            +
                },
         | 
| 1917 | 
            +
                {
         | 
| 1918 | 
            +
                  "epoch": 0.0,
         | 
| 1919 | 
            +
                  "learning_rate": 4.7359376504802594e-05,
         | 
| 1920 | 
            +
                  "loss": 4.0087,
         | 
| 1921 | 
            +
                  "step": 161280
         | 
| 1922 | 
            +
                },
         | 
| 1923 | 
            +
                {
         | 
| 1924 | 
            +
                  "epoch": 0.0,
         | 
| 1925 | 
            +
                  "learning_rate": 4.7350990557292074e-05,
         | 
| 1926 | 
            +
                  "loss": 4.0022,
         | 
| 1927 | 
            +
                  "step": 161792
         | 
| 1928 | 
            +
                },
         | 
| 1929 | 
            +
                {
         | 
| 1930 | 
            +
                  "epoch": 0.0,
         | 
| 1931 | 
            +
                  "learning_rate": 4.7342604609781554e-05,
         | 
| 1932 | 
            +
                  "loss": 4.0041,
         | 
| 1933 | 
            +
                  "step": 162304
         | 
| 1934 | 
            +
                },
         | 
| 1935 | 
            +
                {
         | 
| 1936 | 
            +
                  "epoch": 0.0,
         | 
| 1937 | 
            +
                  "learning_rate": 4.733423504107476e-05,
         | 
| 1938 | 
            +
                  "loss": 4.0239,
         | 
| 1939 | 
            +
                  "step": 162816
         | 
| 1940 | 
            +
                },
         | 
| 1941 | 
            +
                {
         | 
| 1942 | 
            +
                  "epoch": 0.0,
         | 
| 1943 | 
            +
                  "learning_rate": 4.732584909356424e-05,
         | 
| 1944 | 
            +
                  "loss": 3.9994,
         | 
| 1945 | 
            +
                  "step": 163328
         | 
| 1946 | 
            +
                },
         | 
| 1947 | 
            +
                {
         | 
| 1948 | 
            +
                  "epoch": 0.0,
         | 
| 1949 | 
            +
                  "learning_rate": 4.731746314605372e-05,
         | 
| 1950 | 
            +
                  "loss": 3.9946,
         | 
| 1951 | 
            +
                  "step": 163840
         | 
| 1952 | 
            +
                },
         | 
| 1953 | 
            +
                {
         | 
| 1954 | 
            +
                  "epoch": 0.0,
         | 
| 1955 | 
            +
                  "learning_rate": 4.73090771985432e-05,
         | 
| 1956 | 
            +
                  "loss": 4.0021,
         | 
| 1957 | 
            +
                  "step": 164352
         | 
| 1958 | 
            +
                },
         | 
| 1959 | 
            +
                {
         | 
| 1960 | 
            +
                  "epoch": 0.0,
         | 
| 1961 | 
            +
                  "learning_rate": 4.730070762983642e-05,
         | 
| 1962 | 
            +
                  "loss": 4.0077,
         | 
| 1963 | 
            +
                  "step": 164864
         | 
| 1964 | 
            +
                },
         | 
| 1965 | 
            +
                {
         | 
| 1966 | 
            +
                  "epoch": 0.0,
         | 
| 1967 | 
            +
                  "learning_rate": 4.72923216823259e-05,
         | 
| 1968 | 
            +
                  "loss": 3.9908,
         | 
| 1969 | 
            +
                  "step": 165376
         | 
| 1970 | 
            +
                },
         | 
| 1971 | 
            +
                {
         | 
| 1972 | 
            +
                  "epoch": 0.0,
         | 
| 1973 | 
            +
                  "learning_rate": 4.728393573481538e-05,
         | 
| 1974 | 
            +
                  "loss": 3.9969,
         | 
| 1975 | 
            +
                  "step": 165888
         | 
| 1976 | 
            +
                },
         | 
| 1977 | 
            +
                {
         | 
| 1978 | 
            +
                  "epoch": 0.0,
         | 
| 1979 | 
            +
                  "learning_rate": 4.727554978730486e-05,
         | 
| 1980 | 
            +
                  "loss": 3.9984,
         | 
| 1981 | 
            +
                  "step": 166400
         | 
| 1982 | 
            +
                },
         | 
| 1983 | 
            +
                {
         | 
| 1984 | 
            +
                  "epoch": 0.0,
         | 
| 1985 | 
            +
                  "learning_rate": 4.726718021859807e-05,
         | 
| 1986 | 
            +
                  "loss": 3.9948,
         | 
| 1987 | 
            +
                  "step": 166912
         | 
| 1988 | 
            +
                },
         | 
| 1989 | 
            +
                {
         | 
| 1990 | 
            +
                  "epoch": 0.0,
         | 
| 1991 | 
            +
                  "learning_rate": 4.725879427108755e-05,
         | 
| 1992 | 
            +
                  "loss": 3.9809,
         | 
| 1993 | 
            +
                  "step": 167424
         | 
| 1994 | 
            +
                },
         | 
| 1995 | 
            +
                {
         | 
| 1996 | 
            +
                  "epoch": 0.01,
         | 
| 1997 | 
            +
                  "learning_rate": 4.725040832357703e-05,
         | 
| 1998 | 
            +
                  "loss": 3.9865,
         | 
| 1999 | 
            +
                  "step": 167936
         | 
| 2000 | 
            +
                },
         | 
| 2001 | 
            +
                {
         | 
| 2002 | 
            +
                  "epoch": 0.01,
         | 
| 2003 | 
            +
                  "learning_rate": 4.724202237606651e-05,
         | 
| 2004 | 
            +
                  "loss": 3.9889,
         | 
| 2005 | 
            +
                  "step": 168448
         | 
| 2006 | 
            +
                },
         | 
| 2007 | 
            +
                {
         | 
| 2008 | 
            +
                  "epoch": 0.01,
         | 
| 2009 | 
            +
                  "learning_rate": 4.7233652807359716e-05,
         | 
| 2010 | 
            +
                  "loss": 3.9934,
         | 
| 2011 | 
            +
                  "step": 168960
         | 
| 2012 | 
            +
                },
         | 
| 2013 | 
            +
                {
         | 
| 2014 | 
            +
                  "epoch": 0.01,
         | 
| 2015 | 
            +
                  "learning_rate": 4.7225266859849196e-05,
         | 
| 2016 | 
            +
                  "loss": 4.0065,
         | 
| 2017 | 
            +
                  "step": 169472
         | 
| 2018 | 
            +
                },
         | 
| 2019 | 
            +
                {
         | 
| 2020 | 
            +
                  "epoch": 0.01,
         | 
| 2021 | 
            +
                  "learning_rate": 4.7216880912338676e-05,
         | 
| 2022 | 
            +
                  "loss": 3.9845,
         | 
| 2023 | 
            +
                  "step": 169984
         | 
| 2024 | 
            +
                },
         | 
| 2025 | 
            +
                {
         | 
| 2026 | 
            +
                  "epoch": 0.01,
         | 
| 2027 | 
            +
                  "learning_rate": 4.7208494964828156e-05,
         | 
| 2028 | 
            +
                  "loss": 3.9848,
         | 
| 2029 | 
            +
                  "step": 170496
         | 
| 2030 | 
            +
                },
         | 
| 2031 | 
            +
                {
         | 
| 2032 | 
            +
                  "epoch": 0.01,
         | 
| 2033 | 
            +
                  "learning_rate": 4.720010901731764e-05,
         | 
| 2034 | 
            +
                  "loss": 3.996,
         | 
| 2035 | 
            +
                  "step": 171008
         | 
| 2036 | 
            +
                },
         | 
| 2037 | 
            +
                {
         | 
| 2038 | 
            +
                  "epoch": 0.01,
         | 
| 2039 | 
            +
                  "learning_rate": 4.719172306980712e-05,
         | 
| 2040 | 
            +
                  "loss": 3.9793,
         | 
| 2041 | 
            +
                  "step": 171520
         | 
| 2042 | 
            +
                },
         | 
| 2043 | 
            +
                {
         | 
| 2044 | 
            +
                  "epoch": 0.01,
         | 
| 2045 | 
            +
                  "learning_rate": 4.71833371222966e-05,
         | 
| 2046 | 
            +
                  "loss": 3.9776,
         | 
| 2047 | 
            +
                  "step": 172032
         | 
| 2048 | 
            +
                },
         | 
| 2049 | 
            +
                {
         | 
| 2050 | 
            +
                  "epoch": 0.01,
         | 
| 2051 | 
            +
                  "learning_rate": 4.717496755358981e-05,
         | 
| 2052 | 
            +
                  "loss": 3.9745,
         | 
| 2053 | 
            +
                  "step": 172544
         | 
| 2054 | 
            +
                },
         | 
| 2055 | 
            +
                {
         | 
| 2056 | 
            +
                  "epoch": 0.01,
         | 
| 2057 | 
            +
                  "learning_rate": 4.716658160607929e-05,
         | 
| 2058 | 
            +
                  "loss": 3.9827,
         | 
| 2059 | 
            +
                  "step": 173056
         | 
| 2060 | 
            +
                },
         | 
| 2061 | 
            +
                {
         | 
| 2062 | 
            +
                  "epoch": 0.01,
         | 
| 2063 | 
            +
                  "learning_rate": 4.715819565856877e-05,
         | 
| 2064 | 
            +
                  "loss": 3.9709,
         | 
| 2065 | 
            +
                  "step": 173568
         | 
| 2066 | 
            +
                },
         | 
| 2067 | 
            +
                {
         | 
| 2068 | 
            +
                  "epoch": 0.01,
         | 
| 2069 | 
            +
                  "learning_rate": 4.714980971105825e-05,
         | 
| 2070 | 
            +
                  "loss": 3.9936,
         | 
| 2071 | 
            +
                  "step": 174080
         | 
| 2072 | 
            +
                },
         | 
| 2073 | 
            +
                {
         | 
| 2074 | 
            +
                  "epoch": 0.01,
         | 
| 2075 | 
            +
                  "learning_rate": 4.714144014235146e-05,
         | 
| 2076 | 
            +
                  "loss": 3.9745,
         | 
| 2077 | 
            +
                  "step": 174592
         | 
| 2078 | 
            +
                },
         | 
| 2079 | 
            +
                {
         | 
| 2080 | 
            +
                  "epoch": 0.01,
         | 
| 2081 | 
            +
                  "learning_rate": 4.713305419484094e-05,
         | 
| 2082 | 
            +
                  "loss": 3.9844,
         | 
| 2083 | 
            +
                  "step": 175104
         | 
| 2084 | 
            +
                },
         | 
| 2085 | 
            +
                {
         | 
| 2086 | 
            +
                  "epoch": 0.01,
         | 
| 2087 | 
            +
                  "learning_rate": 4.712466824733042e-05,
         | 
| 2088 | 
            +
                  "loss": 3.9788,
         | 
| 2089 | 
            +
                  "step": 175616
         | 
| 2090 | 
            +
                },
         | 
| 2091 | 
            +
                {
         | 
| 2092 | 
            +
                  "epoch": 0.01,
         | 
| 2093 | 
            +
                  "learning_rate": 4.71162822998199e-05,
         | 
| 2094 | 
            +
                  "loss": 3.9783,
         | 
| 2095 | 
            +
                  "step": 176128
         | 
| 2096 | 
            +
                },
         | 
| 2097 | 
            +
                {
         | 
| 2098 | 
            +
                  "epoch": 0.01,
         | 
| 2099 | 
            +
                  "learning_rate": 4.710791273111311e-05,
         | 
| 2100 | 
            +
                  "loss": 3.9774,
         | 
| 2101 | 
            +
                  "step": 176640
         | 
| 2102 | 
            +
                },
         | 
| 2103 | 
            +
                {
         | 
| 2104 | 
            +
                  "epoch": 0.01,
         | 
| 2105 | 
            +
                  "learning_rate": 4.709952678360259e-05,
         | 
| 2106 | 
            +
                  "loss": 3.9654,
         | 
| 2107 | 
            +
                  "step": 177152
         | 
| 2108 | 
            +
                },
         | 
| 2109 | 
            +
                {
         | 
| 2110 | 
            +
                  "epoch": 0.01,
         | 
| 2111 | 
            +
                  "learning_rate": 4.709114083609208e-05,
         | 
| 2112 | 
            +
                  "loss": 3.9623,
         | 
| 2113 | 
            +
                  "step": 177664
         | 
| 2114 | 
            +
                },
         | 
| 2115 | 
            +
                {
         | 
| 2116 | 
            +
                  "epoch": 0.01,
         | 
| 2117 | 
            +
                  "learning_rate": 4.708275488858156e-05,
         | 
| 2118 | 
            +
                  "loss": 3.9837,
         | 
| 2119 | 
            +
                  "step": 178176
         | 
| 2120 | 
            +
                },
         | 
| 2121 | 
            +
                {
         | 
| 2122 | 
            +
                  "epoch": 0.01,
         | 
| 2123 | 
            +
                  "learning_rate": 4.7074385319874766e-05,
         | 
| 2124 | 
            +
                  "loss": 3.9745,
         | 
| 2125 | 
            +
                  "step": 178688
         | 
| 2126 | 
            +
                },
         | 
| 2127 | 
            +
                {
         | 
| 2128 | 
            +
                  "epoch": 0.01,
         | 
| 2129 | 
            +
                  "learning_rate": 4.7065999372364246e-05,
         | 
| 2130 | 
            +
                  "loss": 3.9643,
         | 
| 2131 | 
            +
                  "step": 179200
