Training in progress, step 29500, checkpoint
Browse files- checkpoint-29500/config.json +62 -0
 - checkpoint-29500/model.safetensors +3 -0
 - checkpoint-29500/optimizer.pt +3 -0
 - checkpoint-29500/preprocessor_config.json +26 -0
 - checkpoint-29500/rng_state.pth +3 -0
 - checkpoint-29500/scheduler.pt +3 -0
 - checkpoint-29500/trainer_state.json +2098 -0
 - checkpoint-29500/training_args.bin +3 -0
 
    	
        checkpoint-29500/config.json
    ADDED
    
    | 
         @@ -0,0 +1,62 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "_name_or_path": "facebook/detr-resnet-50-dc5",
         
     | 
| 3 | 
         
            +
              "activation_dropout": 0.0,
         
     | 
| 4 | 
         
            +
              "activation_function": "relu",
         
     | 
| 5 | 
         
            +
              "architectures": [
         
     | 
| 6 | 
         
            +
                "DetrForObjectDetection"
         
     | 
| 7 | 
         
            +
              ],
         
     | 
| 8 | 
         
            +
              "attention_dropout": 0.0,
         
     | 
| 9 | 
         
            +
              "auxiliary_loss": false,
         
     | 
| 10 | 
         
            +
              "backbone": "resnet50",
         
     | 
| 11 | 
         
            +
              "backbone_config": null,
         
     | 
| 12 | 
         
            +
              "backbone_kwargs": {
         
     | 
| 13 | 
         
            +
                "in_chans": 3,
         
     | 
| 14 | 
         
            +
                "out_indices": [
         
     | 
| 15 | 
         
            +
                  1,
         
     | 
| 16 | 
         
            +
                  2,
         
     | 
| 17 | 
         
            +
                  3,
         
     | 
| 18 | 
         
            +
                  4
         
     | 
| 19 | 
         
            +
                ],
         
     | 
| 20 | 
         
            +
                "output_stride": 16
         
     | 
| 21 | 
         
            +
              },
         
     | 
| 22 | 
         
            +
              "bbox_cost": 5,
         
     | 
| 23 | 
         
            +
              "bbox_loss_coefficient": 5,
         
     | 
| 24 | 
         
            +
              "class_cost": 1,
         
     | 
| 25 | 
         
            +
              "classifier_dropout": 0.0,
         
     | 
| 26 | 
         
            +
              "d_model": 256,
         
     | 
| 27 | 
         
            +
              "decoder_attention_heads": 8,
         
     | 
| 28 | 
         
            +
              "decoder_ffn_dim": 2048,
         
     | 
| 29 | 
         
            +
              "decoder_layerdrop": 0.0,
         
     | 
| 30 | 
         
            +
              "decoder_layers": 6,
         
     | 
| 31 | 
         
            +
              "dice_loss_coefficient": 1,
         
     | 
| 32 | 
         
            +
              "dilation": true,
         
     | 
| 33 | 
         
            +
              "dropout": 0.1,
         
     | 
| 34 | 
         
            +
              "encoder_attention_heads": 8,
         
     | 
| 35 | 
         
            +
              "encoder_ffn_dim": 2048,
         
     | 
| 36 | 
         
            +
              "encoder_layerdrop": 0.0,
         
     | 
| 37 | 
         
            +
              "encoder_layers": 6,
         
     | 
| 38 | 
         
            +
              "eos_coefficient": 0.1,
         
     | 
| 39 | 
         
            +
              "giou_cost": 2,
         
     | 
| 40 | 
         
            +
              "giou_loss_coefficient": 2,
         
     | 
| 41 | 
         
            +
              "id2label": {
         
     | 
| 42 | 
         
            +
                "0": "segment"
         
     | 
| 43 | 
         
            +
              },
         
     | 
| 44 | 
         
            +
              "init_std": 0.02,
         
     | 
| 45 | 
         
            +
              "init_xavier_std": 1.0,
         
     | 
| 46 | 
         
            +
              "is_encoder_decoder": true,
         
     | 
| 47 | 
         
            +
              "label2id": {
         
     | 
| 48 | 
         
            +
                "segment": 0
         
     | 
| 49 | 
         
            +
              },
         
     | 
| 50 | 
         
            +
              "mask_loss_coefficient": 1,
         
     | 
| 51 | 
         
            +
              "max_position_embeddings": 1024,
         
     | 
| 52 | 
         
            +
              "model_type": "detr",
         
     | 
| 53 | 
         
            +
              "num_channels": 3,
         
     | 
| 54 | 
         
            +
              "num_hidden_layers": 6,
         
     | 
| 55 | 
         
            +
              "num_queries": 500,
         
     | 
| 56 | 
         
            +
              "position_embedding_type": "sine",
         
     | 
| 57 | 
         
            +
              "scale_embedding": false,
         
     | 
| 58 | 
         
            +
              "torch_dtype": "float32",
         
     | 
| 59 | 
         
            +
              "transformers_version": "4.44.2",
         
     | 
| 60 | 
         
            +
              "use_pretrained_backbone": true,
         
     | 
| 61 | 
         
            +
              "use_timm_backbone": true
         
     | 
| 62 | 
         
            +
            }
         
     | 
    	
        checkpoint-29500/model.safetensors
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:b57a43e59e4124fce7facf1754de9e5e19b600bb9935a401db74a6d53acad9ea
         
     | 
| 3 | 
         
            +
            size 166904424
         
     | 
    	
        checkpoint-29500/optimizer.pt
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:8ab0b67c70cb414ed30751e5a8345b4bbf2e8362ba5e07aede5b3d07247d1b4f
         
     | 
| 3 | 
         
            +
            size 331310970
         
     | 
    	
        checkpoint-29500/preprocessor_config.json
    ADDED
    
    | 
         @@ -0,0 +1,26 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "do_convert_annotations": true,
         
     | 
| 3 | 
         
            +
              "do_normalize": true,
         
     | 
| 4 | 
         
            +
              "do_pad": true,
         
     | 
| 5 | 
         
            +
              "do_rescale": true,
         
     | 
| 6 | 
         
            +
              "do_resize": true,
         
     | 
| 7 | 
         
            +
              "format": "coco_detection",
         
     | 
| 8 | 
         
            +
              "image_mean": [
         
     | 
| 9 | 
         
            +
                0.485,
         
     | 
| 10 | 
         
            +
                0.456,
         
     | 
| 11 | 
         
            +
                0.406
         
     | 
| 12 | 
         
            +
              ],
         
     | 
| 13 | 
         
            +
              "image_processor_type": "DetrImageProcessor",
         
     | 
| 14 | 
         
            +
              "image_std": [
         
     | 
| 15 | 
         
            +
                0.229,
         
     | 
| 16 | 
         
            +
                0.224,
         
     | 
| 17 | 
         
            +
                0.225
         
     | 
| 18 | 
         
            +
              ],
         
     | 
| 19 | 
         
            +
              "pad_size": null,
         
     | 
| 20 | 
         
            +
              "resample": 2,
         
     | 
| 21 | 
         
            +
              "rescale_factor": 0.00392156862745098,
         
     | 
| 22 | 
         
            +
              "size": {
         
     | 
| 23 | 
         
            +
                "longest_edge": 1333,
         
     | 
| 24 | 
         
            +
                "shortest_edge": 800
         
     | 
| 25 | 
         
            +
              }
         
     | 
| 26 | 
         
            +
            }
         
     | 
    	
        checkpoint-29500/rng_state.pth
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:c34cd15b05bc61082b467e3ee7591522438cfd6dfb93660481f5d220b1b05b61
         
     | 
| 3 | 
         
            +
            size 14180
         
     | 
    	
        checkpoint-29500/scheduler.pt
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:5b6fc78fbc90ab8395367c30f6a7e18298abcb29ab49a5e298ebdaedbaa8e2c0
         
     | 
| 3 | 
         
            +
            size 1064
         
     | 
    	
        checkpoint-29500/trainer_state.json
    ADDED
    
    | 
         @@ -0,0 +1,2098 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            {
         
