Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: t1_5k_v1_tag5
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# t1_5k_v1_tag5
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the t1_5k_v1_tag5 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2328
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3414        | 0.4016 | 100  | 0.2445          |
+| 0.2978        | 0.8032 | 200  | 0.2342          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.23280136287212372,
+    "eval_runtime": 0.91,
+    "eval_samples_per_second": 2.198,
+    "eval_steps_per_second": 1.099,
+    "total_flos": 47804940288000.0,
+    "train_loss": 0.3352415738215887,
+    "train_runtime": 943.4636,
+    "train_samples_per_second": 2.108,
+    "train_steps_per_second": 0.264
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.23280136287212372,
+    "eval_runtime": 0.91,
+    "eval_samples_per_second": 2.198,
+    "eval_steps_per_second": 1.099
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef747c9a14550b6cf860821bbfd45607e9adbb4fb87727fa385705f81ff0a657
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aa9d4b7afd118bebfec57c812120b7224dd16924f20dcf2f22d19b83b431dfa
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb81abddddfc80deca967e5105cf8d3ba2660eceb5262957d99bab2f54abdeb2
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbc5e02bb781ca59b031b74e3127bc7df77787645cb17ac7cc7a281520f0ed8
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 47804940288000.0,
+    "train_loss": 0.3352415738215887,
+    "train_runtime": 943.4636,
+    "train_samples_per_second": 2.108,
+    "train_steps_per_second": 0.264
+}

trainer_log.jsonl

@@ -0,0 +1,252 @@
+{"current_steps": 1, "total_steps": 249, "loss": 0.7293, "lr": 4.99980102188921e-06, "epoch": 0.004016064257028112, "percentage": 0.4, "elapsed_time": "0:00:05", "remaining_time": "0:20:49"}
+{"current_steps": 2, "total_steps": 249, "loss": 0.7912, "lr": 4.99920411923067e-06, "epoch": 0.008032128514056224, "percentage": 0.8, "elapsed_time": "0:00:08", "remaining_time": "0:18:10"}
+{"current_steps": 3, "total_steps": 249, "loss": 0.6689, "lr": 4.998209387040829e-06, "epoch": 0.012048192771084338, "percentage": 1.2, "elapsed_time": "0:00:12", "remaining_time": "0:17:08"}
+{"current_steps": 4, "total_steps": 249, "loss": 0.6017, "lr": 4.996816983663635e-06, "epoch": 0.01606425702811245, "percentage": 1.61, "elapsed_time": "0:00:16", "remaining_time": "0:16:38"}
+{"current_steps": 5, "total_steps": 249, "loss": 0.6071, "lr": 4.995027130745322e-06, "epoch": 0.020080321285140562, "percentage": 2.01, "elapsed_time": "0:00:19", "remaining_time": "0:16:06"}
+{"current_steps": 6, "total_steps": 249, "loss": 0.5896, "lr": 4.992840113199131e-06, "epoch": 0.024096385542168676, "percentage": 2.41, "elapsed_time": "0:00:23", "remaining_time": "0:15:54"}
+{"current_steps": 7, "total_steps": 249, "loss": 0.5191, "lr": 4.990256279159958e-06, "epoch": 0.028112449799196786, "percentage": 2.81, "elapsed_time": "0:00:27", "remaining_time": "0:15:43"}
+{"current_steps": 8, "total_steps": 249, "loss": 0.4819, "lr": 4.9872760399289365e-06, "epoch": 0.0321285140562249, "percentage": 3.21, "elapsed_time": "0:00:31", "remaining_time": "0:15:35"}
+{"current_steps": 9, "total_steps": 249, "loss": 0.5347, "lr": 4.983899869907963e-06, "epoch": 0.03614457831325301, "percentage": 3.61, "elapsed_time": "0:00:34", "remaining_time": "0:15:24"}
+{"current_steps": 10, "total_steps": 249, "loss": 0.5212, "lr": 4.980128306524184e-06, "epoch": 0.040160642570281124, "percentage": 4.02, "elapsed_time": "0:00:38", "remaining_time": "0:15:15"}
+{"current_steps": 11, "total_steps": 249, "loss": 0.4289, "lr": 4.975961950144444e-06, "epoch": 0.04417670682730924, "percentage": 4.42, "elapsed_time": "0:00:42", "remaining_time": "0:15:11"}
+{"current_steps": 12, "total_steps": 249, "loss": 0.5039, "lr": 4.971401463979722e-06, "epoch": 0.04819277108433735, "percentage": 4.82, "elapsed_time": "0:00:45", "remaining_time": "0:15:03"}
+{"current_steps": 13, "total_steps": 249, "loss": 0.4403, "lr": 4.966447573979553e-06, "epoch": 0.05220883534136546, "percentage": 5.22, "elapsed_time": "0:00:49", "remaining_time": "0:14:57"}
+{"current_steps": 14, "total_steps": 249, "loss": 0.4045, "lr": 4.961101068716477e-06, "epoch": 0.05622489959839357, "percentage": 5.62, "elapsed_time": "0:00:53", "remaining_time": "0:14:49"}
+{"current_steps": 15, "total_steps": 249, "loss": 0.4462, "lr": 4.955362799260507e-06, "epoch": 0.060240963855421686, "percentage": 6.02, "elapsed_time": "0:00:56", "remaining_time": "0:14:44"}
+{"current_steps": 16, "total_steps": 249, "loss": 0.4087, "lr": 4.949233679043655e-06, "epoch": 0.0642570281124498, "percentage": 6.43, "elapsed_time": "0:01:00", "remaining_time": "0:14:39"}
+{"current_steps": 17, "total_steps": 249, "loss": 0.369, "lr": 4.942714683714531e-06, "epoch": 0.06827309236947791, "percentage": 6.83, "elapsed_time": "0:01:03", "remaining_time": "0:14:32"}
+{"current_steps": 18, "total_steps": 249, "loss": 0.379, "lr": 4.935806850983034e-06, "epoch": 0.07228915662650602, "percentage": 7.23, "elapsed_time": "0:01:07", "remaining_time": "0:14:26"}
+{"current_steps": 19, "total_steps": 249, "loss": 0.4172, "lr": 4.928511280455169e-06, "epoch": 0.07630522088353414, "percentage": 7.63, "elapsed_time": "0:01:11", "remaining_time": "0:14:20"}
+{"current_steps": 20, "total_steps": 249, "loss": 0.4468, "lr": 4.92082913345801e-06, "epoch": 0.08032128514056225, "percentage": 8.03, "elapsed_time": "0:01:14", "remaining_time": "0:14:16"}
+{"current_steps": 21, "total_steps": 249, "loss": 0.536, "lr": 4.912761632854834e-06, "epoch": 0.08433734939759036, "percentage": 8.43, "elapsed_time": "0:01:18", "remaining_time": "0:14:11"}
+{"current_steps": 22, "total_steps": 249, "loss": 0.4384, "lr": 4.904310062850463e-06, "epoch": 0.08835341365461848, "percentage": 8.84, "elapsed_time": "0:01:22", "remaining_time": "0:14:06"}
+{"current_steps": 23, "total_steps": 249, "loss": 0.4502, "lr": 4.895475768786843e-06, "epoch": 0.09236947791164658, "percentage": 9.24, "elapsed_time": "0:01:25", "remaining_time": "0:14:02"}
+{"current_steps": 24, "total_steps": 249, "loss": 0.3537, "lr": 4.8862601569288885e-06, "epoch": 0.0963855421686747, "percentage": 9.64, "elapsed_time": "0:01:29", "remaining_time": "0:13:57"}
+{"current_steps": 25, "total_steps": 249, "loss": 0.3975, "lr": 4.8766646942406305e-06, "epoch": 0.10040160642570281, "percentage": 10.04, "elapsed_time": "0:01:32", "remaining_time": "0:13:52"}
+{"current_steps": 26, "total_steps": 249, "loss": 0.3857, "lr": 4.866690908151698e-06, "epoch": 0.10441767068273092, "percentage": 10.44, "elapsed_time": "0:01:36", "remaining_time": "0:13:46"}
+{"current_steps": 27, "total_steps": 249, "loss": 0.3883, "lr": 4.8563403863141825e-06, "epoch": 0.10843373493975904, "percentage": 10.84, "elapsed_time": "0:01:40", "remaining_time": "0:13:42"}
+{"current_steps": 28, "total_steps": 249, "loss": 0.4982, "lr": 4.8456147763499085e-06, "epoch": 0.11244979919678715, "percentage": 11.24, "elapsed_time": "0:01:43", "remaining_time": "0:13:38"}
+{"current_steps": 29, "total_steps": 249, "loss": 0.3641, "lr": 4.834515785588161e-06, "epoch": 0.11646586345381527, "percentage": 11.65, "elapsed_time": "0:01:47", "remaining_time": "0:13:33"}
+{"current_steps": 30, "total_steps": 249, "loss": 0.334, "lr": 4.823045180793914e-06, "epoch": 0.12048192771084337, "percentage": 12.05, "elapsed_time": "0:01:50", "remaining_time": "0:13:30"}
+{"current_steps": 31, "total_steps": 249, "loss": 0.3852, "lr": 4.811204787886581e-06, "epoch": 0.12449799196787148, "percentage": 12.45, "elapsed_time": "0:01:54", "remaining_time": "0:13:26"}
+{"current_steps": 32, "total_steps": 249, "loss": 0.4285, "lr": 4.798996491649374e-06, "epoch": 0.1285140562248996, "percentage": 12.85, "elapsed_time": "0:01:58", "remaining_time": "0:13:21"}
+{"current_steps": 33, "total_steps": 249, "loss": 0.4512, "lr": 4.786422235429269e-06, "epoch": 0.13253012048192772, "percentage": 13.25, "elapsed_time": "0:02:01", "remaining_time": "0:13:18"}
+{"current_steps": 34, "total_steps": 249, "loss": 0.3162, "lr": 4.773484020827663e-06, "epoch": 0.13654618473895583, "percentage": 13.65, "elapsed_time": "0:02:05", "remaining_time": "0:13:13"}
+{"current_steps": 35, "total_steps": 249, "loss": 0.3483, "lr": 4.760183907381757e-06, "epoch": 0.14056224899598393, "percentage": 14.06, "elapsed_time": "0:02:09", "remaining_time": "0:13:10"}
+{"current_steps": 36, "total_steps": 249, "loss": 0.3528, "lr": 4.746524012236706e-06, "epoch": 0.14457831325301204, "percentage": 14.46, "elapsed_time": "0:02:12", "remaining_time": "0:13:06"}
+{"current_steps": 37, "total_steps": 249, "loss": 0.2981, "lr": 4.732506509808615e-06, "epoch": 0.14859437751004015, "percentage": 14.86, "elapsed_time": "0:02:16", "remaining_time": "0:13:02"}
+{"current_steps": 38, "total_steps": 249, "loss": 0.3184, "lr": 4.718133631438404e-06, "epoch": 0.15261044176706828, "percentage": 15.26, "elapsed_time": "0:02:20", "remaining_time": "0:12:59"}
+{"current_steps": 39, "total_steps": 249, "loss": 0.3176, "lr": 4.703407665036622e-06, "epoch": 0.1566265060240964, "percentage": 15.66, "elapsed_time": "0:02:24", "remaining_time": "0:12:55"}
+{"current_steps": 40, "total_steps": 249, "loss": 0.4134, "lr": 4.688330954719248e-06, "epoch": 0.1606425702811245, "percentage": 16.06, "elapsed_time": "0:02:27", "remaining_time": "0:12:51"}
+{"current_steps": 41, "total_steps": 249, "loss": 0.3554, "lr": 4.67290590043455e-06, "epoch": 0.1646586345381526, "percentage": 16.47, "elapsed_time": "0:02:31", "remaining_time": "0:12:47"}
+{"current_steps": 42, "total_steps": 249, "loss": 0.3823, "lr": 4.657134957581057e-06, "epoch": 0.1686746987951807, "percentage": 16.87, "elapsed_time": "0:02:35", "remaining_time": "0:12:44"}
+{"current_steps": 43, "total_steps": 249, "loss": 0.3576, "lr": 4.641020636616701e-06, "epoch": 0.17269076305220885, "percentage": 17.27, "elapsed_time": "0:02:38", "remaining_time": "0:12:40"}
+{"current_steps": 44, "total_steps": 249, "loss": 0.3735, "lr": 4.624565502659194e-06, "epoch": 0.17670682730923695, "percentage": 17.67, "elapsed_time": "0:02:42", "remaining_time": "0:12:36"}
+{"current_steps": 45, "total_steps": 249, "loss": 0.4104, "lr": 4.607772175077712e-06, "epoch": 0.18072289156626506, "percentage": 18.07, "elapsed_time": "0:02:46", "remaining_time": "0:12:32"}
+{"current_steps": 46, "total_steps": 249, "loss": 0.3666, "lr": 4.59064332707593e-06, "epoch": 0.18473895582329317, "percentage": 18.47, "elapsed_time": "0:02:49", "remaining_time": "0:12:28"}
+{"current_steps": 47, "total_steps": 249, "loss": 0.3329, "lr": 4.573181685266502e-06, "epoch": 0.18875502008032127, "percentage": 18.88, "elapsed_time": "0:02:53", "remaining_time": "0:12:24"}
+{"current_steps": 48, "total_steps": 249, "loss": 0.3038, "lr": 4.555390029237026e-06, "epoch": 0.1927710843373494, "percentage": 19.28, "elapsed_time": "0:02:56", "remaining_time": "0:12:20"}
+{"current_steps": 49, "total_steps": 249, "loss": 0.3932, "lr": 4.537271191107585e-06, "epoch": 0.19678714859437751, "percentage": 19.68, "elapsed_time": "0:03:00", "remaining_time": "0:12:16"}