         | 
| 2132 | 
            +
                },
         | 
| 2133 | 
            +
                {
         | 
| 2134 | 
            +
                  "epoch": 0.01,
         | 
| 2135 | 
            +
                  "learning_rate": 4.7057613424853726e-05,
         | 
| 2136 | 
            +
                  "loss": 3.9668,
         | 
| 2137 | 
            +
                  "step": 179712
         | 
| 2138 | 
            +
                },
         | 
| 2139 | 
            +
                {
         | 
| 2140 | 
            +
                  "epoch": 0.01,
         | 
| 2141 | 
            +
                  "learning_rate": 4.7049227477343206e-05,
         | 
| 2142 | 
            +
                  "loss": 3.9747,
         | 
| 2143 | 
            +
                  "step": 180224
         | 
| 2144 | 
            +
                },
         | 
| 2145 | 
            +
                {
         | 
| 2146 | 
            +
                  "epoch": 0.01,
         | 
| 2147 | 
            +
                  "learning_rate": 4.7040857908636415e-05,
         | 
| 2148 | 
            +
                  "loss": 3.9541,
         | 
| 2149 | 
            +
                  "step": 180736
         | 
| 2150 | 
            +
                },
         | 
| 2151 | 
            +
                {
         | 
| 2152 | 
            +
                  "epoch": 0.01,
         | 
| 2153 | 
            +
                  "learning_rate": 4.7032471961125895e-05,
         | 
| 2154 | 
            +
                  "loss": 3.9765,
         | 
| 2155 | 
            +
                  "step": 181248
         | 
| 2156 | 
            +
                },
         | 
| 2157 | 
            +
                {
         | 
| 2158 | 
            +
                  "epoch": 0.01,
         | 
| 2159 | 
            +
                  "learning_rate": 4.7024086013615375e-05,
         | 
| 2160 | 
            +
                  "loss": 3.9645,
         | 
| 2161 | 
            +
                  "step": 181760
         | 
| 2162 | 
            +
                },
         | 
| 2163 | 
            +
                {
         | 
| 2164 | 
            +
                  "epoch": 0.01,
         | 
| 2165 | 
            +
                  "learning_rate": 4.7015700066104855e-05,
         | 
| 2166 | 
            +
                  "loss": 3.9645,
         | 
| 2167 | 
            +
                  "step": 182272
         | 
| 2168 | 
            +
                },
         | 
| 2169 | 
            +
                {
         | 
| 2170 | 
            +
                  "epoch": 0.01,
         | 
| 2171 | 
            +
                  "learning_rate": 4.7007330497398064e-05,
         | 
| 2172 | 
            +
                  "loss": 3.9803,
         | 
| 2173 | 
            +
                  "step": 182784
         | 
| 2174 | 
            +
                },
         | 
| 2175 | 
            +
                {
         | 
| 2176 | 
            +
                  "epoch": 0.01,
         | 
| 2177 | 
            +
                  "learning_rate": 4.6998944549887544e-05,
         | 
| 2178 | 
            +
                  "loss": 3.9573,
         | 
| 2179 | 
            +
                  "step": 183296
         | 
| 2180 | 
            +
                },
         | 
| 2181 | 
            +
                {
         | 
| 2182 | 
            +
                  "epoch": 0.01,
         | 
| 2183 | 
            +
                  "learning_rate": 4.699055860237703e-05,
         | 
| 2184 | 
            +
                  "loss": 3.9535,
         | 
| 2185 | 
            +
                  "step": 183808
         | 
| 2186 | 
            +
                },
         | 
| 2187 | 
            +
                {
         | 
| 2188 | 
            +
                  "epoch": 0.01,
         | 
| 2189 | 
            +
                  "learning_rate": 4.698217265486651e-05,
         | 
| 2190 | 
            +
                  "loss": 3.9659,
         | 
| 2191 | 
            +
                  "step": 184320
         | 
| 2192 | 
            +
                },
         | 
| 2193 | 
            +
                {
         | 
| 2194 | 
            +
                  "epoch": 0.01,
         | 
| 2195 | 
            +
                  "learning_rate": 4.697380308615972e-05,
         | 
| 2196 | 
            +
                  "loss": 3.9483,
         | 
| 2197 | 
            +
                  "step": 184832
         | 
| 2198 | 
            +
                },
         | 
| 2199 | 
            +
                {
         | 
| 2200 | 
            +
                  "epoch": 0.01,
         | 
| 2201 | 
            +
                  "learning_rate": 4.69654171386492e-05,
         | 
| 2202 | 
            +
                  "loss": 3.9539,
         | 
| 2203 | 
            +
                  "step": 185344
         | 
| 2204 | 
            +
                },
         | 
| 2205 | 
            +
                {
         | 
| 2206 | 
            +
                  "epoch": 0.01,
         | 
| 2207 | 
            +
                  "learning_rate": 4.695703119113868e-05,
         | 
| 2208 | 
            +
                  "loss": 3.9648,
         | 
| 2209 | 
            +
                  "step": 185856
         | 
| 2210 | 
            +
                },
         | 
| 2211 | 
            +
                {
         | 
| 2212 | 
            +
                  "epoch": 0.01,
         | 
| 2213 | 
            +
                  "learning_rate": 4.694864524362816e-05,
         | 
| 2214 | 
            +
                  "loss": 3.9693,
         | 
| 2215 | 
            +
                  "step": 186368
         | 
| 2216 | 
            +
                },
         | 
| 2217 | 
            +
                {
         | 
| 2218 | 
            +
                  "epoch": 0.01,
         | 
| 2219 | 
            +
                  "learning_rate": 4.694027567492137e-05,
         | 
| 2220 | 
            +
                  "loss": 3.9537,
         | 
| 2221 | 
            +
                  "step": 186880
         | 
| 2222 | 
            +
                },
         | 
| 2223 | 
            +
                {
         | 
| 2224 | 
            +
                  "epoch": 0.01,
         | 
| 2225 | 
            +
                  "learning_rate": 4.693188972741085e-05,
         | 
| 2226 | 
            +
                  "loss": 3.9554,
         | 
| 2227 | 
            +
                  "step": 187392
         | 
| 2228 | 
            +
                },
         | 
| 2229 | 
            +
                {
         | 
| 2230 | 
            +
                  "epoch": 0.01,
         | 
| 2231 | 
            +
                  "learning_rate": 4.692352015870406e-05,
         | 
| 2232 | 
            +
                  "loss": 3.9434,
         | 
| 2233 | 
            +
                  "step": 187904
         | 
| 2234 | 
            +
                },
         | 
| 2235 | 
            +
                {
         | 
| 2236 | 
            +
                  "epoch": 0.01,
         | 
| 2237 | 
            +
                  "learning_rate": 4.691513421119354e-05,
         | 
| 2238 | 
            +
                  "loss": 3.9656,
         | 
| 2239 | 
            +
                  "step": 188416
         | 
| 2240 | 
            +
                },
         | 
| 2241 | 
            +
                {
         | 
| 2242 | 
            +
                  "epoch": 0.01,
         | 
| 2243 | 
            +
                  "learning_rate": 4.690674826368302e-05,
         | 
| 2244 | 
            +
                  "loss": 3.9581,
         | 
| 2245 | 
            +
                  "step": 188928
         | 
| 2246 | 
            +
                },
         | 
| 2247 | 
            +
                {
         | 
| 2248 | 
            +
                  "epoch": 0.01,
         | 
| 2249 | 
            +
                  "learning_rate": 4.68983623161725e-05,
         | 
| 2250 | 
            +
                  "loss": 3.9644,
         | 
| 2251 | 
            +
                  "step": 189440
         | 
| 2252 | 
            +
                },
         | 
| 2253 | 
            +
                {
         | 
| 2254 | 
            +
                  "epoch": 0.01,
         | 
| 2255 | 
            +
                  "learning_rate": 4.6889976368661984e-05,
         | 
| 2256 | 
            +
                  "loss": 3.9602,
         | 
| 2257 | 
            +
                  "step": 189952
         | 
| 2258 | 
            +
                },
         | 
| 2259 | 
            +
                {
         | 
| 2260 | 
            +
                  "epoch": 0.01,
         | 
| 2261 | 
            +
                  "learning_rate": 4.688159042115146e-05,
         | 
| 2262 | 
            +
                  "loss": 3.9644,
         | 
| 2263 | 
            +
                  "step": 190464
         | 
| 2264 | 
            +
                },
         | 
| 2265 | 
            +
                {
         | 
| 2266 | 
            +
                  "epoch": 0.01,
         | 
| 2267 | 
            +
                  "learning_rate": 4.687320447364094e-05,
         | 
| 2268 | 
            +
                  "loss": 3.9693,
         | 
| 2269 | 
            +
                  "step": 190976
         | 
| 2270 | 
            +
                },
         | 
| 2271 | 
            +
                {
         | 
| 2272 | 
            +
                  "epoch": 0.01,
         | 
| 2273 | 
            +
                  "learning_rate": 4.686481852613042e-05,
         | 
| 2274 | 
            +
                  "loss": 3.9435,
         | 
| 2275 | 
            +
                  "step": 191488
         | 
| 2276 | 
            +
                },
         | 
| 2277 | 
            +
                {
         | 
| 2278 | 
            +
                  "epoch": 0.01,
         | 
| 2279 | 
            +
                  "learning_rate": 4.685644895742363e-05,
         | 
| 2280 | 
            +
                  "loss": 3.9572,
         | 
| 2281 | 
            +
                  "step": 192000
         | 
| 2282 | 
            +
                },
         | 
| 2283 | 
            +
                {
         | 
| 2284 | 
            +
                  "epoch": 0.01,
         | 
| 2285 | 
            +
                  "learning_rate": 4.6848063009913106e-05,
         | 
| 2286 | 
            +
                  "loss": 3.9608,
         | 
| 2287 | 
            +
                  "step": 192512
         | 
| 2288 | 
            +
                },
         | 
| 2289 | 
            +
                {
         | 
| 2290 | 
            +
                  "epoch": 0.01,
         | 
| 2291 | 
            +
                  "learning_rate": 4.6839677062402586e-05,
         | 
| 2292 | 
            +
                  "loss": 3.944,
         | 
| 2293 | 
            +
                  "step": 193024
         | 
| 2294 | 
            +
                },
         | 
| 2295 | 
            +
                {
         | 
| 2296 | 
            +
                  "epoch": 0.01,
         | 
| 2297 | 
            +
                  "learning_rate": 4.6831291114892066e-05,
         | 
| 2298 | 
            +
                  "loss": 3.9648,
         | 
| 2299 | 
            +
                  "step": 193536
         | 
| 2300 | 
            +
                },
         | 
| 2301 | 
            +
                {
         | 
| 2302 | 
            +
                  "epoch": 0.01,
         | 
| 2303 | 
            +
                  "learning_rate": 4.6822905167381546e-05,
         | 
| 2304 | 
            +
                  "loss": 3.9586,
         | 
| 2305 | 
            +
                  "step": 194048
         | 
| 2306 | 
            +
                },
         | 
| 2307 | 
            +
                {
         | 
| 2308 | 
            +
                  "epoch": 0.01,
         | 
| 2309 | 
            +
                  "learning_rate": 4.6814519219871026e-05,
         | 
| 2310 | 
            +
                  "loss": 3.9626,
         | 
| 2311 | 
            +
                  "step": 194560
         | 
| 2312 | 
            +
                },
         | 
| 2313 | 
            +
                {
         | 
| 2314 | 
            +
                  "epoch": 0.01,
         | 
| 2315 | 
            +
                  "learning_rate": 4.6806133272360506e-05,
         | 
| 2316 | 
            +
                  "loss": 3.9618,
         | 
| 2317 | 
            +
                  "step": 195072
         | 
| 2318 | 
            +
                },
         | 
| 2319 | 
            +
                {
         | 
| 2320 | 
            +
                  "epoch": 0.01,
         | 
| 2321 | 
            +
                  "learning_rate": 4.6797747324849986e-05,
         | 
| 2322 | 
            +
                  "loss": 3.9387,
         | 
| 2323 | 
            +
                  "step": 195584
         | 
| 2324 | 
            +
                },
         | 
| 2325 | 
            +
                {
         | 
| 2326 | 
            +
                  "epoch": 0.01,
         | 
| 2327 | 
            +
                  "learning_rate": 4.67893777561432e-05,
         | 
| 2328 | 
            +
                  "loss": 3.9516,
         | 
| 2329 | 
            +
                  "step": 196096
         | 
| 2330 | 
            +
                },
         | 
| 2331 | 
            +
                {
         | 
| 2332 | 
            +
                  "epoch": 0.01,
         | 
| 2333 | 
            +
                  "learning_rate": 4.678099180863268e-05,
         | 
| 2334 | 
            +
                  "loss": 3.9484,
         | 
| 2335 | 
            +
                  "step": 196608
         | 
| 2336 | 
            +
                },
         | 
| 2337 | 
            +
                {
         | 
| 2338 | 
            +
                  "epoch": 0.01,
         | 
| 2339 | 
            +
                  "learning_rate": 4.677260586112216e-05,
         | 
| 2340 | 
            +
                  "loss": 3.9564,
         | 
| 2341 | 
            +
                  "step": 197120
         | 
| 2342 | 
            +
                },
         | 
| 2343 | 
            +
                {
         | 
| 2344 | 
            +
                  "epoch": 0.01,
         | 
| 2345 | 
            +
                  "learning_rate": 4.676421991361164e-05,
         | 
| 2346 | 
            +
                  "loss": 3.9478,
         | 
| 2347 | 
            +