     | 
| 2 | 
         
            +
              "best_metric": null,
         
     | 
| 3 | 
         
            +
              "best_model_checkpoint": null,
         
     | 
| 4 | 
         
            +
              "epoch": 453.84615384615387,
         
     | 
| 5 | 
         
            +
              "eval_steps": 500,
         
     | 
| 6 | 
         
            +
              "global_step": 29500,
         
     | 
| 7 | 
         
            +
              "is_hyper_param_search": false,
         
     | 
| 8 | 
         
            +
              "is_local_process_zero": true,
         
     | 
| 9 | 
         
            +
              "is_world_process_zero": true,
         
     | 
| 10 | 
         
            +
              "log_history": [
         
     | 
| 11 | 
         
            +
                {
         
     | 
| 12 | 
         
            +
                  "epoch": 1.5384615384615383,
         
     | 
| 13 | 
         
            +
                  "grad_norm": 134.7136688232422,
         
     | 
| 14 | 
         
            +
                  "learning_rate": 9.981600000000001e-06,
         
     | 
| 15 | 
         
            +
                  "loss": 5.6198,
         
     | 
| 16 | 
         
            +
                  "step": 100
         
     | 
| 17 | 
         
            +
                },
         
     | 
| 18 | 
         
            +
                {
         
     | 
| 19 | 
         
            +
                  "epoch": 3.076923076923077,
         
     | 
| 20 | 
         
            +
                  "grad_norm": 115.98611450195312,
         
     | 
| 21 | 
         
            +
                  "learning_rate": 9.961600000000001e-06,
         
     | 
| 22 | 
         
            +
                  "loss": 3.5959,
         
     | 
| 23 | 
         
            +
                  "step": 200
         
     | 
| 24 | 
         
            +
                },
         
     | 
| 25 | 
         
            +
                {
         
     | 
| 26 | 
         
            +
                  "epoch": 4.615384615384615,
         
     | 
| 27 | 
         
            +
                  "grad_norm": 114.23514556884766,
         
     | 
| 28 | 
         
            +
                  "learning_rate": 9.941600000000002e-06,
         
     | 
| 29 | 
         
            +
                  "loss": 3.3845,
         
     | 
| 30 | 
         
            +
                  "step": 300
         
     | 
| 31 | 
         
            +
                },
         
     | 
| 32 | 
         
            +
                {
         
     | 
| 33 | 
         
            +
                  "epoch": 6.153846153846154,
         
     | 
| 34 | 
         
            +
                  "grad_norm": 140.5648193359375,
         
     | 
| 35 | 
         
            +
                  "learning_rate": 9.921600000000002e-06,
         
     | 
| 36 | 
         
            +
                  "loss": 3.1494,
         
     | 
| 37 | 
         
            +
                  "step": 400
         
     | 
| 38 | 
         
            +
                },
         
     | 
| 39 | 
         
            +
                {
         
     | 
| 40 | 
         
            +
                  "epoch": 7.6923076923076925,
         
     | 
| 41 | 
         
            +
                  "grad_norm": 117.4485855102539,
         
     | 
| 42 | 
         
            +
                  "learning_rate": 9.901600000000002e-06,
         
     | 
| 43 | 
         
            +
                  "loss": 3.0773,
         
     | 
| 44 | 
         
            +
                  "step": 500
         
     | 
| 45 | 
         
            +
                },
         
     | 
| 46 | 
         
            +
                {
         
     | 
| 47 | 
         
            +
                  "epoch": 9.23076923076923,
         
     | 
| 48 | 
         
            +
                  "grad_norm": 389.71490478515625,
         
     | 
| 49 | 
         
            +
                  "learning_rate": 9.8816e-06,
         
     | 
| 50 | 
         
            +
                  "loss": 3.2116,
         
     | 
| 51 | 
         
            +
                  "step": 600
         
     | 
| 52 | 
         
            +
                },
         
     | 
| 53 | 
         
            +
                {
         
     | 
| 54 | 
         
            +
                  "epoch": 10.76923076923077,
         
     | 
| 55 | 
         
            +
                  "grad_norm": 107.11251831054688,
         
     | 
| 56 | 
         
            +
                  "learning_rate": 9.8616e-06,
         
     | 
| 57 | 
         
            +
                  "loss": 3.0471,
         
     | 
| 58 | 
         
            +
                  "step": 700
         
     | 
| 59 | 
         
            +
                },
         
     | 
| 60 | 
         
            +
                {
         
     | 
| 61 | 
         
            +
                  "epoch": 12.307692307692308,
         
     | 
| 62 | 
         
            +
                  "grad_norm": 85.49571228027344,
         
     | 
| 63 | 
         
            +
                  "learning_rate": 9.8416e-06,
         
     | 
| 64 | 
         
            +
                  "loss": 3.0201,
         
     | 
| 65 | 
         
            +
                  "step": 800
         
     | 
| 66 | 
         
            +
                },
         
     | 
| 67 | 
         
            +
                {
         
     | 
| 68 | 
         
            +
                  "epoch": 13.846153846153847,
         
     | 
| 69 | 
         
            +
                  "grad_norm": 121.62274932861328,
         
     | 
| 70 | 
         
            +
                  "learning_rate": 9.821600000000001e-06,
         
     | 
| 71 | 
         
            +
                  "loss": 2.9355,
         
     | 
| 72 | 
         
            +
                  "step": 900
         
     | 
| 73 | 
         
            +
                },
         
     | 
| 74 | 
         
            +
                {
         
     | 
| 75 | 
         
            +
                  "epoch": 15.384615384615385,
         
     | 
| 76 | 
         
            +
                  "grad_norm": 64.66451263427734,
         
     | 
| 77 | 
         
            +
                  "learning_rate": 9.801600000000001e-06,
         
     | 
| 78 | 
         
            +
                  "loss": 2.9637,
         
     | 
| 79 | 
         
            +
                  "step": 1000
         
     | 
| 80 | 
         
            +
                },
         
     | 
| 81 | 
         
            +
                {
         
     | 
| 82 | 
         
            +
                  "epoch": 16.923076923076923,
         
     | 
| 83 | 
         
            +
                  "grad_norm": 182.4657440185547,
         
     | 
| 84 | 
         
            +
                  "learning_rate": 9.781600000000001e-06,
         
     | 
| 85 | 
         
            +
                  "loss": 2.9819,
         
     | 
| 86 | 
         
            +
                  "step": 1100
         
     | 
| 87 | 
         
            +
                },
         
     | 
| 88 | 
         
            +
                {
         
     | 
| 89 | 
         
            +
                  "epoch": 18.46153846153846,
         
     | 
| 90 | 
         
            +
                  "grad_norm": 97.80529022216797,
         
     | 
| 91 | 
         
            +
                  "learning_rate": 9.761600000000002e-06,
         
     | 
| 92 | 
         
            +
                  "loss": 2.9486,
         
     | 
| 93 | 
         
            +
                  "step": 1200
         
     | 
| 94 | 
         
            +
                },
         
     | 
| 95 | 
         
            +
                {
         
     | 
| 96 | 
         
            +
                  "epoch": 20.0,
         
     | 
| 97 | 
         
            +
                  "grad_norm": 220.0562744140625,
         
     | 
| 98 | 
         
            +
                  "learning_rate": 9.741600000000002e-06,
         
     | 
| 99 | 
         
            +
                  "loss": 2.8608,
         
     | 
| 100 | 
         
            +
                  "step": 1300
         
     | 
| 101 | 
         
            +
                },
         
     | 
| 102 | 
         
            +
                {
         
     | 
| 103 | 
         
            +
                  "epoch": 21.53846153846154,
         
     | 
| 104 | 
         
            +
                  "grad_norm": 95.53397369384766,
         
     | 
| 105 | 
         
            +
                  "learning_rate": 9.7216e-06,
         
     | 
| 106 | 
         
            +
                  "loss": 2.8322,
         
     | 
| 107 | 
         
            +
                  "step": 1400
         
     | 
| 108 | 
         
            +
                },
         
     | 
| 109 | 
         
            +
                {
         
     | 
| 110 | 
         
            +
                  "epoch": 23.076923076923077,
         
     | 
| 111 | 
         
            +
                  "grad_norm": 67.54853057861328,
         
     | 
| 112 | 
         
            +
                  "learning_rate": 9.7016e-06,
         
     | 
| 113 | 
         
            +
                  "loss": 2.9429,
         
     | 
| 114 | 
         
            +
                  "step": 1500
         
     | 
| 115 | 
         
            +
                },
         
     | 
| 116 | 
         
            +
                {
         
     | 
| 117 | 
         
            +
                  "epoch": 24.615384615384617,
         
     | 
| 118 | 
         
            +
                  "grad_norm": 214.53131103515625,
         
     | 
| 119 | 
         
            +
                  "learning_rate": 9.6816e-06,
         
     | 
| 120 | 
         
            +
                  "loss": 2.7927,
         
     | 
| 121 | 
         
            +
                  "step": 1600
         
     | 
| 122 | 
         
            +
                },
         
     | 
| 123 | 
         
            +
                {
         
     | 
| 124 | 
         
            +
                  "epoch": 26.153846153846153,
         
     | 
| 125 | 
         
            +
                  "grad_norm": 293.3318786621094,
         
     | 
| 126 | 
         
            +
                  "learning_rate": 9.6616e-06,
         
     | 
| 127 | 
         
            +
                  "loss": 2.7665,
         
     | 
| 128 | 
         
            +
                  "step": 1700
         
     | 
| 129 | 
         
            +
                },
         
     | 
| 130 | 
         
            +
                {
         
     | 
| 131 | 
         
            +
                  "epoch": 27.692307692307693,
         
     | 
| 132 | 
         
            +
                  "grad_norm": 216.3682861328125,
         
     | 
| 133 | 
         
            +
                  "learning_rate": 9.641600000000001e-06,
         
     | 
| 134 | 
         
            +
                  "loss": 2.8309,
         
     | 
| 135 | 
         
            +
                  "step": 1800
         
     | 
| 136 | 
         
            +
                },
         
     | 
| 137 | 
         
            +
                {
         
     | 
| 138 | 
         
            +
                  "epoch": 29.23076923076923,
         
     | 
| 139 | 
         
            +
                  "grad_norm": 168.0605010986328,
         
     | 
| 140 | 
         
            +
                  "learning_rate": 9.621600000000001e-06,
         
     | 
| 141 | 
         
            +
                  "loss": 2.8433,
         
     | 
| 142 | 
         
            +
                  "step": 1900
         
     | 
| 143 | 
         
            +
                },
         
     | 
| 144 | 
         
            +
                {
         
     | 
| 145 | 
         
            +
                  "epoch": 30.76923076923077,
         
     | 
| 146 | 
         
            +
                  "grad_norm": 103.49143981933594,
         
     | 
| 147 | 
         
            +
                  "learning_rate": 9.601600000000001e-06,
         
     | 
| 148 | 
         
            +
                  "loss": 2.7606,
         
     | 
| 149 | 
         
            +
                  "step": 2000
         
     | 
| 150 | 
         
            +
                },
         
     | 
| 151 | 
         
            +
                {
         
     | 
| 152 | 
         
            +
                  "epoch": 32.30769230769231,
         
     | 
| 153 | 
         
            +
                  "grad_norm": 116.6761474609375,
         
     | 
| 154 | 
         
            +
                  "learning_rate": 9.581600000000002e-06,
         
     | 
| 155 | 
         
            +
                  "loss": 2.6595,
         
     | 
| 156 | 
         
            +
                  "step": 2100
         
     | 
| 157 | 
         
            +
                },
         
     | 
| 158 | 
         
            +
                {
         
     | 
| 159 | 
         
            +
                  "epoch": 33.84615384615385,
         
     | 
| 160 | 
         
            +
                  "grad_norm": 176.0087432861328,
         
     | 
| 161 | 
         
            +
                  "learning_rate": 9.5616e-06,
         
     | 
| 162 | 
         
            +
                  "loss": 2.632,
         
     | 
| 163 | 
         
            +
                  "step": 2200
         
     | 
| 164 | 
         
            +
                },
         
     | 
| 165 | 
         
            +
                {
         
     | 
| 166 | 
         
            +
                  "epoch": 35.38461538461539,
         
     | 
| 167 | 
         
            +
                  "grad_norm": 120.39679718017578,
         
     | 
| 168 | 
         
            +
                  "learning_rate": 9.5416e-06,
         
     | 
| 169 | 
         
            +
                  "loss": 2.5941,
         
     | 
| 170 | 
         
            +
                  "step": 2300
         
     | 
| 171 | 
         
            +
                },
         
     | 
| 172 | 
         
            +
                {
         
     | 
| 173 | 
         
            +
                  "epoch": 36.92307692307692,
         
     | 
| 174 | 
         
            +
                  "grad_norm": 100.69256591796875,
         
     | 
| 175 | 
         
            +
                  "learning_rate": 9.5216e-06,
         
     | 
| 176 | 
         
            +
                  "loss": 2.6007,
         
     | 
| 177 | 
         
            +
                  "step": 2400
         
     | 
| 178 | 
         
            +
                },
         
     | 
| 179 | 
         
            +
                {
         
     | 
| 180 | 
         
            +
                  "epoch": 38.46153846153846,
         
     | 
| 181 | 
         
            +
                  "grad_norm": 254.54440307617188,
         
     | 
| 182 | 
         
            +
                  "learning_rate": 9.5016e-06,
         
     | 
| 183 | 
         
            +
                  "loss": 2.5548,
         
     | 
| 184 | 
         
            +
                  "step": 2500
         
     | 
| 185 | 
         
            +
                },
         
     | 
| 186 | 
         
            +
                {
         
     | 
| 187 | 
         
            +
                  "epoch": 40.0,
         
     | 
| 188 | 
         
            +
                  "grad_norm": 113.618896484375,
         
     | 
| 189 | 
         
            +
                  "learning_rate": 9.4816e-06,
         
     | 
| 190 | 
         
            +
                  "loss": 2.5157,
         
     | 
| 191 | 
         
            +
                  "step": 2600
         
     | 
| 192 | 
         
            +
                },
         
     | 
| 193 | 
         
            +
                {
         
     | 
| 194 | 
         
            +
                  "epoch": 41.53846153846154,
         
     | 
| 195 | 
         
            +
                  "grad_norm": 825.5616455078125,
         
     | 
| 196 | 
         
            +
                  "learning_rate": 9.461600000000001e-06,
         
     | 
| 197 | 
         
            +
                  "loss": 2.4832,
         
     | 
| 198 | 
         
            +
                  "step": 2700
         
     | 
| 199 | 
         
            +
                },
         
     | 
| 200 | 
         
            +
                {
         
     | 
| 201 | 
         
            +
                  "epoch": 43.07692307692308,
         
     | 
| 202 | 
         
            +
                  "grad_norm": 58.83940505981445,
         
     | 
| 203 | 
         
            +
                  "learning_rate": 9.441600000000001e-06,
         
     | 
| 204 | 
         
            +
                  "loss": 2.4393,
         
     | 
| 205 | 
         
            +
                  "step": 2800
         
     | 
| 206 | 
         
            +
                },
         
     | 
| 207 | 
         
            +
                {
         
     | 
| 208 | 
         
            +
                  "epoch": 44.61538461538461,
         
     | 
| 209 | 
         
            +
                  "grad_norm": 89.66182708740234,
         
     | 
| 210 | 
         
            +
                  "learning_rate": 9.421600000000001e-06,
         
     | 
| 211 | 
         
            +
                  "loss": 2.4381,
         
     | 
| 212 | 
         
            +
                  "step": 2900
         
     | 
| 213 | 
         
            +
                },
         
     | 
| 214 | 
         
            +
                {
         
     | 
| 215 | 
         
            +
                  "epoch": 46.15384615384615,
         
     | 
| 216 | 
         
            +
                  "grad_norm": 242.81410217285156,
         
     | 
| 217 | 
         
            +
                  "learning_rate": 9.4016e-06,
         
     | 
| 218 | 
         
            +
                  "loss": 2.3978,
         
     | 
| 219 | 
         
            +
                  "step": 3000
         
     | 
| 220 | 
         
            +
                },
         
     | 
| 221 | 
         
            +
                {
         
     | 
| 222 | 
         
            +
                  "epoch": 47.69230769230769,
         
     | 
| 223 | 
         
            +
                  "grad_norm": 70.43364715576172,
         
     | 
| 224 | 
         
            +
                  "learning_rate": 9.3816e-06,
         
     | 
| 225 | 
         
            +
                  "loss": 2.3782,
         
     | 
| 226 | 
         
            +
                  "step": 3100
         
     | 
| 227 | 
         
            +
                },
         
     | 
| 228 | 
         
            +
                {
         
     | 
| 229 | 
         
            +
                  "epoch": 49.23076923076923,
         
     | 
| 230 | 
         
            +
                  "grad_norm": 244.31356811523438,
         
     | 
| 231 | 
         
            +
                  "learning_rate": 9.3616e-06,
         
     | 
| 232 | 
         
            +
                  "loss": 2.3319,
         
     | 
| 233 | 
         
            +
                  "step": 3200
         
     | 
| 234 | 
         
            +
                },
         
     | 
| 235 | 
         
            +
                {
         
     | 
| 236 | 
         
            +
                  "epoch": 50.76923076923077,
         
     | 
| 237 | 
         
            +
                  "grad_norm": 59.848697662353516,
         
     | 
| 238 | 
         
            +
                  "learning_rate": 9.3416e-06,
         
     | 
| 239 | 
         
            +
                  "loss": 2.3205,
         
     | 
| 240 | 
         
            +
                  "step": 3300
         
     | 
| 241 | 
         
            +
                },
         
     | 
| 242 | 
         
            +
                {
         
     | 
| 243 | 
         
            +
                  "epoch": 52.30769230769231,
         
     | 
| 244 | 
         
            +
                  "grad_norm": 109.26374053955078,
         
     | 
| 245 | 
         
            +
                  "learning_rate": 9.3216e-06,
         
     | 
| 246 | 
         
            +
                  "loss": 2.2943,
         
     | 
| 247 | 
         
            +
                  "step": 3400
         
     | 
| 248 | 
         
            +
                },
         
     | 
| 249 | 
         
            +
                {
         
     | 
| 250 | 
         
            +
                  "epoch": 53.84615384615385,
         
     | 
| 251 | 
         
            +
                  "grad_norm": 307.2849426269531,
         
     | 
| 252 | 
         
            +
                  "learning_rate": 9.301600000000001e-06,
         
     | 
| 253 | 
         
            +
                  "loss": 2.2913,
         
     | 
| 254 | 
         
            +
                  "step": 3500
         
     | 
| 255 | 
         
            +
                },
         
     | 
| 256 | 
         
            +
                {
         
     | 
| 257 | 
         
            +
                  "epoch": 55.38461538461539,
         
     | 
| 258 | 
         
            +
                  "grad_norm": 69.93729400634766,
         
     | 
| 259 | 
         
            +
                  "learning_rate": 9.281600000000001e-06,
         
     | 
| 260 | 
         
            +
                  "loss": 2.2166,
         
     | 
| 261 | 
         
            +
                  "step": 3600
         
     | 
| 262 | 
         
            +
                },
         
     | 
| 263 | 
         
            +
                {
         
     | 
| 264 | 
         
            +
                  "epoch": 56.92307692307692,
         
     | 
| 265 | 
         
            +
                  "grad_norm": 83.3631591796875,
         
     | 
| 266 | 
         
            +
                  "learning_rate": 9.261600000000001e-06,
         
     | 
| 267 | 
         
            +
                  "loss": 2.2718,
         
     | 
| 268 | 
         
            +
                  "step": 3700
         
     | 
| 269 | 
         
            +
                },
         
     | 
| 270 | 
         
            +
                {
         
     | 
| 271 | 
         
            +
                  "epoch": 58.46153846153846,
         
     | 
| 272 | 
         
            +
                  "grad_norm": 48.52922821044922,
         
     | 
| 273 | 
         
            +
                  "learning_rate": 9.2416e-06,
         
     | 
| 274 | 
         
            +
                  "loss": 2.2645,
         
     | 
| 275 | 
         
            +
                  "step": 3800
         
     | 
| 276 | 
         
            +
                },
         
     | 
| 277 | 
         
            +
                {
         
     | 
| 278 | 
         
            +
                  "epoch": 60.0,
         
     | 
| 279 | 
         
            +
                  "grad_norm": 51.951324462890625,
         
     | 
| 280 | 
         
            +
                  "learning_rate": 9.2218e-06,
         
     | 
| 281 | 
         
            +
                  "loss": 2.2416,
         
     | 
| 282 | 
         
            +
                  "step": 3900
         
     | 
| 283 | 
         
            +
                },
         
     | 
| 284 | 
         
            +
                {
         
     | 
| 285 | 
         
            +
                  "epoch": 61.53846153846154,
         
     | 
| 286 | 
         
            +
                  "grad_norm": 254.99429321289062,
         
     | 
| 287 | 
         
            +
                  "learning_rate": 9.2018e-06,
         
     | 
| 288 | 
         
            +
                  "loss": 2.2104,
         
     | 
| 289 | 
         
            +
                  "step": 4000
         
     | 
| 290 | 
         
            +
                },
         
     | 
| 291 | 
         
            +
                {
         
     | 
| 292 | 
         
            +
                  "epoch": 63.07692307692308,
         
     | 
| 293 | 
         
            +
                  "grad_norm": 109.68157958984375,
         
     | 
| 294 | 
         
            +
                  "learning_rate": 9.1818e-06,
         
     | 
| 295 | 
         
            +
                  "loss": 2.1574,
         
     | 
| 296 | 
         
            +
                  "step": 4100
         
     | 
| 297 | 
         
            +
                },
         
     | 
| 298 | 
         
            +
                {
         
     | 
| 299 | 
         
            +
                  "epoch": 64.61538461538461,
         
     | 
| 300 | 
         
            +
                  "grad_norm": 85.5855941772461,
         
     | 
| 301 | 
         
            +
                  "learning_rate": 9.161800000000001e-06,
         
     | 
| 302 | 
         
            +
                  "loss": 2.1513,
         
     | 
| 303 | 
         
            +
                  "step": 4200
         
     | 
| 304 | 
         
            +
                },
         
     | 