+{"current_steps": 50, "total_steps": 249, "loss": 0.42, "lr": 4.518828055079925e-06, "epoch": 0.20080321285140562, "percentage": 20.08, "elapsed_time": "0:03:04", "remaining_time": "0:12:12"}
+{"current_steps": 51, "total_steps": 249, "loss": 0.2897, "lr": 4.5000635569783365e-06, "epoch": 0.20481927710843373, "percentage": 20.48, "elapsed_time": "0:03:07", "remaining_time": "0:12:09"}
+{"current_steps": 52, "total_steps": 249, "loss": 0.3137, "lr": 4.480980683782326e-06, "epoch": 0.20883534136546184, "percentage": 20.88, "elapsed_time": "0:03:11", "remaining_time": "0:12:05"}
+{"current_steps": 53, "total_steps": 249, "loss": 0.3576, "lr": 4.461582473151137e-06, "epoch": 0.21285140562248997, "percentage": 21.29, "elapsed_time": "0:03:15", "remaining_time": "0:12:02"}
+{"current_steps": 54, "total_steps": 249, "loss": 0.3261, "lr": 4.4418720129402145e-06, "epoch": 0.21686746987951808, "percentage": 21.69, "elapsed_time": "0:03:18", "remaining_time": "0:11:58"}
+{"current_steps": 55, "total_steps": 249, "loss": 0.3665, "lr": 4.4218524407096665e-06, "epoch": 0.22088353413654618, "percentage": 22.09, "elapsed_time": "0:03:22", "remaining_time": "0:11:54"}
+{"current_steps": 56, "total_steps": 249, "loss": 0.3121, "lr": 4.401526943224822e-06, "epoch": 0.2248995983935743, "percentage": 22.49, "elapsed_time": "0:03:26", "remaining_time": "0:11:50"}
+{"current_steps": 57, "total_steps": 249, "loss": 0.3299, "lr": 4.3808987559489536e-06, "epoch": 0.2289156626506024, "percentage": 22.89, "elapsed_time": "0:03:29", "remaining_time": "0:11:46"}
+{"current_steps": 58, "total_steps": 249, "loss": 0.3317, "lr": 4.359971162528248e-06, "epoch": 0.23293172690763053, "percentage": 23.29, "elapsed_time": "0:03:33", "remaining_time": "0:11:42"}
+{"current_steps": 59, "total_steps": 249, "loss": 0.3076, "lr": 4.338747494269105e-06, "epoch": 0.23694779116465864, "percentage": 23.69, "elapsed_time": "0:03:37", "remaining_time": "0:11:39"}
+{"current_steps": 60, "total_steps": 249, "loss": 0.3275, "lr": 4.317231129607859e-06, "epoch": 0.24096385542168675, "percentage": 24.1, "elapsed_time": "0:03:40", "remaining_time": "0:11:35"}
+{"current_steps": 61, "total_steps": 249, "loss": 0.3841, "lr": 4.295425493572982e-06, "epoch": 0.24497991967871485, "percentage": 24.5, "elapsed_time": "0:03:44", "remaining_time": "0:11:31"}
+{"current_steps": 62, "total_steps": 249, "loss": 0.324, "lr": 4.273334057239884e-06, "epoch": 0.24899598393574296, "percentage": 24.9, "elapsed_time": "0:03:48", "remaining_time": "0:11:27"}
+{"current_steps": 63, "total_steps": 249, "loss": 0.308, "lr": 4.2509603371783776e-06, "epoch": 0.25301204819277107, "percentage": 25.3, "elapsed_time": "0:03:51", "remaining_time": "0:11:23"}
+{"current_steps": 64, "total_steps": 249, "loss": 0.3522, "lr": 4.228307894892902e-06, "epoch": 0.2570281124497992, "percentage": 25.7, "elapsed_time": "0:03:55", "remaining_time": "0:11:19"}
+{"current_steps": 65, "total_steps": 249, "loss": 0.2901, "lr": 4.205380336255594e-06, "epoch": 0.26104417670682734, "percentage": 26.1, "elapsed_time": "0:03:58", "remaining_time": "0:11:15"}
+{"current_steps": 66, "total_steps": 249, "loss": 0.348, "lr": 4.1821813109322975e-06, "epoch": 0.26506024096385544, "percentage": 26.51, "elapsed_time": "0:04:02", "remaining_time": "0:11:11"}
+{"current_steps": 67, "total_steps": 249, "loss": 0.3179, "lr": 4.158714511801595e-06, "epoch": 0.26907630522088355, "percentage": 26.91, "elapsed_time": "0:04:06", "remaining_time": "0:11:08"}
+{"current_steps": 68, "total_steps": 249, "loss": 0.2958, "lr": 4.134983674366974e-06, "epoch": 0.27309236947791166, "percentage": 27.31, "elapsed_time": "0:04:09", "remaining_time": "0:11:04"}
+{"current_steps": 69, "total_steps": 249, "loss": 0.3342, "lr": 4.110992576162193e-06, "epoch": 0.27710843373493976, "percentage": 27.71, "elapsed_time": "0:04:13", "remaining_time": "0:11:00"}
+{"current_steps": 70, "total_steps": 249, "loss": 0.3847, "lr": 4.08674503614997e-06, "epoch": 0.28112449799196787, "percentage": 28.11, "elapsed_time": "0:04:16", "remaining_time": "0:10:57"}
+{"current_steps": 71, "total_steps": 249, "loss": 0.3467, "lr": 4.062244914114068e-06, "epoch": 0.285140562248996, "percentage": 28.51, "elapsed_time": "0:04:20", "remaining_time": "0:10:53"}
+{"current_steps": 72, "total_steps": 249, "loss": 0.3367, "lr": 4.037496110044885e-06, "epoch": 0.2891566265060241, "percentage": 28.92, "elapsed_time": "0:04:24", "remaining_time": "0:10:49"}
+{"current_steps": 73, "total_steps": 249, "loss": 0.2797, "lr": 4.012502563518641e-06, "epoch": 0.2931726907630522, "percentage": 29.32, "elapsed_time": "0:04:27", "remaining_time": "0:10:46"}
+{"current_steps": 74, "total_steps": 249, "loss": 0.3253, "lr": 3.987268253070273e-06, "epoch": 0.2971887550200803, "percentage": 29.72, "elapsed_time": "0:04:31", "remaining_time": "0:10:42"}
+{"current_steps": 75, "total_steps": 249, "loss": 0.2731, "lr": 3.961797195560118e-06, "epoch": 0.30120481927710846, "percentage": 30.12, "elapsed_time": "0:04:35", "remaining_time": "0:10:38"}
+{"current_steps": 76, "total_steps": 249, "loss": 0.3526, "lr": 3.936093445534498e-06, "epoch": 0.30522088353413657, "percentage": 30.52, "elapsed_time": "0:04:38", "remaining_time": "0:10:35"}
+{"current_steps": 77, "total_steps": 249, "loss": 0.3421, "lr": 3.910161094580309e-06, "epoch": 0.3092369477911647, "percentage": 30.92, "elapsed_time": "0:04:42", "remaining_time": "0:10:31"}
+{"current_steps": 78, "total_steps": 249, "loss": 0.3119, "lr": 3.884004270673711e-06, "epoch": 0.3132530120481928, "percentage": 31.33, "elapsed_time": "0:04:46", "remaining_time": "0:10:27"}
+{"current_steps": 79, "total_steps": 249, "loss": 0.3081, "lr": 3.857627137523031e-06, "epoch": 0.3172690763052209, "percentage": 31.73, "elapsed_time": "0:04:49", "remaining_time": "0:10:23"}
+{"current_steps": 80, "total_steps": 249, "loss": 0.3021, "lr": 3.831033893905965e-06, "epoch": 0.321285140562249, "percentage": 32.13, "elapsed_time": "0:04:53", "remaining_time": "0:10:20"}
+{"current_steps": 81, "total_steps": 249, "loss": 0.2977, "lr": 3.8042287730012117e-06, "epoch": 0.3253012048192771, "percentage": 32.53, "elapsed_time": "0:04:57", "remaining_time": "0:10:16"}
+{"current_steps": 82, "total_steps": 249, "loss": 0.3607, "lr": 3.7772160417146265e-06, "epoch": 0.3293172690763052, "percentage": 32.93, "elapsed_time": "0:05:00", "remaining_time": "0:10:12"}
+{"current_steps": 83, "total_steps": 249, "loss": 0.3549, "lr": 3.7500000000000005e-06, "epoch": 0.3333333333333333, "percentage": 33.33, "elapsed_time": "0:05:04", "remaining_time": "0:10:09"}
+{"current_steps": 84, "total_steps": 249, "loss": 0.3159, "lr": 3.7225849801745835e-06, "epoch": 0.3373493975903614, "percentage": 33.73, "elapsed_time": "0:05:08", "remaining_time": "0:10:05"}
+{"current_steps": 85, "total_steps": 249, "loss": 0.3472, "lr": 3.694975346229458e-06, "epoch": 0.3413654618473896, "percentage": 34.14, "elapsed_time": "0:05:11", "remaining_time": "0:10:01"}
+{"current_steps": 86, "total_steps": 249, "loss": 0.3088, "lr": 3.6671754931348647e-06, "epoch": 0.3453815261044177, "percentage": 34.54, "elapsed_time": "0:05:15", "remaining_time": "0:09:58"}
+{"current_steps": 87, "total_steps": 249, "loss": 0.3295, "lr": 3.6391898461406045e-06, "epoch": 0.3493975903614458, "percentage": 34.94, "elapsed_time": "0:05:19", "remaining_time": "0:09:54"}
+{"current_steps": 88, "total_steps": 249, "loss": 0.3167, "lr": 3.61102286007161e-06, "epoch": 0.3534136546184739, "percentage": 35.34, "elapsed_time": "0:05:23", "remaining_time": "0:09:51"}
+{"current_steps": 89, "total_steps": 249, "loss": 0.3281, "lr": 3.582679018618822e-06, "epoch": 0.357429718875502, "percentage": 35.74, "elapsed_time": "0:05:26", "remaining_time": "0:09:47"}
+{"current_steps": 90, "total_steps": 249, "loss": 0.3369, "lr": 3.55416283362546e-06, "epoch": 0.3614457831325301, "percentage": 36.14, "elapsed_time": "0:05:30", "remaining_time": "0:09:43"}
+{"current_steps": 91, "total_steps": 249, "loss": 0.2926, "lr": 3.5254788443688188e-06, "epoch": 0.3654618473895582, "percentage": 36.55, "elapsed_time": "0:05:34", "remaining_time": "0:09:39"}
+{"current_steps": 92, "total_steps": 249, "loss": 0.3362, "lr": 3.49663161683769e-06, "epoch": 0.36947791164658633, "percentage": 36.95, "elapsed_time": "0:05:37", "remaining_time": "0:09:36"}
+{"current_steps": 93, "total_steps": 249, "loss": 0.3127, "lr": 3.4676257430055438e-06, "epoch": 0.37349397590361444, "percentage": 37.35, "elapsed_time": "0:05:41", "remaining_time": "0:09:32"}
+{"current_steps": 94, "total_steps": 249, "loss": 0.3227, "lr": 3.4384658400995606e-06, "epoch": 0.37751004016064255, "percentage": 37.75, "elapsed_time": "0:05:45", "remaining_time": "0:09:29"}
+{"current_steps": 95, "total_steps": 249, "loss": 0.3535, "lr": 3.409156549865654e-06, "epoch": 0.3815261044176707, "percentage": 38.15, "elapsed_time": "0:05:48", "remaining_time": "0:09:25"}
+{"current_steps": 96, "total_steps": 249, "loss": 0.3229, "lr": 3.3797025378295826e-06, "epoch": 0.3855421686746988, "percentage": 38.55, "elapsed_time": "0:05:52", "remaining_time": "0:09:21"}
+{"current_steps": 97, "total_steps": 249, "loss": 0.2994, "lr": 3.350108492554284e-06, "epoch": 0.3895582329317269, "percentage": 38.96, "elapsed_time": "0:05:56", "remaining_time": "0:09:18"}
+{"current_steps": 98, "total_steps": 249, "loss": 0.2942, "lr": 3.3203791248935335e-06, "epoch": 0.39357429718875503, "percentage": 39.36, "elapsed_time": "0:05:59", "remaining_time": "0:09:14"}
+{"current_steps": 99, "total_steps": 249, "loss": 0.3136, "lr": 3.29051916724206e-06, "epoch": 0.39759036144578314, "percentage": 39.76, "elapsed_time": "0:06:03", "remaining_time": "0:09:10"}
+{"current_steps": 100, "total_steps": 249, "loss": 0.3414, "lr": 3.2605333727822335e-06, "epoch": 0.40160642570281124, "percentage": 40.16, "elapsed_time": "0:06:07", "remaining_time": "0:09:07"}
+{"current_steps": 100, "total_steps": 249, "eval_loss": 0.2444542795419693, "epoch": 0.40160642570281124, "percentage": 40.16, "elapsed_time": "0:06:08", "remaining_time": "0:09:08"}
+{"current_steps": 101, "total_steps": 249, "loss": 0.3283, "lr": 3.2304265147274394e-06, "epoch": 0.40562248995983935, "percentage": 40.56, "elapsed_time": "0:06:11", "remaining_time": "0:09:04"}
+{"current_steps": 102, "total_steps": 249, "loss": 0.4056, "lr": 3.2002033855622683e-06, "epoch": 0.40963855421686746, "percentage": 40.96, "elapsed_time": "0:06:15", "remaining_time": "0:09:01"}
+{"current_steps": 103, "total_steps": 249, "loss": 0.307, "lr": 3.1698687962796338e-06, "epoch": 0.41365461847389556, "percentage": 41.37, "elapsed_time": "0:06:19", "remaining_time": "0:08:57"}
+{"current_steps": 104, "total_steps": 249, "loss": 0.354, "lr": 3.1394275756149507e-06, "epoch": 0.41767068273092367, "percentage": 41.77, "elapsed_time": "0:06:22", "remaining_time": "0:08:53"}
+{"current_steps": 105, "total_steps": 249, "loss": 0.3349, "lr": 3.1088845692774798e-06, "epoch": 0.42168674698795183, "percentage": 42.17, "elapsed_time": "0:06:26", "remaining_time": "0:08:50"}