                  "step": 197632
         | 
| 2348 | 
            +
                },
         | 
| 2349 | 
            +
                {
         | 
| 2350 | 
            +
                  "epoch": 0.01,
         | 
| 2351 | 
            +
                  "learning_rate": 4.675585034490485e-05,
         | 
| 2352 | 
            +
                  "loss": 3.9475,
         | 
| 2353 | 
            +
                  "step": 198144
         | 
| 2354 | 
            +
                },
         | 
| 2355 | 
            +
                {
         | 
| 2356 | 
            +
                  "epoch": 0.02,
         | 
| 2357 | 
            +
                  "learning_rate": 4.674746439739433e-05,
         | 
| 2358 | 
            +
                  "loss": 3.9522,
         | 
| 2359 | 
            +
                  "step": 198656
         | 
| 2360 | 
            +
                },
         | 
| 2361 | 
            +
                {
         | 
| 2362 | 
            +
                  "epoch": 0.02,
         | 
| 2363 | 
            +
                  "learning_rate": 4.673907844988381e-05,
         | 
| 2364 | 
            +
                  "loss": 3.9495,
         | 
| 2365 | 
            +
                  "step": 199168
         | 
| 2366 | 
            +
                },
         | 
| 2367 | 
            +
                {
         | 
| 2368 | 
            +
                  "epoch": 0.02,
         | 
| 2369 | 
            +
                  "learning_rate": 4.673069250237329e-05,
         | 
| 2370 | 
            +
                  "loss": 3.9351,
         | 
| 2371 | 
            +
                  "step": 199680
         | 
| 2372 | 
            +
                },
         | 
| 2373 | 
            +
                {
         | 
| 2374 | 
            +
                  "epoch": 0.02,
         | 
| 2375 | 
            +
                  "learning_rate": 4.67223229336665e-05,
         | 
| 2376 | 
            +
                  "loss": 3.9416,
         | 
| 2377 | 
            +
                  "step": 200192
         | 
| 2378 | 
            +
                },
         | 
| 2379 | 
            +
                {
         | 
| 2380 | 
            +
                  "epoch": 0.02,
         | 
| 2381 | 
            +
                  "learning_rate": 4.671393698615598e-05,
         | 
| 2382 | 
            +
                  "loss": 3.9505,
         | 
| 2383 | 
            +
                  "step": 200704
         | 
| 2384 | 
            +
                },
         | 
| 2385 | 
            +
                {
         | 
| 2386 | 
            +
                  "epoch": 0.02,
         | 
| 2387 | 
            +
                  "learning_rate": 4.670556741744919e-05,
         | 
| 2388 | 
            +
                  "loss": 3.9569,
         | 
| 2389 | 
            +
                  "step": 201216
         | 
| 2390 | 
            +
                },
         | 
| 2391 | 
            +
                {
         | 
| 2392 | 
            +
                  "epoch": 0.02,
         | 
| 2393 | 
            +
                  "learning_rate": 4.6697181469938675e-05,
         | 
| 2394 | 
            +
                  "loss": 3.9474,
         | 
| 2395 | 
            +
                  "step": 201728
         | 
| 2396 | 
            +
                },
         | 
| 2397 | 
            +
                {
         | 
| 2398 | 
            +
                  "epoch": 0.02,
         | 
| 2399 | 
            +
                  "learning_rate": 4.6688795522428155e-05,
         | 
| 2400 | 
            +
                  "loss": 3.9269,
         | 
| 2401 | 
            +
                  "step": 202240
         | 
| 2402 | 
            +
                },
         | 
| 2403 | 
            +
                {
         | 
| 2404 | 
            +
                  "epoch": 0.02,
         | 
| 2405 | 
            +
                  "learning_rate": 4.6680409574917635e-05,
         | 
| 2406 | 
            +
                  "loss": 3.9391,
         | 
| 2407 | 
            +
                  "step": 202752
         | 
| 2408 | 
            +
                },
         | 
| 2409 | 
            +
                {
         | 
| 2410 | 
            +
                  "epoch": 0.02,
         | 
| 2411 | 
            +
                  "learning_rate": 4.6672023627407115e-05,
         | 
| 2412 | 
            +
                  "loss": 3.9474,
         | 
| 2413 | 
            +
                  "step": 203264
         | 
| 2414 | 
            +
                },
         | 
| 2415 | 
            +
                {
         | 
| 2416 | 
            +
                  "epoch": 0.02,
         | 
| 2417 | 
            +
                  "learning_rate": 4.6663654058700324e-05,
         | 
| 2418 | 
            +
                  "loss": 3.944,
         | 
| 2419 | 
            +
                  "step": 203776
         | 
| 2420 | 
            +
                },
         | 
| 2421 | 
            +
                {
         | 
| 2422 | 
            +
                  "epoch": 0.02,
         | 
| 2423 | 
            +
                  "learning_rate": 4.6655268111189804e-05,
         | 
| 2424 | 
            +
                  "loss": 3.9414,
         | 
| 2425 | 
            +
                  "step": 204288
         | 
| 2426 | 
            +
                },
         | 
| 2427 | 
            +
                {
         | 
| 2428 | 
            +
                  "epoch": 0.02,
         | 
| 2429 | 
            +
                  "learning_rate": 4.6646882163679284e-05,
         | 
| 2430 | 
            +
                  "loss": 3.9361,
         | 
| 2431 | 
            +
                  "step": 204800
         | 
| 2432 | 
            +
                },
         | 
| 2433 | 
            +
                {
         | 
| 2434 | 
            +
                  "epoch": 0.02,
         | 
| 2435 | 
            +
                  "learning_rate": 4.6638496216168764e-05,
         | 
| 2436 | 
            +
                  "loss": 3.9264,
         | 
| 2437 | 
            +
                  "step": 205312
         | 
| 2438 | 
            +
                },
         | 
| 2439 | 
            +
                {
         | 
| 2440 | 
            +
                  "epoch": 0.02,
         | 
| 2441 | 
            +
                  "learning_rate": 4.6630110268658244e-05,
         | 
| 2442 | 
            +
                  "loss": 3.9458,
         | 
| 2443 | 
            +
                  "step": 205824
         | 
| 2444 | 
            +
                },
         | 
| 2445 | 
            +
                {
         | 
| 2446 | 
            +
                  "epoch": 0.02,
         | 
| 2447 | 
            +
                  "learning_rate": 4.662174069995145e-05,
         | 
| 2448 | 
            +
                  "loss": 3.9211,
         | 
| 2449 | 
            +
                  "step": 206336
         | 
| 2450 | 
            +
                },
         | 
| 2451 | 
            +
                {
         | 
| 2452 | 
            +
                  "epoch": 0.02,
         | 
| 2453 | 
            +
                  "learning_rate": 4.661335475244093e-05,
         | 
| 2454 | 
            +
                  "loss": 3.9351,
         | 
| 2455 | 
            +
                  "step": 206848
         | 
| 2456 | 
            +
                },
         | 
| 2457 | 
            +
                {
         | 
| 2458 | 
            +
                  "epoch": 0.02,
         | 
| 2459 | 
            +
                  "learning_rate": 4.660496880493041e-05,
         | 
| 2460 | 
            +
                  "loss": 3.9315,
         | 
| 2461 | 
            +
                  "step": 207360
         | 
| 2462 | 
            +
                },
         | 
| 2463 | 
            +
                {
         | 
| 2464 | 
            +
                  "epoch": 0.02,
         | 
| 2465 | 
            +
                  "learning_rate": 4.659658285741989e-05,
         | 
| 2466 | 
            +
                  "loss": 3.943,
         | 
| 2467 | 
            +
                  "step": 207872
         | 
| 2468 | 
            +
                },
         | 
| 2469 | 
            +
                {
         | 
| 2470 | 
            +
                  "epoch": 0.02,
         | 
| 2471 | 
            +
                  "learning_rate": 4.658821328871311e-05,
         | 
| 2472 | 
            +
                  "loss": 3.9272,
         | 
| 2473 | 
            +
                  "step": 208384
         | 
| 2474 | 
            +
                },
         | 
| 2475 | 
            +
                {
         | 
| 2476 | 
            +
                  "epoch": 0.02,
         | 
| 2477 | 
            +
                  "learning_rate": 4.657982734120259e-05,
         | 
| 2478 | 
            +
                  "loss": 3.9401,
         | 
| 2479 | 
            +
                  "step": 208896
         | 
| 2480 | 
            +
                },
         | 
| 2481 | 
            +
                {
         | 
| 2482 | 
            +
                  "epoch": 0.02,
         | 
| 2483 | 
            +
                  "learning_rate": 4.657144139369207e-05,
         | 
| 2484 | 
            +
                  "loss": 3.9298,
         | 
| 2485 | 
            +
                  "step": 209408
         | 
| 2486 | 
            +
                },
         | 
| 2487 | 
            +
                {
         | 
| 2488 | 
            +
                  "epoch": 0.02,
         | 
| 2489 | 
            +
                  "learning_rate": 4.656305544618155e-05,
         | 
| 2490 | 
            +
                  "loss": 3.9292,
         | 
| 2491 | 
            +
                  "step": 209920
         | 
| 2492 | 
            +
                },
         | 
| 2493 | 
            +
                {
         | 
| 2494 | 
            +
                  "epoch": 0.02,
         | 
| 2495 | 
            +
                  "learning_rate": 4.655466949867103e-05,
         | 
| 2496 | 
            +
                  "loss": 3.9344,
         | 
| 2497 | 
            +
                  "step": 210432
         | 
| 2498 | 
            +
                },
         | 
| 2499 | 
            +
                {
         | 
| 2500 | 
            +
                  "epoch": 0.02,
         | 
| 2501 | 
            +
                  "learning_rate": 4.654628355116051e-05,
         | 
| 2502 | 
            +
                  "loss": 3.9229,
         | 
| 2503 | 
            +
                  "step": 210944
         | 
| 2504 | 
            +
                },
         | 
| 2505 | 
            +
                {
         | 
| 2506 | 
            +
                  "epoch": 0.02,
         | 
| 2507 | 
            +
                  "learning_rate": 4.653789760364999e-05,
         | 
| 2508 | 
            +
                  "loss": 3.9399,
         | 
| 2509 | 
            +
                  "step": 211456
         | 
| 2510 | 
            +
                },
         | 
| 2511 | 
            +
                {
         | 
| 2512 | 
            +
                  "epoch": 0.02,
         | 
| 2513 | 
            +
                  "learning_rate": 4.652951165613947e-05,
         | 
| 2514 | 
            +
                  "loss": 3.9386,
         | 
| 2515 | 
            +
                  "step": 211968
         | 
| 2516 | 
            +
                },
         | 
| 2517 | 
            +
                {
         | 
| 2518 | 
            +
                  "epoch": 0.02,
         | 
| 2519 | 
            +
                  "learning_rate": 4.652115846623641e-05,
         | 
| 2520 | 
            +
                  "loss": 3.9365,
         | 
| 2521 | 
            +
                  "step": 212480
         | 
| 2522 | 
            +
                },
         | 
| 2523 | 
            +
                {
         | 
| 2524 | 
            +
                  "epoch": 0.02,
         | 
| 2525 | 
            +
                  "learning_rate": 4.651277251872589e-05,
         | 
| 2526 | 
            +
                  "loss": 3.9297,
         | 
| 2527 | 
            +
                  "step": 212992
         | 
| 2528 | 
            +
                },
         | 
| 2529 | 
            +
                {
         | 
| 2530 | 
            +
                  "epoch": 0.02,
         | 
| 2531 | 
            +
                  "learning_rate": 4.650438657121537e-05,
         | 
| 2532 | 
            +
                  "loss": 3.9341,
         | 
| 2533 | 
            +
                  "step": 213504
         | 
| 2534 | 
            +
                },
         | 
| 2535 | 
            +
                {
         | 
| 2536 | 
            +
                  "epoch": 0.02,
         | 
| 2537 | 
            +
                  "learning_rate": 4.649600062370485e-05,
         | 
| 2538 | 
            +
                  "loss": 3.9345,
         | 
| 2539 | 
            +
                  "step": 214016
         | 
| 2540 | 
            +
                },
         | 
| 2541 | 
            +
                {
         | 
| 2542 | 
            +
                  "epoch": 0.02,
         | 
| 2543 | 
            +
                  "learning_rate": 4.648761467619433e-05,
         | 
| 2544 | 
            +
                  "loss": 3.9155,
         | 
| 2545 | 
            +
                  "step": 214528
         | 
| 2546 | 
            +
                },
         | 
| 2547 | 
            +
                {
         | 
| 2548 | 
            +
                  "epoch": 0.02,
         | 
| 2549 | 
            +
                  "learning_rate": 4.647922872868381e-05,
         | 
| 2550 | 
            +
                  "loss": 3.9416,
         | 
| 2551 | 
            +
                  "step": 215040
         | 
| 2552 | 
            +
                },
         | 
| 2553 | 
            +
                {
         | 
| 2554 | 
            +
                  "epoch": 0.02,
         | 
| 2555 | 
            +
                  "learning_rate": 4.6470842781173294e-05,
         | 
| 2556 | 
            +
                  "loss": 3.9279,
         | 
| 2557 | 
            +
                  "step": 215552
         | 
| 2558 | 
            +
                },
         | 
| 2559 | 
            +
                {
         | 
| 2560 | 
            +
                  "epoch": 0.02,
         | 
| 2561 | 
            +
                  "learning_rate": 4.646245683366277e-05,
         | 
| 2562 | 
            +
                  "loss": 3.9346,