| 305 | 
         
            +
                {
         
     | 
| 306 | 
         
            +
                  "epoch": 66.15384615384616,
         
     | 
| 307 | 
         
            +
                  "grad_norm": 63.89781951904297,
         
     | 
| 308 | 
         
            +
                  "learning_rate": 9.141800000000001e-06,
         
     | 
| 309 | 
         
            +
                  "loss": 2.1331,
         
     | 
| 310 | 
         
            +
                  "step": 4300
         
     | 
| 311 | 
         
            +
                },
         
     | 
| 312 | 
         
            +
                {
         
     | 
| 313 | 
         
            +
                  "epoch": 67.6923076923077,
         
     | 
| 314 | 
         
            +
                  "grad_norm": 184.29612731933594,
         
     | 
| 315 | 
         
            +
                  "learning_rate": 9.121800000000001e-06,
         
     | 
| 316 | 
         
            +
                  "loss": 2.1866,
         
     | 
| 317 | 
         
            +
                  "step": 4400
         
     | 
| 318 | 
         
            +
                },
         
     | 
| 319 | 
         
            +
                {
         
     | 
| 320 | 
         
            +
                  "epoch": 69.23076923076923,
         
     | 
| 321 | 
         
            +
                  "grad_norm": 108.59600830078125,
         
     | 
| 322 | 
         
            +
                  "learning_rate": 9.1018e-06,
         
     | 
| 323 | 
         
            +
                  "loss": 2.1453,
         
     | 
| 324 | 
         
            +
                  "step": 4500
         
     | 
| 325 | 
         
            +
                },
         
     | 
| 326 | 
         
            +
                {
         
     | 
| 327 | 
         
            +
                  "epoch": 70.76923076923077,
         
     | 
| 328 | 
         
            +
                  "grad_norm": 80.51258087158203,
         
     | 
| 329 | 
         
            +
                  "learning_rate": 9.0818e-06,
         
     | 
| 330 | 
         
            +
                  "loss": 2.1125,
         
     | 
| 331 | 
         
            +
                  "step": 4600
         
     | 
| 332 | 
         
            +
                },
         
     | 
| 333 | 
         
            +
                {
         
     | 
| 334 | 
         
            +
                  "epoch": 72.3076923076923,
         
     | 
| 335 | 
         
            +
                  "grad_norm": 172.7328643798828,
         
     | 
| 336 | 
         
            +
                  "learning_rate": 9.0618e-06,
         
     | 
| 337 | 
         
            +
                  "loss": 2.141,
         
     | 
| 338 | 
         
            +
                  "step": 4700
         
     | 
| 339 | 
         
            +
                },
         
     | 
| 340 | 
         
            +
                {
         
     | 
| 341 | 
         
            +
                  "epoch": 73.84615384615384,
         
     | 
| 342 | 
         
            +
                  "grad_norm": 58.20785903930664,
         
     | 
| 343 | 
         
            +
                  "learning_rate": 9.0418e-06,
         
     | 
| 344 | 
         
            +
                  "loss": 2.0786,
         
     | 
| 345 | 
         
            +
                  "step": 4800
         
     | 
| 346 | 
         
            +
                },
         
     | 
| 347 | 
         
            +
                {
         
     | 
| 348 | 
         
            +
                  "epoch": 75.38461538461539,
         
     | 
| 349 | 
         
            +
                  "grad_norm": 72.46143341064453,
         
     | 
| 350 | 
         
            +
                  "learning_rate": 9.0218e-06,
         
     | 
| 351 | 
         
            +
                  "loss": 2.0914,
         
     | 
| 352 | 
         
            +
                  "step": 4900
         
     | 
| 353 | 
         
            +
                },
         
     | 
| 354 | 
         
            +
                {
         
     | 
| 355 | 
         
            +
                  "epoch": 76.92307692307692,
         
     | 
| 356 | 
         
            +
                  "grad_norm": 48.18838119506836,
         
     | 
| 357 | 
         
            +
                  "learning_rate": 9.0018e-06,
         
     | 
| 358 | 
         
            +
                  "loss": 2.0439,
         
     | 
| 359 | 
         
            +
                  "step": 5000
         
     | 
| 360 | 
         
            +
                },
         
     | 
| 361 | 
         
            +
                {
         
     | 
| 362 | 
         
            +
                  "epoch": 78.46153846153847,
         
     | 
| 363 | 
         
            +
                  "grad_norm": 87.95365905761719,
         
     | 
| 364 | 
         
            +
                  "learning_rate": 8.981800000000001e-06,
         
     | 
| 365 | 
         
            +
                  "loss": 2.0331,
         
     | 
| 366 | 
         
            +
                  "step": 5100
         
     | 
| 367 | 
         
            +
                },
         
     | 
| 368 | 
         
            +
                {
         
     | 
| 369 | 
         
            +
                  "epoch": 80.0,
         
     | 
| 370 | 
         
            +
                  "grad_norm": 99.82858276367188,
         
     | 
| 371 | 
         
            +
                  "learning_rate": 8.961800000000001e-06,
         
     | 
| 372 | 
         
            +
                  "loss": 2.1268,
         
     | 
| 373 | 
         
            +
                  "step": 5200
         
     | 
| 374 | 
         
            +
                },
         
     | 
| 375 | 
         
            +
                {
         
     | 
| 376 | 
         
            +
                  "epoch": 81.53846153846153,
         
     | 
| 377 | 
         
            +
                  "grad_norm": 85.33229064941406,
         
     | 
| 378 | 
         
            +
                  "learning_rate": 8.9418e-06,
         
     | 
| 379 | 
         
            +
                  "loss": 2.028,
         
     | 
| 380 | 
         
            +
                  "step": 5300
         
     | 
| 381 | 
         
            +
                },
         
     | 
| 382 | 
         
            +
                {
         
     | 
| 383 | 
         
            +
                  "epoch": 83.07692307692308,
         
     | 
| 384 | 
         
            +
                  "grad_norm": 83.01776885986328,
         
     | 
| 385 | 
         
            +
                  "learning_rate": 8.9218e-06,
         
     | 
| 386 | 
         
            +
                  "loss": 2.0179,
         
     | 
| 387 | 
         
            +
                  "step": 5400
         
     | 
| 388 | 
         
            +
                },
         
     | 
| 389 | 
         
            +
                {
         
     | 
| 390 | 
         
            +
                  "epoch": 84.61538461538461,
         
     | 
| 391 | 
         
            +
                  "grad_norm": 95.0901107788086,
         
     | 
| 392 | 
         
            +
                  "learning_rate": 8.9018e-06,
         
     | 
| 393 | 
         
            +
                  "loss": 2.0825,
         
     | 
| 394 | 
         
            +
                  "step": 5500
         
     | 
| 395 | 
         
            +
                },
         
     | 
| 396 | 
         
            +
                {
         
     | 
| 397 | 
         
            +
                  "epoch": 86.15384615384616,
         
     | 
| 398 | 
         
            +
                  "grad_norm": 85.66802978515625,
         
     | 
| 399 | 
         
            +
                  "learning_rate": 8.8818e-06,
         
     | 
| 400 | 
         
            +
                  "loss": 2.0588,
         
     | 
| 401 | 
         
            +
                  "step": 5600
         
     | 
| 402 | 
         
            +
                },
         
     | 
| 403 | 
         
            +
                {
         
     | 
| 404 | 
         
            +
                  "epoch": 87.6923076923077,
         
     | 
| 405 | 
         
            +
                  "grad_norm": 69.63407897949219,
         
     | 
| 406 | 
         
            +
                  "learning_rate": 8.8618e-06,
         
     | 
| 407 | 
         
            +
                  "loss": 2.0298,
         
     | 
| 408 | 
         
            +
                  "step": 5700
         
     | 
| 409 | 
         
            +
                },
         
     | 
| 410 | 
         
            +
                {
         
     | 
| 411 | 
         
            +
                  "epoch": 89.23076923076923,
         
     | 
| 412 | 
         
            +
                  "grad_norm": 174.88063049316406,
         
     | 
| 413 | 
         
            +
                  "learning_rate": 8.8418e-06,
         
     | 
| 414 | 
         
            +
                  "loss": 1.9867,
         
     | 
| 415 | 
         
            +
                  "step": 5800
         
     | 
| 416 | 
         
            +
                },
         
     | 
| 417 | 
         
            +
                {
         
     | 
| 418 | 
         
            +
                  "epoch": 90.76923076923077,
         
     | 
| 419 | 
         
            +
                  "grad_norm": 65.64617156982422,
         
     | 
| 420 | 
         
            +
                  "learning_rate": 8.8218e-06,
         
     | 
| 421 | 
         
            +
                  "loss": 2.0674,
         
     | 
| 422 | 
         
            +
                  "step": 5900
         
     | 
| 423 | 
         
            +
                },
         
     | 
| 424 | 
         
            +
                {
         
     | 
| 425 | 
         
            +
                  "epoch": 92.3076923076923,
         
     | 
| 426 | 
         
            +
                  "grad_norm": 152.2218780517578,
         
     | 
| 427 | 
         
            +
                  "learning_rate": 8.802e-06,
         
     | 
| 428 | 
         
            +
                  "loss": 1.992,
         
     | 
| 429 | 
         
            +
                  "step": 6000
         
     | 
| 430 | 
         
            +
                },
         
     | 
| 431 | 
         
            +
                {
         
     | 
| 432 | 
         
            +
                  "epoch": 93.84615384615384,
         
     | 
| 433 | 
         
            +
                  "grad_norm": 74.4027328491211,
         
     | 
| 434 | 
         
            +
                  "learning_rate": 8.782e-06,
         
     | 
| 435 | 
         
            +
                  "loss": 2.0016,
         
     | 
| 436 | 
         
            +
                  "step": 6100
         
     | 
| 437 | 
         
            +
                },
         
     | 
| 438 | 
         
            +
                {
         
     | 
| 439 | 
         
            +
                  "epoch": 95.38461538461539,
         
     | 
| 440 | 
         
            +
                  "grad_norm": 67.4207992553711,
         
     | 
| 441 | 
         
            +
                  "learning_rate": 8.762e-06,
         
     | 
| 442 | 
         
            +
                  "loss": 2.0001,
         
     | 
| 443 | 
         
            +
                  "step": 6200
         
     | 
| 444 | 
         
            +
                },
         
     | 
| 445 | 
         
            +
                {
         
     | 
| 446 | 
         
            +
                  "epoch": 96.92307692307692,
         
     | 
| 447 | 
         
            +
                  "grad_norm": 182.99061584472656,
         
     | 
| 448 | 
         
            +
                  "learning_rate": 8.742e-06,
         
     | 
| 449 | 
         
            +
                  "loss": 1.9897,
         
     | 
| 450 | 
         
            +
                  "step": 6300
         
     | 
| 451 | 
         
            +
                },
         
     | 
| 452 | 
         
            +
                {
         
     | 
| 453 | 
         
            +
                  "epoch": 98.46153846153847,
         
     | 
| 454 | 
         
            +
                  "grad_norm": 70.14286804199219,
         
     | 
| 455 | 
         
            +
                  "learning_rate": 8.722e-06,
         
     | 
| 456 | 
         
            +
                  "loss": 2.0146,
         
     | 
| 457 | 
         
            +
                  "step": 6400
         
     | 
| 458 | 
         
            +
                },
         
     | 
| 459 | 
         
            +
                {
         
     | 
| 460 | 
         
            +
                  "epoch": 100.0,
         
     | 
| 461 | 
         
            +
                  "grad_norm": 117.57647705078125,
         
     | 
| 462 | 
         
            +
                  "learning_rate": 8.702e-06,
         
     | 
| 463 | 
         
            +
                  "loss": 1.9298,
         
     | 
| 464 | 
         
            +
                  "step": 6500
         
     | 
| 465 | 
         
            +
                },
         
     | 
| 466 | 
         
            +
                {
         
     | 
| 467 | 
         
            +
                  "epoch": 101.53846153846153,
         
     | 
| 468 | 
         
            +
                  "grad_norm": 80.27694702148438,
         
     | 
| 469 | 
         
            +
                  "learning_rate": 8.682000000000001e-06,
         
     | 
| 470 | 
         
            +
                  "loss": 1.9364,
         
     | 
| 471 | 
         
            +
                  "step": 6600
         
     | 
| 472 | 
         
            +
                },
         
     | 
| 473 | 
         
            +
                {
         
     | 
| 474 | 
         
            +
                  "epoch": 103.07692307692308,
         
     | 
| 475 | 
         
            +
                  "grad_norm": 219.95655822753906,
         
     | 
| 476 | 
         
            +
                  "learning_rate": 8.662000000000001e-06,
         
     | 
| 477 | 
         
            +
                  "loss": 1.9289,
         
     | 
| 478 | 
         
            +
                  "step": 6700
         
     | 
| 479 | 
         
            +
                },
         
     | 
| 480 | 
         
            +
                {
         
     | 
| 481 | 
         
            +
                  "epoch": 104.61538461538461,
         
     | 
| 482 | 
         
            +
                  "grad_norm": 176.79177856445312,
         
     | 
| 483 | 
         
            +
                  "learning_rate": 8.642e-06,
         
     | 
| 484 | 
         
            +
                  "loss": 1.9142,
         
     | 
| 485 | 
         
            +
                  "step": 6800
         
     | 
| 486 | 
         
            +
                },
         
     | 
| 487 | 
         
            +
                {
         
     | 
| 488 | 
         
            +
                  "epoch": 106.15384615384616,
         
     | 
| 489 | 
         
            +
                  "grad_norm": 60.430049896240234,
         
     | 
| 490 | 
         
            +
                  "learning_rate": 8.622e-06,
         
     | 
| 491 | 
         
            +
                  "loss": 1.8986,
         
     | 
| 492 | 
         
            +
                  "step": 6900
         
     | 
| 493 | 
         
            +
                },
         
     | 
| 494 | 
         
            +
                {
         
     | 
| 495 | 
         
            +
                  "epoch": 107.6923076923077,
         
     | 
| 496 | 
         
            +
                  "grad_norm": 53.74516296386719,
         
     | 
| 497 | 
         
            +
                  "learning_rate": 8.602e-06,
         
     | 
| 498 | 
         
            +
                  "loss": 1.9029,
         
     | 
| 499 | 
         
            +
                  "step": 7000
         
     | 
| 500 | 
         
            +
                },
         
     | 
| 501 | 
         
            +
                {
         
     | 
| 502 | 
         
            +
                  "epoch": 109.23076923076923,
         
     | 
| 503 | 
         
            +
                  "grad_norm": 70.89128112792969,
         
     | 
| 504 | 
         
            +
                  "learning_rate": 8.582e-06,
         
     | 
| 505 | 
         
            +
                  "loss": 1.9313,
         
     | 
| 506 | 
         
            +
                  "step": 7100
         
     | 
| 507 | 
         
            +
                },
         
     | 
| 508 | 
         
            +
                {
         
     | 
| 509 | 
         
            +
                  "epoch": 110.76923076923077,
         
     | 
| 510 | 
         
            +
                  "grad_norm": 137.73828125,
         
     | 
| 511 | 
         
            +
                  "learning_rate": 8.562e-06,
         
     | 
| 512 | 
         
            +
                  "loss": 1.9328,
         
     | 
| 513 | 
         
            +
                  "step": 7200
         
     | 
| 514 | 
         
            +
                },
         
     | 
| 515 | 
         
            +
                {
         
     | 
| 516 | 
         
            +
                  "epoch": 112.3076923076923,
         
     | 
| 517 | 
         
            +
                  "grad_norm": 86.80708312988281,
         
     | 
| 518 | 
         
            +
                  "learning_rate": 8.542e-06,
         
     | 
| 519 | 
         
            +
                  "loss": 1.8831,
         
     | 
| 520 | 
         
            +
                  "step": 7300
         
     | 
| 521 | 
         
            +
                },
         
     | 
| 522 | 
         
            +
                {
         
     | 
| 523 | 
         
            +
                  "epoch": 113.84615384615384,
         
     | 
| 524 | 
         
            +
                  "grad_norm": 52.322608947753906,
         
     | 
| 525 | 
         
            +
                  "learning_rate": 8.522200000000001e-06,
         
     | 
| 526 | 
         
            +
                  "loss": 1.8679,
         
     | 
| 527 | 
         
            +
                  "step": 7400
         
     | 
| 528 | 
         
            +
                },
         
     | 
| 529 | 
         
            +
                {
         
     | 
| 530 | 
         
            +
                  "epoch": 115.38461538461539,
         
     | 
| 531 | 
         
            +
                  "grad_norm": 215.9288787841797,
         
     | 
| 532 | 
         
            +
                  "learning_rate": 8.5022e-06,
         
     | 
| 533 | 
         
            +
                  "loss": 1.8743,
         
     | 
| 534 | 
         
            +
                  "step": 7500
         
     | 
| 535 | 
         
            +
                },
         
     | 
| 536 | 
         
            +
                {
         
     | 
| 537 | 
         
            +
                  "epoch": 116.92307692307692,
         
     | 
| 538 | 
         
            +
                  "grad_norm": 74.13555908203125,
         
     | 
| 539 | 
         
            +
                  "learning_rate": 8.4822e-06,
         
     | 
| 540 | 
         
            +
                  "loss": 1.8575,
         
     | 
| 541 | 
         
            +
                  "step": 7600
         
     | 
| 542 | 
         
            +
                },
         
     | 
| 543 | 
         
            +
                {
         
     | 
| 544 | 
         
            +
                  "epoch": 118.46153846153847,
         
     | 
| 545 | 
         
            +
                  "grad_norm": 138.6452178955078,
         
     | 
| 546 | 
         
            +
                  "learning_rate": 8.4622e-06,
         
     | 
| 547 | 
         
            +
                  "loss": 1.8942,
         
     | 
| 548 | 
         
            +
                  "step": 7700
         
     | 
| 549 | 
         
            +
                },
         
     | 
| 550 | 
         
            +
                {
         
     | 
| 551 | 
         
            +
                  "epoch": 120.0,
         
     | 
| 552 | 
         
            +
                  "grad_norm": 57.42049789428711,
         
     | 
| 553 | 
         
            +
                  "learning_rate": 8.4422e-06,
         
     | 
| 554 | 
         
            +
                  "loss": 1.8777,
         
     | 
| 555 | 
         
            +
                  "step": 7800
         
     | 
| 556 | 
         
            +
                },
         
     | 
| 557 | 
         
            +
                {
         
     | 
| 558 | 
         
            +
                  "epoch": 121.53846153846153,
         
     | 
| 559 | 
         
            +
                  "grad_norm": 41.08803939819336,
         
     | 
| 560 | 
         
            +
                  "learning_rate": 8.4222e-06,
         
     | 
| 561 | 
         
            +
                  "loss": 1.8409,
         
     | 
| 562 | 
         
            +
                  "step": 7900
         
     | 
| 563 | 
         
            +
                },
         
     | 
| 564 | 
         
            +
                {
         
     | 
| 565 | 
         
            +
                  "epoch": 123.07692307692308,
         
     | 
| 566 | 
         
            +
                  "grad_norm": 66.80331420898438,
         
     | 
| 567 | 
         
            +
                  "learning_rate": 8.4022e-06,
         
     | 
| 568 | 
         
            +
                  "loss": 1.8325,
         
     | 
| 569 | 
         
            +
                  "step": 8000
         
     | 
| 570 | 
         
            +
                },
         
     | 
| 571 | 
         
            +
                {
         
     | 
| 572 | 
         
            +
                  "epoch": 124.61538461538461,
         
     | 
| 573 | 
         
            +
                  "grad_norm": 69.8762435913086,
         
     | 
| 574 | 
         
            +
                  "learning_rate": 8.3822e-06,
         
     | 
| 575 | 
         
            +
                  "loss": 1.8685,
         
     | 
| 576 | 
         
            +
                  "step": 8100
         
     | 
| 577 | 
         
            +
                },
         
     | 
| 578 | 
         
            +
                {
         
     | 
| 579 | 
         
            +
                  "epoch": 126.15384615384616,
         
     | 
| 580 | 
         
            +
                  "grad_norm": 109.0595703125,
         
     | 
| 581 | 
         
            +
                  "learning_rate": 8.362200000000001e-06,
         
     | 
| 582 | 
         
            +
                  "loss": 1.8423,
         
     | 
| 583 | 
         
            +
                  "step": 8200
         
     | 
| 584 | 
         
            +
                },
         
     | 
| 585 | 
         
            +
                {
         
     | 
| 586 | 
         
            +
                  "epoch": 127.6923076923077,
         
     | 
| 587 | 
         
            +
                  "grad_norm": 75.782470703125,
         
     | 
| 588 | 
         
            +
                  "learning_rate": 8.3422e-06,
         
     | 
| 589 | 
         
            +
                  "loss": 1.8278,
         
     | 
| 590 | 
         
            +
                  "step": 8300
         
     | 
| 591 | 
         
            +
                },
         
     | 
| 592 | 
         
            +
                {
         
     | 
| 593 | 
         
            +
                  "epoch": 129.23076923076923,
         
     | 
| 594 | 
         
            +
                  "grad_norm": 495.26025390625,
         
     | 
| 595 | 
         
            +
                  "learning_rate": 8.3222e-06,
         
     | 
| 596 | 
         
            +
                  "loss": 1.823,
         
     | 
| 597 | 
         
            +
                  "step": 8400
         
     | 
| 598 | 
         
            +
                },
         
     | 
| 599 | 
         
            +
                {
         
     | 
| 600 | 
         
            +
                  "epoch": 130.76923076923077,
         
     | 
| 601 | 
         
            +
                  "grad_norm": 132.37982177734375,
         
     | 
| 602 | 
         
            +
                  "learning_rate": 8.3022e-06,
         
     | 
| 603 | 
         
            +
                  "loss": 1.8122,
         
     | 
| 604 | 
         
            +
                  "step": 8500
         
     | 
| 605 | 
         
            +
                },
         
     | 
| 606 | 
         
            +
                {
         
     | 
| 607 | 
         
            +
                  "epoch": 132.30769230769232,
         
     | 
| 608 | 
         
            +
                  "grad_norm": 110.41214752197266,
         
     | 
| 609 | 
         