+{"current_steps": 106, "total_steps": 249, "loss": 0.2843, "lr": 3.0782446391789834e-06, "epoch": 0.42570281124497994, "percentage": 42.57, "elapsed_time": "0:06:30", "remaining_time": "0:08:46"}
+{"current_steps": 107, "total_steps": 249, "loss": 0.3013, "lr": 3.0475126626597828e-06, "epoch": 0.42971887550200805, "percentage": 42.97, "elapsed_time": "0:06:33", "remaining_time": "0:08:42"}
+{"current_steps": 108, "total_steps": 249, "loss": 0.3325, "lr": 3.0166935317123824e-06, "epoch": 0.43373493975903615, "percentage": 43.37, "elapsed_time": "0:06:37", "remaining_time": "0:08:39"}
+{"current_steps": 109, "total_steps": 249, "loss": 0.3291, "lr": 2.9857921522027443e-06, "epoch": 0.43775100401606426, "percentage": 43.78, "elapsed_time": "0:06:41", "remaining_time": "0:08:35"}
+{"current_steps": 110, "total_steps": 249, "loss": 0.333, "lr": 2.9548134430893605e-06, "epoch": 0.44176706827309237, "percentage": 44.18, "elapsed_time": "0:06:44", "remaining_time": "0:08:31"}
+{"current_steps": 111, "total_steps": 249, "loss": 0.3079, "lr": 2.9237623356402423e-06, "epoch": 0.4457831325301205, "percentage": 44.58, "elapsed_time": "0:06:48", "remaining_time": "0:08:28"}
+{"current_steps": 112, "total_steps": 249, "loss": 0.2814, "lr": 2.8926437726479476e-06, "epoch": 0.4497991967871486, "percentage": 44.98, "elapsed_time": "0:06:52", "remaining_time": "0:08:24"}
+{"current_steps": 113, "total_steps": 249, "loss": 0.2745, "lr": 2.8614627076427777e-06, "epoch": 0.4538152610441767, "percentage": 45.38, "elapsed_time": "0:06:56", "remaining_time": "0:08:20"}
+{"current_steps": 114, "total_steps": 249, "loss": 0.3072, "lr": 2.8302241041042564e-06, "epoch": 0.4578313253012048, "percentage": 45.78, "elapsed_time": "0:06:59", "remaining_time": "0:08:16"}
+{"current_steps": 115, "total_steps": 249, "loss": 0.3368, "lr": 2.7989329346710375e-06, "epoch": 0.46184738955823296, "percentage": 46.18, "elapsed_time": "0:07:03", "remaining_time": "0:08:13"}
+{"current_steps": 116, "total_steps": 249, "loss": 0.3159, "lr": 2.7675941803493435e-06, "epoch": 0.46586345381526106, "percentage": 46.59, "elapsed_time": "0:07:07", "remaining_time": "0:08:09"}
+{"current_steps": 117, "total_steps": 249, "loss": 0.2746, "lr": 2.7362128297200784e-06, "epoch": 0.46987951807228917, "percentage": 46.99, "elapsed_time": "0:07:10", "remaining_time": "0:08:05"}
+{"current_steps": 118, "total_steps": 249, "loss": 0.3444, "lr": 2.704793878144731e-06, "epoch": 0.4738955823293173, "percentage": 47.39, "elapsed_time": "0:07:14", "remaining_time": "0:08:02"}
+{"current_steps": 119, "total_steps": 249, "loss": 0.2835, "lr": 2.673342326970204e-06, "epoch": 0.4779116465863454, "percentage": 47.79, "elapsed_time": "0:07:18", "remaining_time": "0:07:58"}
+{"current_steps": 120, "total_steps": 249, "loss": 0.2958, "lr": 2.6418631827326857e-06, "epoch": 0.4819277108433735, "percentage": 48.19, "elapsed_time": "0:07:21", "remaining_time": "0:07:54"}
+{"current_steps": 121, "total_steps": 249, "loss": 0.3106, "lr": 2.6103614563606933e-06, "epoch": 0.4859437751004016, "percentage": 48.59, "elapsed_time": "0:07:25", "remaining_time": "0:07:51"}
+{"current_steps": 122, "total_steps": 249, "loss": 0.318, "lr": 2.578842162377429e-06, "epoch": 0.4899598393574297, "percentage": 49.0, "elapsed_time": "0:07:29", "remaining_time": "0:07:47"}
+{"current_steps": 123, "total_steps": 249, "loss": 0.3058, "lr": 2.547310318102548e-06, "epoch": 0.4939759036144578, "percentage": 49.4, "elapsed_time": "0:07:32", "remaining_time": "0:07:43"}
+{"current_steps": 124, "total_steps": 249, "loss": 0.3136, "lr": 2.5157709428534936e-06, "epoch": 0.4979919678714859, "percentage": 49.8, "elapsed_time": "0:07:36", "remaining_time": "0:07:40"}
+{"current_steps": 125, "total_steps": 249, "loss": 0.2879, "lr": 2.4842290571465068e-06, "epoch": 0.5020080321285141, "percentage": 50.2, "elapsed_time": "0:07:40", "remaining_time": "0:07:36"}
+{"current_steps": 126, "total_steps": 249, "loss": 0.295, "lr": 2.4526896818974534e-06, "epoch": 0.5060240963855421, "percentage": 50.6, "elapsed_time": "0:07:43", "remaining_time": "0:07:32"}
+{"current_steps": 127, "total_steps": 249, "loss": 0.3504, "lr": 2.421157837622572e-06, "epoch": 0.5100401606425703, "percentage": 51.0, "elapsed_time": "0:07:47", "remaining_time": "0:07:28"}
+{"current_steps": 128, "total_steps": 249, "loss": 0.2718, "lr": 2.3896385436393076e-06, "epoch": 0.5140562248995983, "percentage": 51.41, "elapsed_time": "0:07:51", "remaining_time": "0:07:25"}
+{"current_steps": 129, "total_steps": 249, "loss": 0.346, "lr": 2.358136817267315e-06, "epoch": 0.5180722891566265, "percentage": 51.81, "elapsed_time": "0:07:54", "remaining_time": "0:07:21"}
+{"current_steps": 130, "total_steps": 249, "loss": 0.2684, "lr": 2.326657673029796e-06, "epoch": 0.5220883534136547, "percentage": 52.21, "elapsed_time": "0:07:58", "remaining_time": "0:07:17"}
+{"current_steps": 131, "total_steps": 249, "loss": 0.2578, "lr": 2.2952061218552692e-06, "epoch": 0.5261044176706827, "percentage": 52.61, "elapsed_time": "0:08:01", "remaining_time": "0:07:14"}
+{"current_steps": 132, "total_steps": 249, "loss": 0.3356, "lr": 2.263787170279922e-06, "epoch": 0.5301204819277109, "percentage": 53.01, "elapsed_time": "0:08:05", "remaining_time": "0:07:10"}
+{"current_steps": 133, "total_steps": 249, "loss": 0.2665, "lr": 2.232405819650657e-06, "epoch": 0.5341365461847389, "percentage": 53.41, "elapsed_time": "0:08:09", "remaining_time": "0:07:06"}
+{"current_steps": 134, "total_steps": 249, "loss": 0.3338, "lr": 2.2010670653289624e-06, "epoch": 0.5381526104417671, "percentage": 53.82, "elapsed_time": "0:08:12", "remaining_time": "0:07:02"}
+{"current_steps": 135, "total_steps": 249, "loss": 0.3162, "lr": 2.169775895895745e-06, "epoch": 0.5421686746987951, "percentage": 54.22, "elapsed_time": "0:08:16", "remaining_time": "0:06:59"}
+{"current_steps": 136, "total_steps": 249, "loss": 0.3051, "lr": 2.1385372923572236e-06, "epoch": 0.5461847389558233, "percentage": 54.62, "elapsed_time": "0:08:20", "remaining_time": "0:06:55"}
+{"current_steps": 137, "total_steps": 249, "loss": 0.2959, "lr": 2.1073562273520536e-06, "epoch": 0.5502008032128514, "percentage": 55.02, "elapsed_time": "0:08:23", "remaining_time": "0:06:51"}
+{"current_steps": 138, "total_steps": 249, "loss": 0.3855, "lr": 2.0762376643597586e-06, "epoch": 0.5542168674698795, "percentage": 55.42, "elapsed_time": "0:08:27", "remaining_time": "0:06:48"}
+{"current_steps": 139, "total_steps": 249, "loss": 0.2796, "lr": 2.0451865569106403e-06, "epoch": 0.5582329317269076, "percentage": 55.82, "elapsed_time": "0:08:31", "remaining_time": "0:06:44"}
+{"current_steps": 140, "total_steps": 249, "loss": 0.3197, "lr": 2.014207847797256e-06, "epoch": 0.5622489959839357, "percentage": 56.22, "elapsed_time": "0:08:34", "remaining_time": "0:06:40"}
+{"current_steps": 141, "total_steps": 249, "loss": 0.3097, "lr": 1.9833064682876175e-06, "epoch": 0.5662650602409639, "percentage": 56.63, "elapsed_time": "0:08:38", "remaining_time": "0:06:36"}
+{"current_steps": 142, "total_steps": 249, "loss": 0.3169, "lr": 1.952487337340218e-06, "epoch": 0.570281124497992, "percentage": 57.03, "elapsed_time": "0:08:41", "remaining_time": "0:06:33"}
+{"current_steps": 143, "total_steps": 249, "loss": 0.2728, "lr": 1.921755360821018e-06, "epoch": 0.5742971887550201, "percentage": 57.43, "elapsed_time": "0:08:45", "remaining_time": "0:06:29"}
+{"current_steps": 144, "total_steps": 249, "loss": 0.2503, "lr": 1.8911154307225204e-06, "epoch": 0.5783132530120482, "percentage": 57.83, "elapsed_time": "0:08:49", "remaining_time": "0:06:25"}
+{"current_steps": 145, "total_steps": 249, "loss": 0.3661, "lr": 1.8605724243850501e-06, "epoch": 0.5823293172690763, "percentage": 58.23, "elapsed_time": "0:08:53", "remaining_time": "0:06:22"}
+{"current_steps": 146, "total_steps": 249, "loss": 0.2907, "lr": 1.8301312037203677e-06, "epoch": 0.5863453815261044, "percentage": 58.63, "elapsed_time": "0:08:56", "remaining_time": "0:06:18"}
+{"current_steps": 147, "total_steps": 249, "loss": 0.2832, "lr": 1.7997966144377328e-06, "epoch": 0.5903614457831325, "percentage": 59.04, "elapsed_time": "0:09:00", "remaining_time": "0:06:14"}
+{"current_steps": 148, "total_steps": 249, "loss": 0.2703, "lr": 1.769573485272562e-06, "epoch": 0.5943775100401606, "percentage": 59.44, "elapsed_time": "0:09:03", "remaining_time": "0:06:11"}
+{"current_steps": 149, "total_steps": 249, "loss": 0.2727, "lr": 1.739466627217767e-06, "epoch": 0.5983935742971888, "percentage": 59.84, "elapsed_time": "0:09:07", "remaining_time": "0:06:07"}
+{"current_steps": 150, "total_steps": 249, "loss": 0.2831, "lr": 1.7094808327579401e-06, "epoch": 0.6024096385542169, "percentage": 60.24, "elapsed_time": "0:09:11", "remaining_time": "0:06:03"}
+{"current_steps": 151, "total_steps": 249, "loss": 0.3299, "lr": 1.679620875106467e-06, "epoch": 0.606425702811245, "percentage": 60.64, "elapsed_time": "0:09:14", "remaining_time": "0:06:00"}
+{"current_steps": 152, "total_steps": 249, "loss": 0.2759, "lr": 1.6498915074457158e-06, "epoch": 0.6104417670682731, "percentage": 61.04, "elapsed_time": "0:09:18", "remaining_time": "0:05:56"}
+{"current_steps": 153, "total_steps": 249, "loss": 0.4144, "lr": 1.6202974621704176e-06, "epoch": 0.6144578313253012, "percentage": 61.45, "elapsed_time": "0:09:22", "remaining_time": "0:05:52"}
+{"current_steps": 154, "total_steps": 249, "loss": 0.2816, "lr": 1.590843450134347e-06, "epoch": 0.6184738955823293, "percentage": 61.85, "elapsed_time": "0:09:25", "remaining_time": "0:05:49"}
+{"current_steps": 155, "total_steps": 249, "loss": 0.2631, "lr": 1.5615341599004408e-06, "epoch": 0.6224899598393574, "percentage": 62.25, "elapsed_time": "0:09:29", "remaining_time": "0:05:45"}
+{"current_steps": 156, "total_steps": 249, "loss": 0.3085, "lr": 1.5323742569944573e-06, "epoch": 0.6265060240963856, "percentage": 62.65, "elapsed_time": "0:09:33", "remaining_time": "0:05:41"}
+{"current_steps": 157, "total_steps": 249, "loss": 0.2662, "lr": 1.5033683831623115e-06, "epoch": 0.6305220883534136, "percentage": 63.05, "elapsed_time": "0:09:36", "remaining_time": "0:05:37"}
+{"current_steps": 158, "total_steps": 249, "loss": 0.2754, "lr": 1.4745211556311823e-06, "epoch": 0.6345381526104418, "percentage": 63.45, "elapsed_time": "0:09:40", "remaining_time": "0:05:34"}
+{"current_steps": 159, "total_steps": 249, "loss": 0.2745, "lr": 1.44583716637454e-06, "epoch": 0.6385542168674698, "percentage": 63.86, "elapsed_time": "0:09:43", "remaining_time": "0:05:30"}
+{"current_steps": 160, "total_steps": 249, "loss": 0.2935, "lr": 1.417320981381179e-06, "epoch": 0.642570281124498, "percentage": 64.26, "elapsed_time": "0:09:47", "remaining_time": "0:05:26"}
+{"current_steps": 161, "total_steps": 249, "loss": 0.3028, "lr": 1.3889771399283902e-06, "epoch": 0.6465863453815262, "percentage": 64.66, "elapsed_time": "0:09:51", "remaining_time": "0:05:23"}
+{"current_steps": 162, "total_steps": 249, "loss": 0.304, "lr": 1.3608101538593965e-06, "epoch": 0.6506024096385542, "percentage": 65.06, "elapsed_time": "0:09:55", "remaining_time": "0:05:19"}