         | 
| 2563 | 
            +
                  "step": 216064
         | 
| 2564 | 
            +
                },
         | 
| 2565 | 
            +
                {
         | 
| 2566 | 
            +
                  "epoch": 0.02,
         | 
| 2567 | 
            +
                  "learning_rate": 4.645408726495598e-05,
         | 
| 2568 | 
            +
                  "loss": 3.9222,
         | 
| 2569 | 
            +
                  "step": 216576
         | 
| 2570 | 
            +
                },
         | 
| 2571 | 
            +
                {
         | 
| 2572 | 
            +
                  "epoch": 0.02,
         | 
| 2573 | 
            +
                  "learning_rate": 4.644570131744546e-05,
         | 
| 2574 | 
            +
                  "loss": 3.9244,
         | 
| 2575 | 
            +
                  "step": 217088
         | 
| 2576 | 
            +
                },
         | 
| 2577 | 
            +
                {
         | 
| 2578 | 
            +
                  "epoch": 0.02,
         | 
| 2579 | 
            +
                  "learning_rate": 4.643731536993494e-05,
         | 
| 2580 | 
            +
                  "loss": 3.9128,
         | 
| 2581 | 
            +
                  "step": 217600
         | 
| 2582 | 
            +
                },
         | 
| 2583 | 
            +
                {
         | 
| 2584 | 
            +
                  "epoch": 0.02,
         | 
| 2585 | 
            +
                  "learning_rate": 4.6428929422424416e-05,
         | 
| 2586 | 
            +
                  "loss": 3.9204,
         | 
| 2587 | 
            +
                  "step": 218112
         | 
| 2588 | 
            +
                },
         | 
| 2589 | 
            +
                {
         | 
| 2590 | 
            +
                  "epoch": 0.02,
         | 
| 2591 | 
            +
                  "learning_rate": 4.642055985371763e-05,
         | 
| 2592 | 
            +
                  "loss": 3.919,
         | 
| 2593 | 
            +
                  "step": 218624
         | 
| 2594 | 
            +
                },
         | 
| 2595 | 
            +
                {
         | 
| 2596 | 
            +
                  "epoch": 0.02,
         | 
| 2597 | 
            +
                  "learning_rate": 4.641217390620711e-05,
         | 
| 2598 | 
            +
                  "loss": 3.9338,
         | 
| 2599 | 
            +
                  "step": 219136
         | 
| 2600 | 
            +
                },
         | 
| 2601 | 
            +
                {
         | 
| 2602 | 
            +
                  "epoch": 0.02,
         | 
| 2603 | 
            +
                  "learning_rate": 4.640378795869659e-05,
         | 
| 2604 | 
            +
                  "loss": 3.9356,
         | 
| 2605 | 
            +
                  "step": 219648
         | 
| 2606 | 
            +
                },
         | 
| 2607 | 
            +
                {
         | 
| 2608 | 
            +
                  "epoch": 0.02,
         | 
| 2609 | 
            +
                  "learning_rate": 4.6395402011186065e-05,
         | 
| 2610 | 
            +
                  "loss": 3.9235,
         | 
| 2611 | 
            +
                  "step": 220160
         | 
| 2612 | 
            +
                },
         | 
| 2613 | 
            +
                {
         | 
| 2614 | 
            +
                  "epoch": 0.02,
         | 
| 2615 | 
            +
                  "learning_rate": 4.638703244247928e-05,
         | 
| 2616 | 
            +
                  "loss": 3.9154,
         | 
| 2617 | 
            +
                  "step": 220672
         | 
| 2618 | 
            +
                },
         | 
| 2619 | 
            +
                {
         | 
| 2620 | 
            +
                  "epoch": 0.02,
         | 
| 2621 | 
            +
                  "learning_rate": 4.637864649496876e-05,
         | 
| 2622 | 
            +
                  "loss": 3.9256,
         | 
| 2623 | 
            +
                  "step": 221184
         | 
| 2624 | 
            +
                },
         | 
| 2625 | 
            +
                {
         | 
| 2626 | 
            +
                  "epoch": 0.02,
         | 
| 2627 | 
            +
                  "learning_rate": 4.637026054745824e-05,
         | 
| 2628 | 
            +
                  "loss": 3.9266,
         | 
| 2629 | 
            +
                  "step": 221696
         | 
| 2630 | 
            +
                },
         | 
| 2631 | 
            +
                {
         | 
| 2632 | 
            +
                  "epoch": 0.02,
         | 
| 2633 | 
            +
                  "learning_rate": 4.636187459994772e-05,
         | 
| 2634 | 
            +
                  "loss": 3.9315,
         | 
| 2635 | 
            +
                  "step": 222208
         | 
| 2636 | 
            +
                },
         | 
| 2637 | 
            +
                {
         | 
| 2638 | 
            +
                  "epoch": 0.02,
         | 
| 2639 | 
            +
                  "learning_rate": 4.6353505031240936e-05,
         | 
| 2640 | 
            +
                  "loss": 3.9275,
         | 
| 2641 | 
            +
                  "step": 222720
         | 
| 2642 | 
            +
                },
         | 
| 2643 | 
            +
                {
         | 
| 2644 | 
            +
                  "epoch": 0.02,
         | 
| 2645 | 
            +
                  "learning_rate": 4.6345119083730416e-05,
         | 
| 2646 | 
            +
                  "loss": 3.9174,
         | 
| 2647 | 
            +
                  "step": 223232
         | 
| 2648 | 
            +
                },
         | 
| 2649 | 
            +
                {
         | 
| 2650 | 
            +
                  "epoch": 0.02,
         | 
| 2651 | 
            +
                  "learning_rate": 4.6336749515023625e-05,
         | 
| 2652 | 
            +
                  "loss": 3.9248,
         | 
| 2653 | 
            +
                  "step": 223744
         | 
| 2654 | 
            +
                },
         | 
| 2655 | 
            +
                {
         | 
| 2656 | 
            +
                  "epoch": 0.02,
         | 
| 2657 | 
            +
                  "learning_rate": 4.6328363567513105e-05,
         | 
| 2658 | 
            +
                  "loss": 3.9292,
         | 
| 2659 | 
            +
                  "step": 224256
         | 
| 2660 | 
            +
                },
         | 
| 2661 | 
            +
                {
         | 
| 2662 | 
            +
                  "epoch": 0.02,
         | 
| 2663 | 
            +
                  "learning_rate": 4.6319977620002585e-05,
         | 
| 2664 | 
            +
                  "loss": 3.915,
         | 
| 2665 | 
            +
                  "step": 224768
         | 
| 2666 | 
            +
                },
         | 
| 2667 | 
            +
                {
         | 
| 2668 | 
            +
                  "epoch": 0.02,
         | 
| 2669 | 
            +
                  "learning_rate": 4.631159167249206e-05,
         | 
| 2670 | 
            +
                  "loss": 3.9225,
         | 
| 2671 | 
            +
                  "step": 225280
         | 
| 2672 | 
            +
                },
         | 
| 2673 | 
            +
                {
         | 
| 2674 | 
            +
                  "epoch": 0.02,
         | 
| 2675 | 
            +
                  "learning_rate": 4.630320572498154e-05,
         | 
| 2676 | 
            +
                  "loss": 3.9175,
         | 
| 2677 | 
            +
                  "step": 225792
         | 
| 2678 | 
            +
                },
         | 
| 2679 | 
            +
                {
         | 
| 2680 | 
            +
                  "epoch": 0.02,
         | 
| 2681 | 
            +
                  "learning_rate": 4.629481977747102e-05,
         | 
| 2682 | 
            +
                  "loss": 3.9107,
         | 
| 2683 | 
            +
                  "step": 226304
         | 
| 2684 | 
            +
                },
         | 
| 2685 | 
            +
                {
         | 
| 2686 | 
            +
                  "epoch": 0.02,
         | 
| 2687 | 
            +
                  "learning_rate": 4.6286450208764234e-05,
         | 
| 2688 | 
            +
                  "loss": 3.9311,
         | 
| 2689 | 
            +
                  "step": 226816
         | 
| 2690 | 
            +
                },
         | 
| 2691 | 
            +
                {
         | 
| 2692 | 
            +
                  "epoch": 0.02,
         | 
| 2693 | 
            +
                  "learning_rate": 4.6278064261253714e-05,
         | 
| 2694 | 
            +
                  "loss": 3.9154,
         | 
| 2695 | 
            +
                  "step": 227328
         | 
| 2696 | 
            +
                },
         | 
| 2697 | 
            +
                {
         | 
| 2698 | 
            +
                  "epoch": 0.02,
         | 
| 2699 | 
            +
                  "learning_rate": 4.6269678313743194e-05,
         | 
| 2700 | 
            +
                  "loss": 3.912,
         | 
| 2701 | 
            +
                  "step": 227840
         | 
| 2702 | 
            +
                },
         | 
| 2703 | 
            +
                {
         | 
| 2704 | 
            +
                  "epoch": 0.02,
         | 
| 2705 | 
            +
                  "learning_rate": 4.6261292366232674e-05,
         | 
| 2706 | 
            +
                  "loss": 3.9144,
         | 
| 2707 | 
            +
                  "step": 228352
         | 
| 2708 | 
            +
                },
         | 
| 2709 | 
            +
                {
         | 
| 2710 | 
            +
                  "epoch": 0.02,
         | 
| 2711 | 
            +
                  "learning_rate": 4.6252906418722154e-05,
         | 
| 2712 | 
            +
                  "loss": 3.91,
         | 
| 2713 | 
            +
                  "step": 228864
         | 
| 2714 | 
            +
                },
         | 
| 2715 | 
            +
                {
         | 
| 2716 | 
            +
                  "epoch": 0.03,
         | 
| 2717 | 
            +
                  "eval_loss": 3.9538862705230713,
         | 
| 2718 | 
            +
                  "eval_runtime": 302.4885,
         | 
| 2719 | 
            +
                  "eval_samples_per_second": 1261.506,
         | 
| 2720 | 
            +
                  "eval_steps_per_second": 39.423,
         | 
| 2721 | 
            +
                  "step": 228960
         | 
| 2722 | 
            +
                },
         | 
| 2723 | 
            +
                {
         | 
| 2724 | 
            +
                  "epoch": 1.0,
         | 
| 2725 | 
            +
                  "learning_rate": 4.624453685001536e-05,
         | 
| 2726 | 
            +
                  "loss": 3.9037,
         | 
| 2727 | 
            +
                  "step": 229376
         | 
| 2728 | 
            +
                },
         | 
| 2729 | 
            +
                {
         | 
| 2730 | 
            +
                  "epoch": 1.0,
         | 
| 2731 | 
            +
                  "learning_rate": 4.623615090250484e-05,
         | 
| 2732 | 
            +
                  "loss": 3.9107,
         | 
| 2733 | 
            +
                  "step": 229888
         | 
| 2734 | 
            +
                },
         | 
| 2735 | 
            +
                {
         | 
| 2736 | 
            +
                  "epoch": 1.0,
         | 
| 2737 | 
            +
                  "learning_rate": 4.622776495499432e-05,
         | 
| 2738 | 
            +
                  "loss": 3.9273,
         | 
| 2739 | 
            +
                  "step": 230400
         | 
| 2740 | 
            +
                },
         | 
| 2741 | 
            +
                {
         | 
| 2742 | 
            +
                  "epoch": 1.0,
         | 
| 2743 | 
            +
                  "learning_rate": 4.62193790074838e-05,
         | 
| 2744 | 
            +
                  "loss": 3.9119,
         | 
| 2745 | 
            +
                  "step": 230912
         | 
| 2746 | 
            +
                },
         | 
| 2747 | 
            +
                {
         | 
| 2748 | 
            +
                  "epoch": 1.0,
         | 
| 2749 | 
            +
                  "learning_rate": 4.621099305997328e-05,
         | 
| 2750 | 
            +
                  "loss": 3.9315,
         | 
| 2751 | 
            +
                  "step": 231424
         | 
| 2752 | 
            +
                },
         | 
| 2753 | 
            +
                {
         | 
| 2754 | 
            +
                  "epoch": 1.0,
         | 
| 2755 | 
            +
                  "learning_rate": 4.620260711246276e-05,
         | 
| 2756 | 
            +
                  "loss": 3.8984,
         | 
| 2757 | 
            +
                  "step": 231936
         | 
| 2758 | 
            +
                },
         | 
| 2759 | 
            +
                {
         | 
| 2760 | 
            +
                  "epoch": 1.0,
         | 
| 2761 | 
            +
                  "learning_rate": 4.619422116495224e-05,
         | 
| 2762 | 
            +
                  "loss": 3.9195,
         | 
| 2763 | 
            +
                  "step": 232448
         | 
| 2764 | 
            +
                },
         | 
| 2765 | 
            +
                {
         | 
| 2766 | 
            +
                  "epoch": 1.0,
         | 
| 2767 | 
            +
                  "learning_rate": 4.618585159624545e-05,
         | 
| 2768 | 
            +
                  "loss": 3.8957,
         | 
| 2769 | 
            +
                  "step": 232960
         | 
| 2770 | 
            +
                },
         | 
| 2771 | 
            +
                {
         | 
| 2772 | 
            +
                  "epoch": 1.0,
         | 
| 2773 | 
            +
                  "learning_rate": 4.617746564873494e-05,
         | 
| 2774 | 
            +
                  "loss": 3.9131,
         | 
| 2775 | 
            +
                  "step": 233472
         | 
| 2776 | 
            +
                },
         | 
| 2777 | 
            +
                {
         | 
| 2778 | 