            +
                  "learning_rate": 8.2822e-06,
         
     | 
| 610 | 
         
            +
                  "loss": 1.798,
         
     | 
| 611 | 
         
            +
                  "step": 8600
         
     | 
| 612 | 
         
            +
                },
         
     | 
| 613 | 
         
            +
                {
         
     | 
| 614 | 
         
            +
                  "epoch": 133.84615384615384,
         
     | 
| 615 | 
         
            +
                  "grad_norm": 155.9139404296875,
         
     | 
| 616 | 
         
            +
                  "learning_rate": 8.2622e-06,
         
     | 
| 617 | 
         
            +
                  "loss": 1.8158,
         
     | 
| 618 | 
         
            +
                  "step": 8700
         
     | 
| 619 | 
         
            +
                },
         
     | 
| 620 | 
         
            +
                {
         
     | 
| 621 | 
         
            +
                  "epoch": 135.3846153846154,
         
     | 
| 622 | 
         
            +
                  "grad_norm": 61.789390563964844,
         
     | 
| 623 | 
         
            +
                  "learning_rate": 8.2422e-06,
         
     | 
| 624 | 
         
            +
                  "loss": 1.7863,
         
     | 
| 625 | 
         
            +
                  "step": 8800
         
     | 
| 626 | 
         
            +
                },
         
     | 
| 627 | 
         
            +
                {
         
     | 
| 628 | 
         
            +
                  "epoch": 136.92307692307693,
         
     | 
| 629 | 
         
            +
                  "grad_norm": 86.55162048339844,
         
     | 
| 630 | 
         
            +
                  "learning_rate": 8.2222e-06,
         
     | 
| 631 | 
         
            +
                  "loss": 1.7971,
         
     | 
| 632 | 
         
            +
                  "step": 8900
         
     | 
| 633 | 
         
            +
                },
         
     | 
| 634 | 
         
            +
                {
         
     | 
| 635 | 
         
            +
                  "epoch": 138.46153846153845,
         
     | 
| 636 | 
         
            +
                  "grad_norm": 52.087581634521484,
         
     | 
| 637 | 
         
            +
                  "learning_rate": 8.202200000000001e-06,
         
     | 
| 638 | 
         
            +
                  "loss": 1.7676,
         
     | 
| 639 | 
         
            +
                  "step": 9000
         
     | 
| 640 | 
         
            +
                },
         
     | 
| 641 | 
         
            +
                {
         
     | 
| 642 | 
         
            +
                  "epoch": 140.0,
         
     | 
| 643 | 
         
            +
                  "grad_norm": 78.67654418945312,
         
     | 
| 644 | 
         
            +
                  "learning_rate": 8.1822e-06,
         
     | 
| 645 | 
         
            +
                  "loss": 1.8188,
         
     | 
| 646 | 
         
            +
                  "step": 9100
         
     | 
| 647 | 
         
            +
                },
         
     | 
| 648 | 
         
            +
                {
         
     | 
| 649 | 
         
            +
                  "epoch": 141.53846153846155,
         
     | 
| 650 | 
         
            +
                  "grad_norm": 102.5003890991211,
         
     | 
| 651 | 
         
            +
                  "learning_rate": 8.1622e-06,
         
     | 
| 652 | 
         
            +
                  "loss": 1.8154,
         
     | 
| 653 | 
         
            +
                  "step": 9200
         
     | 
| 654 | 
         
            +
                },
         
     | 
| 655 | 
         
            +
                {
         
     | 
| 656 | 
         
            +
                  "epoch": 143.07692307692307,
         
     | 
| 657 | 
         
            +
                  "grad_norm": 112.49629974365234,
         
     | 
| 658 | 
         
            +
                  "learning_rate": 8.142200000000001e-06,
         
     | 
| 659 | 
         
            +
                  "loss": 1.7687,
         
     | 
| 660 | 
         
            +
                  "step": 9300
         
     | 
| 661 | 
         
            +
                },
         
     | 
| 662 | 
         
            +
                {
         
     | 
| 663 | 
         
            +
                  "epoch": 144.6153846153846,
         
     | 
| 664 | 
         
            +
                  "grad_norm": 64.63585662841797,
         
     | 
| 665 | 
         
            +
                  "learning_rate": 8.122200000000002e-06,
         
     | 
| 666 | 
         
            +
                  "loss": 1.7824,
         
     | 
| 667 | 
         
            +
                  "step": 9400
         
     | 
| 668 | 
         
            +
                },
         
     | 
| 669 | 
         
            +
                {
         
     | 
| 670 | 
         
            +
                  "epoch": 146.15384615384616,
         
     | 
| 671 | 
         
            +
                  "grad_norm": 74.50164794921875,
         
     | 
| 672 | 
         
            +
                  "learning_rate": 8.102200000000002e-06,
         
     | 
| 673 | 
         
            +
                  "loss": 1.745,
         
     | 
| 674 | 
         
            +
                  "step": 9500
         
     | 
| 675 | 
         
            +
                },
         
     | 
| 676 | 
         
            +
                {
         
     | 
| 677 | 
         
            +
                  "epoch": 147.69230769230768,
         
     | 
| 678 | 
         
            +
                  "grad_norm": 70.59980010986328,
         
     | 
| 679 | 
         
            +
                  "learning_rate": 8.082200000000002e-06,
         
     | 
| 680 | 
         
            +
                  "loss": 1.8179,
         
     | 
| 681 | 
         
            +
                  "step": 9600
         
     | 
| 682 | 
         
            +
                },
         
     | 
| 683 | 
         
            +
                {
         
     | 
| 684 | 
         
            +
                  "epoch": 149.23076923076923,
         
     | 
| 685 | 
         
            +
                  "grad_norm": 275.9650573730469,
         
     | 
| 686 | 
         
            +
                  "learning_rate": 8.0622e-06,
         
     | 
| 687 | 
         
            +
                  "loss": 1.7744,
         
     | 
| 688 | 
         
            +
                  "step": 9700
         
     | 
| 689 | 
         
            +
                },
         
     | 
| 690 | 
         
            +
                {
         
     | 
| 691 | 
         
            +
                  "epoch": 150.76923076923077,
         
     | 
| 692 | 
         
            +
                  "grad_norm": 54.21783447265625,
         
     | 
| 693 | 
         
            +
                  "learning_rate": 8.0422e-06,
         
     | 
| 694 | 
         
            +
                  "loss": 1.7608,
         
     | 
| 695 | 
         
            +
                  "step": 9800
         
     | 
| 696 | 
         
            +
                },
         
     | 
| 697 | 
         
            +
                {
         
     | 
| 698 | 
         
            +
                  "epoch": 152.30769230769232,
         
     | 
| 699 | 
         
            +
                  "grad_norm": 58.89350128173828,
         
     | 
| 700 | 
         
            +
                  "learning_rate": 8.0224e-06,
         
     | 
| 701 | 
         
            +
                  "loss": 1.7835,
         
     | 
| 702 | 
         
            +
                  "step": 9900
         
     | 
| 703 | 
         
            +
                },
         
     | 
| 704 | 
         
            +
                {
         
     | 
| 705 | 
         
            +
                  "epoch": 153.84615384615384,
         
     | 
| 706 | 
         
            +
                  "grad_norm": 90.88015747070312,
         
     | 
| 707 | 
         
            +
                  "learning_rate": 8.0024e-06,
         
     | 
| 708 | 
         
            +
                  "loss": 1.7567,
         
     | 
| 709 | 
         
            +
                  "step": 10000
         
     | 
| 710 | 
         
            +
                },
         
     | 
| 711 | 
         
            +
                {
         
     | 
| 712 | 
         
            +
                  "epoch": 155.3846153846154,
         
     | 
| 713 | 
         
            +
                  "grad_norm": 45.44640350341797,
         
     | 
| 714 | 
         
            +
                  "learning_rate": 7.9824e-06,
         
     | 
| 715 | 
         
            +
                  "loss": 1.7399,
         
     | 
| 716 | 
         
            +
                  "step": 10100
         
     | 
| 717 | 
         
            +
                },
         
     | 
| 718 | 
         
            +
                {
         
     | 
| 719 | 
         
            +
                  "epoch": 156.92307692307693,
         
     | 
| 720 | 
         
            +
                  "grad_norm": 58.44306945800781,
         
     | 
| 721 | 
         
            +
                  "learning_rate": 7.9624e-06,
         
     | 
| 722 | 
         
            +
                  "loss": 1.7803,
         
     | 
| 723 | 
         
            +
                  "step": 10200
         
     | 
| 724 | 
         
            +
                },
         
     | 
| 725 | 
         
            +
                {
         
     | 
| 726 | 
         
            +
                  "epoch": 158.46153846153845,
         
     | 
| 727 | 
         
            +
                  "grad_norm": 80.27843475341797,
         
     | 
| 728 | 
         
            +
                  "learning_rate": 7.9424e-06,
         
     | 
| 729 | 
         
            +
                  "loss": 1.7106,
         
     | 
| 730 | 
         
            +
                  "step": 10300
         
     | 
| 731 | 
         
            +
                },
         
     | 
| 732 | 
         
            +
                {
         
     | 
| 733 | 
         
            +
                  "epoch": 160.0,
         
     | 
| 734 | 
         
            +
                  "grad_norm": 111.12615203857422,
         
     | 
| 735 | 
         
            +
                  "learning_rate": 7.9224e-06,
         
     | 
| 736 | 
         
            +
                  "loss": 1.7134,
         
     | 
| 737 | 
         
            +
                  "step": 10400
         
     | 
| 738 | 
         
            +
                },
         
     | 
| 739 | 
         
            +
                {
         
     | 
| 740 | 
         
            +
                  "epoch": 161.53846153846155,
         
     | 
| 741 | 
         
            +
                  "grad_norm": 63.302520751953125,
         
     | 
| 742 | 
         
            +
                  "learning_rate": 7.9024e-06,
         
     | 
| 743 | 
         
            +
                  "loss": 1.7031,
         
     | 
| 744 | 
         
            +
                  "step": 10500
         
     | 
| 745 | 
         
            +
                },
         
     | 
| 746 | 
         
            +
                {
         
     | 
| 747 | 
         
            +
                  "epoch": 163.07692307692307,
         
     | 
| 748 | 
         
            +
                  "grad_norm": 41.779808044433594,
         
     | 
| 749 | 
         
            +
                  "learning_rate": 7.882400000000001e-06,
         
     | 
| 750 | 
         
            +
                  "loss": 1.7071,
         
     | 
| 751 | 
         
            +
                  "step": 10600
         
     | 
| 752 | 
         
            +
                },
         
     | 
| 753 | 
         
            +
                {
         
     | 
| 754 | 
         
            +
                  "epoch": 164.6153846153846,
         
     | 
| 755 | 
         
            +
                  "grad_norm": 58.44318389892578,
         
     | 
| 756 | 
         
            +
                  "learning_rate": 7.862400000000001e-06,
         
     | 
| 757 | 
         
            +
                  "loss": 1.6759,
         
     | 
| 758 | 
         
            +
                  "step": 10700
         
     | 
| 759 | 
         
            +
                },
         
     | 
| 760 | 
         
            +
                {
         
     | 
| 761 | 
         
            +
                  "epoch": 166.15384615384616,
         
     | 
| 762 | 
         
            +
                  "grad_norm": 36.30861282348633,
         
     | 
| 763 | 
         
            +
                  "learning_rate": 7.842400000000001e-06,
         
     | 
| 764 | 
         
            +
                  "loss": 1.7012,
         
     | 
| 765 | 
         
            +
                  "step": 10800
         
     | 
| 766 | 
         
            +
                },
         
     | 
| 767 | 
         
            +
                {
         
     | 
| 768 | 
         
            +
                  "epoch": 167.69230769230768,
         
     | 
| 769 | 
         
            +
                  "grad_norm": 68.7526626586914,
         
     | 
| 770 | 
         
            +
                  "learning_rate": 7.822400000000002e-06,
         
     | 
| 771 | 
         
            +
                  "loss": 1.6963,
         
     | 
| 772 | 
         
            +
                  "step": 10900
         
     | 
| 773 | 
         
            +
                },
         
     | 
| 774 | 
         
            +
                {
         
     | 
| 775 | 
         
            +
                  "epoch": 169.23076923076923,
         
     | 
| 776 | 
         
            +
                  "grad_norm": 82.03331756591797,
         
     | 
| 777 | 
         
            +
                  "learning_rate": 7.802400000000002e-06,
         
     | 
| 778 | 
         
            +
                  "loss": 1.7456,
         
     | 
| 779 | 
         
            +
                  "step": 11000
         
     | 
| 780 | 
         
            +
                },
         
     | 
| 781 | 
         
            +
                {
         
     | 
| 782 | 
         
            +
                  "epoch": 170.76923076923077,
         
     | 
| 783 | 
         
            +
                  "grad_norm": 53.351959228515625,
         
     | 
| 784 | 
         
            +
                  "learning_rate": 7.7824e-06,
         
     | 
| 785 | 
         
            +
                  "loss": 1.7284,
         
     | 
| 786 | 
         
            +
                  "step": 11100
         
     | 
| 787 | 
         
            +
                },
         
     | 
| 788 | 
         
            +
                {
         
     | 
| 789 | 
         
            +
                  "epoch": 172.30769230769232,
         
     | 
| 790 | 
         
            +
                  "grad_norm": 58.400909423828125,
         
     | 
| 791 | 
         
            +
                  "learning_rate": 7.7624e-06,
         
     | 
| 792 | 
         
            +
                  "loss": 1.7266,
         
     | 
| 793 | 
         
            +
                  "step": 11200
         
     | 
| 794 | 
         
            +
                },
         
     | 
| 795 | 
         
            +
                {
         
     | 
| 796 | 
         
            +
                  "epoch": 173.84615384615384,
         
     | 
| 797 | 
         
            +
                  "grad_norm": 47.95368576049805,
         
     | 
| 798 | 
         
            +
                  "learning_rate": 7.7424e-06,
         
     | 
| 799 | 
         
            +
                  "loss": 1.6671,
         
     | 
| 800 | 
         
            +
                  "step": 11300
         
     | 
| 801 | 
         
            +
                },
         
     | 
| 802 | 
         
            +
                {
         
     | 
| 803 | 
         
            +
                  "epoch": 175.3846153846154,
         
     | 
| 804 | 
         
            +
                  "grad_norm": 54.79304885864258,
         
     | 
| 805 | 
         
            +
                  "learning_rate": 7.7224e-06,
         
     | 
| 806 | 
         
            +
                  "loss": 1.7092,
         
     | 
| 807 | 
         
            +
                  "step": 11400
         
     | 
| 808 | 
         
            +
                },
         
     | 
| 809 | 
         
            +
                {
         
     | 
| 810 | 
         
            +
                  "epoch": 176.92307692307693,
         
     | 
| 811 | 
         
            +
                  "grad_norm": 34.120758056640625,
         
     | 
| 812 | 
         
            +
                  "learning_rate": 7.702400000000001e-06,
         
     | 
| 813 | 
         
            +
                  "loss": 1.724,
         
     | 
| 814 | 
         
            +
                  "step": 11500
         
     | 
| 815 | 
         
            +
                },
         
     | 
| 816 | 
         
            +
                {
         
     | 
| 817 | 
         
            +
                  "epoch": 178.46153846153845,
         
     | 
| 818 | 
         
            +
                  "grad_norm": 80.98869323730469,
         
     | 
| 819 | 
         
            +
                  "learning_rate": 7.682400000000001e-06,
         
     | 
| 820 | 
         
            +
                  "loss": 1.6693,
         
     | 
| 821 | 
         
            +
                  "step": 11600
         
     | 
| 822 | 
         
            +
                },
         
     | 
| 823 | 
         
            +
                {
         
     | 
| 824 | 
         
            +
                  "epoch": 180.0,
         
     | 
| 825 | 
         
            +
                  "grad_norm": 65.80884552001953,
         
     | 
| 826 | 
         
            +
                  "learning_rate": 7.662400000000001e-06,
         
     | 
| 827 | 
         
            +
                  "loss": 1.6864,
         
     | 
| 828 | 
         
            +
                  "step": 11700
         
     | 
| 829 | 
         
            +
                },
         
     | 
| 830 | 
         
            +
                {
         
     | 
| 831 | 
         
            +
                  "epoch": 181.53846153846155,
         
     | 
| 832 | 
         
            +
                  "grad_norm": 86.81282806396484,
         
     | 
| 833 | 
         
            +
                  "learning_rate": 7.642400000000002e-06,
         
     | 
| 834 | 
         
            +
                  "loss": 1.6715,
         
     | 
| 835 | 
         
            +
                  "step": 11800
         
     | 
| 836 | 
         
            +
                },
         
     | 
| 837 | 
         
            +
                {
         
     | 
| 838 | 
         
            +
                  "epoch": 183.07692307692307,
         
     | 
| 839 | 
         
            +
                  "grad_norm": 63.2209358215332,
         
     | 
| 840 | 
         
            +
                  "learning_rate": 7.622400000000001e-06,
         
     | 
| 841 | 
         
            +
                  "loss": 1.6884,
         
     | 
| 842 | 
         
            +
                  "step": 11900
         
     | 
| 843 | 
         
            +
                },
         
     | 
| 844 | 
         
            +
                {
         
     | 
| 845 | 
         
            +
                  "epoch": 184.6153846153846,
         
     | 
| 846 | 
         
            +
                  "grad_norm": 80.72114562988281,
         
     | 
| 847 | 
         
            +
                  "learning_rate": 7.602400000000001e-06,
         
     | 
| 848 | 
         
            +
                  "loss": 1.6781,
         
     | 
| 849 | 
         
            +
                  "step": 12000
         
     | 
| 850 | 
         
            +
                },
         
     | 
| 851 | 
         
            +
                {
         
     | 
| 852 | 
         
            +
                  "epoch": 186.15384615384616,
         
     | 
| 853 | 
         
            +
                  "grad_norm": 65.09835815429688,
         
     | 
| 854 | 
         
            +
                  "learning_rate": 7.5824000000000005e-06,
         
     | 
| 855 | 
         
            +
                  "loss": 1.6451,
         
     | 
| 856 | 
         
            +
                  "step": 12100
         
     | 
| 857 | 
         
            +
                },
         
     | 
| 858 | 
         
            +
                {
         
     | 
| 859 | 
         
            +
                  "epoch": 187.69230769230768,
         
     | 
| 860 | 
         
            +
                  "grad_norm": 51.8597297668457,
         
     | 
| 861 | 
         
            +
                  "learning_rate": 7.562400000000001e-06,
         
     | 
| 862 | 
         
            +
                  "loss": 1.6425,
         
     | 
| 863 | 
         
            +
                  "step": 12200
         
     | 
| 864 | 
         
            +
                },
         
     | 
| 865 | 
         
            +
                {
         
     | 
| 866 | 
         
            +
                  "epoch": 189.23076923076923,
         
     | 
| 867 | 
         
            +
                  "grad_norm": 55.06999969482422,
         
     | 
| 868 | 
         
            +
                  "learning_rate": 7.542400000000001e-06,
         
     | 
| 869 | 
         
            +
                  "loss": 1.6475,
         
     | 
| 870 | 
         
            +
                  "step": 12300
         
     | 
| 871 | 
         
            +
                },
         
     | 
| 872 | 
         
            +
                {
         
     | 
| 873 | 
         
            +
                  "epoch": 190.76923076923077,
         
     | 
| 874 | 
         
            +
                  "grad_norm": 221.47671508789062,
         
     | 
| 875 | 
         
            +
                  "learning_rate": 7.522400000000001e-06,
         
     | 
| 876 | 
         
            +
                  "loss": 1.6459,
         
     | 
| 877 | 
         
            +
                  "step": 12400
         
     | 
| 878 | 
         
            +
                },
         
     | 
| 879 | 
         
            +
                {
         
     | 
| 880 | 
         
            +
                  "epoch": 192.30769230769232,
         
     | 
| 881 | 
         
            +
                  "grad_norm": 64.53801727294922,
         
     | 
| 882 | 
         
            +
                  "learning_rate": 7.5024e-06,
         
     | 
| 883 | 
         
            +
                  "loss": 1.6149,
         
     | 
| 884 | 
         
            +
                  "step": 12500
         
     | 
| 885 | 
         
            +
                },
         
     | 
| 886 | 
         
            +
                {
         
     | 
| 887 | 
         
            +
                  "epoch": 193.84615384615384,
         
     | 
| 888 | 
         
            +
                  "grad_norm": 96.24422454833984,
         
     | 
| 889 | 
         
            +
                  "learning_rate": 7.4824000000000006e-06,
         
     | 
| 890 | 
         
            +
                  "loss": 1.6204,
         
     | 
| 891 | 
         
            +
                  "step": 12600
         
     | 
| 892 | 
         
            +
                },
         
     | 
| 893 | 
         
            +
                {
         
     | 
| 894 | 
         
            +
                  "epoch": 195.3846153846154,
         
     | 
| 895 | 
         
            +
                  "grad_norm": 44.547306060791016,
         
     | 
| 896 | 
         
            +
                  "learning_rate": 7.462400000000001e-06,
         
     | 
| 897 | 
         
            +
                  "loss": 1.6151,
         
     | 
| 898 | 
         
            +
                  "step": 12700
         
     | 
| 899 | 
         
            +
                },
         
     | 
| 900 | 
         
            +
                {
         
     | 
| 901 | 
         
            +
                  "epoch": 196.92307692307693,
         
     | 
| 902 | 
         
            +
                  "grad_norm": 125.61988830566406,
         
     | 
| 903 | 
         
            +
                  "learning_rate": 7.442400000000001e-06,
         
     | 
| 904 | 
         
            +
                  "loss": 1.6244,
         
     | 
| 905 | 
         
            +
                  "step": 12800
         
     | 
| 906 | 
         
            +
                },
         
     | 
| 907 | 
         
            +
                {
         
     | 
| 908 | 
         
            +
                  "epoch": 198.46153846153845,
         
     | 
| 909 | 
         
            +
                  "grad_norm": 98.02783966064453,
         
     | 
| 910 | 
         
            +
                  "learning_rate": 7.422400000000001e-06,
         