+{"current_steps": 163, "total_steps": 249, "loss": 0.3003, "lr": 1.332824506865135e-06, "epoch": 0.6546184738955824, "percentage": 65.46, "elapsed_time": "0:09:58", "remaining_time": "0:05:15"}
+{"current_steps": 164, "total_steps": 249, "loss": 0.3527, "lr": 1.3050246537705424e-06, "epoch": 0.6586345381526104, "percentage": 65.86, "elapsed_time": "0:10:02", "remaining_time": "0:05:12"}
+{"current_steps": 165, "total_steps": 249, "loss": 0.3171, "lr": 1.277415019825417e-06, "epoch": 0.6626506024096386, "percentage": 66.27, "elapsed_time": "0:10:06", "remaining_time": "0:05:08"}
+{"current_steps": 166, "total_steps": 249, "loss": 0.2624, "lr": 1.2500000000000007e-06, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:10:09", "remaining_time": "0:05:04"}
+{"current_steps": 167, "total_steps": 249, "loss": 0.2982, "lr": 1.2227839582853737e-06, "epoch": 0.6706827309236948, "percentage": 67.07, "elapsed_time": "0:10:13", "remaining_time": "0:05:01"}
+{"current_steps": 168, "total_steps": 249, "loss": 0.362, "lr": 1.195771226998789e-06, "epoch": 0.6746987951807228, "percentage": 67.47, "elapsed_time": "0:10:17", "remaining_time": "0:04:57"}
+{"current_steps": 169, "total_steps": 249, "loss": 0.2973, "lr": 1.1689661060940366e-06, "epoch": 0.678714859437751, "percentage": 67.87, "elapsed_time": "0:10:20", "remaining_time": "0:04:53"}
+{"current_steps": 170, "total_steps": 249, "loss": 0.2765, "lr": 1.1423728624769694e-06, "epoch": 0.6827309236947792, "percentage": 68.27, "elapsed_time": "0:10:24", "remaining_time": "0:04:50"}
+{"current_steps": 171, "total_steps": 249, "loss": 0.3193, "lr": 1.1159957293262888e-06, "epoch": 0.6867469879518072, "percentage": 68.67, "elapsed_time": "0:10:28", "remaining_time": "0:04:46"}
+{"current_steps": 172, "total_steps": 249, "loss": 0.418, "lr": 1.0898389054196912e-06, "epoch": 0.6907630522088354, "percentage": 69.08, "elapsed_time": "0:10:31", "remaining_time": "0:04:42"}
+{"current_steps": 173, "total_steps": 249, "loss": 0.2812, "lr": 1.0639065544655034e-06, "epoch": 0.6947791164658634, "percentage": 69.48, "elapsed_time": "0:10:35", "remaining_time": "0:04:39"}
+{"current_steps": 174, "total_steps": 249, "loss": 0.3433, "lr": 1.0382028044398823e-06, "epoch": 0.6987951807228916, "percentage": 69.88, "elapsed_time": "0:10:39", "remaining_time": "0:04:35"}
+{"current_steps": 175, "total_steps": 249, "loss": 0.3253, "lr": 1.0127317469297277e-06, "epoch": 0.7028112449799196, "percentage": 70.28, "elapsed_time": "0:10:42", "remaining_time": "0:04:31"}
+{"current_steps": 176, "total_steps": 249, "loss": 0.266, "lr": 9.874974364813594e-07, "epoch": 0.7068273092369478, "percentage": 70.68, "elapsed_time": "0:10:46", "remaining_time": "0:04:28"}
+{"current_steps": 177, "total_steps": 249, "loss": 0.3141, "lr": 9.625038899551162e-07, "epoch": 0.7108433734939759, "percentage": 71.08, "elapsed_time": "0:10:49", "remaining_time": "0:04:24"}
+{"current_steps": 178, "total_steps": 249, "loss": 0.3187, "lr": 9.377550858859325e-07, "epoch": 0.714859437751004, "percentage": 71.49, "elapsed_time": "0:10:53", "remaining_time": "0:04:20"}
+{"current_steps": 179, "total_steps": 249, "loss": 0.2784, "lr": 9.132549638500307e-07, "epoch": 0.7188755020080321, "percentage": 71.89, "elapsed_time": "0:10:57", "remaining_time": "0:04:17"}
+{"current_steps": 180, "total_steps": 249, "loss": 0.3243, "lr": 8.890074238378074e-07, "epoch": 0.7228915662650602, "percentage": 72.29, "elapsed_time": "0:11:01", "remaining_time": "0:04:13"}
+{"current_steps": 181, "total_steps": 249, "loss": 0.2574, "lr": 8.650163256330271e-07, "epoch": 0.7269076305220884, "percentage": 72.69, "elapsed_time": "0:11:04", "remaining_time": "0:04:09"}
+{"current_steps": 182, "total_steps": 249, "loss": 0.2778, "lr": 8.412854881984056e-07, "epoch": 0.7309236947791165, "percentage": 73.09, "elapsed_time": "0:11:08", "remaining_time": "0:04:06"}
+{"current_steps": 183, "total_steps": 249, "loss": 0.272, "lr": 8.178186890677029e-07, "epoch": 0.7349397590361446, "percentage": 73.49, "elapsed_time": "0:11:12", "remaining_time": "0:04:02"}
+{"current_steps": 184, "total_steps": 249, "loss": 0.2979, "lr": 7.94619663744406e-07, "epoch": 0.7389558232931727, "percentage": 73.9, "elapsed_time": "0:11:15", "remaining_time": "0:03:58"}
+{"current_steps": 185, "total_steps": 249, "loss": 0.3243, "lr": 7.71692105107098e-07, "epoch": 0.7429718875502008, "percentage": 74.3, "elapsed_time": "0:11:19", "remaining_time": "0:03:55"}
+{"current_steps": 186, "total_steps": 249, "loss": 0.3045, "lr": 7.490396628216237e-07, "epoch": 0.7469879518072289, "percentage": 74.7, "elapsed_time": "0:11:23", "remaining_time": "0:03:51"}
+{"current_steps": 187, "total_steps": 249, "loss": 0.3466, "lr": 7.26665942760117e-07, "epoch": 0.751004016064257, "percentage": 75.1, "elapsed_time": "0:11:26", "remaining_time": "0:03:47"}
+{"current_steps": 188, "total_steps": 249, "loss": 0.2677, "lr": 7.045745064270187e-07, "epoch": 0.7550200803212851, "percentage": 75.5, "elapsed_time": "0:11:30", "remaining_time": "0:03:43"}
+{"current_steps": 189, "total_steps": 249, "loss": 0.3087, "lr": 6.827688703921407e-07, "epoch": 0.7590361445783133, "percentage": 75.9, "elapsed_time": "0:11:34", "remaining_time": "0:03:40"}
+{"current_steps": 190, "total_steps": 249, "loss": 0.3273, "lr": 6.61252505730895e-07, "epoch": 0.7630522088353414, "percentage": 76.31, "elapsed_time": "0:11:37", "remaining_time": "0:03:36"}
+{"current_steps": 191, "total_steps": 249, "loss": 0.2695, "lr": 6.400288374717534e-07, "epoch": 0.7670682730923695, "percentage": 76.71, "elapsed_time": "0:11:41", "remaining_time": "0:03:33"}
+{"current_steps": 192, "total_steps": 249, "loss": 0.3405, "lr": 6.191012440510469e-07, "epoch": 0.7710843373493976, "percentage": 77.11, "elapsed_time": "0:11:45", "remaining_time": "0:03:29"}
+{"current_steps": 193, "total_steps": 249, "loss": 0.2968, "lr": 5.984730567751787e-07, "epoch": 0.7751004016064257, "percentage": 77.51, "elapsed_time": "0:11:48", "remaining_time": "0:03:25"}
+{"current_steps": 194, "total_steps": 249, "loss": 0.2858, "lr": 5.781475592903337e-07, "epoch": 0.7791164658634538, "percentage": 77.91, "elapsed_time": "0:11:52", "remaining_time": "0:03:21"}
+{"current_steps": 195, "total_steps": 249, "loss": 0.4297, "lr": 5.581279870597866e-07, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:11:55", "remaining_time": "0:03:18"}
+{"current_steps": 196, "total_steps": 249, "loss": 0.3367, "lr": 5.38417526848864e-07, "epoch": 0.7871485943775101, "percentage": 78.71, "elapsed_time": "0:11:59", "remaining_time": "0:03:14"}
+{"current_steps": 197, "total_steps": 249, "loss": 0.2804, "lr": 5.190193162176754e-07, "epoch": 0.7911646586345381, "percentage": 79.12, "elapsed_time": "0:12:03", "remaining_time": "0:03:10"}
+{"current_steps": 198, "total_steps": 249, "loss": 0.2939, "lr": 4.999364430216639e-07, "epoch": 0.7951807228915663, "percentage": 79.52, "elapsed_time": "0:12:07", "remaining_time": "0:03:07"}
+{"current_steps": 199, "total_steps": 249, "loss": 0.2827, "lr": 4.811719449200755e-07, "epoch": 0.7991967871485943, "percentage": 79.92, "elapsed_time": "0:12:10", "remaining_time": "0:03:03"}
+{"current_steps": 200, "total_steps": 249, "loss": 0.2978, "lr": 4.6272880889241563e-07, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:12:14", "remaining_time": "0:02:59"}
+{"current_steps": 200, "total_steps": 249, "eval_loss": 0.23421859741210938, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:12:15", "remaining_time": "0:03:00"}
+{"current_steps": 201, "total_steps": 249, "loss": 0.3036, "lr": 4.4460997076297504e-07, "epoch": 0.8072289156626506, "percentage": 80.72, "elapsed_time": "0:12:19", "remaining_time": "0:02:56"}
+{"current_steps": 202, "total_steps": 249, "loss": 0.2942, "lr": 4.2681831473349896e-07, "epoch": 0.8112449799196787, "percentage": 81.12, "elapsed_time": "0:12:22", "remaining_time": "0:02:52"}
+{"current_steps": 203, "total_steps": 249, "loss": 0.3199, "lr": 4.093566729240708e-07, "epoch": 0.8152610441767069, "percentage": 81.53, "elapsed_time": "0:12:26", "remaining_time": "0:02:49"}
+{"current_steps": 204, "total_steps": 249, "loss": 0.3158, "lr": 3.922278249222894e-07, "epoch": 0.8192771084337349, "percentage": 81.93, "elapsed_time": "0:12:30", "remaining_time": "0:02:45"}
+{"current_steps": 205, "total_steps": 249, "loss": 0.2809, "lr": 3.754344973408064e-07, "epoch": 0.8232931726907631, "percentage": 82.33, "elapsed_time": "0:12:33", "remaining_time": "0:02:41"}
+{"current_steps": 206, "total_steps": 249, "loss": 0.3014, "lr": 3.5897936338329995e-07, "epoch": 0.8273092369477911, "percentage": 82.73, "elapsed_time": "0:12:37", "remaining_time": "0:02:38"}
+{"current_steps": 207, "total_steps": 249, "loss": 0.2903, "lr": 3.4286504241894283e-07, "epoch": 0.8313253012048193, "percentage": 83.13, "elapsed_time": "0:12:41", "remaining_time": "0:02:34"}
+{"current_steps": 208, "total_steps": 249, "loss": 0.3376, "lr": 3.2709409956545065e-07, "epoch": 0.8353413654618473, "percentage": 83.53, "elapsed_time": "0:12:44", "remaining_time": "0:02:30"}
+{"current_steps": 209, "total_steps": 249, "loss": 0.2503, "lr": 3.1166904528075247e-07, "epoch": 0.8393574297188755, "percentage": 83.94, "elapsed_time": "0:12:48", "remaining_time": "0:02:27"}
+{"current_steps": 210, "total_steps": 249, "loss": 0.2972, "lr": 2.965923349633779e-07, "epoch": 0.8433734939759037, "percentage": 84.34, "elapsed_time": "0:12:52", "remaining_time": "0:02:23"}
+{"current_steps": 211, "total_steps": 249, "loss": 0.282, "lr": 2.8186636856159605e-07, "epoch": 0.8473895582329317, "percentage": 84.74, "elapsed_time": "0:12:55", "remaining_time": "0:02:19"}
+{"current_steps": 212, "total_steps": 249, "loss": 0.2918, "lr": 2.6749349019138585e-07, "epoch": 0.8514056224899599, "percentage": 85.14, "elapsed_time": "0:12:59", "remaining_time": "0:02:16"}
+{"current_steps": 213, "total_steps": 249, "loss": 0.2991, "lr": 2.53475987763295e-07, "epoch": 0.8554216867469879, "percentage": 85.54, "elapsed_time": "0:13:03", "remaining_time": "0:02:12"}
+{"current_steps": 214, "total_steps": 249, "loss": 0.342, "lr": 2.3981609261824384e-07, "epoch": 0.8594377510040161, "percentage": 85.94, "elapsed_time": "0:13:06", "remaining_time": "0:02:08"}
+{"current_steps": 215, "total_steps": 249, "loss": 0.3218, "lr": 2.2651597917233731e-07, "epoch": 0.8634538152610441, "percentage": 86.35, "elapsed_time": "0:13:10", "remaining_time": "0:02:05"}
+{"current_steps": 216, "total_steps": 249, "loss": 0.3587, "lr": 2.135777645707318e-07, "epoch": 0.8674698795180723, "percentage": 86.75, "elapsed_time": "0:13:14", "remaining_time": "0:02:01"}
+{"current_steps": 217, "total_steps": 249, "loss": 0.3273, "lr": 2.0100350835062705e-07, "epoch": 0.8714859437751004, "percentage": 87.15, "elapsed_time": "0:13:17", "remaining_time": "0:01:57"}
+{"current_steps": 218, "total_steps": 249, "loss": 0.3335, "lr": 1.8879521211341956e-07, "epoch": 0.8755020080321285, "percentage": 87.55, "elapsed_time": "0:13:21", "remaining_time": "0:01:53"}