            +
                  "epoch": 1.0,
         | 
| 2779 | 
            +
                  "learning_rate": 4.616907970122442e-05,
         | 
| 2780 | 
            +
                  "loss": 3.9148,
         | 
| 2781 | 
            +
                  "step": 233984
         | 
| 2782 | 
            +
                },
         | 
| 2783 | 
            +
                {
         | 
| 2784 | 
            +
                  "epoch": 1.0,
         | 
| 2785 | 
            +
                  "learning_rate": 4.61606937537139e-05,
         | 
| 2786 | 
            +
                  "loss": 3.9083,
         | 
| 2787 | 
            +
                  "step": 234496
         | 
| 2788 | 
            +
                },
         | 
| 2789 | 
            +
                {
         | 
| 2790 | 
            +
                  "epoch": 1.0,
         | 
| 2791 | 
            +
                  "learning_rate": 4.615230780620338e-05,
         | 
| 2792 | 
            +
                  "loss": 3.9165,
         | 
| 2793 | 
            +
                  "step": 235008
         | 
| 2794 | 
            +
                },
         | 
| 2795 | 
            +
                {
         | 
| 2796 | 
            +
                  "epoch": 1.0,
         | 
| 2797 | 
            +
                  "learning_rate": 4.614393823749659e-05,
         | 
| 2798 | 
            +
                  "loss": 3.8992,
         | 
| 2799 | 
            +
                  "step": 235520
         | 
| 2800 | 
            +
                },
         | 
| 2801 | 
            +
                {
         | 
| 2802 | 
            +
                  "epoch": 1.0,
         | 
| 2803 | 
            +
                  "learning_rate": 4.613555228998607e-05,
         | 
| 2804 | 
            +
                  "loss": 3.8971,
         | 
| 2805 | 
            +
                  "step": 236032
         | 
| 2806 | 
            +
                },
         | 
| 2807 | 
            +
                {
         | 
| 2808 | 
            +
                  "epoch": 1.0,
         | 
| 2809 | 
            +
                  "learning_rate": 4.612716634247555e-05,
         | 
| 2810 | 
            +
                  "loss": 3.8962,
         | 
| 2811 | 
            +
                  "step": 236544
         | 
| 2812 | 
            +
                },
         | 
| 2813 | 
            +
                {
         | 
| 2814 | 
            +
                  "epoch": 1.0,
         | 
| 2815 | 
            +
                  "learning_rate": 4.611878039496503e-05,
         | 
| 2816 | 
            +
                  "loss": 3.9008,
         | 
| 2817 | 
            +
                  "step": 237056
         | 
| 2818 | 
            +
                },
         | 
| 2819 | 
            +
                {
         | 
| 2820 | 
            +
                  "epoch": 1.0,
         | 
| 2821 | 
            +
                  "learning_rate": 4.6110410826258237e-05,
         | 
| 2822 | 
            +
                  "loss": 3.9076,
         | 
| 2823 | 
            +
                  "step": 237568
         | 
| 2824 | 
            +
                },
         | 
| 2825 | 
            +
                {
         | 
| 2826 | 
            +
                  "epoch": 1.0,
         | 
| 2827 | 
            +
                  "learning_rate": 4.6102024878747717e-05,
         | 
| 2828 | 
            +
                  "loss": 3.9012,
         | 
| 2829 | 
            +
                  "step": 238080
         | 
| 2830 | 
            +
                },
         | 
| 2831 | 
            +
                {
         | 
| 2832 | 
            +
                  "epoch": 1.0,
         | 
| 2833 | 
            +
                  "learning_rate": 4.6093638931237196e-05,
         | 
| 2834 | 
            +
                  "loss": 3.9041,
         | 
| 2835 | 
            +
                  "step": 238592
         | 
| 2836 | 
            +
                },
         | 
| 2837 | 
            +
                {
         | 
| 2838 | 
            +
                  "epoch": 1.0,
         | 
| 2839 | 
            +
                  "learning_rate": 4.6085252983726676e-05,
         | 
| 2840 | 
            +
                  "loss": 3.9225,
         | 
| 2841 | 
            +
                  "step": 239104
         | 
| 2842 | 
            +
                },
         | 
| 2843 | 
            +
                {
         | 
| 2844 | 
            +
                  "epoch": 1.0,
         | 
| 2845 | 
            +
                  "learning_rate": 4.607688341501989e-05,
         | 
| 2846 | 
            +
                  "loss": 3.9027,
         | 
| 2847 | 
            +
                  "step": 239616
         | 
| 2848 | 
            +
                },
         | 
| 2849 | 
            +
                {
         | 
| 2850 | 
            +
                  "epoch": 1.0,
         | 
| 2851 | 
            +
                  "learning_rate": 4.606849746750937e-05,
         | 
| 2852 | 
            +
                  "loss": 3.8997,
         | 
| 2853 | 
            +
                  "step": 240128
         | 
| 2854 | 
            +
                },
         | 
| 2855 | 
            +
                {
         | 
| 2856 | 
            +
                  "epoch": 1.0,
         | 
| 2857 | 
            +
                  "learning_rate": 4.606011151999885e-05,
         | 
| 2858 | 
            +
                  "loss": 3.9046,
         | 
| 2859 | 
            +
                  "step": 240640
         | 
| 2860 | 
            +
                },
         | 
| 2861 | 
            +
                {
         | 
| 2862 | 
            +
                  "epoch": 1.0,
         | 
| 2863 | 
            +
                  "learning_rate": 4.605172557248833e-05,
         | 
| 2864 | 
            +
                  "loss": 3.9062,
         | 
| 2865 | 
            +
                  "step": 241152
         | 
| 2866 | 
            +
                },
         | 
| 2867 | 
            +
                {
         | 
| 2868 | 
            +
                  "epoch": 1.0,
         | 
| 2869 | 
            +
                  "learning_rate": 4.604335600378154e-05,
         | 
| 2870 | 
            +
                  "loss": 3.8915,
         | 
| 2871 | 
            +
                  "step": 241664
         | 
| 2872 | 
            +
                },
         | 
| 2873 | 
            +
                {
         | 
| 2874 | 
            +
                  "epoch": 1.0,
         | 
| 2875 | 
            +
                  "learning_rate": 4.603497005627102e-05,
         | 
| 2876 | 
            +
                  "loss": 3.9013,
         | 
| 2877 | 
            +
                  "step": 242176
         | 
| 2878 | 
            +
                },
         | 
| 2879 | 
            +
                {
         | 
| 2880 | 
            +
                  "epoch": 1.0,
         | 
| 2881 | 
            +
                  "learning_rate": 4.60265841087605e-05,
         | 
| 2882 | 
            +
                  "loss": 3.9022,
         | 
| 2883 | 
            +
                  "step": 242688
         | 
| 2884 | 
            +
                },
         | 
| 2885 | 
            +
                {
         | 
| 2886 | 
            +
                  "epoch": 1.0,
         | 
| 2887 | 
            +
                  "learning_rate": 4.601819816124998e-05,
         | 
| 2888 | 
            +
                  "loss": 3.8943,
         | 
| 2889 | 
            +
                  "step": 243200
         | 
| 2890 | 
            +
                },
         | 
| 2891 | 
            +
                {
         | 
| 2892 | 
            +
                  "epoch": 1.0,
         | 
| 2893 | 
            +
                  "learning_rate": 4.600981221373946e-05,
         | 
| 2894 | 
            +
                  "loss": 3.8868,
         | 
| 2895 | 
            +
                  "step": 243712
         | 
| 2896 | 
            +
                },
         | 
| 2897 | 
            +
                {
         | 
| 2898 | 
            +
                  "epoch": 1.01,
         | 
| 2899 | 
            +
                  "learning_rate": 4.600142626622894e-05,
         | 
| 2900 | 
            +
                  "loss": 3.8853,
         | 
| 2901 | 
            +
                  "step": 244224
         | 
| 2902 | 
            +
                },
         | 
| 2903 | 
            +
                {
         | 
| 2904 | 
            +
                  "epoch": 1.01,
         | 
| 2905 | 
            +
                  "learning_rate": 4.599305669752215e-05,
         | 
| 2906 | 
            +
                  "loss": 3.8975,
         | 
| 2907 | 
            +
                  "step": 244736
         | 
| 2908 | 
            +
                },
         | 
| 2909 | 
            +
                {
         | 
| 2910 | 
            +
                  "epoch": 1.01,
         | 
| 2911 | 
            +
                  "learning_rate": 4.598467075001163e-05,
         | 
| 2912 | 
            +
                  "loss": 3.8959,
         | 
| 2913 | 
            +
                  "step": 245248
         | 
| 2914 | 
            +
                },
         | 
| 2915 | 
            +
                {
         | 
| 2916 | 
            +
                  "epoch": 1.01,
         | 
| 2917 | 
            +
                  "learning_rate": 4.597628480250111e-05,
         | 
| 2918 | 
            +
                  "loss": 3.9098,
         | 
| 2919 | 
            +
                  "step": 245760
         | 
| 2920 | 
            +
                },
         | 
| 2921 | 
            +
                {
         | 
| 2922 | 
            +
                  "epoch": 1.01,
         | 
| 2923 | 
            +
                  "learning_rate": 4.596789885499059e-05,
         | 
| 2924 | 
            +
                  "loss": 3.8971,
         | 
| 2925 | 
            +
                  "step": 246272
         | 
| 2926 | 
            +
                },
         | 
| 2927 | 
            +
                {
         | 
| 2928 | 
            +
                  "epoch": 1.01,
         | 
| 2929 | 
            +
                  "learning_rate": 4.595951290748008e-05,
         | 
| 2930 | 
            +
                  "loss": 3.8862,
         | 
| 2931 | 
            +
                  "step": 246784
         | 
| 2932 | 
            +
                },
         | 
| 2933 | 
            +
                {
         | 
| 2934 | 
            +
                  "epoch": 1.01,
         | 
| 2935 | 
            +
                  "learning_rate": 4.5951143338773286e-05,
         | 
| 2936 | 
            +
                  "loss": 3.8985,
         | 
| 2937 | 
            +
                  "step": 247296
         | 
| 2938 | 
            +
                },
         | 
| 2939 | 
            +
                {
         | 
| 2940 | 
            +
                  "epoch": 1.01,
         | 
| 2941 | 
            +
                  "learning_rate": 4.5942757391262766e-05,
         | 
| 2942 | 
            +
                  "loss": 3.889,
         | 
| 2943 | 
            +
                  "step": 247808
         | 
| 2944 | 
            +
                },
         | 
| 2945 | 
            +
                {
         | 
| 2946 | 
            +
                  "epoch": 1.01,
         | 
| 2947 | 
            +
                  "learning_rate": 4.5934371443752246e-05,
         | 
| 2948 | 
            +
                  "loss": 3.8807,
         | 
| 2949 | 
            +
                  "step": 248320
         | 
| 2950 | 
            +
                },
         | 
| 2951 | 
            +
                {
         | 
| 2952 | 
            +
                  "epoch": 1.01,
         | 
| 2953 | 
            +
                  "learning_rate": 4.5925985496241726e-05,
         | 
| 2954 | 
            +
                  "loss": 3.8831,
         | 
| 2955 | 
            +
                  "step": 248832
         | 
| 2956 | 
            +
                },
         | 
| 2957 | 
            +
                {
         | 
| 2958 | 
            +
                  "epoch": 1.01,
         | 
| 2959 | 
            +
                  "learning_rate": 4.59175995487312e-05,
         | 
| 2960 | 
            +
                  "loss": 3.887,
         | 
| 2961 | 
            +
                  "step": 249344
         | 
| 2962 | 
            +
                },
         | 
| 2963 | 
            +
                {
         | 
| 2964 | 
            +
                  "epoch": 1.01,
         | 
| 2965 | 
            +
                  "learning_rate": 4.590921360122068e-05,
         | 
| 2966 | 
            +
                  "loss": 3.8802,
         | 
| 2967 | 
            +
                  "step": 249856
         | 
| 2968 | 
            +
                },
         | 
| 2969 | 
            +
                {
         | 
| 2970 | 
            +
                  "epoch": 1.01,
         | 
| 2971 | 
            +
                  "learning_rate": 4.590082765371016e-05,
         | 
| 2972 | 
            +
                  "loss": 3.9009,
         | 
| 2973 | 
            +
                  "step": 250368
         | 
| 2974 | 
            +
                },
         | 
| 2975 | 
            +
                {
         | 
| 2976 | 
            +
                  "epoch": 1.01,
         | 
| 2977 | 
            +
                  "learning_rate": 4.589245808500337e-05,
         | 
| 2978 | 
            +
                  "loss": 3.8842,
         | 
| 2979 | 
            +
                  "step": 250880
         | 
| 2980 | 
            +
                },
         | 
| 2981 | 
            +
                {
         | 
| 2982 | 
            +
                  "epoch": 1.01,
         | 
| 2983 | 
            +
                  "learning_rate": 4.5884088516296584e-05,
         | 
| 2984 | 
            +
                  "loss": 3.8912,
         | 
| 2985 | 
            +
                  "step": 251392
         | 
| 2986 | 
            +
                },
         | 
| 2987 | 
            +
                {
         | 
| 2988 | 
            +
                  "epoch": 1.01,
         | 
| 2989 | 
            +
                  "learning_rate": 4.5875702568786064e-05,
         | 
| 2990 | 
            +
                  "loss": 3.8897,
         | 
| 2991 | 
            +
                  "step": 251904
         | 
| 2992 | 
            +
                },
         | 
| 2993 | 
            +
                {
         | 