     | 
| 911 | 
         
            +
                  "loss": 1.625,
         
     | 
| 912 | 
         
            +
                  "step": 12900
         
     | 
| 913 | 
         
            +
                },
         
     | 
| 914 | 
         
            +
                {
         
     | 
| 915 | 
         
            +
                  "epoch": 200.0,
         
     | 
| 916 | 
         
            +
                  "grad_norm": 72.0836181640625,
         
     | 
| 917 | 
         
            +
                  "learning_rate": 7.4024000000000005e-06,
         
     | 
| 918 | 
         
            +
                  "loss": 1.6201,
         
     | 
| 919 | 
         
            +
                  "step": 13000
         
     | 
| 920 | 
         
            +
                },
         
     | 
| 921 | 
         
            +
                {
         
     | 
| 922 | 
         
            +
                  "epoch": 201.53846153846155,
         
     | 
| 923 | 
         
            +
                  "grad_norm": 157.2918701171875,
         
     | 
| 924 | 
         
            +
                  "learning_rate": 7.382400000000001e-06,
         
     | 
| 925 | 
         
            +
                  "loss": 1.6065,
         
     | 
| 926 | 
         
            +
                  "step": 13100
         
     | 
| 927 | 
         
            +
                },
         
     | 
| 928 | 
         
            +
                {
         
     | 
| 929 | 
         
            +
                  "epoch": 203.07692307692307,
         
     | 
| 930 | 
         
            +
                  "grad_norm": 51.04494094848633,
         
     | 
| 931 | 
         
            +
                  "learning_rate": 7.362400000000001e-06,
         
     | 
| 932 | 
         
            +
                  "loss": 1.6227,
         
     | 
| 933 | 
         
            +
                  "step": 13200
         
     | 
| 934 | 
         
            +
                },
         
     | 
| 935 | 
         
            +
                {
         
     | 
| 936 | 
         
            +
                  "epoch": 204.6153846153846,
         
     | 
| 937 | 
         
            +
                  "grad_norm": 53.116188049316406,
         
     | 
| 938 | 
         
            +
                  "learning_rate": 7.342400000000001e-06,
         
     | 
| 939 | 
         
            +
                  "loss": 1.6284,
         
     | 
| 940 | 
         
            +
                  "step": 13300
         
     | 
| 941 | 
         
            +
                },
         
     | 
| 942 | 
         
            +
                {
         
     | 
| 943 | 
         
            +
                  "epoch": 206.15384615384616,
         
     | 
| 944 | 
         
            +
                  "grad_norm": 80.10623168945312,
         
     | 
| 945 | 
         
            +
                  "learning_rate": 7.3224e-06,
         
     | 
| 946 | 
         
            +
                  "loss": 1.619,
         
     | 
| 947 | 
         
            +
                  "step": 13400
         
     | 
| 948 | 
         
            +
                },
         
     | 
| 949 | 
         
            +
                {
         
     | 
| 950 | 
         
            +
                  "epoch": 207.69230769230768,
         
     | 
| 951 | 
         
            +
                  "grad_norm": 249.86141967773438,
         
     | 
| 952 | 
         
            +
                  "learning_rate": 7.302400000000001e-06,
         
     | 
| 953 | 
         
            +
                  "loss": 1.6018,
         
     | 
| 954 | 
         
            +
                  "step": 13500
         
     | 
| 955 | 
         
            +
                },
         
     | 
| 956 | 
         
            +
                {
         
     | 
| 957 | 
         
            +
                  "epoch": 209.23076923076923,
         
     | 
| 958 | 
         
            +
                  "grad_norm": 77.1427001953125,
         
     | 
| 959 | 
         
            +
                  "learning_rate": 7.282400000000001e-06,
         
     | 
| 960 | 
         
            +
                  "loss": 1.6329,
         
     | 
| 961 | 
         
            +
                  "step": 13600
         
     | 
| 962 | 
         
            +
                },
         
     | 
| 963 | 
         
            +
                {
         
     | 
| 964 | 
         
            +
                  "epoch": 210.76923076923077,
         
     | 
| 965 | 
         
            +
                  "grad_norm": 86.5726318359375,
         
     | 
| 966 | 
         
            +
                  "learning_rate": 7.2626000000000006e-06,
         
     | 
| 967 | 
         
            +
                  "loss": 1.6112,
         
     | 
| 968 | 
         
            +
                  "step": 13700
         
     | 
| 969 | 
         
            +
                },
         
     | 
| 970 | 
         
            +
                {
         
     | 
| 971 | 
         
            +
                  "epoch": 212.30769230769232,
         
     | 
| 972 | 
         
            +
                  "grad_norm": 66.48815155029297,
         
     | 
| 973 | 
         
            +
                  "learning_rate": 7.242600000000001e-06,
         
     | 
| 974 | 
         
            +
                  "loss": 1.6128,
         
     | 
| 975 | 
         
            +
                  "step": 13800
         
     | 
| 976 | 
         
            +
                },
         
     | 
| 977 | 
         
            +
                {
         
     | 
| 978 | 
         
            +
                  "epoch": 213.84615384615384,
         
     | 
| 979 | 
         
            +
                  "grad_norm": 99.87622833251953,
         
     | 
| 980 | 
         
            +
                  "learning_rate": 7.222600000000001e-06,
         
     | 
| 981 | 
         
            +
                  "loss": 1.5902,
         
     | 
| 982 | 
         
            +
                  "step": 13900
         
     | 
| 983 | 
         
            +
                },
         
     | 
| 984 | 
         
            +
                {
         
     | 
| 985 | 
         
            +
                  "epoch": 215.3846153846154,
         
     | 
| 986 | 
         
            +
                  "grad_norm": 78.00489807128906,
         
     | 
| 987 | 
         
            +
                  "learning_rate": 7.2026e-06,
         
     | 
| 988 | 
         
            +
                  "loss": 1.5964,
         
     | 
| 989 | 
         
            +
                  "step": 14000
         
     | 
| 990 | 
         
            +
                },
         
     | 
| 991 | 
         
            +
                {
         
     | 
| 992 | 
         
            +
                  "epoch": 216.92307692307693,
         
     | 
| 993 | 
         
            +
                  "grad_norm": 726.4310913085938,
         
     | 
| 994 | 
         
            +
                  "learning_rate": 7.1826000000000005e-06,
         
     | 
| 995 | 
         
            +
                  "loss": 1.6301,
         
     | 
| 996 | 
         
            +
                  "step": 14100
         
     | 
| 997 | 
         
            +
                },
         
     | 
| 998 | 
         
            +
                {
         
     | 
| 999 | 
         
            +
                  "epoch": 218.46153846153845,
         
     | 
| 1000 | 
         
            +
                  "grad_norm": 60.30306625366211,
         
     | 
| 1001 | 
         
            +
                  "learning_rate": 7.162600000000001e-06,
         
     | 
| 1002 | 
         
            +
                  "loss": 1.5653,
         
     | 
| 1003 | 
         
            +
                  "step": 14200
         
     | 
| 1004 | 
         
            +
                },
         
     | 
| 1005 | 
         
            +
                {
         
     | 
| 1006 | 
         
            +
                  "epoch": 220.0,
         
     | 
| 1007 | 
         
            +
                  "grad_norm": 88.68881225585938,
         
     | 
| 1008 | 
         
            +
                  "learning_rate": 7.142600000000001e-06,
         
     | 
| 1009 | 
         
            +
                  "loss": 1.5743,
         
     | 
| 1010 | 
         
            +
                  "step": 14300
         
     | 
| 1011 | 
         
            +
                },
         
     | 
| 1012 | 
         
            +
                {
         
     | 
| 1013 | 
         
            +
                  "epoch": 221.53846153846155,
         
     | 
| 1014 | 
         
            +
                  "grad_norm": 101.28644561767578,
         
     | 
| 1015 | 
         
            +
                  "learning_rate": 7.1226e-06,
         
     | 
| 1016 | 
         
            +
                  "loss": 1.5589,
         
     | 
| 1017 | 
         
            +
                  "step": 14400
         
     | 
| 1018 | 
         
            +
                },
         
     | 
| 1019 | 
         
            +
                {
         
     | 
| 1020 | 
         
            +
                  "epoch": 223.07692307692307,
         
     | 
| 1021 | 
         
            +
                  "grad_norm": 248.6482696533203,
         
     | 
| 1022 | 
         
            +
                  "learning_rate": 7.1026e-06,
         
     | 
| 1023 | 
         
            +
                  "loss": 1.5706,
         
     | 
| 1024 | 
         
            +
                  "step": 14500
         
     | 
| 1025 | 
         
            +
                },
         
     | 
| 1026 | 
         
            +
                {
         
     | 
| 1027 | 
         
            +
                  "epoch": 224.6153846153846,
         
     | 
| 1028 | 
         
            +
                  "grad_norm": 110.11705780029297,
         
     | 
| 1029 | 
         
            +
                  "learning_rate": 7.082600000000001e-06,
         
     | 
| 1030 | 
         
            +
                  "loss": 1.5843,
         
     | 
| 1031 | 
         
            +
                  "step": 14600
         
     | 
| 1032 | 
         
            +
                },
         
     | 
| 1033 | 
         
            +
                {
         
     | 
| 1034 | 
         
            +
                  "epoch": 226.15384615384616,
         
     | 
| 1035 | 
         
            +
                  "grad_norm": 67.07064819335938,
         
     | 
| 1036 | 
         
            +
                  "learning_rate": 7.062600000000001e-06,
         
     | 
| 1037 | 
         
            +
                  "loss": 1.5643,
         
     | 
| 1038 | 
         
            +
                  "step": 14700
         
     | 
| 1039 | 
         
            +
                },
         
     | 
| 1040 | 
         
            +
                {
         
     | 
| 1041 | 
         
            +
                  "epoch": 227.69230769230768,
         
     | 
| 1042 | 
         
            +
                  "grad_norm": 97.37787628173828,
         
     | 
| 1043 | 
         
            +
                  "learning_rate": 7.0426e-06,
         
     | 
| 1044 | 
         
            +
                  "loss": 1.5424,
         
     | 
| 1045 | 
         
            +
                  "step": 14800
         
     | 
| 1046 | 
         
            +
                },
         
     | 
| 1047 | 
         
            +
                {
         
     | 
| 1048 | 
         
            +
                  "epoch": 229.23076923076923,
         
     | 
| 1049 | 
         
            +
                  "grad_norm": 53.19269561767578,
         
     | 
| 1050 | 
         
            +
                  "learning_rate": 7.0226e-06,
         
     | 
| 1051 | 
         
            +
                  "loss": 1.5644,
         
     | 
| 1052 | 
         
            +
                  "step": 14900
         
     | 
| 1053 | 
         
            +
                },
         
     | 
| 1054 | 
         
            +
                {
         
     | 
| 1055 | 
         
            +
                  "epoch": 230.76923076923077,
         
     | 
| 1056 | 
         
            +
                  "grad_norm": 213.32289123535156,
         
     | 
| 1057 | 
         
            +
                  "learning_rate": 7.0026000000000005e-06,
         
     | 
| 1058 | 
         
            +
                  "loss": 1.5541,
         
     | 
| 1059 | 
         
            +
                  "step": 15000
         
     | 
| 1060 | 
         
            +
                },
         
     | 
| 1061 | 
         
            +
                {
         
     | 
| 1062 | 
         
            +
                  "epoch": 232.30769230769232,
         
     | 
| 1063 | 
         
            +
                  "grad_norm": 105.63107299804688,
         
     | 
| 1064 | 
         
            +
                  "learning_rate": 6.982600000000001e-06,
         
     | 
| 1065 | 
         
            +
                  "loss": 1.5518,
         
     | 
| 1066 | 
         
            +
                  "step": 15100
         
     | 
| 1067 | 
         
            +
                },
         
     | 
| 1068 | 
         
            +
                {
         
     | 
| 1069 | 
         
            +
                  "epoch": 233.84615384615384,
         
     | 
| 1070 | 
         
            +
                  "grad_norm": 43.85015106201172,
         
     | 
| 1071 | 
         
            +
                  "learning_rate": 6.9626e-06,
         
     | 
| 1072 | 
         
            +
                  "loss": 1.5385,
         
     | 
| 1073 | 
         
            +
                  "step": 15200
         
     | 
| 1074 | 
         
            +
                },
         
     | 
| 1075 | 
         
            +
                {
         
     | 
| 1076 | 
         
            +
                  "epoch": 235.3846153846154,
         
     | 
| 1077 | 
         
            +
                  "grad_norm": 135.48651123046875,
         
     | 
| 1078 | 
         
            +
                  "learning_rate": 6.9426e-06,
         
     | 
| 1079 | 
         
            +
                  "loss": 1.5093,
         
     | 
| 1080 | 
         
            +
                  "step": 15300
         
     | 
| 1081 | 
         
            +
                },
         
     | 
| 1082 | 
         
            +
                {
         
     | 
| 1083 | 
         
            +
                  "epoch": 236.92307692307693,
         
     | 
| 1084 | 
         
            +
                  "grad_norm": 73.94020080566406,
         
     | 
| 1085 | 
         
            +
                  "learning_rate": 6.9226000000000004e-06,
         
     | 
| 1086 | 
         
            +
                  "loss": 1.537,
         
     | 
| 1087 | 
         
            +
                  "step": 15400
         
     | 
| 1088 | 
         
            +
                },
         
     | 
| 1089 | 
         
            +
                {
         
     | 
| 1090 | 
         
            +
                  "epoch": 238.46153846153845,
         
     | 
| 1091 | 
         
            +
                  "grad_norm": 157.08612060546875,
         
     | 
| 1092 | 
         
            +
                  "learning_rate": 6.902600000000001e-06,
         
     | 
| 1093 | 
         
            +
                  "loss": 1.5757,
         
     | 
| 1094 | 
         
            +
                  "step": 15500
         
     | 
| 1095 | 
         
            +
                },
         
     | 
| 1096 | 
         
            +
                {
         
     | 
| 1097 | 
         
            +
                  "epoch": 240.0,
         
     | 
| 1098 | 
         
            +
                  "grad_norm": 79.48292541503906,
         
     | 
| 1099 | 
         
            +
                  "learning_rate": 6.8826e-06,
         
     | 
| 1100 | 
         
            +
                  "loss": 1.5214,
         
     | 
| 1101 | 
         
            +
                  "step": 15600
         
     | 
| 1102 | 
         
            +
                },
         
     | 
| 1103 | 
         
            +
                {
         
     | 
| 1104 | 
         
            +
                  "epoch": 241.53846153846155,
         
     | 
| 1105 | 
         
            +
                  "grad_norm": 59.73866653442383,
         
     | 
| 1106 | 
         
            +
                  "learning_rate": 6.8626e-06,
         
     | 
| 1107 | 
         
            +
                  "loss": 1.5166,
         
     | 
| 1108 | 
         
            +
                  "step": 15700
         
     | 
| 1109 | 
         
            +
                },
         
     | 
| 1110 | 
         
            +
                {
         
     | 
| 1111 | 
         
            +
                  "epoch": 243.07692307692307,
         
     | 
| 1112 | 
         
            +
                  "grad_norm": 97.34918212890625,
         
     | 
| 1113 | 
         
            +
                  "learning_rate": 6.8426e-06,
         
     | 
| 1114 | 
         
            +
                  "loss": 1.5145,
         
     | 
| 1115 | 
         
            +
                  "step": 15800
         
     | 
| 1116 | 
         
            +
                },
         
     | 
| 1117 | 
         
            +
                {
         
     | 
| 1118 | 
         
            +
                  "epoch": 244.6153846153846,
         
     | 
| 1119 | 
         
            +
                  "grad_norm": 198.27203369140625,
         
     | 
| 1120 | 
         
            +
                  "learning_rate": 6.8226000000000005e-06,
         
     | 
| 1121 | 
         
            +
                  "loss": 1.5237,
         
     | 
| 1122 | 
         
            +
                  "step": 15900
         
     | 
| 1123 | 
         
            +
                },
         
     | 
| 1124 | 
         
            +
                {
         
     | 
| 1125 | 
         
            +
                  "epoch": 246.15384615384616,
         
     | 
| 1126 | 
         
            +
                  "grad_norm": 38.80288314819336,
         
     | 
| 1127 | 
         
            +
                  "learning_rate": 6.802600000000001e-06,
         
     | 
| 1128 | 
         
            +
                  "loss": 1.5118,
         
     | 
| 1129 | 
         
            +
                  "step": 16000
         
     | 
| 1130 | 
         
            +
                },
         
     | 
| 1131 | 
         
            +
                {
         
     | 
| 1132 | 
         
            +
                  "epoch": 247.69230769230768,
         
     | 
| 1133 | 
         
            +
                  "grad_norm": 89.98989868164062,
         
     | 
| 1134 | 
         
            +
                  "learning_rate": 6.7828000000000005e-06,
         
     | 
| 1135 | 
         
            +
                  "loss": 1.5171,
         
     | 
| 1136 | 
         
            +
                  "step": 16100
         
     | 
| 1137 | 
         
            +
                },
         
     | 
| 1138 | 
         
            +
                {
         
     | 
| 1139 | 
         
            +
                  "epoch": 249.23076923076923,
         
     | 
| 1140 | 
         
            +
                  "grad_norm": 55.13770294189453,
         
     | 
| 1141 | 
         
            +
                  "learning_rate": 6.762800000000001e-06,
         
     | 
| 1142 | 
         
            +
                  "loss": 1.5044,
         
     | 
| 1143 | 
         
            +
                  "step": 16200
         
     | 
| 1144 | 
         
            +
                },
         
     | 
| 1145 | 
         
            +
                {
         
     | 
| 1146 | 
         
            +
                  "epoch": 250.76923076923077,
         
     | 
| 1147 | 
         
            +
                  "grad_norm": 34.529293060302734,
         
     | 
| 1148 | 
         
            +
                  "learning_rate": 6.7428e-06,
         
     | 
| 1149 | 
         
            +
                  "loss": 1.4981,
         
     | 
| 1150 | 
         
            +
                  "step": 16300
         
     | 
| 1151 | 
         
            +
                },
         
     | 
| 1152 | 
         
            +
                {
         
     | 
| 1153 | 
         
            +
                  "epoch": 252.30769230769232,
         
     | 
| 1154 | 
         
            +
                  "grad_norm": 79.73957824707031,
         
     | 
| 1155 | 
         
            +
                  "learning_rate": 6.7228e-06,
         
     | 
| 1156 | 
         
            +
                  "loss": 1.501,
         
     | 
| 1157 | 
         
            +
                  "step": 16400
         
     | 
| 1158 | 
         
            +
                },
         
     | 
| 1159 | 
         
            +
                {
         
     | 
| 1160 | 
         
            +
                  "epoch": 253.84615384615384,
         
     | 
| 1161 | 
         
            +
                  "grad_norm": 51.99100875854492,
         
     | 
| 1162 | 
         
            +
                  "learning_rate": 6.7028000000000004e-06,
         
     | 
| 1163 | 
         
            +
                  "loss": 1.4968,
         
     | 
| 1164 | 
         
            +
                  "step": 16500
         
     | 
| 1165 | 
         
            +
                },
         
     | 
| 1166 | 
         
            +
                {
         
     | 
| 1167 | 
         
            +
                  "epoch": 255.3846153846154,
         
     | 
| 1168 | 
         
            +
                  "grad_norm": 47.11521530151367,
         
     | 
| 1169 | 
         
            +
                  "learning_rate": 6.682800000000001e-06,
         
     | 
| 1170 | 
         
            +
                  "loss": 1.4961,
         
     | 
| 1171 | 
         
            +
                  "step": 16600
         
     | 
| 1172 | 
         
            +
                },
         
     | 
| 1173 | 
         
            +
                {
         
     | 
| 1174 | 
         
            +
                  "epoch": 256.9230769230769,
         
     | 
| 1175 | 
         
            +
                  "grad_norm": 70.4249496459961,
         
     | 
| 1176 | 
         
            +
                  "learning_rate": 6.6628e-06,
         
     | 
| 1177 | 
         
            +
                  "loss": 1.5162,
         
     | 
| 1178 | 
         
            +
                  "step": 16700
         
     | 
| 1179 | 
         
            +
                },
         
     | 
| 1180 | 
         
            +
                {
         
     | 
| 1181 | 
         
            +
                  "epoch": 258.46153846153845,
         
     | 
| 1182 | 
         
            +
                  "grad_norm": 56.895957946777344,
         
     | 
| 1183 | 
         
            +
                  "learning_rate": 6.6428e-06,
         
     | 
| 1184 | 
         
            +
                  "loss": 1.5187,
         
     | 
| 1185 | 
         
            +
                  "step": 16800
         
     | 
| 1186 | 
         
            +
                },
         
     | 
| 1187 | 
         
            +
                {
         
     | 
| 1188 | 
         
            +
                  "epoch": 260.0,
         
     | 
| 1189 | 
         
            +
                  "grad_norm": 34.502071380615234,
         
     | 
| 1190 | 
         
            +
                  "learning_rate": 6.623000000000001e-06,
         
     | 
| 1191 | 
         
            +
                  "loss": 1.5325,
         
     | 
| 1192 | 
         
            +
                  "step": 16900
         
     | 
| 1193 | 
         
            +
                },
         
     | 
| 1194 | 
         
            +
                {
         
     | 
| 1195 | 
         
            +
                  "epoch": 261.53846153846155,
         
     | 
| 1196 | 
         
            +
                  "grad_norm": 66.03074645996094,
         
     | 
| 1197 | 
         
            +
                  "learning_rate": 6.603e-06,
         
     | 
| 1198 | 
         
            +
                  "loss": 1.5103,
         
     | 
| 1199 | 
         
            +
                  "step": 17000
         
     | 
| 1200 | 
         
            +
                },
         
     | 
| 1201 | 
         
            +
                {
         
     | 
| 1202 | 
         
            +
                  "epoch": 263.0769230769231,
         
     | 
| 1203 | 
         
            +
                  "grad_norm": 110.48493957519531,
         
     | 
| 1204 | 
         
            +
                  "learning_rate": 6.583e-06,
         
     | 
| 1205 | 
         
            +
                  "loss": 1.4571,
         
     | 
| 1206 | 
         
            +
                  "step": 17100
         
     | 
| 1207 | 
         
            +
                },
         
     | 
| 1208 | 
         
            +
                {
         
     | 
| 1209 | 
         
            +
                  "epoch": 264.61538461538464,
         