+{"current_steps": 219, "total_steps": 249, "loss": 0.3231, "lr": 1.7695481920608716e-07, "epoch": 0.8795180722891566, "percentage": 87.95, "elapsed_time": "0:13:25", "remaining_time": "0:01:50"}
+{"current_steps": 220, "total_steps": 249, "loss": 0.3265, "lr": 1.6548421441183876e-07, "epoch": 0.8835341365461847, "percentage": 88.35, "elapsed_time": "0:13:28", "remaining_time": "0:01:46"}
+{"current_steps": 221, "total_steps": 249, "loss": 0.2498, "lr": 1.5438522365009258e-07, "epoch": 0.8875502008032129, "percentage": 88.76, "elapsed_time": "0:13:32", "remaining_time": "0:01:42"}
+{"current_steps": 222, "total_steps": 249, "loss": 0.2963, "lr": 1.4365961368581844e-07, "epoch": 0.891566265060241, "percentage": 89.16, "elapsed_time": "0:13:36", "remaining_time": "0:01:39"}
+{"current_steps": 223, "total_steps": 249, "loss": 0.3422, "lr": 1.3330909184830265e-07, "epoch": 0.8955823293172691, "percentage": 89.56, "elapsed_time": "0:13:39", "remaining_time": "0:01:35"}
+{"current_steps": 224, "total_steps": 249, "loss": 0.3094, "lr": 1.233353057593703e-07, "epoch": 0.8995983935742972, "percentage": 89.96, "elapsed_time": "0:13:43", "remaining_time": "0:01:31"}
+{"current_steps": 225, "total_steps": 249, "loss": 0.3314, "lr": 1.137398430711123e-07, "epoch": 0.9036144578313253, "percentage": 90.36, "elapsed_time": "0:13:47", "remaining_time": "0:01:28"}
+{"current_steps": 226, "total_steps": 249, "loss": 0.2793, "lr": 1.0452423121315835e-07, "epoch": 0.9076305220883534, "percentage": 90.76, "elapsed_time": "0:13:51", "remaining_time": "0:01:24"}
+{"current_steps": 227, "total_steps": 249, "loss": 0.3052, "lr": 9.568993714953818e-08, "epoch": 0.9116465863453815, "percentage": 91.16, "elapsed_time": "0:13:54", "remaining_time": "0:01:20"}
+{"current_steps": 228, "total_steps": 249, "loss": 0.3106, "lr": 8.723836714516681e-08, "epoch": 0.9156626506024096, "percentage": 91.57, "elapsed_time": "0:13:58", "remaining_time": "0:01:17"}
+{"current_steps": 229, "total_steps": 249, "loss": 0.3244, "lr": 7.91708665419899e-08, "epoch": 0.9196787148594378, "percentage": 91.97, "elapsed_time": "0:14:01", "remaining_time": "0:01:13"}
+{"current_steps": 230, "total_steps": 249, "loss": 0.3409, "lr": 7.148871954483106e-08, "epoch": 0.9236947791164659, "percentage": 92.37, "elapsed_time": "0:14:05", "remaining_time": "0:01:09"}
+{"current_steps": 231, "total_steps": 249, "loss": 0.2569, "lr": 6.419314901696671e-08, "epoch": 0.927710843373494, "percentage": 92.77, "elapsed_time": "0:14:09", "remaining_time": "0:01:06"}
+{"current_steps": 232, "total_steps": 249, "loss": 0.2572, "lr": 5.728531628546946e-08, "epoch": 0.9317269076305221, "percentage": 93.17, "elapsed_time": "0:14:13", "remaining_time": "0:01:02"}
+{"current_steps": 233, "total_steps": 249, "loss": 0.29, "lr": 5.076632095634526e-08, "epoch": 0.9357429718875502, "percentage": 93.57, "elapsed_time": "0:14:16", "remaining_time": "0:00:58"}
+{"current_steps": 234, "total_steps": 249, "loss": 0.3242, "lr": 4.4637200739493514e-08, "epoch": 0.9397590361445783, "percentage": 93.98, "elapsed_time": "0:14:20", "remaining_time": "0:00:55"}
+{"current_steps": 235, "total_steps": 249, "loss": 0.2738, "lr": 3.8898931283523346e-08, "epoch": 0.9437751004016064, "percentage": 94.38, "elapsed_time": "0:14:24", "remaining_time": "0:00:51"}
+{"current_steps": 236, "total_steps": 249, "loss": 0.3054, "lr": 3.355242602044728e-08, "epoch": 0.9477911646586346, "percentage": 94.78, "elapsed_time": "0:14:27", "remaining_time": "0:00:47"}
+{"current_steps": 237, "total_steps": 249, "loss": 0.2997, "lr": 2.8598536020278678e-08, "epoch": 0.9518072289156626, "percentage": 95.18, "elapsed_time": "0:14:31", "remaining_time": "0:00:44"}
+{"current_steps": 238, "total_steps": 249, "loss": 0.2741, "lr": 2.403804985555619e-08, "epoch": 0.9558232931726908, "percentage": 95.58, "elapsed_time": "0:14:34", "remaining_time": "0:00:40"}
+{"current_steps": 239, "total_steps": 249, "loss": 0.3034, "lr": 1.9871693475816965e-08, "epoch": 0.9598393574297188, "percentage": 95.98, "elapsed_time": "0:14:38", "remaining_time": "0:00:36"}
+{"current_steps": 240, "total_steps": 249, "loss": 0.2513, "lr": 1.6100130092037704e-08, "epoch": 0.963855421686747, "percentage": 96.39, "elapsed_time": "0:14:42", "remaining_time": "0:00:33"}
+{"current_steps": 241, "total_steps": 249, "loss": 0.2952, "lr": 1.2723960071064356e-08, "epoch": 0.9678714859437751, "percentage": 96.79, "elapsed_time": "0:14:45", "remaining_time": "0:00:29"}
+{"current_steps": 242, "total_steps": 249, "loss": 0.2645, "lr": 9.743720840042491e-09, "epoch": 0.9718875502008032, "percentage": 97.19, "elapsed_time": "0:14:49", "remaining_time": "0:00:25"}
+{"current_steps": 243, "total_steps": 249, "loss": 0.3033, "lr": 7.159886800869875e-09, "epoch": 0.9759036144578314, "percentage": 97.59, "elapsed_time": "0:14:53", "remaining_time": "0:00:22"}
+{"current_steps": 244, "total_steps": 249, "loss": 0.2963, "lr": 4.9728692546791024e-09, "epoch": 0.9799196787148594, "percentage": 97.99, "elapsed_time": "0:14:57", "remaining_time": "0:00:18"}
+{"current_steps": 245, "total_steps": 249, "loss": 0.2747, "lr": 3.1830163363655296e-09, "epoch": 0.9839357429718876, "percentage": 98.39, "elapsed_time": "0:15:00", "remaining_time": "0:00:14"}
+{"current_steps": 246, "total_steps": 249, "loss": 0.3044, "lr": 1.7906129591713228e-09, "epoch": 0.9879518072289156, "percentage": 98.8, "elapsed_time": "0:15:04", "remaining_time": "0:00:11"}
+{"current_steps": 247, "total_steps": 249, "loss": 0.2705, "lr": 7.95880769331181e-10, "epoch": 0.9919678714859438, "percentage": 99.2, "elapsed_time": "0:15:08", "remaining_time": "0:00:07"}
+{"current_steps": 248, "total_steps": 249, "loss": 0.2825, "lr": 1.9897811079055973e-10, "epoch": 0.9959839357429718, "percentage": 99.6, "elapsed_time": "0:15:11", "remaining_time": "0:00:03"}
+{"current_steps": 249, "total_steps": 249, "loss": 0.2814, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:15:15", "remaining_time": "0:00:00"}
+{"current_steps": 249, "total_steps": 249, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:15:43", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1801 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 249,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004016064257028112,
+      "grad_norm": 3.7381256166820815,
+      "learning_rate": 4.99980102188921e-06,
+      "loss": 0.7293,
+      "step": 1
+    },
+    {
+      "epoch": 0.008032128514056224,
+      "grad_norm": 3.3672061497902877,
+      "learning_rate": 4.99920411923067e-06,
+      "loss": 0.7912,
+      "step": 2
+    },
+    {
+      "epoch": 0.012048192771084338,
+      "grad_norm": 2.194011371619709,
+      "learning_rate": 4.998209387040829e-06,
+      "loss": 0.6689,
+      "step": 3
+    },
+    {
+      "epoch": 0.01606425702811245,
+      "grad_norm": 1.9452462057828979,
+      "learning_rate": 4.996816983663635e-06,
+      "loss": 0.6017,
+      "step": 4
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "grad_norm": 1.597126433284444,
+      "learning_rate": 4.995027130745322e-06,
+      "loss": 0.6071,
+      "step": 5
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 1.637144526560106,
+      "learning_rate": 4.992840113199131e-06,
+      "loss": 0.5896,
+      "step": 6
+    },
+    {
+      "epoch": 0.028112449799196786,
+      "grad_norm": 1.4051269965405901,
+      "learning_rate": 4.990256279159958e-06,
+      "loss": 0.5191,
+      "step": 7
+    },
+    {
+      "epoch": 0.0321285140562249,
+      "grad_norm": 1.5295294770984917,
+      "learning_rate": 4.9872760399289365e-06,
+      "loss": 0.4819,
+      "step": 8
+    },
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 1.9123706702594945,
+      "learning_rate": 4.983899869907963e-06,
+      "loss": 0.5347,
+      "step": 9
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 1.4772031218541921,
+      "learning_rate": 4.980128306524184e-06,
+      "loss": 0.5212,
+      "step": 10
+    },
+    {
+      "epoch": 0.04417670682730924,
+      "grad_norm": 1.1582158040919177,
+      "learning_rate": 4.975961950144444e-06,
+      "loss": 0.4289,
+      "step": 11
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 1.2688143364406612,
+      "learning_rate": 4.971401463979722e-06,
+      "loss": 0.5039,
+      "step": 12
+    },
+    {
+      "epoch": 0.05220883534136546,
+      "grad_norm": 1.0323752220847646,
+      "learning_rate": 4.966447573979553e-06,
+      "loss": 0.4403,
+      "step": 13
+    },
+    {
+      "epoch": 0.05622489959839357,
+      "grad_norm": 1.1735618741096847,
+      "learning_rate": 4.961101068716477e-06,
+      "loss": 0.4045,
+      "step": 14
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "grad_norm": 1.1522575861053823,
+      "learning_rate": 4.955362799260507e-06,
+      "loss": 0.4462,
+      "step": 15
+    },
+    {
+      "epoch": 0.0642570281124498,
+      "grad_norm": 1.1373958862336098,
+      "learning_rate": 4.949233679043655e-06,
+      "loss": 0.4087,
+      "step": 16
+    },
+    {
+      "epoch": 0.06827309236947791,
+      "grad_norm": 1.0546979214807763,
+      "learning_rate": 4.942714683714531e-06,
+      "loss": 0.369,
+      "step": 17
+    },
+    {
+      "epoch": 0.07228915662650602,
+      "grad_norm": 1.737491435638374,
+      "learning_rate": 4.935806850983034e-06,
+      "loss": 0.379,
+      "step": 18
+    },
+    {
+      "epoch": 0.07630522088353414,
+      "grad_norm": 1.1529742703608215,
+      "learning_rate": 4.928511280455169e-06,
+      "loss": 0.4172,
+      "step": 19
+    },
+    {
+      "epoch": 0.08032128514056225,
+      "grad_norm": 1.1120131285702335,
+      "learning_rate": 4.92082913345801e-06,
+      "loss": 0.4468,
+      "step": 20
+    },
+    {
+      "epoch": 0.08433734939759036,
+      "grad_norm": 1.2711480973452018,
+      "learning_rate": 4.912761632854834e-06,
+      "loss": 0.536,
+      "step": 21
+    },
+    {
+      "epoch": 0.08835341365461848,
+      "grad_norm": 1.225271737981665,
+      "learning_rate": 4.904310062850463e-06,
+      "loss": 0.4384,
+      "step": 22
+    },
+    {
+      "epoch": 0.09236947791164658,
+      "grad_norm": 1.209762626853535,
+      "learning_rate": 4.895475768786843e-06,
+      "loss": 0.4502,
+      "step": 23
+    },
+    {
+      "epoch": 0.0963855421686747,
+      "grad_norm": 0.9437708041453261,
+      "learning_rate": 4.8862601569288885e-06,
+      "loss": 0.3537,
+      "step": 24
+    },
+    {
+      "epoch": 0.10040160642570281,
+      "grad_norm": 1.0771127631895787,
+      "learning_rate": 4.8766646942406305e-06,
+      "loss": 0.3975,
+      "step": 25
+    },
+    {
+      "epoch": 0.10441767068273092,
+      "grad_norm": 1.393185690505992,
+      "learning_rate": 4.866690908151698e-06,
+      "loss": 0.3857,
+      "step": 26
+    },
+    {
+      "epoch": 0.10843373493975904,
+      "grad_norm": 0.9363570936316468,
+      "learning_rate": 4.8563403863141825e-06,
+      "loss": 0.3883,
+      "step": 27
+    },
+    {
+      "epoch": 0.11244979919678715,
+      "grad_norm": 1.1291481660993423,
+      "learning_rate": 4.8456147763499085e-06,
+      "loss": 0.4982,
+      "step": 28
+    },