| 2994 | 
            +
                  "epoch": 1.01,
         | 
| 2995 | 
            +
                  "learning_rate": 4.5867316621275544e-05,
         | 
| 2996 | 
            +
                  "loss": 3.8834,
         | 
| 2997 | 
            +
                  "step": 252416
         | 
| 2998 | 
            +
                },
         | 
| 2999 | 
            +
                {
         | 
| 3000 | 
            +
                  "epoch": 1.01,
         | 
| 3001 | 
            +
                  "learning_rate": 4.5858930673765024e-05,
         | 
| 3002 | 
            +
                  "loss": 3.8882,
         | 
| 3003 | 
            +
                  "step": 252928
         | 
| 3004 | 
            +
                },
         | 
| 3005 | 
            +
                {
         | 
| 3006 | 
            +
                  "epoch": 1.01,
         | 
| 3007 | 
            +
                  "learning_rate": 4.5850544726254504e-05,
         | 
| 3008 | 
            +
                  "loss": 3.8727,
         | 
| 3009 | 
            +
                  "step": 253440
         | 
| 3010 | 
            +
                },
         | 
| 3011 | 
            +
                {
         | 
| 3012 | 
            +
                  "epoch": 1.01,
         | 
| 3013 | 
            +
                  "learning_rate": 4.5842158778743984e-05,
         | 
| 3014 | 
            +
                  "loss": 3.8633,
         | 
| 3015 | 
            +
                  "step": 253952
         | 
| 3016 | 
            +
                },
         | 
| 3017 | 
            +
                {
         | 
| 3018 | 
            +
                  "epoch": 1.01,
         | 
| 3019 | 
            +
                  "learning_rate": 4.5833772831233464e-05,
         | 
| 3020 | 
            +
                  "loss": 3.8964,
         | 
| 3021 | 
            +
                  "step": 254464
         | 
| 3022 | 
            +
                },
         | 
| 3023 | 
            +
                {
         | 
| 3024 | 
            +
                  "epoch": 1.01,
         | 
| 3025 | 
            +
                  "learning_rate": 4.582540326252667e-05,
         | 
| 3026 | 
            +
                  "loss": 3.8859,
         | 
| 3027 | 
            +
                  "step": 254976
         | 
| 3028 | 
            +
                },
         | 
| 3029 | 
            +
                {
         | 
| 3030 | 
            +
                  "epoch": 1.01,
         | 
| 3031 | 
            +
                  "learning_rate": 4.581701731501615e-05,
         | 
| 3032 | 
            +
                  "loss": 3.8793,
         | 
| 3033 | 
            +
                  "step": 255488
         | 
| 3034 | 
            +
                },
         | 
| 3035 | 
            +
                {
         | 
| 3036 | 
            +
                  "epoch": 1.01,
         | 
| 3037 | 
            +
                  "learning_rate": 4.580863136750563e-05,
         | 
| 3038 | 
            +
                  "loss": 3.8741,
         | 
| 3039 | 
            +
                  "step": 256000
         | 
| 3040 | 
            +
                },
         | 
| 3041 | 
            +
                {
         | 
| 3042 | 
            +
                  "epoch": 1.01,
         | 
| 3043 | 
            +
                  "learning_rate": 4.580024541999511e-05,
         | 
| 3044 | 
            +
                  "loss": 3.8816,
         | 
| 3045 | 
            +
                  "step": 256512
         | 
| 3046 | 
            +
                },
         | 
| 3047 | 
            +
                {
         | 
| 3048 | 
            +
                  "epoch": 1.01,
         | 
| 3049 | 
            +
                  "learning_rate": 4.579187585128832e-05,
         | 
| 3050 | 
            +
                  "loss": 3.8669,
         | 
| 3051 | 
            +
                  "step": 257024
         | 
| 3052 | 
            +
                },
         | 
| 3053 | 
            +
                {
         | 
| 3054 | 
            +
                  "epoch": 1.01,
         | 
| 3055 | 
            +
                  "learning_rate": 4.57834899037778e-05,
         | 
| 3056 | 
            +
                  "loss": 3.8855,
         | 
| 3057 | 
            +
                  "step": 257536
         | 
| 3058 | 
            +
                },
         | 
| 3059 | 
            +
                {
         | 
| 3060 | 
            +
                  "epoch": 1.01,
         | 
| 3061 | 
            +
                  "learning_rate": 4.577510395626728e-05,
         | 
| 3062 | 
            +
                  "loss": 3.8802,
         | 
| 3063 | 
            +
                  "step": 258048
         | 
| 3064 | 
            +
                },
         | 
| 3065 | 
            +
                {
         | 
| 3066 | 
            +
                  "epoch": 1.01,
         | 
| 3067 | 
            +
                  "learning_rate": 4.576671800875677e-05,
         | 
| 3068 | 
            +
                  "loss": 3.878,
         | 
| 3069 | 
            +
                  "step": 258560
         | 
| 3070 | 
            +
                },
         | 
| 3071 | 
            +
                {
         | 
| 3072 | 
            +
                  "epoch": 1.01,
         | 
| 3073 | 
            +
                  "learning_rate": 4.575833206124625e-05,
         | 
| 3074 | 
            +
                  "loss": 3.8896,
         | 
| 3075 | 
            +
                  "step": 259072
         | 
| 3076 | 
            +
                },
         | 
| 3077 | 
            +
                {
         | 
| 3078 | 
            +
                  "epoch": 1.01,
         | 
| 3079 | 
            +
                  "learning_rate": 4.574994611373573e-05,
         | 
| 3080 | 
            +
                  "loss": 3.8682,
         | 
| 3081 | 
            +
                  "step": 259584
         | 
| 3082 | 
            +
                },
         | 
| 3083 | 
            +
                {
         | 
| 3084 | 
            +
                  "epoch": 1.01,
         | 
| 3085 | 
            +
                  "learning_rate": 4.574156016622521e-05,
         | 
| 3086 | 
            +
                  "loss": 3.8664,
         | 
| 3087 | 
            +
                  "step": 260096
         | 
| 3088 | 
            +
                },
         | 
| 3089 | 
            +
                {
         | 
| 3090 | 
            +
                  "epoch": 1.01,
         | 
| 3091 | 
            +
                  "learning_rate": 4.573319059751842e-05,
         | 
| 3092 | 
            +
                  "loss": 3.8826,
         | 
| 3093 | 
            +
                  "step": 260608
         | 
| 3094 | 
            +
                },
         | 
| 3095 | 
            +
                {
         | 
| 3096 | 
            +
                  "epoch": 1.01,
         | 
| 3097 | 
            +
                  "learning_rate": 4.57248046500079e-05,
         | 
| 3098 | 
            +
                  "loss": 3.8575,
         | 
| 3099 | 
            +
                  "step": 261120
         | 
| 3100 | 
            +
                },
         | 
| 3101 | 
            +
                {
         | 
| 3102 | 
            +
                  "epoch": 1.01,
         | 
| 3103 | 
            +
                  "learning_rate": 4.571641870249738e-05,
         | 
| 3104 | 
            +
                  "loss": 3.863,
         | 
| 3105 | 
            +
                  "step": 261632
         | 
| 3106 | 
            +
                },
         | 
| 3107 | 
            +
                {
         | 
| 3108 | 
            +
                  "epoch": 1.01,
         | 
| 3109 | 
            +
                  "learning_rate": 4.570803275498686e-05,
         | 
| 3110 | 
            +
                  "loss": 3.8807,
         | 
| 3111 | 
            +
                  "step": 262144
         | 
| 3112 | 
            +
                },
         | 
| 3113 | 
            +
                {
         | 
| 3114 | 
            +
                  "epoch": 1.01,
         | 
| 3115 | 
            +
                  "learning_rate": 4.569964680747634e-05,
         | 
| 3116 | 
            +
                  "loss": 3.8832,
         | 
| 3117 | 
            +
                  "step": 262656
         | 
| 3118 | 
            +
                },
         | 
| 3119 | 
            +
                {
         | 
| 3120 | 
            +
                  "epoch": 1.01,
         | 
| 3121 | 
            +
                  "learning_rate": 4.569126085996582e-05,
         | 
| 3122 | 
            +
                  "loss": 3.8624,
         | 
| 3123 | 
            +
                  "step": 263168
         | 
| 3124 | 
            +
                },
         | 
| 3125 | 
            +
                {
         | 
| 3126 | 
            +
                  "epoch": 1.01,
         | 
| 3127 | 
            +
                  "learning_rate": 4.56828749124553e-05,
         | 
| 3128 | 
            +
                  "loss": 3.8739,
         | 
| 3129 | 
            +
                  "step": 263680
         | 
| 3130 | 
            +
                },
         | 
| 3131 | 
            +
                {
         | 
| 3132 | 
            +
                  "epoch": 1.01,
         | 
| 3133 | 
            +
                  "learning_rate": 4.567448896494478e-05,
         | 
| 3134 | 
            +
                  "loss": 3.8554,
         | 
| 3135 | 
            +
                  "step": 264192
         | 
| 3136 | 
            +
                },
         | 
| 3137 | 
            +
                {
         | 
| 3138 | 
            +
                  "epoch": 1.01,
         | 
| 3139 | 
            +
                  "learning_rate": 4.5666119396237986e-05,
         | 
| 3140 | 
            +
                  "loss": 3.8799,
         | 
| 3141 | 
            +
                  "step": 264704
         | 
| 3142 | 
            +
                },
         | 
| 3143 | 
            +
                {
         | 
| 3144 | 
            +
                  "epoch": 1.01,
         | 
| 3145 | 
            +
                  "learning_rate": 4.5657733448727466e-05,
         | 
| 3146 | 
            +
                  "loss": 3.8728,
         | 
| 3147 | 
            +
                  "step": 265216
         | 
| 3148 | 
            +
                },
         | 
| 3149 | 
            +
                {
         | 
| 3150 | 
            +
                  "epoch": 1.01,
         | 
| 3151 | 
            +
                  "learning_rate": 4.5649347501216946e-05,
         | 
| 3152 | 
            +
                  "loss": 3.8802,
         | 
| 3153 | 
            +
                  "step": 265728
         | 
| 3154 | 
            +
                },
         | 
| 3155 | 
            +
                {
         | 
| 3156 | 
            +
                  "epoch": 1.01,
         | 
| 3157 | 
            +
                  "learning_rate": 4.564096155370643e-05,
         | 
| 3158 | 
            +
                  "loss": 3.8711,
         | 
| 3159 | 
            +
                  "step": 266240
         | 
| 3160 | 
            +
                },
         | 
| 3161 | 
            +
                {
         | 
| 3162 | 
            +
                  "epoch": 1.01,
         | 
| 3163 | 
            +
                  "learning_rate": 4.563257560619591e-05,
         | 
| 3164 | 
            +
                  "loss": 3.8786,
         | 
| 3165 | 
            +
                  "step": 266752
         | 
| 3166 | 
            +
                },
         | 
| 3167 | 
            +
                {
         | 
| 3168 | 
            +
                  "epoch": 1.01,
         | 
| 3169 | 
            +
                  "learning_rate": 4.562420603748912e-05,
         | 
| 3170 | 
            +
                  "loss": 3.8855,
         | 
| 3171 | 
            +
                  "step": 267264
         | 
| 3172 | 
            +
                },
         | 
| 3173 | 
            +
                {
         | 
| 3174 | 
            +
                  "epoch": 1.01,
         | 
| 3175 | 
            +
                  "learning_rate": 4.56158200899786e-05,
         | 
| 3176 | 
            +
                  "loss": 3.8558,
         | 
| 3177 | 
            +
                  "step": 267776
         | 
| 3178 | 
            +
                },
         | 
| 3179 | 
            +
                {
         | 
| 3180 | 
            +
                  "epoch": 1.01,
         | 
| 3181 | 
            +
                  "learning_rate": 4.560743414246808e-05,
         | 
| 3182 | 
            +
                  "loss": 3.8762,
         | 
| 3183 | 
            +
                  "step": 268288
         | 
| 3184 | 
            +
                },
         | 
| 3185 | 
            +
                {
         | 
| 3186 | 
            +
                  "epoch": 1.01,
         | 
| 3187 | 
            +
                  "learning_rate": 4.5599048194957555e-05,
         | 
| 3188 | 
            +
                  "loss": 3.8783,
         | 
| 3189 | 
            +
                  "step": 268800
         | 
| 3190 | 
            +
                },
         | 
| 3191 | 
            +
                {
         | 
| 3192 | 
            +
                  "epoch": 1.01,
         | 
| 3193 | 
            +
                  "learning_rate": 4.5590662247447035e-05,
         | 
| 3194 | 
            +
                  "loss": 3.8542,
         | 
| 3195 | 
            +
                  "step": 269312
         | 
| 3196 | 
            +
                },
         | 
| 3197 | 
            +
                {
         | 
| 3198 | 
            +
                  "epoch": 1.01,
         | 
| 3199 | 
            +
                  "learning_rate": 4.558229267874025e-05,
         | 
| 3200 | 
            +
                  "loss": 3.8836,
         | 
| 3201 | 
            +
                  "step": 269824
         | 
| 3202 | 
            +
                },
         | 
| 3203 | 
            +
                {
         | 
| 3204 | 
            +
                  "epoch": 1.01,
         | 
| 3205 | 
            +
                  "learning_rate": 4.557390673122973e-05,
         | 
| 3206 | 
            +
                  "loss": 3.8754,
         | 
| 3207 | 
            +
                  "step": 270336
         | 
| 3208 | 
            +
                },
         | 
| 3209 | 
            +