     | 
| 1210 | 
         
            +
                  "grad_norm": 55.59686279296875,
         
     | 
| 1211 | 
         
            +
                  "learning_rate": 6.5630000000000005e-06,
         
     | 
| 1212 | 
         
            +
                  "loss": 1.5147,
         
     | 
| 1213 | 
         
            +
                  "step": 17200
         
     | 
| 1214 | 
         
            +
                },
         
     | 
| 1215 | 
         
            +
                {
         
     | 
| 1216 | 
         
            +
                  "epoch": 266.15384615384613,
         
     | 
| 1217 | 
         
            +
                  "grad_norm": 72.83611297607422,
         
     | 
| 1218 | 
         
            +
                  "learning_rate": 6.543000000000001e-06,
         
     | 
| 1219 | 
         
            +
                  "loss": 1.48,
         
     | 
| 1220 | 
         
            +
                  "step": 17300
         
     | 
| 1221 | 
         
            +
                },
         
     | 
| 1222 | 
         
            +
                {
         
     | 
| 1223 | 
         
            +
                  "epoch": 267.6923076923077,
         
     | 
| 1224 | 
         
            +
                  "grad_norm": 54.794437408447266,
         
     | 
| 1225 | 
         
            +
                  "learning_rate": 6.523e-06,
         
     | 
| 1226 | 
         
            +
                  "loss": 1.461,
         
     | 
| 1227 | 
         
            +
                  "step": 17400
         
     | 
| 1228 | 
         
            +
                },
         
     | 
| 1229 | 
         
            +
                {
         
     | 
| 1230 | 
         
            +
                  "epoch": 269.2307692307692,
         
     | 
| 1231 | 
         
            +
                  "grad_norm": 41.280731201171875,
         
     | 
| 1232 | 
         
            +
                  "learning_rate": 6.503e-06,
         
     | 
| 1233 | 
         
            +
                  "loss": 1.4188,
         
     | 
| 1234 | 
         
            +
                  "step": 17500
         
     | 
| 1235 | 
         
            +
                },
         
     | 
| 1236 | 
         
            +
                {
         
     | 
| 1237 | 
         
            +
                  "epoch": 270.7692307692308,
         
     | 
| 1238 | 
         
            +
                  "grad_norm": 81.90428924560547,
         
     | 
| 1239 | 
         
            +
                  "learning_rate": 6.4830000000000004e-06,
         
     | 
| 1240 | 
         
            +
                  "loss": 1.4256,
         
     | 
| 1241 | 
         
            +
                  "step": 17600
         
     | 
| 1242 | 
         
            +
                },
         
     | 
| 1243 | 
         
            +
                {
         
     | 
| 1244 | 
         
            +
                  "epoch": 272.3076923076923,
         
     | 
| 1245 | 
         
            +
                  "grad_norm": 67.94799041748047,
         
     | 
| 1246 | 
         
            +
                  "learning_rate": 6.463000000000001e-06,
         
     | 
| 1247 | 
         
            +
                  "loss": 1.4295,
         
     | 
| 1248 | 
         
            +
                  "step": 17700
         
     | 
| 1249 | 
         
            +
                },
         
     | 
| 1250 | 
         
            +
                {
         
     | 
| 1251 | 
         
            +
                  "epoch": 273.84615384615387,
         
     | 
| 1252 | 
         
            +
                  "grad_norm": 77.92097473144531,
         
     | 
| 1253 | 
         
            +
                  "learning_rate": 6.443e-06,
         
     | 
| 1254 | 
         
            +
                  "loss": 1.4575,
         
     | 
| 1255 | 
         
            +
                  "step": 17800
         
     | 
| 1256 | 
         
            +
                },
         
     | 
| 1257 | 
         
            +
                {
         
     | 
| 1258 | 
         
            +
                  "epoch": 275.38461538461536,
         
     | 
| 1259 | 
         
            +
                  "grad_norm": 83.06784057617188,
         
     | 
| 1260 | 
         
            +
                  "learning_rate": 6.423e-06,
         
     | 
| 1261 | 
         
            +
                  "loss": 1.434,
         
     | 
| 1262 | 
         
            +
                  "step": 17900
         
     | 
| 1263 | 
         
            +
                },
         
     | 
| 1264 | 
         
            +
                {
         
     | 
| 1265 | 
         
            +
                  "epoch": 276.9230769230769,
         
     | 
| 1266 | 
         
            +
                  "grad_norm": 60.48369598388672,
         
     | 
| 1267 | 
         
            +
                  "learning_rate": 6.403e-06,
         
     | 
| 1268 | 
         
            +
                  "loss": 1.4496,
         
     | 
| 1269 | 
         
            +
                  "step": 18000
         
     | 
| 1270 | 
         
            +
                },
         
     | 
| 1271 | 
         
            +
                {
         
     | 
| 1272 | 
         
            +
                  "epoch": 278.46153846153845,
         
     | 
| 1273 | 
         
            +
                  "grad_norm": 47.32282257080078,
         
     | 
| 1274 | 
         
            +
                  "learning_rate": 6.3830000000000006e-06,
         
     | 
| 1275 | 
         
            +
                  "loss": 1.4149,
         
     | 
| 1276 | 
         
            +
                  "step": 18100
         
     | 
| 1277 | 
         
            +
                },
         
     | 
| 1278 | 
         
            +
                {
         
     | 
| 1279 | 
         
            +
                  "epoch": 280.0,
         
     | 
| 1280 | 
         
            +
                  "grad_norm": 134.77822875976562,
         
     | 
| 1281 | 
         
            +
                  "learning_rate": 6.363e-06,
         
     | 
| 1282 | 
         
            +
                  "loss": 1.3949,
         
     | 
| 1283 | 
         
            +
                  "step": 18200
         
     | 
| 1284 | 
         
            +
                },
         
     | 
| 1285 | 
         
            +
                {
         
     | 
| 1286 | 
         
            +
                  "epoch": 281.53846153846155,
         
     | 
| 1287 | 
         
            +
                  "grad_norm": 72.09223937988281,
         
     | 
| 1288 | 
         
            +
                  "learning_rate": 6.343e-06,
         
     | 
| 1289 | 
         
            +
                  "loss": 1.4298,
         
     | 
| 1290 | 
         
            +
                  "step": 18300
         
     | 
| 1291 | 
         
            +
                },
         
     | 
| 1292 | 
         
            +
                {
         
     | 
| 1293 | 
         
            +
                  "epoch": 283.0769230769231,
         
     | 
| 1294 | 
         
            +
                  "grad_norm": 95.94608306884766,
         
     | 
| 1295 | 
         
            +
                  "learning_rate": 6.323e-06,
         
     | 
| 1296 | 
         
            +
                  "loss": 1.4189,
         
     | 
| 1297 | 
         
            +
                  "step": 18400
         
     | 
| 1298 | 
         
            +
                },
         
     | 
| 1299 | 
         
            +
                {
         
     | 
| 1300 | 
         
            +
                  "epoch": 284.61538461538464,
         
     | 
| 1301 | 
         
            +
                  "grad_norm": 79.95153045654297,
         
     | 
| 1302 | 
         
            +
                  "learning_rate": 6.3030000000000005e-06,
         
     | 
| 1303 | 
         
            +
                  "loss": 1.4066,
         
     | 
| 1304 | 
         
            +
                  "step": 18500
         
     | 
| 1305 | 
         
            +
                },
         
     | 
| 1306 | 
         
            +
                {
         
     | 
| 1307 | 
         
            +
                  "epoch": 286.15384615384613,
         
     | 
| 1308 | 
         
            +
                  "grad_norm": 165.74986267089844,
         
     | 
| 1309 | 
         
            +
                  "learning_rate": 6.283e-06,
         
     | 
| 1310 | 
         
            +
                  "loss": 1.4231,
         
     | 
| 1311 | 
         
            +
                  "step": 18600
         
     | 
| 1312 | 
         
            +
                },
         
     | 
| 1313 | 
         
            +
                {
         
     | 
| 1314 | 
         
            +
                  "epoch": 287.6923076923077,
         
     | 
| 1315 | 
         
            +
                  "grad_norm": 105.84443664550781,
         
     | 
| 1316 | 
         
            +
                  "learning_rate": 6.263e-06,
         
     | 
| 1317 | 
         
            +
                  "loss": 1.3851,
         
     | 
| 1318 | 
         
            +
                  "step": 18700
         
     | 
| 1319 | 
         
            +
                },
         
     | 
| 1320 | 
         
            +
                {
         
     | 
| 1321 | 
         
            +
                  "epoch": 289.2307692307692,
         
     | 
| 1322 | 
         
            +
                  "grad_norm": 48.660987854003906,
         
     | 
| 1323 | 
         
            +
                  "learning_rate": 6.243e-06,
         
     | 
| 1324 | 
         
            +
                  "loss": 1.4234,
         
     | 
| 1325 | 
         
            +
                  "step": 18800
         
     | 
| 1326 | 
         
            +
                },
         
     | 
| 1327 | 
         
            +
                {
         
     | 
| 1328 | 
         
            +
                  "epoch": 290.7692307692308,
         
     | 
| 1329 | 
         
            +
                  "grad_norm": 53.28395462036133,
         
     | 
| 1330 | 
         
            +
                  "learning_rate": 6.223e-06,
         
     | 
| 1331 | 
         
            +
                  "loss": 1.3861,
         
     | 
| 1332 | 
         
            +
                  "step": 18900
         
     | 
| 1333 | 
         
            +
                },
         
     | 
| 1334 | 
         
            +
                {
         
     | 
| 1335 | 
         
            +
                  "epoch": 292.3076923076923,
         
     | 
| 1336 | 
         
            +
                  "grad_norm": 54.91928482055664,
         
     | 
| 1337 | 
         
            +
                  "learning_rate": 6.203e-06,
         
     | 
| 1338 | 
         
            +
                  "loss": 1.3799,
         
     | 
| 1339 | 
         
            +
                  "step": 19000
         
     | 
| 1340 | 
         
            +
                },
         
     | 
| 1341 | 
         
            +
                {
         
     | 
| 1342 | 
         
            +
                  "epoch": 293.84615384615387,
         
     | 
| 1343 | 
         
            +
                  "grad_norm": 69.98273468017578,
         
     | 
| 1344 | 
         
            +
                  "learning_rate": 6.183e-06,
         
     | 
| 1345 | 
         
            +
                  "loss": 1.4223,
         
     | 
| 1346 | 
         
            +
                  "step": 19100
         
     | 
| 1347 | 
         
            +
                },
         
     | 
| 1348 | 
         
            +
                {
         
     | 
| 1349 | 
         
            +
                  "epoch": 295.38461538461536,
         
     | 
| 1350 | 
         
            +
                  "grad_norm": 55.819786071777344,
         
     | 
| 1351 | 
         
            +
                  "learning_rate": 6.163e-06,
         
     | 
| 1352 | 
         
            +
                  "loss": 1.3747,
         
     | 
| 1353 | 
         
            +
                  "step": 19200
         
     | 
| 1354 | 
         
            +
                },
         
     | 
| 1355 | 
         
            +
                {
         
     | 
| 1356 | 
         
            +
                  "epoch": 296.9230769230769,
         
     | 
| 1357 | 
         
            +
                  "grad_norm": 64.86967468261719,
         
     | 
| 1358 | 
         
            +
                  "learning_rate": 6.143e-06,
         
     | 
| 1359 | 
         
            +
                  "loss": 1.4014,
         
     | 
| 1360 | 
         
            +
                  "step": 19300
         
     | 
| 1361 | 
         
            +
                },
         
     | 
| 1362 | 
         
            +
                {
         
     | 
| 1363 | 
         
            +
                  "epoch": 298.46153846153845,
         
     | 
| 1364 | 
         
            +
                  "grad_norm": 96.05943298339844,
         
     | 
| 1365 | 
         
            +
                  "learning_rate": 6.123e-06,
         
     | 
| 1366 | 
         
            +
                  "loss": 1.3517,
         
     | 
| 1367 | 
         
            +
                  "step": 19400
         
     | 
| 1368 | 
         
            +
                },
         
     | 
| 1369 | 
         
            +
                {
         
     | 
| 1370 | 
         
            +
                  "epoch": 300.0,
         
     | 
| 1371 | 
         
            +
                  "grad_norm": 37.66103744506836,
         
     | 
| 1372 | 
         
            +
                  "learning_rate": 6.103e-06,
         
     | 
| 1373 | 
         
            +
                  "loss": 1.3625,
         
     | 
| 1374 | 
         
            +
                  "step": 19500
         
     | 
| 1375 | 
         
            +
                },
         
     | 
| 1376 | 
         
            +
                {
         
     | 
| 1377 | 
         
            +
                  "epoch": 301.53846153846155,
         
     | 
| 1378 | 
         
            +
                  "grad_norm": 38.60346603393555,
         
     | 
| 1379 | 
         
            +
                  "learning_rate": 6.083e-06,
         
     | 
| 1380 | 
         
            +
                  "loss": 1.4039,
         
     | 
| 1381 | 
         
            +
                  "step": 19600
         
     | 
| 1382 | 
         
            +
                },
         
     | 
| 1383 | 
         
            +
                {
         
     | 
| 1384 | 
         
            +
                  "epoch": 303.0769230769231,
         
     | 
| 1385 | 
         
            +
                  "grad_norm": 51.319610595703125,
         
     | 
| 1386 | 
         
            +
                  "learning_rate": 6.063e-06,
         
     | 
| 1387 | 
         
            +
                  "loss": 1.3722,
         
     | 
| 1388 | 
         
            +
                  "step": 19700
         
     | 
| 1389 | 
         
            +
                },
         
     | 
| 1390 | 
         
            +
                {
         
     | 
| 1391 | 
         
            +
                  "epoch": 304.61538461538464,
         
     | 
| 1392 | 
         
            +
                  "grad_norm": 63.50655746459961,
         
     | 
| 1393 | 
         
            +
                  "learning_rate": 6.0429999999999996e-06,
         
     | 
| 1394 | 
         
            +
                  "loss": 1.3789,
         
     | 
| 1395 | 
         
            +
                  "step": 19800
         
     | 
| 1396 | 
         
            +
                },
         
     | 
| 1397 | 
         
            +
                {
         
     | 
| 1398 | 
         
            +
                  "epoch": 306.15384615384613,
         
     | 
| 1399 | 
         
            +
                  "grad_norm": 1452.8902587890625,
         
     | 
| 1400 | 
         
            +
                  "learning_rate": 6.023e-06,
         
     | 
| 1401 | 
         
            +
                  "loss": 1.352,
         
     | 
| 1402 | 
         
            +
                  "step": 19900
         
     | 
| 1403 | 
         
            +
                },
         
     | 
| 1404 | 
         
            +
                {
         
     | 
| 1405 | 
         
            +
                  "epoch": 307.6923076923077,
         
     | 
| 1406 | 
         
            +
                  "grad_norm": 45.927669525146484,
         
     | 
| 1407 | 
         
            +
                  "learning_rate": 6.003e-06,
         
     | 
| 1408 | 
         
            +
                  "loss": 1.3539,
         
     | 
| 1409 | 
         
            +
                  "step": 20000
         
     | 
| 1410 | 
         
            +
                },
         
     | 
| 1411 | 
         
            +
                {
         
     | 
| 1412 | 
         
            +
                  "epoch": 309.2307692307692,
         
     | 
| 1413 | 
         
            +
                  "grad_norm": 118.03652954101562,
         
     | 
| 1414 | 
         
            +
                  "learning_rate": 5.983000000000001e-06,
         
     | 
| 1415 | 
         
            +
                  "loss": 1.3753,
         
     | 
| 1416 | 
         
            +
                  "step": 20100
         
     | 
| 1417 | 
         
            +
                },
         
     | 
| 1418 | 
         
            +
                {
         
     | 
| 1419 | 
         
            +
                  "epoch": 310.7692307692308,
         
     | 
| 1420 | 
         
            +
                  "grad_norm": 78.8291015625,
         
     | 
| 1421 | 
         
            +
                  "learning_rate": 5.963000000000001e-06,
         
     | 
| 1422 | 
         
            +
                  "loss": 1.3559,
         
     | 
| 1423 | 
         
            +
                  "step": 20200
         
     | 
| 1424 | 
         
            +
                },
         
     | 
| 1425 | 
         
            +
                {
         
     | 
| 1426 | 
         
            +
                  "epoch": 312.3076923076923,
         
     | 
| 1427 | 
         
            +
                  "grad_norm": 97.92073059082031,
         
     | 
| 1428 | 
         
            +
                  "learning_rate": 5.943000000000001e-06,
         
     | 
| 1429 | 
         
            +
                  "loss": 1.3443,
         
     | 
| 1430 | 
         
            +
                  "step": 20300
         
     | 
| 1431 | 
         
            +
                },
         
     | 
| 1432 | 
         
            +
                {
         
     | 
| 1433 | 
         
            +
                  "epoch": 313.84615384615387,
         
     | 
| 1434 | 
         
            +
                  "grad_norm": 92.97972869873047,
         
     | 
| 1435 | 
         
            +
                  "learning_rate": 5.923000000000001e-06,
         
     | 
| 1436 | 
         
            +
                  "loss": 1.3573,
         
     | 
| 1437 | 
         
            +
                  "step": 20400
         
     | 
| 1438 | 
         
            +
                },
         
     | 
| 1439 | 
         
            +
                {
         
     | 
| 1440 | 
         
            +
                  "epoch": 315.38461538461536,
         
     | 
| 1441 | 
         
            +
                  "grad_norm": 24.576528549194336,
         
     | 
| 1442 | 
         
            +
                  "learning_rate": 5.903000000000001e-06,
         
     | 
| 1443 | 
         
            +
                  "loss": 1.3376,
         
     | 
| 1444 | 
         
            +
                  "step": 20500
         
     | 
| 1445 | 
         
            +
                },
         
     | 
| 1446 | 
         
            +
                {
         
     | 
| 1447 | 
         
            +
                  "epoch": 316.9230769230769,
         
     | 
| 1448 | 
         
            +
                  "grad_norm": 30.237171173095703,
         
     | 
| 1449 | 
         
            +
                  "learning_rate": 5.883000000000001e-06,
         
     | 
| 1450 | 
         
            +
                  "loss": 1.3321,
         
     | 
| 1451 | 
         
            +
                  "step": 20600
         
     | 
| 1452 | 
         
            +
                },
         
     | 
| 1453 | 
         
            +
                {
         
     | 
| 1454 | 
         
            +
                  "epoch": 318.46153846153845,
         
     | 
| 1455 | 
         
            +
                  "grad_norm": 42.16428756713867,
         
     | 
| 1456 | 
         
            +
                  "learning_rate": 5.863000000000001e-06,
         
     | 
| 1457 | 
         
            +
                  "loss": 1.351,
         
     | 
| 1458 | 
         
            +
                  "step": 20700
         
     | 
| 1459 | 
         
            +
                },
         
     | 
| 1460 | 
         
            +
                {
         
     | 
| 1461 | 
         
            +
                  "epoch": 320.0,
         
     | 
| 1462 | 
         
            +
                  "grad_norm": 31.800731658935547,
         
     | 
| 1463 | 
         
            +
                  "learning_rate": 5.843000000000001e-06,
         
     | 
| 1464 | 
         
            +
                  "loss": 1.3395,
         
     | 
| 1465 | 
         
            +
                  "step": 20800
         
     | 
| 1466 | 
         
            +
                },
         
     | 
| 1467 | 
         
            +
                {
         
     | 
| 1468 | 
         
            +
                  "epoch": 321.53846153846155,
         
     | 
| 1469 | 
         
            +
                  "grad_norm": 44.216575622558594,
         
     | 
| 1470 | 
         
            +
                  "learning_rate": 5.823000000000001e-06,
         
     | 
| 1471 | 
         
            +
                  "loss": 1.3145,
         
     | 
| 1472 | 
         
            +
                  "step": 20900
         
     | 
| 1473 | 
         
            +
                },
         
     | 
| 1474 | 
         
            +
                {
         
     | 
| 1475 | 
         
            +
                  "epoch": 323.0769230769231,
         
     | 
| 1476 | 
         
            +
                  "grad_norm": 83.01956939697266,
         
     | 
| 1477 | 
         
            +
                  "learning_rate": 5.803000000000001e-06,
         
     | 
| 1478 | 
         
            +
                  "loss": 1.319,
         
     | 
| 1479 | 
         
            +
                  "step": 21000
         
     | 
| 1480 | 
         
            +
                },
         
     | 
| 1481 | 
         
            +
                {
         
     | 
| 1482 | 
         
            +
                  "epoch": 324.61538461538464,
         
     | 
| 1483 | 
         
            +
                  "grad_norm": 26.41292953491211,
         
     | 
| 1484 | 
         
            +
                  "learning_rate": 5.783000000000001e-06,
         
     | 
| 1485 | 
         
            +
                  "loss": 1.3289,
         
     | 
| 1486 | 
         
            +
                  "step": 21100
         
     | 
| 1487 | 
         
            +
                },
         
     | 
| 1488 | 
         
            +
                {
         
     | 
| 1489 | 
         
            +
                  "epoch": 326.15384615384613,
         
     | 
| 1490 | 
         
            +
                  "grad_norm": 49.88239288330078,
         
     | 
| 1491 | 
         
            +
                  "learning_rate": 5.7630000000000006e-06,
         
     | 
| 1492 | 
         
            +
                  "loss": 1.3391,
         
     | 
| 1493 | 
         
            +
                  "step": 21200
         
     | 
| 1494 | 
         
            +
                },
         
     | 
| 1495 | 
         
            +
                {
         
     | 
| 1496 | 
         
            +
                  "epoch": 327.6923076923077,
         
     | 
| 1497 | 
         
            +
                  "grad_norm": 60.012489318847656,
         
     | 
| 1498 | 
         
            +
                  "learning_rate": 5.743000000000001e-06,
         
     | 
| 1499 | 
         
            +
                  "loss": 1.3322,
         
     | 
| 1500 | 
         
            +
                  "step": 21300
         
     | 
| 1501 | 
         
            +
                },
         
     | 
| 1502 | 
         
            +
                {
         
     | 
| 1503 | 
         
            +
                  "epoch": 329.2307692307692,
         
     | 
| 1504 | 
         
            +
                  "grad_norm": 44.294063568115234,
         
     | 
| 1505 | 
         
            +
                  "learning_rate": 5.723000000000001e-06,
         
     | 
| 1506 | 
         
            +
                  "loss": 1.3022,
         
     | 
| 1507 | 
         
            +
                  "step": 21400
         