+    {
+      "epoch": 0.11646586345381527,
+      "grad_norm": 1.221445504588287,
+      "learning_rate": 4.834515785588161e-06,
+      "loss": 0.3641,
+      "step": 29
+    },
+    {
+      "epoch": 0.12048192771084337,
+      "grad_norm": 0.9802169453502032,
+      "learning_rate": 4.823045180793914e-06,
+      "loss": 0.334,
+      "step": 30
+    },
+    {
+      "epoch": 0.12449799196787148,
+      "grad_norm": 1.0246308543906417,
+      "learning_rate": 4.811204787886581e-06,
+      "loss": 0.3852,
+      "step": 31
+    },
+    {
+      "epoch": 0.1285140562248996,
+      "grad_norm": 1.3354309507515414,
+      "learning_rate": 4.798996491649374e-06,
+      "loss": 0.4285,
+      "step": 32
+    },
+    {
+      "epoch": 0.13253012048192772,
+      "grad_norm": 1.1066169739004894,
+      "learning_rate": 4.786422235429269e-06,
+      "loss": 0.4512,
+      "step": 33
+    },
+    {
+      "epoch": 0.13654618473895583,
+      "grad_norm": 1.010166471265323,
+      "learning_rate": 4.773484020827663e-06,
+      "loss": 0.3162,
+      "step": 34
+    },
+    {
+      "epoch": 0.14056224899598393,
+      "grad_norm": 1.4482856479348927,
+      "learning_rate": 4.760183907381757e-06,
+      "loss": 0.3483,
+      "step": 35
+    },
+    {
+      "epoch": 0.14457831325301204,
+      "grad_norm": 0.9926964293432772,
+      "learning_rate": 4.746524012236706e-06,
+      "loss": 0.3528,
+      "step": 36
+    },
+    {
+      "epoch": 0.14859437751004015,
+      "grad_norm": 0.8415168505184463,
+      "learning_rate": 4.732506509808615e-06,
+      "loss": 0.2981,
+      "step": 37
+    },
+    {
+      "epoch": 0.15261044176706828,
+      "grad_norm": 0.9289919097958238,
+      "learning_rate": 4.718133631438404e-06,
+      "loss": 0.3184,
+      "step": 38
+    },
+    {
+      "epoch": 0.1566265060240964,
+      "grad_norm": 0.9685170893885421,
+      "learning_rate": 4.703407665036622e-06,
+      "loss": 0.3176,
+      "step": 39
+    },
+    {
+      "epoch": 0.1606425702811245,
+      "grad_norm": 1.0453016168570457,
+      "learning_rate": 4.688330954719248e-06,
+      "loss": 0.4134,
+      "step": 40
+    },
+    {
+      "epoch": 0.1646586345381526,
+      "grad_norm": 0.881758321222451,
+      "learning_rate": 4.67290590043455e-06,
+      "loss": 0.3554,
+      "step": 41
+    },
+    {
+      "epoch": 0.1686746987951807,
+      "grad_norm": 1.004596251073134,
+      "learning_rate": 4.657134957581057e-06,
+      "loss": 0.3823,
+      "step": 42
+    },
+    {
+      "epoch": 0.17269076305220885,
+      "grad_norm": 1.0382743623586705,
+      "learning_rate": 4.641020636616701e-06,
+      "loss": 0.3576,
+      "step": 43
+    },
+    {
+      "epoch": 0.17670682730923695,
+      "grad_norm": 1.0051168233366194,
+      "learning_rate": 4.624565502659194e-06,
+      "loss": 0.3735,
+      "step": 44
+    },
+    {
+      "epoch": 0.18072289156626506,
+      "grad_norm": 1.0203677275921266,
+      "learning_rate": 4.607772175077712e-06,
+      "loss": 0.4104,
+      "step": 45
+    },
+    {
+      "epoch": 0.18473895582329317,
+      "grad_norm": 1.0123996963330042,
+      "learning_rate": 4.59064332707593e-06,
+      "loss": 0.3666,
+      "step": 46
+    },
+    {
+      "epoch": 0.18875502008032127,
+      "grad_norm": 1.2301357534930417,
+      "learning_rate": 4.573181685266502e-06,
+      "loss": 0.3329,
+      "step": 47
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 0.903057283555397,
+      "learning_rate": 4.555390029237026e-06,
+      "loss": 0.3038,
+      "step": 48
+    },
+    {
+      "epoch": 0.19678714859437751,
+      "grad_norm": 1.0644647080411465,
+      "learning_rate": 4.537271191107585e-06,
+      "loss": 0.3932,
+      "step": 49
+    },
+    {
+      "epoch": 0.20080321285140562,
+      "grad_norm": 1.2172751597811455,
+      "learning_rate": 4.518828055079925e-06,
+      "loss": 0.42,
+      "step": 50
+    },
+    {
+      "epoch": 0.20481927710843373,
+      "grad_norm": 0.9082309928219806,
+      "learning_rate": 4.5000635569783365e-06,
+      "loss": 0.2897,
+      "step": 51
+    },
+    {
+      "epoch": 0.20883534136546184,
+      "grad_norm": 0.9029944529068655,
+      "learning_rate": 4.480980683782326e-06,
+      "loss": 0.3137,
+      "step": 52
+    },
+    {
+      "epoch": 0.21285140562248997,
+      "grad_norm": 1.0879446592114403,
+      "learning_rate": 4.461582473151137e-06,
+      "loss": 0.3576,
+      "step": 53
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "grad_norm": 0.9903812190065193,
+      "learning_rate": 4.4418720129402145e-06,
+      "loss": 0.3261,
+      "step": 54
+    },
+    {
+      "epoch": 0.22088353413654618,
+      "grad_norm": 1.100831678928015,
+      "learning_rate": 4.4218524407096665e-06,
+      "loss": 0.3665,
+      "step": 55
+    },
+    {
+      "epoch": 0.2248995983935743,
+      "grad_norm": 0.9270697302511666,
+      "learning_rate": 4.401526943224822e-06,
+      "loss": 0.3121,
+      "step": 56
+    },
+    {
+      "epoch": 0.2289156626506024,
+      "grad_norm": 0.968943320545301,
+      "learning_rate": 4.3808987559489536e-06,
+      "loss": 0.3299,
+      "step": 57
+    },
+    {
+      "epoch": 0.23293172690763053,
+      "grad_norm": 0.9742834769427793,
+      "learning_rate": 4.359971162528248e-06,
+      "loss": 0.3317,
+      "step": 58
+    },
+    {
+      "epoch": 0.23694779116465864,
+      "grad_norm": 0.8615741806790194,
+      "learning_rate": 4.338747494269105e-06,
+      "loss": 0.3076,
+      "step": 59
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.8979608545089511,
+      "learning_rate": 4.317231129607859e-06,
+      "loss": 0.3275,
+      "step": 60
+    },
+    {
+      "epoch": 0.24497991967871485,
+      "grad_norm": 0.9825422664041035,
+      "learning_rate": 4.295425493572982e-06,
+      "loss": 0.3841,
+      "step": 61
+    },
+    {
+      "epoch": 0.24899598393574296,
+      "grad_norm": 0.9353992739567255,
+      "learning_rate": 4.273334057239884e-06,
+      "loss": 0.324,
+      "step": 62
+    },
+    {
+      "epoch": 0.25301204819277107,
+      "grad_norm": 0.9663920997998383,
+      "learning_rate": 4.2509603371783776e-06,
+      "loss": 0.308,
+      "step": 63
+    },
+    {
+      "epoch": 0.2570281124497992,
+      "grad_norm": 1.020408297495902,
+      "learning_rate": 4.228307894892902e-06,
+      "loss": 0.3522,
+      "step": 64
+    },
+    {
+      "epoch": 0.26104417670682734,
+      "grad_norm": 0.9580239366308128,
+      "learning_rate": 4.205380336255594e-06,
+      "loss": 0.2901,
+      "step": 65
+    },
+    {
+      "epoch": 0.26506024096385544,
+      "grad_norm": 0.9872990779734367,
+      "learning_rate": 4.1821813109322975e-06,
+      "loss": 0.348,
+      "step": 66
+    },
+    {
+      "epoch": 0.26907630522088355,
+      "grad_norm": 0.9201846742568568,
+      "learning_rate": 4.158714511801595e-06,
+      "loss": 0.3179,
+      "step": 67
+    },
+    {
+      "epoch": 0.27309236947791166,
+      "grad_norm": 0.8760099041031381,
+      "learning_rate": 4.134983674366974e-06,
+      "loss": 0.2958,
+      "step": 68
+    },
+    {
+      "epoch": 0.27710843373493976,
+      "grad_norm": 0.9304134001683236,
+      "learning_rate": 4.110992576162193e-06,
+      "loss": 0.3342,
+      "step": 69
+    },
+    {
+      "epoch": 0.28112449799196787,
+      "grad_norm": 1.0298631505831966,
+      "learning_rate": 4.08674503614997e-06,
+      "loss": 0.3847,
+      "step": 70
+    },
+    {
+      "epoch": 0.285140562248996,
+      "grad_norm": 0.9160315195337018,
+      "learning_rate": 4.062244914114068e-06,
+      "loss": 0.3467,
+      "step": 71
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 0.9313699764318901,
+      "learning_rate": 4.037496110044885e-06,
+      "loss": 0.3367,
+      "step": 72
+    },
+    {
+      "epoch": 0.2931726907630522,
+      "grad_norm": 1.0106406350843846,
+      "learning_rate": 4.012502563518641e-06,
+      "loss": 0.2797,
+      "step": 73
+    },
+    {
+      "epoch": 0.2971887550200803,
+      "grad_norm": 0.9027554935829752,
+      "learning_rate": 3.987268253070273e-06,
+      "loss": 0.3253,
+      "step": 74
+    },
+    {
+      "epoch": 0.30120481927710846,
+      "grad_norm": 0.8779933821419647,
+      "learning_rate": 3.961797195560118e-06,
+      "loss": 0.2731,
+      "step": 75
+    },
+    {
+      "epoch": 0.30522088353413657,
+      "grad_norm": 0.9085315306116011,
+      "learning_rate": 3.936093445534498e-06,
+      "loss": 0.3526,
+      "step": 76
+    },
+    {
+      "epoch": 0.3092369477911647,
+      "grad_norm": 0.9889033974145789,
+      "learning_rate": 3.910161094580309e-06,
+      "loss": 0.3421,
+      "step": 77
+    },
+    {
+      "epoch": 0.3132530120481928,
+      "grad_norm": 1.0188219722127239,
+      "learning_rate": 3.884004270673711e-06,
+      "loss": 0.3119,
+      "step": 78
+    },
+    {
+      "epoch": 0.3172690763052209,
+      "grad_norm": 1.09033561392929,
+      "learning_rate": 3.857627137523031e-06,
+      "loss": 0.3081,
+      "step": 79
+    },
+    {
+      "epoch": 0.321285140562249,
+      "grad_norm": 0.9405092490451631,
+      "learning_rate": 3.831033893905965e-06,
+      "loss": 0.3021,
+      "step": 80
+    },
+    {
+      "epoch": 0.3253012048192771,
+      "grad_norm": 0.9295303862150599,
+      "learning_rate": 3.8042287730012117e-06,
+      "loss": 0.2977,
+      "step": 81
+    },
+    {
+      "epoch": 0.3293172690763052,
+      "grad_norm": 0.9282109769014534,
+      "learning_rate": 3.7772160417146265e-06,
+      "loss": 0.3607,
+      "step": 82
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.9824429360273624,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.3549,
+      "step": 83
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 0.9784056217278692,
+      "learning_rate": 3.7225849801745835e-06,
+      "loss": 0.3159,
+      "step": 84
+    },
+    {
+      "epoch": 0.3413654618473896,
+      "grad_norm": 0.8658398764322316,
+      "learning_rate": 3.694975346229458e-06,
+      "loss": 0.3472,
+      "step": 85
+    },
+    {
+      "epoch": 0.3453815261044177,
+      "grad_norm": 0.8950256355153389,
+      "learning_rate": 3.6671754931348647e-06,
+      "loss": 0.3088,
+      "step": 86
+    },
+    {
+      "epoch": 0.3493975903614458,
+      "grad_norm": 0.9854526598682575,
+      "learning_rate": 3.6391898461406045e-06,
+      "loss": 0.3295,
+      "step": 87
+    },
+    {
+      "epoch": 0.3534136546184739,
+      "grad_norm": 0.9605871223212953,
+      "learning_rate": 3.61102286007161e-06,
+      "loss": 0.3167,
+      "step": 88
+    },
+    {
+      "epoch": 0.357429718875502,
+      "grad_norm": 0.948686275738336,
+      "learning_rate": 3.582679018618822e-06,
+      "loss": 0.3281,
+      "step": 89
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 0.881600487147473,
+      "learning_rate": 3.55416283362546e-06,
+      "loss": 0.3369,
+      "step": 90
+    },
+    {
+      "epoch": 0.3654618473895582,
+      "grad_norm": 0.960319289840297,
+      "learning_rate": 3.5254788443688188e-06,