                {
         | 
| 3210 | 
            +
                  "epoch": 1.01,
         | 
| 3211 | 
            +
                  "learning_rate": 4.5565520783719204e-05,
         | 
| 3212 | 
            +
                  "loss": 3.8765,
         | 
| 3213 | 
            +
                  "step": 270848
         | 
| 3214 | 
            +
                },
         | 
| 3215 | 
            +
                {
         | 
| 3216 | 
            +
                  "epoch": 1.01,
         | 
| 3217 | 
            +
                  "learning_rate": 4.5557134836208684e-05,
         | 
| 3218 | 
            +
                  "loss": 3.8805,
         | 
| 3219 | 
            +
                  "step": 271360
         | 
| 3220 | 
            +
                },
         | 
| 3221 | 
            +
                {
         | 
| 3222 | 
            +
                  "epoch": 1.01,
         | 
| 3223 | 
            +
                  "learning_rate": 4.554874888869817e-05,
         | 
| 3224 | 
            +
                  "loss": 3.8586,
         | 
| 3225 | 
            +
                  "step": 271872
         | 
| 3226 | 
            +
                },
         | 
| 3227 | 
            +
                {
         | 
| 3228 | 
            +
                  "epoch": 1.01,
         | 
| 3229 | 
            +
                  "learning_rate": 4.554036294118765e-05,
         | 
| 3230 | 
            +
                  "loss": 3.8616,
         | 
| 3231 | 
            +
                  "step": 272384
         | 
| 3232 | 
            +
                },
         | 
| 3233 | 
            +
                {
         | 
| 3234 | 
            +
                  "epoch": 1.01,
         | 
| 3235 | 
            +
                  "learning_rate": 4.553199337248086e-05,
         | 
| 3236 | 
            +
                  "loss": 3.8662,
         | 
| 3237 | 
            +
                  "step": 272896
         | 
| 3238 | 
            +
                },
         | 
| 3239 | 
            +
                {
         | 
| 3240 | 
            +
                  "epoch": 1.01,
         | 
| 3241 | 
            +
                  "learning_rate": 4.552360742497034e-05,
         | 
| 3242 | 
            +
                  "loss": 3.8729,
         | 
| 3243 | 
            +
                  "step": 273408
         | 
| 3244 | 
            +
                },
         | 
| 3245 | 
            +
                {
         | 
| 3246 | 
            +
                  "epoch": 1.01,
         | 
| 3247 | 
            +
                  "learning_rate": 4.551522147745982e-05,
         | 
| 3248 | 
            +
                  "loss": 3.8638,
         | 
| 3249 | 
            +
                  "step": 273920
         | 
| 3250 | 
            +
                },
         | 
| 3251 | 
            +
                {
         | 
| 3252 | 
            +
                  "epoch": 1.01,
         | 
| 3253 | 
            +
                  "learning_rate": 4.55068355299493e-05,
         | 
| 3254 | 
            +
                  "loss": 3.8668,
         | 
| 3255 | 
            +
                  "step": 274432
         | 
| 3256 | 
            +
                },
         | 
| 3257 | 
            +
                {
         | 
| 3258 | 
            +
                  "epoch": 1.02,
         | 
| 3259 | 
            +
                  "learning_rate": 4.549844958243878e-05,
         | 
| 3260 | 
            +
                  "loss": 3.8659,
         | 
| 3261 | 
            +
                  "step": 274944
         | 
| 3262 | 
            +
                },
         | 
| 3263 | 
            +
                {
         | 
| 3264 | 
            +
                  "epoch": 1.02,
         | 
| 3265 | 
            +
                  "learning_rate": 4.549008001373199e-05,
         | 
| 3266 | 
            +
                  "loss": 3.8741,
         | 
| 3267 | 
            +
                  "step": 275456
         | 
| 3268 | 
            +
                },
         | 
| 3269 | 
            +
                {
         | 
| 3270 | 
            +
                  "epoch": 1.02,
         | 
| 3271 | 
            +
                  "learning_rate": 4.548169406622147e-05,
         | 
| 3272 | 
            +
                  "loss": 3.8544,
         | 
| 3273 | 
            +
                  "step": 275968
         | 
| 3274 | 
            +
                },
         | 
| 3275 | 
            +
                {
         | 
| 3276 | 
            +
                  "epoch": 1.02,
         | 
| 3277 | 
            +
                  "learning_rate": 4.547330811871095e-05,
         | 
| 3278 | 
            +
                  "loss": 3.8592,
         | 
| 3279 | 
            +
                  "step": 276480
         | 
| 3280 | 
            +
                },
         | 
| 3281 | 
            +
                {
         | 
| 3282 | 
            +
                  "epoch": 1.02,
         | 
| 3283 | 
            +
                  "learning_rate": 4.546492217120043e-05,
         | 
| 3284 | 
            +
                  "loss": 3.8692,
         | 
| 3285 | 
            +
                  "step": 276992
         | 
| 3286 | 
            +
                },
         | 
| 3287 | 
            +
                {
         | 
| 3288 | 
            +
                  "epoch": 1.02,
         | 
| 3289 | 
            +
                  "learning_rate": 4.545655260249364e-05,
         | 
| 3290 | 
            +
                  "loss": 3.8778,
         | 
| 3291 | 
            +
                  "step": 277504
         | 
| 3292 | 
            +
                },
         | 
| 3293 | 
            +
                {
         | 
| 3294 | 
            +
                  "epoch": 1.02,
         | 
| 3295 | 
            +
                  "learning_rate": 4.5448166654983124e-05,
         | 
| 3296 | 
            +
                  "loss": 3.8687,
         | 
| 3297 | 
            +
                  "step": 278016
         | 
| 3298 | 
            +
                },
         | 
| 3299 | 
            +
                {
         | 
| 3300 | 
            +
                  "epoch": 1.02,
         | 
| 3301 | 
            +
                  "learning_rate": 4.5439780707472604e-05,
         | 
| 3302 | 
            +
                  "loss": 3.8462,
         | 
| 3303 | 
            +
                  "step": 278528
         | 
| 3304 | 
            +
                },
         | 
| 3305 | 
            +
                {
         | 
| 3306 | 
            +
                  "epoch": 1.02,
         | 
| 3307 | 
            +
                  "learning_rate": 4.5431394759962084e-05,
         | 
| 3308 | 
            +
                  "loss": 3.8575,
         | 
| 3309 | 
            +
                  "step": 279040
         | 
| 3310 | 
            +
                },
         | 
| 3311 | 
            +
                {
         | 
| 3312 | 
            +
                  "epoch": 1.02,
         | 
| 3313 | 
            +
                  "learning_rate": 4.542302519125529e-05,
         | 
| 3314 | 
            +
                  "loss": 3.8649,
         | 
| 3315 | 
            +
                  "step": 279552
         | 
| 3316 | 
            +
                },
         | 
| 3317 | 
            +
                {
         | 
| 3318 | 
            +
                  "epoch": 1.02,
         | 
| 3319 | 
            +
                  "learning_rate": 4.541463924374477e-05,
         | 
| 3320 | 
            +
                  "loss": 3.8661,
         | 
| 3321 | 
            +
                  "step": 280064
         | 
| 3322 | 
            +
                },
         | 
| 3323 | 
            +
                {
         | 
| 3324 | 
            +
                  "epoch": 1.02,
         | 
| 3325 | 
            +
                  "learning_rate": 4.540625329623425e-05,
         | 
| 3326 | 
            +
                  "loss": 3.8652,
         | 
| 3327 | 
            +
                  "step": 280576
         | 
| 3328 | 
            +
                },
         | 
| 3329 | 
            +
                {
         | 
| 3330 | 
            +
                  "epoch": 1.02,
         | 
| 3331 | 
            +
                  "learning_rate": 4.539786734872373e-05,
         | 
| 3332 | 
            +
                  "loss": 3.8569,
         | 
| 3333 | 
            +
                  "step": 281088
         | 
| 3334 | 
            +
                },
         | 
| 3335 | 
            +
                {
         | 
| 3336 | 
            +
                  "epoch": 1.02,
         | 
| 3337 | 
            +
                  "learning_rate": 4.538949778001694e-05,
         | 
| 3338 | 
            +
                  "loss": 3.8476,
         | 
| 3339 | 
            +
                  "step": 281600
         | 
| 3340 | 
            +
                },
         | 
| 3341 | 
            +
                {
         | 
| 3342 | 
            +
                  "epoch": 1.02,
         | 
| 3343 | 
            +
                  "learning_rate": 4.538111183250642e-05,
         | 
| 3344 | 
            +
                  "loss": 3.864,
         | 
| 3345 | 
            +
                  "step": 282112
         | 
| 3346 | 
            +
                },
         | 
| 3347 | 
            +
                {
         | 
| 3348 | 
            +
                  "epoch": 1.02,
         | 
| 3349 | 
            +
                  "learning_rate": 4.53727258849959e-05,
         | 
| 3350 | 
            +
                  "loss": 3.8461,
         | 
| 3351 | 
            +
                  "step": 282624
         | 
| 3352 | 
            +
                },
         | 
| 3353 | 
            +
                {
         | 
| 3354 | 
            +
                  "epoch": 1.02,
         | 
| 3355 | 
            +
                  "learning_rate": 4.536433993748538e-05,
         | 
| 3356 | 
            +
                  "loss": 3.8556,
         | 
| 3357 | 
            +
                  "step": 283136
         | 
| 3358 | 
            +
                },
         | 
| 3359 | 
            +
                {
         | 
| 3360 | 
            +
                  "epoch": 1.02,
         | 
| 3361 | 
            +
                  "learning_rate": 4.535597036877859e-05,
         | 
| 3362 | 
            +
                  "loss": 3.85,
         | 
| 3363 | 
            +
                  "step": 283648
         | 
| 3364 | 
            +
                },
         | 
| 3365 | 
            +
                {
         | 
| 3366 | 
            +
                  "epoch": 1.02,
         | 
| 3367 | 
            +
                  "learning_rate": 4.534758442126808e-05,
         | 
| 3368 | 
            +
                  "loss": 3.8645,
         | 
| 3369 | 
            +
                  "step": 284160
         | 
| 3370 | 
            +
                },
         | 
| 3371 | 
            +
                {
         | 
| 3372 | 
            +
                  "epoch": 1.02,
         | 
| 3373 | 
            +
                  "learning_rate": 4.533919847375756e-05,
         | 
| 3374 | 
            +
                  "loss": 3.8494,
         | 
| 3375 | 
            +
                  "step": 284672
         | 
| 3376 | 
            +
                },
         | 
| 3377 | 
            +
                {
         | 
| 3378 | 
            +
                  "epoch": 1.02,
         | 
| 3379 | 
            +
                  "learning_rate": 4.533081252624704e-05,
         | 
| 3380 | 
            +
                  "loss": 3.8662,
         | 
| 3381 | 
            +
                  "step": 285184
         | 
| 3382 | 
            +
                },
         | 
| 3383 | 
            +
                {
         | 
| 3384 | 
            +
                  "epoch": 1.02,
         | 
| 3385 | 
            +
                  "learning_rate": 4.532242657873652e-05,
         | 
| 3386 | 
            +
                  "loss": 3.8469,
         | 
| 3387 | 
            +
                  "step": 285696
         | 
| 3388 | 
            +
                },
         | 
| 3389 | 
            +
                {
         | 
| 3390 | 
            +
                  "epoch": 1.02,
         | 
| 3391 | 
            +
                  "learning_rate": 4.531405701002973e-05,
         | 
| 3392 | 
            +
                  "loss": 3.8539,
         | 
| 3393 | 
            +
                  "step": 286208
         | 
| 3394 | 
            +
                },
         | 
| 3395 | 
            +
                {
         | 
| 3396 | 
            +
                  "epoch": 1.02,
         | 
| 3397 | 
            +
                  "learning_rate": 4.530567106251921e-05,
         | 
| 3398 | 
            +
                  "loss": 3.8554,
         | 
| 3399 | 
            +
                  "step": 286720
         | 
| 3400 | 
            +
                },
         | 
| 3401 | 
            +
                {
         | 
| 3402 | 
            +
                  "epoch": 1.02,
         | 
| 3403 | 
            +
                  "learning_rate": 4.529728511500869e-05,
         | 
| 3404 | 
            +
                  "loss": 3.8511,
         | 
| 3405 | 
            +
                  "step": 287232
         | 
| 3406 | 
            +
                },
         | 
| 3407 | 
            +
                {
         | 
| 3408 | 
            +
                  "epoch": 1.02,
         | 
| 3409 | 
            +
                  "learning_rate": 4.5288899167498167e-05,
         | 
| 3410 | 
            +
                  "loss": 3.8584,
         | 
| 3411 | 
            +
                  "step": 287744
         | 
| 3412 | 
            +
                },
         | 
| 3413 | 
            +
                {
         | 
| 3414 | 
            +
                  "epoch": 1.02,
         | 
| 3415 | 
            +
                  "learning_rate": 4.5280529598791376e-05,
         | 
| 3416 | 
            +
                  "loss": 3.8647,
         | 
| 3417 | 
            +
                  "step": 288256
         | 
| 3418 | 
            +
                },
         | 
| 3419 | 
            +
                {
         | 
| 3420 | 
            +
                  "epoch": 1.02,
         | 
| 3421 | 
            +
                  "learning_rate": 4.5272143651280856e-05,
         | 
| 3422 | 
            +
                  "loss": 3.8579,
         | 
| 3423 | 
            +
                  "step": 288768
         | 
| 3424 | 
            +
                },