     | 
| 1508 | 
         
            +
                },
         
     | 
| 1509 | 
         
            +
                {
         
     | 
| 1510 | 
         
            +
                  "epoch": 330.7692307692308,
         
     | 
| 1511 | 
         
            +
                  "grad_norm": 51.85730743408203,
         
     | 
| 1512 | 
         
            +
                  "learning_rate": 5.703000000000001e-06,
         
     | 
| 1513 | 
         
            +
                  "loss": 1.3182,
         
     | 
| 1514 | 
         
            +
                  "step": 21500
         
     | 
| 1515 | 
         
            +
                },
         
     | 
| 1516 | 
         
            +
                {
         
     | 
| 1517 | 
         
            +
                  "epoch": 332.3076923076923,
         
     | 
| 1518 | 
         
            +
                  "grad_norm": 36.159053802490234,
         
     | 
| 1519 | 
         
            +
                  "learning_rate": 5.6830000000000005e-06,
         
     | 
| 1520 | 
         
            +
                  "loss": 1.3076,
         
     | 
| 1521 | 
         
            +
                  "step": 21600
         
     | 
| 1522 | 
         
            +
                },
         
     | 
| 1523 | 
         
            +
                {
         
     | 
| 1524 | 
         
            +
                  "epoch": 333.84615384615387,
         
     | 
| 1525 | 
         
            +
                  "grad_norm": 45.60377883911133,
         
     | 
| 1526 | 
         
            +
                  "learning_rate": 5.663000000000001e-06,
         
     | 
| 1527 | 
         
            +
                  "loss": 1.3157,
         
     | 
| 1528 | 
         
            +
                  "step": 21700
         
     | 
| 1529 | 
         
            +
                },
         
     | 
| 1530 | 
         
            +
                {
         
     | 
| 1531 | 
         
            +
                  "epoch": 335.38461538461536,
         
     | 
| 1532 | 
         
            +
                  "grad_norm": 53.93402099609375,
         
     | 
| 1533 | 
         
            +
                  "learning_rate": 5.643000000000001e-06,
         
     | 
| 1534 | 
         
            +
                  "loss": 1.3112,
         
     | 
| 1535 | 
         
            +
                  "step": 21800
         
     | 
| 1536 | 
         
            +
                },
         
     | 
| 1537 | 
         
            +
                {
         
     | 
| 1538 | 
         
            +
                  "epoch": 336.9230769230769,
         
     | 
| 1539 | 
         
            +
                  "grad_norm": 28.81892967224121,
         
     | 
| 1540 | 
         
            +
                  "learning_rate": 5.623000000000001e-06,
         
     | 
| 1541 | 
         
            +
                  "loss": 1.3075,
         
     | 
| 1542 | 
         
            +
                  "step": 21900
         
     | 
| 1543 | 
         
            +
                },
         
     | 
| 1544 | 
         
            +
                {
         
     | 
| 1545 | 
         
            +
                  "epoch": 338.46153846153845,
         
     | 
| 1546 | 
         
            +
                  "grad_norm": 39.13862991333008,
         
     | 
| 1547 | 
         
            +
                  "learning_rate": 5.603e-06,
         
     | 
| 1548 | 
         
            +
                  "loss": 1.311,
         
     | 
| 1549 | 
         
            +
                  "step": 22000
         
     | 
| 1550 | 
         
            +
                },
         
     | 
| 1551 | 
         
            +
                {
         
     | 
| 1552 | 
         
            +
                  "epoch": 340.0,
         
     | 
| 1553 | 
         
            +
                  "grad_norm": 70.76419067382812,
         
     | 
| 1554 | 
         
            +
                  "learning_rate": 5.583000000000001e-06,
         
     | 
| 1555 | 
         
            +
                  "loss": 1.2963,
         
     | 
| 1556 | 
         
            +
                  "step": 22100
         
     | 
| 1557 | 
         
            +
                },
         
     | 
| 1558 | 
         
            +
                {
         
     | 
| 1559 | 
         
            +
                  "epoch": 341.53846153846155,
         
     | 
| 1560 | 
         
            +
                  "grad_norm": 53.80701446533203,
         
     | 
| 1561 | 
         
            +
                  "learning_rate": 5.563000000000001e-06,
         
     | 
| 1562 | 
         
            +
                  "loss": 1.2943,
         
     | 
| 1563 | 
         
            +
                  "step": 22200
         
     | 
| 1564 | 
         
            +
                },
         
     | 
| 1565 | 
         
            +
                {
         
     | 
| 1566 | 
         
            +
                  "epoch": 343.0769230769231,
         
     | 
| 1567 | 
         
            +
                  "grad_norm": 60.86161422729492,
         
     | 
| 1568 | 
         
            +
                  "learning_rate": 5.543000000000001e-06,
         
     | 
| 1569 | 
         
            +
                  "loss": 1.2993,
         
     | 
| 1570 | 
         
            +
                  "step": 22300
         
     | 
| 1571 | 
         
            +
                },
         
     | 
| 1572 | 
         
            +
                {
         
     | 
| 1573 | 
         
            +
                  "epoch": 344.61538461538464,
         
     | 
| 1574 | 
         
            +
                  "grad_norm": 38.120018005371094,
         
     | 
| 1575 | 
         
            +
                  "learning_rate": 5.523e-06,
         
     | 
| 1576 | 
         
            +
                  "loss": 1.2945,
         
     | 
| 1577 | 
         
            +
                  "step": 22400
         
     | 
| 1578 | 
         
            +
                },
         
     | 
| 1579 | 
         
            +
                {
         
     | 
| 1580 | 
         
            +
                  "epoch": 346.15384615384613,
         
     | 
| 1581 | 
         
            +
                  "grad_norm": 71.47781372070312,
         
     | 
| 1582 | 
         
            +
                  "learning_rate": 5.5030000000000005e-06,
         
     | 
| 1583 | 
         
            +
                  "loss": 1.2871,
         
     | 
| 1584 | 
         
            +
                  "step": 22500
         
     | 
| 1585 | 
         
            +
                },
         
     | 
| 1586 | 
         
            +
                {
         
     | 
| 1587 | 
         
            +
                  "epoch": 347.6923076923077,
         
     | 
| 1588 | 
         
            +
                  "grad_norm": 355.5455627441406,
         
     | 
| 1589 | 
         
            +
                  "learning_rate": 5.483000000000001e-06,
         
     | 
| 1590 | 
         
            +
                  "loss": 1.2836,
         
     | 
| 1591 | 
         
            +
                  "step": 22600
         
     | 
| 1592 | 
         
            +
                },
         
     | 
| 1593 | 
         
            +
                {
         
     | 
| 1594 | 
         
            +
                  "epoch": 349.2307692307692,
         
     | 
| 1595 | 
         
            +
                  "grad_norm": 47.89547348022461,
         
     | 
| 1596 | 
         
            +
                  "learning_rate": 5.463000000000001e-06,
         
     | 
| 1597 | 
         
            +
                  "loss": 1.3028,
         
     | 
| 1598 | 
         
            +
                  "step": 22700
         
     | 
| 1599 | 
         
            +
                },
         
     | 
| 1600 | 
         
            +
                {
         
     | 
| 1601 | 
         
            +
                  "epoch": 350.7692307692308,
         
     | 
| 1602 | 
         
            +
                  "grad_norm": 54.10429382324219,
         
     | 
| 1603 | 
         
            +
                  "learning_rate": 5.443e-06,
         
     | 
| 1604 | 
         
            +
                  "loss": 1.2849,
         
     | 
| 1605 | 
         
            +
                  "step": 22800
         
     | 
| 1606 | 
         
            +
                },
         
     | 
| 1607 | 
         
            +
                {
         
     | 
| 1608 | 
         
            +
                  "epoch": 352.3076923076923,
         
     | 
| 1609 | 
         
            +
                  "grad_norm": 82.28721618652344,
         
     | 
| 1610 | 
         
            +
                  "learning_rate": 5.4230000000000004e-06,
         
     | 
| 1611 | 
         
            +
                  "loss": 1.2522,
         
     | 
| 1612 | 
         
            +
                  "step": 22900
         
     | 
| 1613 | 
         
            +
                },
         
     | 
| 1614 | 
         
            +
                {
         
     | 
| 1615 | 
         
            +
                  "epoch": 353.84615384615387,
         
     | 
| 1616 | 
         
            +
                  "grad_norm": 50.41508102416992,
         
     | 
| 1617 | 
         
            +
                  "learning_rate": 5.403000000000001e-06,
         
     | 
| 1618 | 
         
            +
                  "loss": 1.2886,
         
     | 
| 1619 | 
         
            +
                  "step": 23000
         
     | 
| 1620 | 
         
            +
                },
         
     | 
| 1621 | 
         
            +
                {
         
     | 
| 1622 | 
         
            +
                  "epoch": 355.38461538461536,
         
     | 
| 1623 | 
         
            +
                  "grad_norm": 40.82347106933594,
         
     | 
| 1624 | 
         
            +
                  "learning_rate": 5.383000000000001e-06,
         
     | 
| 1625 | 
         
            +
                  "loss": 1.2982,
         
     | 
| 1626 | 
         
            +
                  "step": 23100
         
     | 
| 1627 | 
         
            +
                },
         
     | 
| 1628 | 
         
            +
                {
         
     | 
| 1629 | 
         
            +
                  "epoch": 356.9230769230769,
         
     | 
| 1630 | 
         
            +
                  "grad_norm": 43.295387268066406,
         
     | 
| 1631 | 
         
            +
                  "learning_rate": 5.363e-06,
         
     | 
| 1632 | 
         
            +
                  "loss": 1.2746,
         
     | 
| 1633 | 
         
            +
                  "step": 23200
         
     | 
| 1634 | 
         
            +
                },
         
     | 
| 1635 | 
         
            +
                {
         
     | 
| 1636 | 
         
            +
                  "epoch": 358.46153846153845,
         
     | 
| 1637 | 
         
            +
                  "grad_norm": 31.1278133392334,
         
     | 
| 1638 | 
         
            +
                  "learning_rate": 5.343e-06,
         
     | 
| 1639 | 
         
            +
                  "loss": 1.277,
         
     | 
| 1640 | 
         
            +
                  "step": 23300
         
     | 
| 1641 | 
         
            +
                },
         
     | 
| 1642 | 
         
            +
                {
         
     | 
| 1643 | 
         
            +
                  "epoch": 360.0,
         
     | 
| 1644 | 
         
            +
                  "grad_norm": 95.73058319091797,
         
     | 
| 1645 | 
         
            +
                  "learning_rate": 5.3230000000000005e-06,
         
     | 
| 1646 | 
         
            +
                  "loss": 1.2659,
         
     | 
| 1647 | 
         
            +
                  "step": 23400
         
     | 
| 1648 | 
         
            +
                },
         
     | 
| 1649 | 
         
            +
                {
         
     | 
| 1650 | 
         
            +
                  "epoch": 361.53846153846155,
         
     | 
| 1651 | 
         
            +
                  "grad_norm": 510.55548095703125,
         
     | 
| 1652 | 
         
            +
                  "learning_rate": 5.303000000000001e-06,
         
     | 
| 1653 | 
         
            +
                  "loss": 1.2856,
         
     | 
| 1654 | 
         
            +
                  "step": 23500
         
     | 
| 1655 | 
         
            +
                },
         
     | 
| 1656 | 
         
            +
                {
         
     | 
| 1657 | 
         
            +
                  "epoch": 363.0769230769231,
         
     | 
| 1658 | 
         
            +
                  "grad_norm": 65.73866271972656,
         
     | 
| 1659 | 
         
            +
                  "learning_rate": 5.283e-06,
         
     | 
| 1660 | 
         
            +
                  "loss": 1.2533,
         
     | 
| 1661 | 
         
            +
                  "step": 23600
         
     | 
| 1662 | 
         
            +
                },
         
     | 
| 1663 | 
         
            +
                {
         
     | 
| 1664 | 
         
            +
                  "epoch": 364.61538461538464,
         
     | 
| 1665 | 
         
            +
                  "grad_norm": 42.63539123535156,
         
     | 
| 1666 | 
         
            +
                  "learning_rate": 5.263e-06,
         
     | 
| 1667 | 
         
            +
                  "loss": 1.2784,
         
     | 
| 1668 | 
         
            +
                  "step": 23700
         
     | 
| 1669 | 
         
            +
                },
         
     | 
| 1670 | 
         
            +
                {
         
     | 
| 1671 | 
         
            +
                  "epoch": 366.15384615384613,
         
     | 
| 1672 | 
         
            +
                  "grad_norm": 48.91270065307617,
         
     | 
| 1673 | 
         
            +
                  "learning_rate": 5.243200000000001e-06,
         
     | 
| 1674 | 
         
            +
                  "loss": 1.2694,
         
     | 
| 1675 | 
         
            +
                  "step": 23800
         
     | 
| 1676 | 
         
            +
                },
         
     | 
| 1677 | 
         
            +
                {
         
     | 
| 1678 | 
         
            +
                  "epoch": 367.6923076923077,
         
     | 
| 1679 | 
         
            +
                  "grad_norm": 42.82520294189453,
         
     | 
| 1680 | 
         
            +
                  "learning_rate": 5.2232e-06,
         
     | 
| 1681 | 
         
            +
                  "loss": 1.2676,
         
     | 
| 1682 | 
         
            +
                  "step": 23900
         
     | 
| 1683 | 
         
            +
                },
         
     | 
| 1684 | 
         
            +
                {
         
     | 
| 1685 | 
         
            +
                  "epoch": 369.2307692307692,
         
     | 
| 1686 | 
         
            +
                  "grad_norm": 64.28822326660156,
         
     | 
| 1687 | 
         
            +
                  "learning_rate": 5.203400000000001e-06,
         
     | 
| 1688 | 
         
            +
                  "loss": 1.2474,
         
     | 
| 1689 | 
         
            +
                  "step": 24000
         
     | 
| 1690 | 
         
            +
                },
         
     | 
| 1691 | 
         
            +
                {
         
     | 
| 1692 | 
         
            +
                  "epoch": 370.7692307692308,
         
     | 
| 1693 | 
         
            +
                  "grad_norm": 75.25623321533203,
         
     | 
| 1694 | 
         
            +
                  "learning_rate": 5.183400000000001e-06,
         
     | 
| 1695 | 
         
            +
                  "loss": 1.2274,
         
     | 
| 1696 | 
         
            +
                  "step": 24100
         
     | 
| 1697 | 
         
            +
                },
         
     | 
| 1698 | 
         
            +
                {
         
     | 
| 1699 | 
         
            +
                  "epoch": 372.3076923076923,
         
     | 
| 1700 | 
         
            +
                  "grad_norm": 48.8359375,
         
     | 
| 1701 | 
         
            +
                  "learning_rate": 5.1634e-06,
         
     | 
| 1702 | 
         
            +
                  "loss": 1.2463,
         
     | 
| 1703 | 
         
            +
                  "step": 24200
         
     | 
| 1704 | 
         
            +
                },
         
     | 
| 1705 | 
         
            +
                {
         
     | 
| 1706 | 
         
            +
                  "epoch": 373.84615384615387,
         
     | 
| 1707 | 
         
            +
                  "grad_norm": 31.74736213684082,
         
     | 
| 1708 | 
         
            +
                  "learning_rate": 5.143400000000001e-06,
         
     | 
| 1709 | 
         
            +
                  "loss": 1.2617,
         
     | 
| 1710 | 
         
            +
                  "step": 24300
         
     | 
| 1711 | 
         
            +
                },
         
     | 
| 1712 | 
         
            +
                {
         
     | 
| 1713 | 
         
            +
                  "epoch": 375.38461538461536,
         
     | 
| 1714 | 
         
            +
                  "grad_norm": 27.45305824279785,
         
     | 
| 1715 | 
         
            +
                  "learning_rate": 5.123400000000001e-06,
         
     | 
| 1716 | 
         
            +
                  "loss": 1.2679,
         
     | 
| 1717 | 
         
            +
                  "step": 24400
         
     | 
| 1718 | 
         
            +
                },
         
     | 
| 1719 | 
         
            +
                {
         
     | 
| 1720 | 
         
            +
                  "epoch": 376.9230769230769,
         
     | 
| 1721 | 
         
            +
                  "grad_norm": 71.166259765625,
         
     | 
| 1722 | 
         
            +
                  "learning_rate": 5.103400000000001e-06,
         
     | 
| 1723 | 
         
            +
                  "loss": 1.2764,
         
     | 
| 1724 | 
         
            +
                  "step": 24500
         
     | 
| 1725 | 
         
            +
                },
         
     | 
| 1726 | 
         
            +
                {
         
     | 
| 1727 | 
         
            +
                  "epoch": 378.46153846153845,
         
     | 
| 1728 | 
         
            +
                  "grad_norm": 43.75248718261719,
         
     | 
| 1729 | 
         
            +
                  "learning_rate": 5.0834e-06,
         
     | 
| 1730 | 
         
            +
                  "loss": 1.2334,
         
     | 
| 1731 | 
         
            +
                  "step": 24600
         
     | 
| 1732 | 
         
            +
                },
         
     | 
| 1733 | 
         
            +
                {
         
     | 
| 1734 | 
         
            +
                  "epoch": 380.0,
         
     | 
| 1735 | 
         
            +
                  "grad_norm": 103.99686431884766,
         
     | 
| 1736 | 
         
            +
                  "learning_rate": 5.0634000000000005e-06,
         
     | 
| 1737 | 
         
            +
                  "loss": 1.2367,
         
     | 
| 1738 | 
         
            +
                  "step": 24700
         
     | 
| 1739 | 
         
            +
                },
         
     | 
| 1740 | 
         
            +
                {
         
     | 
| 1741 | 
         
            +
                  "epoch": 381.53846153846155,
         
     | 
| 1742 | 
         
            +
                  "grad_norm": 25.603742599487305,
         
     | 
| 1743 | 
         
            +
                  "learning_rate": 5.043400000000001e-06,
         
     | 
| 1744 | 
         
            +
                  "loss": 1.2408,
         
     | 
| 1745 | 
         
            +
                  "step": 24800
         
     | 
| 1746 | 
         
            +
                },
         
     | 
| 1747 | 
         
            +
                {
         
     | 
| 1748 | 
         
            +
                  "epoch": 383.0769230769231,
         
     | 
| 1749 | 
         
            +
                  "grad_norm": 41.11650085449219,
         
     | 
| 1750 | 
         
            +
                  "learning_rate": 5.023400000000001e-06,
         
     | 
| 1751 | 
         
            +
                  "loss": 1.2525,
         
     | 
| 1752 | 
         
            +
                  "step": 24900
         
     | 
| 1753 | 
         
            +
                },
         
     | 
| 1754 | 
         
            +
                {
         
     | 
| 1755 | 
         
            +
                  "epoch": 384.61538461538464,
         
     | 
| 1756 | 
         
            +
                  "grad_norm": 62.1868896484375,
         
     | 
| 1757 | 
         
            +
                  "learning_rate": 5.0034e-06,
         
     | 
| 1758 | 
         
            +
                  "loss": 1.2408,
         
     | 
| 1759 | 
         
            +
                  "step": 25000
         
     | 
| 1760 | 
         
            +
                },
         
     | 
| 1761 | 
         
            +
                {
         
     | 
| 1762 | 
         
            +
                  "epoch": 386.15384615384613,
         
     | 
| 1763 | 
         
            +
                  "grad_norm": 47.254390716552734,
         
     | 
| 1764 | 
         
            +
                  "learning_rate": 4.9834000000000004e-06,
         
     | 
| 1765 | 
         
            +
                  "loss": 1.2595,
         
     | 
| 1766 | 
         
            +
                  "step": 25100
         
     | 
| 1767 | 
         
            +
                },
         
     | 
| 1768 | 
         
            +
                {
         
     | 
| 1769 | 
         
            +
                  "epoch": 387.6923076923077,
         
     | 
| 1770 | 
         
            +
                  "grad_norm": 36.716033935546875,
         
     | 
| 1771 | 
         
            +
                  "learning_rate": 4.963400000000001e-06,
         
     | 
| 1772 | 
         
            +
                  "loss": 1.246,
         
     | 
| 1773 | 
         
            +
                  "step": 25200
         
     | 
| 1774 | 
         
            +
                },
         
     | 
| 1775 | 
         
            +
                {
         
     | 
| 1776 | 
         
            +
                  "epoch": 389.2307692307692,
         
     | 
| 1777 | 
         
            +
                  "grad_norm": 222.34286499023438,
         
     | 
| 1778 | 
         
            +
                  "learning_rate": 4.943400000000001e-06,
         
     | 
| 1779 | 
         
            +
                  "loss": 1.2328,
         
     | 
| 1780 | 
         
            +
                  "step": 25300
         
     | 
| 1781 | 
         
            +
                },
         
     | 
| 1782 | 
         
            +
                {
         
     | 
| 1783 | 
         
            +
                  "epoch": 390.7692307692308,
         
     | 
| 1784 | 
         
            +
                  "grad_norm": 129.1654815673828,
         
     | 
| 1785 | 
         
            +
                  "learning_rate": 4.9234e-06,
         
     | 
| 1786 | 
         
            +
                  "loss": 1.2248,
         
     | 
| 1787 | 
         
            +
                  "step": 25400
         
     | 
| 1788 | 
         
            +
                },
         
     | 
| 1789 | 
         
            +
                {
         
     | 
| 1790 | 
         
            +
                  "epoch": 392.3076923076923,
         
     | 
| 1791 | 
         
            +
                  "grad_norm": 59.3955192565918,
         
     | 
| 1792 | 
         
            +
                  "learning_rate": 4.9034e-06,
         
     | 
| 1793 | 
         
            +
                  "loss": 1.2488,
         
     | 
| 1794 | 
         
            +
                  "step": 25500
         
     | 
| 1795 | 
         
            +
                },
         
     | 
| 1796 | 
         
            +
                {
         
     | 
| 1797 | 
         
            +
                  "epoch": 393.84615384615387,
         
     | 
| 1798 | 
         
            +
                  "grad_norm": 81.6048355102539,
         
     | 
| 1799 | 
         
            +
                  "learning_rate": 4.8834000000000005e-06,
         
     | 
| 1800 | 
         
            +
                  "loss": 1.2459,
         
     | 
| 1801 | 
         
            +
                  "step": 25600
         
     | 
| 1802 | 
         
            +
                },
         
     | 
| 1803 | 
         
            +
                {
         
     | 
| 1804 | 
         
            +
                  "epoch": 395.38461538461536,
         
     | 
| 1805 | 
         
            +