+      "loss": 0.2926,
+      "step": 91
+    },
+    {
+      "epoch": 0.36947791164658633,
+      "grad_norm": 0.8864429602889681,
+      "learning_rate": 3.49663161683769e-06,
+      "loss": 0.3362,
+      "step": 92
+    },
+    {
+      "epoch": 0.37349397590361444,
+      "grad_norm": 0.936218129048692,
+      "learning_rate": 3.4676257430055438e-06,
+      "loss": 0.3127,
+      "step": 93
+    },
+    {
+      "epoch": 0.37751004016064255,
+      "grad_norm": 0.9266423950461504,
+      "learning_rate": 3.4384658400995606e-06,
+      "loss": 0.3227,
+      "step": 94
+    },
+    {
+      "epoch": 0.3815261044176707,
+      "grad_norm": 0.9454286007213476,
+      "learning_rate": 3.409156549865654e-06,
+      "loss": 0.3535,
+      "step": 95
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 0.9833851309571829,
+      "learning_rate": 3.3797025378295826e-06,
+      "loss": 0.3229,
+      "step": 96
+    },
+    {
+      "epoch": 0.3895582329317269,
+      "grad_norm": 0.8753521692846463,
+      "learning_rate": 3.350108492554284e-06,
+      "loss": 0.2994,
+      "step": 97
+    },
+    {
+      "epoch": 0.39357429718875503,
+      "grad_norm": 1.0547364280190044,
+      "learning_rate": 3.3203791248935335e-06,
+      "loss": 0.2942,
+      "step": 98
+    },
+    {
+      "epoch": 0.39759036144578314,
+      "grad_norm": 1.0320712869880992,
+      "learning_rate": 3.29051916724206e-06,
+      "loss": 0.3136,
+      "step": 99
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "grad_norm": 0.9221294969769842,
+      "learning_rate": 3.2605333727822335e-06,
+      "loss": 0.3414,
+      "step": 100
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "eval_loss": 0.2444542795419693,
+      "eval_runtime": 0.9334,
+      "eval_samples_per_second": 2.143,
+      "eval_steps_per_second": 1.071,
+      "step": 100
+    },
+    {
+      "epoch": 0.40562248995983935,
+      "grad_norm": 1.1951204611768427,
+      "learning_rate": 3.2304265147274394e-06,
+      "loss": 0.3283,
+      "step": 101
+    },
+    {
+      "epoch": 0.40963855421686746,
+      "grad_norm": 1.0857187093552796,
+      "learning_rate": 3.2002033855622683e-06,
+      "loss": 0.4056,
+      "step": 102
+    },
+    {
+      "epoch": 0.41365461847389556,
+      "grad_norm": 0.926034072527587,
+      "learning_rate": 3.1698687962796338e-06,
+      "loss": 0.307,
+      "step": 103
+    },
+    {
+      "epoch": 0.41767068273092367,
+      "grad_norm": 0.9397640507954169,
+      "learning_rate": 3.1394275756149507e-06,
+      "loss": 0.354,
+      "step": 104
+    },
+    {
+      "epoch": 0.42168674698795183,
+      "grad_norm": 0.8924145471459917,
+      "learning_rate": 3.1088845692774798e-06,
+      "loss": 0.3349,
+      "step": 105
+    },
+    {
+      "epoch": 0.42570281124497994,
+      "grad_norm": 0.869498130498454,
+      "learning_rate": 3.0782446391789834e-06,
+      "loss": 0.2843,
+      "step": 106
+    },
+    {
+      "epoch": 0.42971887550200805,
+      "grad_norm": 0.9000443704387898,
+      "learning_rate": 3.0475126626597828e-06,
+      "loss": 0.3013,
+      "step": 107
+    },
+    {
+      "epoch": 0.43373493975903615,
+      "grad_norm": 0.9045315827651242,
+      "learning_rate": 3.0166935317123824e-06,
+      "loss": 0.3325,
+      "step": 108
+    },
+    {
+      "epoch": 0.43775100401606426,
+      "grad_norm": 1.3130064165371518,
+      "learning_rate": 2.9857921522027443e-06,
+      "loss": 0.3291,
+      "step": 109
+    },
+    {
+      "epoch": 0.44176706827309237,
+      "grad_norm": 1.2125230221996564,
+      "learning_rate": 2.9548134430893605e-06,
+      "loss": 0.333,
+      "step": 110
+    },
+    {
+      "epoch": 0.4457831325301205,
+      "grad_norm": 0.8858999391729862,
+      "learning_rate": 2.9237623356402423e-06,
+      "loss": 0.3079,
+      "step": 111
+    },
+    {
+      "epoch": 0.4497991967871486,
+      "grad_norm": 0.9184414245701322,
+      "learning_rate": 2.8926437726479476e-06,
+      "loss": 0.2814,
+      "step": 112
+    },
+    {
+      "epoch": 0.4538152610441767,
+      "grad_norm": 0.8337575509868793,
+      "learning_rate": 2.8614627076427777e-06,
+      "loss": 0.2745,
+      "step": 113
+    },
+    {
+      "epoch": 0.4578313253012048,
+      "grad_norm": 0.9602239586027415,
+      "learning_rate": 2.8302241041042564e-06,
+      "loss": 0.3072,
+      "step": 114
+    },
+    {
+      "epoch": 0.46184738955823296,
+      "grad_norm": 0.8473688696867774,
+      "learning_rate": 2.7989329346710375e-06,
+      "loss": 0.3368,
+      "step": 115
+    },
+    {
+      "epoch": 0.46586345381526106,
+      "grad_norm": 0.8856562852420043,
+      "learning_rate": 2.7675941803493435e-06,
+      "loss": 0.3159,
+      "step": 116
+    },
+    {
+      "epoch": 0.46987951807228917,
+      "grad_norm": 0.8060464415211829,
+      "learning_rate": 2.7362128297200784e-06,
+      "loss": 0.2746,
+      "step": 117
+    },
+    {
+      "epoch": 0.4738955823293173,
+      "grad_norm": 0.9478997264745931,
+      "learning_rate": 2.704793878144731e-06,
+      "loss": 0.3444,
+      "step": 118
+    },
+    {
+      "epoch": 0.4779116465863454,
+      "grad_norm": 0.8623677074753655,
+      "learning_rate": 2.673342326970204e-06,
+      "loss": 0.2835,
+      "step": 119
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.9433731544499216,
+      "learning_rate": 2.6418631827326857e-06,
+      "loss": 0.2958,
+      "step": 120
+    },
+    {
+      "epoch": 0.4859437751004016,
+      "grad_norm": 0.9438165151710101,
+      "learning_rate": 2.6103614563606933e-06,
+      "loss": 0.3106,
+      "step": 121
+    },
+    {
+      "epoch": 0.4899598393574297,
+      "grad_norm": 1.0126289543705882,
+      "learning_rate": 2.578842162377429e-06,
+      "loss": 0.318,
+      "step": 122
+    },
+    {
+      "epoch": 0.4939759036144578,
+      "grad_norm": 0.8793953283304695,
+      "learning_rate": 2.547310318102548e-06,
+      "loss": 0.3058,
+      "step": 123
+    },
+    {
+      "epoch": 0.4979919678714859,
+      "grad_norm": 0.8366269333452555,
+      "learning_rate": 2.5157709428534936e-06,
+      "loss": 0.3136,
+      "step": 124
+    },
+    {
+      "epoch": 0.5020080321285141,
+      "grad_norm": 0.8456630579186564,
+      "learning_rate": 2.4842290571465068e-06,
+      "loss": 0.2879,
+      "step": 125
+    },
+    {
+      "epoch": 0.5060240963855421,
+      "grad_norm": 0.846125317510436,
+      "learning_rate": 2.4526896818974534e-06,
+      "loss": 0.295,
+      "step": 126
+    },
+    {
+      "epoch": 0.5100401606425703,
+      "grad_norm": 0.9948942123001171,
+      "learning_rate": 2.421157837622572e-06,
+      "loss": 0.3504,
+      "step": 127
+    },
+    {
+      "epoch": 0.5140562248995983,
+      "grad_norm": 0.8386465846111418,
+      "learning_rate": 2.3896385436393076e-06,
+      "loss": 0.2718,
+      "step": 128
+    },
+    {
+      "epoch": 0.5180722891566265,
+      "grad_norm": 0.9931462862199858,
+      "learning_rate": 2.358136817267315e-06,
+      "loss": 0.346,
+      "step": 129
+    },
+    {
+      "epoch": 0.5220883534136547,
+      "grad_norm": 0.9132982198772955,
+      "learning_rate": 2.326657673029796e-06,
+      "loss": 0.2684,
+      "step": 130
+    },
+    {
+      "epoch": 0.5261044176706827,
+      "grad_norm": 0.8104372881872128,
+      "learning_rate": 2.2952061218552692e-06,
+      "loss": 0.2578,
+      "step": 131
+    },
+    {
+      "epoch": 0.5301204819277109,
+      "grad_norm": 0.9234061899296159,
+      "learning_rate": 2.263787170279922e-06,
+      "loss": 0.3356,
+      "step": 132
+    },
+    {
+      "epoch": 0.5341365461847389,
+      "grad_norm": 0.8024400437631107,
+      "learning_rate": 2.232405819650657e-06,
+      "loss": 0.2665,
+      "step": 133
+    },
+    {
+      "epoch": 0.5381526104417671,
+      "grad_norm": 0.9544299960693641,
+      "learning_rate": 2.2010670653289624e-06,
+      "loss": 0.3338,
+      "step": 134
+    },
+    {
+      "epoch": 0.5421686746987951,
+      "grad_norm": 1.1684039390365473,
+      "learning_rate": 2.169775895895745e-06,
+      "loss": 0.3162,
+      "step": 135
+    },
+    {
+      "epoch": 0.5461847389558233,
+      "grad_norm": 0.8981710684464966,
+      "learning_rate": 2.1385372923572236e-06,
+      "loss": 0.3051,
+      "step": 136
+    },
+    {
+      "epoch": 0.5502008032128514,
+      "grad_norm": 0.8989374347879261,
+      "learning_rate": 2.1073562273520536e-06,
+      "loss": 0.2959,
+      "step": 137
+    },
+    {
+      "epoch": 0.5542168674698795,
+      "grad_norm": 0.9740871562824379,
+      "learning_rate": 2.0762376643597586e-06,
+      "loss": 0.3855,
+      "step": 138
+    },
+    {
+      "epoch": 0.5582329317269076,
+      "grad_norm": 0.8418831694627811,
+      "learning_rate": 2.0451865569106403e-06,
+      "loss": 0.2796,
+      "step": 139
+    },
+    {
+      "epoch": 0.5622489959839357,
+      "grad_norm": 0.9490528215001864,
+      "learning_rate": 2.014207847797256e-06,
+      "loss": 0.3197,
+      "step": 140
+    },
+    {
+      "epoch": 0.5662650602409639,
+      "grad_norm": 0.8904535775802285,
+      "learning_rate": 1.9833064682876175e-06,
+      "loss": 0.3097,
+      "step": 141
+    },
+    {
+      "epoch": 0.570281124497992,
+      "grad_norm": 0.8540248257584768,
+      "learning_rate": 1.952487337340218e-06,
+      "loss": 0.3169,
+      "step": 142
+    },
+    {
+      "epoch": 0.5742971887550201,
+      "grad_norm": 0.8311114610148337,
+      "learning_rate": 1.921755360821018e-06,
+      "loss": 0.2728,
+      "step": 143
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 0.8604090580769889,
+      "learning_rate": 1.8911154307225204e-06,
+      "loss": 0.2503,
+      "step": 144
+    },
+    {
+      "epoch": 0.5823293172690763,
+      "grad_norm": 0.9445719502903895,
+      "learning_rate": 1.8605724243850501e-06,
+      "loss": 0.3661,
+      "step": 145
+    },
+    {
+      "epoch": 0.5863453815261044,
+      "grad_norm": 0.8954718745898371,
+      "learning_rate": 1.8301312037203677e-06,
+      "loss": 0.2907,
+      "step": 146
+    },
+    {
+      "epoch": 0.5903614457831325,
+      "grad_norm": 0.8658078147526114,
+      "learning_rate": 1.7997966144377328e-06,
+      "loss": 0.2832,
+      "step": 147
+    },
+    {
+      "epoch": 0.5943775100401606,
+      "grad_norm": 0.8798049076569305,
+      "learning_rate": 1.769573485272562e-06,
+      "loss": 0.2703,
+      "step": 148
+    },
+    {
+      "epoch": 0.5983935742971888,
+      "grad_norm": 0.9166332225970434,
+      "learning_rate": 1.739466627217767e-06,
+      "loss": 0.2727,
+      "step": 149
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 0.8454353291506335,
+      "learning_rate": 1.7094808327579401e-06,
+      "loss": 0.2831,
+      "step": 150
+    },
+    {
+      "epoch": 0.606425702811245,
+      "grad_norm": 0.9126133879322927,
+      "learning_rate": 1.679620875106467e-06,
+      "loss": 0.3299,
+      "step": 151
+    },
+    {
+      "epoch": 0.6104417670682731,
+      "grad_norm": 0.8400684847025619,
+      "learning_rate": 1.6498915074457158e-06,