         | 
| 3425 | 
            +
                {
         | 
| 3426 | 
            +
                  "epoch": 1.02,
         | 
| 3427 | 
            +
                  "learning_rate": 4.5263757703770336e-05,
         | 
| 3428 | 
            +
                  "loss": 3.852,
         | 
| 3429 | 
            +
                  "step": 289280
         | 
| 3430 | 
            +
                },
         | 
| 3431 | 
            +
                {
         | 
| 3432 | 
            +
                  "epoch": 1.02,
         | 
| 3433 | 
            +
                  "learning_rate": 4.5255371756259816e-05,
         | 
| 3434 | 
            +
                  "loss": 3.8574,
         | 
| 3435 | 
            +
                  "step": 289792
         | 
| 3436 | 
            +
                },
         | 
| 3437 | 
            +
                {
         | 
| 3438 | 
            +
                  "epoch": 1.02,
         | 
| 3439 | 
            +
                  "learning_rate": 4.5246985808749295e-05,
         | 
| 3440 | 
            +
                  "loss": 3.858,
         | 
| 3441 | 
            +
                  "step": 290304
         | 
| 3442 | 
            +
                },
         | 
| 3443 | 
            +
                {
         | 
| 3444 | 
            +
                  "epoch": 1.02,
         | 
| 3445 | 
            +
                  "learning_rate": 4.523861624004251e-05,
         | 
| 3446 | 
            +
                  "loss": 3.8398,
         | 
| 3447 | 
            +
                  "step": 290816
         | 
| 3448 | 
            +
                },
         | 
| 3449 | 
            +
                {
         | 
| 3450 | 
            +
                  "epoch": 1.02,
         | 
| 3451 | 
            +
                  "learning_rate": 4.523023029253199e-05,
         | 
| 3452 | 
            +
                  "loss": 3.8636,
         | 
| 3453 | 
            +
                  "step": 291328
         | 
| 3454 | 
            +
                },
         | 
| 3455 | 
            +
                {
         | 
| 3456 | 
            +
                  "epoch": 1.02,
         | 
| 3457 | 
            +
                  "learning_rate": 4.522184434502147e-05,
         | 
| 3458 | 
            +
                  "loss": 3.8486,
         | 
| 3459 | 
            +
                  "step": 291840
         | 
| 3460 | 
            +
                },
         | 
| 3461 | 
            +
                {
         | 
| 3462 | 
            +
                  "epoch": 1.02,
         | 
| 3463 | 
            +
                  "learning_rate": 4.521345839751095e-05,
         | 
| 3464 | 
            +
                  "loss": 3.8621,
         | 
| 3465 | 
            +
                  "step": 292352
         | 
| 3466 | 
            +
                },
         | 
| 3467 | 
            +
                {
         | 
| 3468 | 
            +
                  "epoch": 1.02,
         | 
| 3469 | 
            +
                  "learning_rate": 4.520507245000043e-05,
         | 
| 3470 | 
            +
                  "loss": 3.85,
         | 
| 3471 | 
            +
                  "step": 292864
         | 
| 3472 | 
            +
                },
         | 
| 3473 | 
            +
                {
         | 
| 3474 | 
            +
                  "epoch": 1.02,
         | 
| 3475 | 
            +
                  "learning_rate": 4.519670288129364e-05,
         | 
| 3476 | 
            +
                  "loss": 3.8495,
         | 
| 3477 | 
            +
                  "step": 293376
         | 
| 3478 | 
            +
                },
         | 
| 3479 | 
            +
                {
         | 
| 3480 | 
            +
                  "epoch": 1.02,
         | 
| 3481 | 
            +
                  "learning_rate": 4.518831693378312e-05,
         | 
| 3482 | 
            +
                  "loss": 3.8367,
         | 
| 3483 | 
            +
                  "step": 293888
         | 
| 3484 | 
            +
                },
         | 
| 3485 | 
            +
                {
         | 
| 3486 | 
            +
                  "epoch": 1.02,
         | 
| 3487 | 
            +
                  "learning_rate": 4.51799309862726e-05,
         | 
| 3488 | 
            +
                  "loss": 3.8497,
         | 
| 3489 | 
            +
                  "step": 294400
         | 
| 3490 | 
            +
                },
         | 
| 3491 | 
            +
                {
         | 
| 3492 | 
            +
                  "epoch": 1.02,
         | 
| 3493 | 
            +
                  "learning_rate": 4.517154503876208e-05,
         | 
| 3494 | 
            +
                  "loss": 3.8454,
         | 
| 3495 | 
            +
                  "step": 294912
         | 
| 3496 | 
            +
                },
         | 
| 3497 | 
            +
                {
         | 
| 3498 | 
            +
                  "epoch": 1.02,
         | 
| 3499 | 
            +
                  "learning_rate": 4.516317547005529e-05,
         | 
| 3500 | 
            +
                  "loss": 3.8537,
         | 
| 3501 | 
            +
                  "step": 295424
         | 
| 3502 | 
            +
                },
         | 
| 3503 | 
            +
                {
         | 
| 3504 | 
            +
                  "epoch": 1.02,
         | 
| 3505 | 
            +
                  "learning_rate": 4.515478952254477e-05,
         | 
| 3506 | 
            +
                  "loss": 3.859,
         | 
| 3507 | 
            +
                  "step": 295936
         | 
| 3508 | 
            +
                },
         | 
| 3509 | 
            +
                {
         | 
| 3510 | 
            +
                  "epoch": 1.02,
         | 
| 3511 | 
            +
                  "learning_rate": 4.514640357503425e-05,
         | 
| 3512 | 
            +
                  "loss": 3.8537,
         | 
| 3513 | 
            +
                  "step": 296448
         | 
| 3514 | 
            +
                },
         | 
| 3515 | 
            +
                {
         | 
| 3516 | 
            +
                  "epoch": 1.02,
         | 
| 3517 | 
            +
                  "learning_rate": 4.513801762752373e-05,
         | 
| 3518 | 
            +
                  "loss": 3.8374,
         | 
| 3519 | 
            +
                  "step": 296960
         | 
| 3520 | 
            +
                },
         | 
| 3521 | 
            +
                {
         | 
| 3522 | 
            +
                  "epoch": 1.02,
         | 
| 3523 | 
            +
                  "learning_rate": 4.512963168001321e-05,
         | 
| 3524 | 
            +
                  "loss": 3.8531,
         | 
| 3525 | 
            +
                  "step": 297472
         | 
| 3526 | 
            +
                },
         | 
| 3527 | 
            +
                {
         | 
| 3528 | 
            +
                  "epoch": 1.02,
         | 
| 3529 | 
            +
                  "learning_rate": 4.5121262111306425e-05,
         | 
| 3530 | 
            +
                  "loss": 3.8536,
         | 
| 3531 | 
            +
                  "step": 297984
         | 
| 3532 | 
            +
                },
         | 
| 3533 | 
            +
                {
         | 
| 3534 | 
            +
                  "epoch": 1.02,
         | 
| 3535 | 
            +
                  "learning_rate": 4.5112876163795905e-05,
         | 
| 3536 | 
            +
                  "loss": 3.8569,
         | 
| 3537 | 
            +
                  "step": 298496
         | 
| 3538 | 
            +
                },
         | 
| 3539 | 
            +
                {
         | 
| 3540 | 
            +
                  "epoch": 1.02,
         | 
| 3541 | 
            +
                  "learning_rate": 4.5104490216285385e-05,
         | 
| 3542 | 
            +
                  "loss": 3.8533,
         | 
| 3543 | 
            +
                  "step": 299008
         | 
| 3544 | 
            +
                },
         | 
| 3545 | 
            +
                {
         | 
| 3546 | 
            +
                  "epoch": 1.02,
         | 
| 3547 | 
            +
                  "learning_rate": 4.5096104268774865e-05,
         | 
| 3548 | 
            +
                  "loss": 3.8444,
         | 
| 3549 | 
            +
                  "step": 299520
         | 
| 3550 | 
            +
                },
         | 
| 3551 | 
            +
                {
         | 
| 3552 | 
            +
                  "epoch": 1.02,
         | 
| 3553 | 
            +
                  "learning_rate": 4.5087734700068074e-05,
         | 
| 3554 | 
            +
                  "loss": 3.8488,
         | 
| 3555 | 
            +
                  "step": 300032
         | 
| 3556 | 
            +
                },
         | 
| 3557 | 
            +
                {
         | 
| 3558 | 
            +
                  "epoch": 1.02,
         | 
| 3559 | 
            +
                  "learning_rate": 4.5079348752557554e-05,
         | 
| 3560 | 
            +
                  "loss": 3.8579,
         | 
| 3561 | 
            +
                  "step": 300544
         | 
| 3562 | 
            +
                },
         | 
| 3563 | 
            +
                {
         | 
| 3564 | 
            +
                  "epoch": 1.02,
         | 
| 3565 | 
            +
                  "learning_rate": 4.5070962805047034e-05,
         | 
| 3566 | 
            +
                  "loss": 3.8412,
         | 
| 3567 | 
            +
                  "step": 301056
         | 
| 3568 | 
            +
                },
         | 
| 3569 | 
            +
                {
         | 
| 3570 | 
            +
                  "epoch": 1.02,
         | 
| 3571 | 
            +
                  "learning_rate": 4.5062576857536514e-05,
         | 
| 3572 | 
            +
                  "loss": 3.8505,
         | 
| 3573 | 
            +
                  "step": 301568
         | 
| 3574 | 
            +
                },
         | 
| 3575 | 
            +
                {
         | 
| 3576 | 
            +
                  "epoch": 1.02,
         | 
| 3577 | 
            +
                  "learning_rate": 4.505420728882972e-05,
         | 
| 3578 | 
            +
                  "loss": 3.8401,
         | 
| 3579 | 
            +
                  "step": 302080
         | 
| 3580 | 
            +
                },
         | 
| 3581 | 
            +
                {
         | 
| 3582 | 
            +
                  "epoch": 1.02,
         | 
| 3583 | 
            +
                  "learning_rate": 4.50458213413192e-05,
         | 
| 3584 | 
            +
                  "loss": 3.8439,
         | 
| 3585 | 
            +
                  "step": 302592
         | 
| 3586 | 
            +
                },
         | 
| 3587 | 
            +
                {
         | 
| 3588 | 
            +
                  "epoch": 1.02,
         | 
| 3589 | 
            +
                  "learning_rate": 4.503743539380868e-05,
         | 
| 3590 | 
            +
                  "loss": 3.8579,
         | 
| 3591 | 
            +
                  "step": 303104
         | 
| 3592 | 
            +
                },
         | 
| 3593 | 
            +
                {
         | 
| 3594 | 
            +
                  "epoch": 1.02,
         | 
| 3595 | 
            +
                  "learning_rate": 4.502904944629816e-05,
         | 
| 3596 | 
            +
                  "loss": 3.8443,
         | 
| 3597 | 
            +
                  "step": 303616
         | 
| 3598 | 
            +
                },
         | 
| 3599 | 
            +
                {
         | 
| 3600 | 
            +
                  "epoch": 1.02,
         | 
| 3601 | 
            +
                  "learning_rate": 4.502066349878764e-05,
         | 
| 3602 | 
            +
                  "loss": 3.8407,
         | 
| 3603 | 
            +
                  "step": 304128
         | 
| 3604 | 
            +
                },
         | 
| 3605 | 
            +
                {
         | 
| 3606 | 
            +
                  "epoch": 1.02,
         | 
| 3607 | 
            +
                  "learning_rate": 4.501229393008086e-05,
         | 
| 3608 | 
            +
                  "loss": 3.8382,
         | 
| 3609 | 
            +
                  "step": 304640
         | 
| 3610 | 
            +
                },
         | 
| 3611 | 
            +
                {
         | 
| 3612 | 
            +
                  "epoch": 1.02,
         | 
| 3613 | 
            +
                  "learning_rate": 4.500390798257034e-05,
         | 
| 3614 | 
            +
                  "loss": 3.842,
         | 
| 3615 | 
            +
                  "step": 305152
         | 
| 3616 | 
            +
                },
         | 
| 3617 | 
            +
                {
         | 
| 3618 | 
            +
                  "epoch": 1.03,
         | 
| 3619 | 
            +
                  "eval_loss": 3.9126405715942383,
         | 
| 3620 | 
            +
                  "eval_runtime": 301.972,
         | 
| 3621 | 
            +
                  "eval_samples_per_second": 1263.664,
         | 
| 3622 | 
            +
                  "eval_steps_per_second": 39.49,
         | 
| 3623 | 
            +
                  "step": 305280
         | 
| 3624 | 
            +
                }
         | 
| 3625 | 
            +
              ],
         | 
| 3626 | 
            +
              "logging_steps": 512,
         | 
| 3627 | 
            +
              "max_steps": 3052726,
         | 
| 3628 | 
            +
              "num_train_epochs": 9223372036854775807,
         | 
| 3629 | 
            +
              "save_steps": 10,
         | 
| 3630 | 
            +
              "total_flos": 2.1158923574167142e+17,
         | 
| 3631 | 
            +
              "trial_name": null,
         | 
| 3632 | 
            +
              "trial_params": null
         | 
| 3633 | 
            +
            }
         | 
    	
        checkpoint-305280/training_args.bin
    ADDED
    
    | @@ -0,0 +1,3 @@ | |
|  | |
|  | |
|  | 
|  | |
| 1 | 
            +
            version https://git-lfs.github.com/spec/v1
         | 
| 2 | 
            +
            oid sha256:1514bfbfbfd81dfc9e41cecd9dda23bb0db8303d79a00cabf86f0d8da0f5ae28
         | 
| 3 | 
            +
            size 4347
         | 