                  "grad_norm": 19.443572998046875,
         
     | 
| 1806 | 
         
            +
                  "learning_rate": 4.863400000000001e-06,
         
     | 
| 1807 | 
         
            +
                  "loss": 1.2275,
         
     | 
| 1808 | 
         
            +
                  "step": 25700
         
     | 
| 1809 | 
         
            +
                },
         
     | 
| 1810 | 
         
            +
                {
         
     | 
| 1811 | 
         
            +
                  "epoch": 396.9230769230769,
         
     | 
| 1812 | 
         
            +
                  "grad_norm": 42.00278091430664,
         
     | 
| 1813 | 
         
            +
                  "learning_rate": 4.8434e-06,
         
     | 
| 1814 | 
         
            +
                  "loss": 1.2542,
         
     | 
| 1815 | 
         
            +
                  "step": 25800
         
     | 
| 1816 | 
         
            +
                },
         
     | 
| 1817 | 
         
            +
                {
         
     | 
| 1818 | 
         
            +
                  "epoch": 398.46153846153845,
         
     | 
| 1819 | 
         
            +
                  "grad_norm": 45.863975524902344,
         
     | 
| 1820 | 
         
            +
                  "learning_rate": 4.8234e-06,
         
     | 
| 1821 | 
         
            +
                  "loss": 1.2425,
         
     | 
| 1822 | 
         
            +
                  "step": 25900
         
     | 
| 1823 | 
         
            +
                },
         
     | 
| 1824 | 
         
            +
                {
         
     | 
| 1825 | 
         
            +
                  "epoch": 400.0,
         
     | 
| 1826 | 
         
            +
                  "grad_norm": 51.47980499267578,
         
     | 
| 1827 | 
         
            +
                  "learning_rate": 4.8034000000000005e-06,
         
     | 
| 1828 | 
         
            +
                  "loss": 1.2434,
         
     | 
| 1829 | 
         
            +
                  "step": 26000
         
     | 
| 1830 | 
         
            +
                },
         
     | 
| 1831 | 
         
            +
                {
         
     | 
| 1832 | 
         
            +
                  "epoch": 401.53846153846155,
         
     | 
| 1833 | 
         
            +
                  "grad_norm": 38.02336502075195,
         
     | 
| 1834 | 
         
            +
                  "learning_rate": 4.783400000000001e-06,
         
     | 
| 1835 | 
         
            +
                  "loss": 1.2508,
         
     | 
| 1836 | 
         
            +
                  "step": 26100
         
     | 
| 1837 | 
         
            +
                },
         
     | 
| 1838 | 
         
            +
                {
         
     | 
| 1839 | 
         
            +
                  "epoch": 403.0769230769231,
         
     | 
| 1840 | 
         
            +
                  "grad_norm": 52.39328384399414,
         
     | 
| 1841 | 
         
            +
                  "learning_rate": 4.7634e-06,
         
     | 
| 1842 | 
         
            +
                  "loss": 1.2373,
         
     | 
| 1843 | 
         
            +
                  "step": 26200
         
     | 
| 1844 | 
         
            +
                },
         
     | 
| 1845 | 
         
            +
                {
         
     | 
| 1846 | 
         
            +
                  "epoch": 404.61538461538464,
         
     | 
| 1847 | 
         
            +
                  "grad_norm": 39.42361068725586,
         
     | 
| 1848 | 
         
            +
                  "learning_rate": 4.7434e-06,
         
     | 
| 1849 | 
         
            +
                  "loss": 1.2253,
         
     | 
| 1850 | 
         
            +
                  "step": 26300
         
     | 
| 1851 | 
         
            +
                },
         
     | 
| 1852 | 
         
            +
                {
         
     | 
| 1853 | 
         
            +
                  "epoch": 406.15384615384613,
         
     | 
| 1854 | 
         
            +
                  "grad_norm": 46.898441314697266,
         
     | 
| 1855 | 
         
            +
                  "learning_rate": 4.7234e-06,
         
     | 
| 1856 | 
         
            +
                  "loss": 1.2044,
         
     | 
| 1857 | 
         
            +
                  "step": 26400
         
     | 
| 1858 | 
         
            +
                },
         
     | 
| 1859 | 
         
            +
                {
         
     | 
| 1860 | 
         
            +
                  "epoch": 407.6923076923077,
         
     | 
| 1861 | 
         
            +
                  "grad_norm": 47.6523323059082,
         
     | 
| 1862 | 
         
            +
                  "learning_rate": 4.7034000000000006e-06,
         
     | 
| 1863 | 
         
            +
                  "loss": 1.2058,
         
     | 
| 1864 | 
         
            +
                  "step": 26500
         
     | 
| 1865 | 
         
            +
                },
         
     | 
| 1866 | 
         
            +
                {
         
     | 
| 1867 | 
         
            +
                  "epoch": 409.2307692307692,
         
     | 
| 1868 | 
         
            +
                  "grad_norm": 78.52135467529297,
         
     | 
| 1869 | 
         
            +
                  "learning_rate": 4.6834e-06,
         
     | 
| 1870 | 
         
            +
                  "loss": 1.2259,
         
     | 
| 1871 | 
         
            +
                  "step": 26600
         
     | 
| 1872 | 
         
            +
                },
         
     | 
| 1873 | 
         
            +
                {
         
     | 
| 1874 | 
         
            +
                  "epoch": 410.7692307692308,
         
     | 
| 1875 | 
         
            +
                  "grad_norm": 36.37205505371094,
         
     | 
| 1876 | 
         
            +
                  "learning_rate": 4.6634e-06,
         
     | 
| 1877 | 
         
            +
                  "loss": 1.2241,
         
     | 
| 1878 | 
         
            +
                  "step": 26700
         
     | 
| 1879 | 
         
            +
                },
         
     | 
| 1880 | 
         
            +
                {
         
     | 
| 1881 | 
         
            +
                  "epoch": 412.3076923076923,
         
     | 
| 1882 | 
         
            +
                  "grad_norm": 48.53520965576172,
         
     | 
| 1883 | 
         
            +
                  "learning_rate": 4.6434e-06,
         
     | 
| 1884 | 
         
            +
                  "loss": 1.2118,
         
     | 
| 1885 | 
         
            +
                  "step": 26800
         
     | 
| 1886 | 
         
            +
                },
         
     | 
| 1887 | 
         
            +
                {
         
     | 
| 1888 | 
         
            +
                  "epoch": 413.84615384615387,
         
     | 
| 1889 | 
         
            +
                  "grad_norm": 33.66633605957031,
         
     | 
| 1890 | 
         
            +
                  "learning_rate": 4.6234000000000005e-06,
         
     | 
| 1891 | 
         
            +
                  "loss": 1.241,
         
     | 
| 1892 | 
         
            +
                  "step": 26900
         
     | 
| 1893 | 
         
            +
                },
         
     | 
| 1894 | 
         
            +
                {
         
     | 
| 1895 | 
         
            +
                  "epoch": 415.38461538461536,
         
     | 
| 1896 | 
         
            +
                  "grad_norm": 60.33393096923828,
         
     | 
| 1897 | 
         
            +
                  "learning_rate": 4.603400000000001e-06,
         
     | 
| 1898 | 
         
            +
                  "loss": 1.2208,
         
     | 
| 1899 | 
         
            +
                  "step": 27000
         
     | 
| 1900 | 
         
            +
                },
         
     | 
| 1901 | 
         
            +
                {
         
     | 
| 1902 | 
         
            +
                  "epoch": 416.9230769230769,
         
     | 
| 1903 | 
         
            +
                  "grad_norm": 96.51435089111328,
         
     | 
| 1904 | 
         
            +
                  "learning_rate": 4.583400000000001e-06,
         
     | 
| 1905 | 
         
            +
                  "loss": 1.1945,
         
     | 
| 1906 | 
         
            +
                  "step": 27100
         
     | 
| 1907 | 
         
            +
                },
         
     | 
| 1908 | 
         
            +
                {
         
     | 
| 1909 | 
         
            +
                  "epoch": 418.46153846153845,
         
     | 
| 1910 | 
         
            +
                  "grad_norm": 48.80552291870117,
         
     | 
| 1911 | 
         
            +
                  "learning_rate": 4.5634e-06,
         
     | 
| 1912 | 
         
            +
                  "loss": 1.2249,
         
     | 
| 1913 | 
         
            +
                  "step": 27200
         
     | 
| 1914 | 
         
            +
                },
         
     | 
| 1915 | 
         
            +
                {
         
     | 
| 1916 | 
         
            +
                  "epoch": 420.0,
         
     | 
| 1917 | 
         
            +
                  "grad_norm": 46.613800048828125,
         
     | 
| 1918 | 
         
            +
                  "learning_rate": 4.5434e-06,
         
     | 
| 1919 | 
         
            +
                  "loss": 1.2164,
         
     | 
| 1920 | 
         
            +
                  "step": 27300
         
     | 
| 1921 | 
         
            +
                },
         
     | 
| 1922 | 
         
            +
                {
         
     | 
| 1923 | 
         
            +
                  "epoch": 421.53846153846155,
         
     | 
| 1924 | 
         
            +
                  "grad_norm": 66.00172424316406,
         
     | 
| 1925 | 
         
            +
                  "learning_rate": 4.523400000000001e-06,
         
     | 
| 1926 | 
         
            +
                  "loss": 1.2302,
         
     | 
| 1927 | 
         
            +
                  "step": 27400
         
     | 
| 1928 | 
         
            +
                },
         
     | 
| 1929 | 
         
            +
                {
         
     | 
| 1930 | 
         
            +
                  "epoch": 423.0769230769231,
         
     | 
| 1931 | 
         
            +
                  "grad_norm": 114.08313751220703,
         
     | 
| 1932 | 
         
            +
                  "learning_rate": 4.503400000000001e-06,
         
     | 
| 1933 | 
         
            +
                  "loss": 1.215,
         
     | 
| 1934 | 
         
            +
                  "step": 27500
         
     | 
| 1935 | 
         
            +
                },
         
     | 
| 1936 | 
         
            +
                {
         
     | 
| 1937 | 
         
            +
                  "epoch": 424.61538461538464,
         
     | 
| 1938 | 
         
            +
                  "grad_norm": 81.00666046142578,
         
     | 
| 1939 | 
         
            +
                  "learning_rate": 4.4834e-06,
         
     | 
| 1940 | 
         
            +
                  "loss": 1.2031,
         
     | 
| 1941 | 
         
            +
                  "step": 27600
         
     | 
| 1942 | 
         
            +
                },
         
     | 
| 1943 | 
         
            +
                {
         
     | 
| 1944 | 
         
            +
                  "epoch": 426.15384615384613,
         
     | 
| 1945 | 
         
            +
                  "grad_norm": 41.911373138427734,
         
     | 
| 1946 | 
         
            +
                  "learning_rate": 4.4634e-06,
         
     | 
| 1947 | 
         
            +
                  "loss": 1.1958,
         
     | 
| 1948 | 
         
            +
                  "step": 27700
         
     | 
| 1949 | 
         
            +
                },
         
     | 
| 1950 | 
         
            +
                {
         
     | 
| 1951 | 
         
            +
                  "epoch": 427.6923076923077,
         
     | 
| 1952 | 
         
            +
                  "grad_norm": 643.6279907226562,
         
     | 
| 1953 | 
         
            +
                  "learning_rate": 4.4434000000000005e-06,
         
     | 
| 1954 | 
         
            +
                  "loss": 1.2033,
         
     | 
| 1955 | 
         
            +
                  "step": 27800
         
     | 
| 1956 | 
         
            +
                },
         
     | 
| 1957 | 
         
            +
                {
         
     | 
| 1958 | 
         
            +
                  "epoch": 429.2307692307692,
         
     | 
| 1959 | 
         
            +
                  "grad_norm": 35.13188552856445,
         
     | 
| 1960 | 
         
            +
                  "learning_rate": 4.423400000000001e-06,
         
     | 
| 1961 | 
         
            +
                  "loss": 1.2025,
         
     | 
| 1962 | 
         
            +
                  "step": 27900
         
     | 
| 1963 | 
         
            +
                },
         
     | 
| 1964 | 
         
            +
                {
         
     | 
| 1965 | 
         
            +
                  "epoch": 430.7692307692308,
         
     | 
| 1966 | 
         
            +
                  "grad_norm": 27.267776489257812,
         
     | 
| 1967 | 
         
            +
                  "learning_rate": 4.4034e-06,
         
     | 
| 1968 | 
         
            +
                  "loss": 1.2085,
         
     | 
| 1969 | 
         
            +
                  "step": 28000
         
     | 
| 1970 | 
         
            +
                },
         
     | 
| 1971 | 
         
            +
                {
         
     | 
| 1972 | 
         
            +
                  "epoch": 432.3076923076923,
         
     | 
| 1973 | 
         
            +
                  "grad_norm": 68.7784652709961,
         
     | 
| 1974 | 
         
            +
                  "learning_rate": 4.3834e-06,
         
     | 
| 1975 | 
         
            +
                  "loss": 1.202,
         
     | 
| 1976 | 
         
            +
                  "step": 28100
         
     | 
| 1977 | 
         
            +
                },
         
     | 
| 1978 | 
         
            +
                {
         
     | 
| 1979 | 
         
            +
                  "epoch": 433.84615384615387,
         
     | 
| 1980 | 
         
            +
                  "grad_norm": 119.0069351196289,
         
     | 
| 1981 | 
         
            +
                  "learning_rate": 4.3634000000000004e-06,
         
     | 
| 1982 | 
         
            +
                  "loss": 1.1972,
         
     | 
| 1983 | 
         
            +
                  "step": 28200
         
     | 
| 1984 | 
         
            +
                },
         
     | 
| 1985 | 
         
            +
                {
         
     | 
| 1986 | 
         
            +
                  "epoch": 435.38461538461536,
         
     | 
| 1987 | 
         
            +
                  "grad_norm": 80.1543960571289,
         
     | 
| 1988 | 
         
            +
                  "learning_rate": 4.3436e-06,
         
     | 
| 1989 | 
         
            +
                  "loss": 1.1966,
         
     | 
| 1990 | 
         
            +
                  "step": 28300
         
     | 
| 1991 | 
         
            +
                },
         
     | 
| 1992 | 
         
            +
                {
         
     | 
| 1993 | 
         
            +
                  "epoch": 436.9230769230769,
         
     | 
| 1994 | 
         
            +
                  "grad_norm": 54.1822509765625,
         
     | 
| 1995 | 
         
            +
                  "learning_rate": 4.3236e-06,
         
     | 
| 1996 | 
         
            +
                  "loss": 1.1858,
         
     | 
| 1997 | 
         
            +
                  "step": 28400
         
     | 
| 1998 | 
         
            +
                },
         
     | 
| 1999 | 
         
            +
                {
         
     | 
| 2000 | 
         
            +
                  "epoch": 438.46153846153845,
         
     | 
| 2001 | 
         
            +
                  "grad_norm": 145.3723602294922,
         
     | 
| 2002 | 
         
            +
                  "learning_rate": 4.303600000000001e-06,
         
     | 
| 2003 | 
         
            +
                  "loss": 1.1921,
         
     | 
| 2004 | 
         
            +
                  "step": 28500
         
     | 
| 2005 | 
         
            +
                },
         
     | 
| 2006 | 
         
            +
                {
         
     | 
| 2007 | 
         
            +
                  "epoch": 440.0,
         
     | 
| 2008 | 
         
            +
                  "grad_norm": 65.41217041015625,
         
     | 
| 2009 | 
         
            +
                  "learning_rate": 4.283600000000001e-06,
         
     | 
| 2010 | 
         
            +
                  "loss": 1.2062,
         
     | 
| 2011 | 
         
            +
                  "step": 28600
         
     | 
| 2012 | 
         
            +
                },
         
     | 
| 2013 | 
         
            +
                {
         
     | 
| 2014 | 
         
            +
                  "epoch": 441.53846153846155,
         
     | 
| 2015 | 
         
            +
                  "grad_norm": 91.25973510742188,
         
     | 
| 2016 | 
         
            +
                  "learning_rate": 4.263800000000001e-06,
         
     | 
| 2017 | 
         
            +
                  "loss": 1.1916,
         
     | 
| 2018 | 
         
            +
                  "step": 28700
         
     | 
| 2019 | 
         
            +
                },
         
     | 
| 2020 | 
         
            +
                {
         
     | 
| 2021 | 
         
            +
                  "epoch": 443.0769230769231,
         
     | 
| 2022 | 
         
            +
                  "grad_norm": 52.53120803833008,
         
     | 
| 2023 | 
         
            +
                  "learning_rate": 4.2438e-06,
         
     | 
| 2024 | 
         
            +
                  "loss": 1.1725,
         
     | 
| 2025 | 
         
            +
                  "step": 28800
         
     | 
| 2026 | 
         
            +
                },
         
     | 
| 2027 | 
         
            +
                {
         
     | 
| 2028 | 
         
            +
                  "epoch": 444.61538461538464,
         
     | 
| 2029 | 
         
            +
                  "grad_norm": 65.57294464111328,
         
     | 
| 2030 | 
         
            +
                  "learning_rate": 4.2238e-06,
         
     | 
| 2031 | 
         
            +
                  "loss": 1.2011,
         
     | 
| 2032 | 
         
            +
                  "step": 28900
         
     | 
| 2033 | 
         
            +
                },
         
     | 
| 2034 | 
         
            +
                {
         
     | 
| 2035 | 
         
            +
                  "epoch": 446.15384615384613,
         
     | 
| 2036 | 
         
            +
                  "grad_norm": 51.5538444519043,
         
     | 
| 2037 | 
         
            +
                  "learning_rate": 4.2038e-06,
         
     | 
| 2038 | 
         
            +
                  "loss": 1.1634,
         
     | 
| 2039 | 
         
            +
                  "step": 29000
         
     | 
| 2040 | 
         
            +
                },
         
     | 
| 2041 | 
         
            +
                {
         
     | 
| 2042 | 
         
            +
                  "epoch": 447.6923076923077,
         
     | 
| 2043 | 
         
            +
                  "grad_norm": 108.87830352783203,
         
     | 
| 2044 | 
         
            +
                  "learning_rate": 4.1838000000000005e-06,
         
     | 
| 2045 | 
         
            +
                  "loss": 1.2041,
         
     | 
| 2046 | 
         
            +
                  "step": 29100
         
     | 
| 2047 | 
         
            +
                },
         
     | 
| 2048 | 
         
            +
                {
         
     | 
| 2049 | 
         
            +
                  "epoch": 449.2307692307692,
         
     | 
| 2050 | 
         
            +
                  "grad_norm": 126.54178619384766,
         
     | 
| 2051 | 
         
            +
                  "learning_rate": 4.1638e-06,
         
     | 
| 2052 | 
         
            +
                  "loss": 1.172,
         
     | 
| 2053 | 
         
            +
                  "step": 29200
         
     | 
| 2054 | 
         
            +
                },
         
     | 
| 2055 | 
         
            +
                {
         
     | 
| 2056 | 
         
            +
                  "epoch": 450.7692307692308,
         
     | 
| 2057 | 
         
            +
                  "grad_norm": 58.80292510986328,
         
     | 
| 2058 | 
         
            +
                  "learning_rate": 4.143800000000001e-06,
         
     | 
| 2059 | 
         
            +
                  "loss": 1.1607,
         
     | 
| 2060 | 
         
            +
                  "step": 29300
         
     | 
| 2061 | 
         
            +
                },
         
     | 
| 2062 | 
         
            +
                {
         
     | 
| 2063 | 
         
            +
                  "epoch": 452.3076923076923,
         
     | 
| 2064 | 
         
            +
                  "grad_norm": 27.22450828552246,
         
     | 
| 2065 | 
         
            +
                  "learning_rate": 4.1238e-06,
         
     | 
| 2066 | 
         
            +
                  "loss": 1.205,
         
     | 
| 2067 | 
         
            +
                  "step": 29400
         
     | 
| 2068 | 
         
            +
                },
         
     | 
| 2069 | 
         
            +
                {
         
     | 
| 2070 | 
         
            +
                  "epoch": 453.84615384615387,
         
     | 
| 2071 | 
         
            +
                  "grad_norm": 49.21129608154297,
         
     | 
| 2072 | 
         
            +
                  "learning_rate": 4.1038e-06,
         
     | 
| 2073 | 
         
            +
                  "loss": 1.168,
         
     | 
| 2074 | 
         
            +
                  "step": 29500
         
     | 
| 2075 | 
         
            +
                }
         
     | 
| 2076 | 
         
            +
              ],
         
     | 
| 2077 | 
         
            +
              "logging_steps": 100,
         
     | 
| 2078 | 
         
            +
              "max_steps": 50000,
         
     | 
| 2079 | 
         
            +
              "num_input_tokens_seen": 0,
         
     | 
| 2080 | 
         
            +
              "num_train_epochs": 770,
         
     | 
| 2081 | 
         
            +
              "save_steps": 500,
         
     | 
| 2082 | 
         
            +
              "stateful_callbacks": {
         
     | 
| 2083 | 
         
            +
                "TrainerControl": {
         
     | 
| 2084 | 
         
            +
                  "args": {
         
     | 
| 2085 | 
         
            +
                    "should_epoch_stop": false,
         
     | 
| 2086 | 
         
            +
                    "should_evaluate": false,
         
     | 
| 2087 | 
         
            +
                    "should_log": false,
         
     | 
| 2088 | 
         
            +
                    "should_save": true,
         
     | 
| 2089 | 
         
            +
                    "should_training_stop": false
         
     | 
| 2090 | 
         
            +
                  },
         
     | 
| 2091 | 
         
            +
                  "attributes": {}
         
     | 
| 2092 | 
         
            +
                }
         
     | 
| 2093 | 
         
            +
              },
         
     | 
| 2094 | 
         
            +
              "total_flos": 1.1276173403136e+20,
         
     | 
| 2095 | 
         
            +
              "train_batch_size": 8,
         
     | 
| 2096 | 
         
            +
              "trial_name": null,
         
     | 
| 2097 | 
         
            +
              "trial_params": null
         
     | 
| 2098 | 
         
            +
            }
         
     | 
    	
        checkpoint-29500/training_args.bin
    ADDED
    
    | 
         @@ -0,0 +1,3 @@ 
     | 
|
| 
         | 
|
| 
         | 
|
| 
         | 
| 
         | 
|
| 1 | 
         
            +
            version https://git-lfs.github.com/spec/v1
         
     | 
| 2 | 
         
            +
            oid sha256:ee77453dae7076acf919eb7bcd8ccb5a082573a80b4f2c85a6a7d7ad1edcbedf
         
     | 
| 3 | 
         
            +
            size 5240
         
     |