+      "loss": 0.2759,
+      "step": 152
+    },
+    {
+      "epoch": 0.6144578313253012,
+      "grad_norm": 1.1158835606550768,
+      "learning_rate": 1.6202974621704176e-06,
+      "loss": 0.4144,
+      "step": 153
+    },
+    {
+      "epoch": 0.6184738955823293,
+      "grad_norm": 0.8951620126724423,
+      "learning_rate": 1.590843450134347e-06,
+      "loss": 0.2816,
+      "step": 154
+    },
+    {
+      "epoch": 0.6224899598393574,
+      "grad_norm": 0.8606146622801194,
+      "learning_rate": 1.5615341599004408e-06,
+      "loss": 0.2631,
+      "step": 155
+    },
+    {
+      "epoch": 0.6265060240963856,
+      "grad_norm": 0.897791010063829,
+      "learning_rate": 1.5323742569944573e-06,
+      "loss": 0.3085,
+      "step": 156
+    },
+    {
+      "epoch": 0.6305220883534136,
+      "grad_norm": 0.8301094006947285,
+      "learning_rate": 1.5033683831623115e-06,
+      "loss": 0.2662,
+      "step": 157
+    },
+    {
+      "epoch": 0.6345381526104418,
+      "grad_norm": 1.023005502834577,
+      "learning_rate": 1.4745211556311823e-06,
+      "loss": 0.2754,
+      "step": 158
+    },
+    {
+      "epoch": 0.6385542168674698,
+      "grad_norm": 0.8773469246688017,
+      "learning_rate": 1.44583716637454e-06,
+      "loss": 0.2745,
+      "step": 159
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 0.8949059843168533,
+      "learning_rate": 1.417320981381179e-06,
+      "loss": 0.2935,
+      "step": 160
+    },
+    {
+      "epoch": 0.6465863453815262,
+      "grad_norm": 0.863999071570885,
+      "learning_rate": 1.3889771399283902e-06,
+      "loss": 0.3028,
+      "step": 161
+    },
+    {
+      "epoch": 0.6506024096385542,
+      "grad_norm": 0.8590344677080577,
+      "learning_rate": 1.3608101538593965e-06,
+      "loss": 0.304,
+      "step": 162
+    },
+    {
+      "epoch": 0.6546184738955824,
+      "grad_norm": 0.872557559723761,
+      "learning_rate": 1.332824506865135e-06,
+      "loss": 0.3003,
+      "step": 163
+    },
+    {
+      "epoch": 0.6586345381526104,
+      "grad_norm": 0.9264900800392235,
+      "learning_rate": 1.3050246537705424e-06,
+      "loss": 0.3527,
+      "step": 164
+    },
+    {
+      "epoch": 0.6626506024096386,
+      "grad_norm": 0.9657440387945403,
+      "learning_rate": 1.277415019825417e-06,
+      "loss": 0.3171,
+      "step": 165
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.9371751021919456,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.2624,
+      "step": 166
+    },
+    {
+      "epoch": 0.6706827309236948,
+      "grad_norm": 0.8521322466094515,
+      "learning_rate": 1.2227839582853737e-06,
+      "loss": 0.2982,
+      "step": 167
+    },
+    {
+      "epoch": 0.6746987951807228,
+      "grad_norm": 1.0152101047071984,
+      "learning_rate": 1.195771226998789e-06,
+      "loss": 0.362,
+      "step": 168
+    },
+    {
+      "epoch": 0.678714859437751,
+      "grad_norm": 0.8665101487373718,
+      "learning_rate": 1.1689661060940366e-06,
+      "loss": 0.2973,
+      "step": 169
+    },
+    {
+      "epoch": 0.6827309236947792,
+      "grad_norm": 0.8158808275561102,
+      "learning_rate": 1.1423728624769694e-06,
+      "loss": 0.2765,
+      "step": 170
+    },
+    {
+      "epoch": 0.6867469879518072,
+      "grad_norm": 0.9491312131861737,
+      "learning_rate": 1.1159957293262888e-06,
+      "loss": 0.3193,
+      "step": 171
+    },
+    {
+      "epoch": 0.6907630522088354,
+      "grad_norm": 1.0154902751042207,
+      "learning_rate": 1.0898389054196912e-06,
+      "loss": 0.418,
+      "step": 172
+    },
+    {
+      "epoch": 0.6947791164658634,
+      "grad_norm": 0.8756826749462664,
+      "learning_rate": 1.0639065544655034e-06,
+      "loss": 0.2812,
+      "step": 173
+    },
+    {
+      "epoch": 0.6987951807228916,
+      "grad_norm": 0.8489315276663506,
+      "learning_rate": 1.0382028044398823e-06,
+      "loss": 0.3433,
+      "step": 174
+    },
+    {
+      "epoch": 0.7028112449799196,
+      "grad_norm": 1.3430085997094816,
+      "learning_rate": 1.0127317469297277e-06,
+      "loss": 0.3253,
+      "step": 175
+    },
+    {
+      "epoch": 0.7068273092369478,
+      "grad_norm": 0.8650932771542087,
+      "learning_rate": 9.874974364813594e-07,
+      "loss": 0.266,
+      "step": 176
+    },
+    {
+      "epoch": 0.7108433734939759,
+      "grad_norm": 0.9845310341416343,
+      "learning_rate": 9.625038899551162e-07,
+      "loss": 0.3141,
+      "step": 177
+    },
+    {
+      "epoch": 0.714859437751004,
+      "grad_norm": 0.9077769989817156,
+      "learning_rate": 9.377550858859325e-07,
+      "loss": 0.3187,
+      "step": 178
+    },
+    {
+      "epoch": 0.7188755020080321,
+      "grad_norm": 0.7913054226741821,
+      "learning_rate": 9.132549638500307e-07,
+      "loss": 0.2784,
+      "step": 179
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.9635260951247112,
+      "learning_rate": 8.890074238378074e-07,
+      "loss": 0.3243,
+      "step": 180
+    },
+    {
+      "epoch": 0.7269076305220884,
+      "grad_norm": 0.8976458789949958,
+      "learning_rate": 8.650163256330271e-07,
+      "loss": 0.2574,
+      "step": 181
+    },
+    {
+      "epoch": 0.7309236947791165,
+      "grad_norm": 0.8369854189565434,
+      "learning_rate": 8.412854881984056e-07,
+      "loss": 0.2778,
+      "step": 182
+    },
+    {
+      "epoch": 0.7349397590361446,
+      "grad_norm": 0.8303213044797815,
+      "learning_rate": 8.178186890677029e-07,
+      "loss": 0.272,
+      "step": 183
+    },
+    {
+      "epoch": 0.7389558232931727,
+      "grad_norm": 0.8693684478819016,
+      "learning_rate": 7.94619663744406e-07,
+      "loss": 0.2979,
+      "step": 184
+    },
+    {
+      "epoch": 0.7429718875502008,
+      "grad_norm": 0.8952474924101241,
+      "learning_rate": 7.71692105107098e-07,
+      "loss": 0.3243,
+      "step": 185
+    },
+    {
+      "epoch": 0.7469879518072289,
+      "grad_norm": 0.8701660615965138,
+      "learning_rate": 7.490396628216237e-07,
+      "loss": 0.3045,
+      "step": 186
+    },
+    {
+      "epoch": 0.751004016064257,
+      "grad_norm": 1.3403658627429307,
+      "learning_rate": 7.26665942760117e-07,
+      "loss": 0.3466,
+      "step": 187
+    },
+    {
+      "epoch": 0.7550200803212851,
+      "grad_norm": 0.8170947479511871,
+      "learning_rate": 7.045745064270187e-07,
+      "loss": 0.2677,
+      "step": 188
+    },
+    {
+      "epoch": 0.7590361445783133,
+      "grad_norm": 0.8909793428078998,
+      "learning_rate": 6.827688703921407e-07,
+      "loss": 0.3087,
+      "step": 189
+    },
+    {
+      "epoch": 0.7630522088353414,
+      "grad_norm": 1.3467915728955462,
+      "learning_rate": 6.61252505730895e-07,
+      "loss": 0.3273,
+      "step": 190
+    },
+    {
+      "epoch": 0.7670682730923695,
+      "grad_norm": 0.8656699807321914,
+      "learning_rate": 6.400288374717534e-07,
+      "loss": 0.2695,
+      "step": 191
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "grad_norm": 0.9347923964159922,
+      "learning_rate": 6.191012440510469e-07,
+      "loss": 0.3405,
+      "step": 192
+    },
+    {
+      "epoch": 0.7751004016064257,
+      "grad_norm": 0.8900800862951639,
+      "learning_rate": 5.984730567751787e-07,
+      "loss": 0.2968,
+      "step": 193
+    },
+    {
+      "epoch": 0.7791164658634538,
+      "grad_norm": 0.8653314986783313,
+      "learning_rate": 5.781475592903337e-07,
+      "loss": 0.2858,
+      "step": 194
+    },
+    {
+      "epoch": 0.7831325301204819,
+      "grad_norm": 1.597823782198494,
+      "learning_rate": 5.581279870597866e-07,
+      "loss": 0.4297,
+      "step": 195
+    },
+    {
+      "epoch": 0.7871485943775101,
+      "grad_norm": 0.9370451095711089,
+      "learning_rate": 5.38417526848864e-07,
+      "loss": 0.3367,
+      "step": 196
+    },
+    {
+      "epoch": 0.7911646586345381,
+      "grad_norm": 0.8228825833731124,
+      "learning_rate": 5.190193162176754e-07,
+      "loss": 0.2804,
+      "step": 197
+    },
+    {
+      "epoch": 0.7951807228915663,
+      "grad_norm": 0.8801990441637932,
+      "learning_rate": 4.999364430216639e-07,
+      "loss": 0.2939,
+      "step": 198
+    },
+    {
+      "epoch": 0.7991967871485943,
+      "grad_norm": 0.825692265923809,
+      "learning_rate": 4.811719449200755e-07,
+      "loss": 0.2827,
+      "step": 199
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "grad_norm": 0.9003585979560632,
+      "learning_rate": 4.6272880889241563e-07,
+      "loss": 0.2978,
+      "step": 200
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "eval_loss": 0.23421859741210938,
+      "eval_runtime": 0.9292,
+      "eval_samples_per_second": 2.152,
+      "eval_steps_per_second": 1.076,
+      "step": 200
+    },
+    {
+      "epoch": 0.8072289156626506,
+      "grad_norm": 0.9627424648323483,
+      "learning_rate": 4.4460997076297504e-07,
+      "loss": 0.3036,
+      "step": 201
+    },
+    {
+      "epoch": 0.8112449799196787,
+      "grad_norm": 0.8702804973430297,
+      "learning_rate": 4.2681831473349896e-07,
+      "loss": 0.2942,
+      "step": 202
+    },
+    {
+      "epoch": 0.8152610441767069,
+      "grad_norm": 0.9280806159398163,
+      "learning_rate": 4.093566729240708e-07,
+      "loss": 0.3199,
+      "step": 203
+    },
+    {
+      "epoch": 0.8192771084337349,
+      "grad_norm": 0.8568960890728319,
+      "learning_rate": 3.922278249222894e-07,
+      "loss": 0.3158,
+      "step": 204
+    },
+    {
+      "epoch": 0.8232931726907631,
+      "grad_norm": 0.7968710685288891,
+      "learning_rate": 3.754344973408064e-07,
+      "loss": 0.2809,
+      "step": 205
+    },
+    {
+      "epoch": 0.8273092369477911,
+      "grad_norm": 1.0407547143150109,
+      "learning_rate": 3.5897936338329995e-07,
+      "loss": 0.3014,
+      "step": 206
+    },
+    {
+      "epoch": 0.8313253012048193,
+      "grad_norm": 0.8069859870734059,
+      "learning_rate": 3.4286504241894283e-07,
+      "loss": 0.2903,
+      "step": 207
+    },
+    {
+      "epoch": 0.8353413654618473,
+      "grad_norm": 1.0814136325243136,
+      "learning_rate": 3.2709409956545065e-07,
+      "loss": 0.3376,
+      "step": 208
+    },
+    {
+      "epoch": 0.8393574297188755,
+      "grad_norm": 0.7858772398221392,
+      "learning_rate": 3.1166904528075247e-07,
+      "loss": 0.2503,
+      "step": 209
+    },
+    {
+      "epoch": 0.8433734939759037,
+      "grad_norm": 0.905650990370268,
+      "learning_rate": 2.965923349633779e-07,
+      "loss": 0.2972,
+      "step": 210
+    },
+    {
+      "epoch": 0.8473895582329317,
+      "grad_norm": 0.8662172360948996,
+      "learning_rate": 2.8186636856159605e-07,
+      "loss": 0.282,
+      "step": 211
+    },
+    {
+      "epoch": 0.8514056224899599,
+      "grad_norm": 0.8511470828803235,
+      "learning_rate": 2.6749349019138585e-07,
+      "loss": 0.2918,
+      "step": 212
+    },
+    {
+      "epoch": 0.8554216867469879,
+      "grad_norm": 0.8359253771306859,
+      "learning_rate": 2.53475987763295e-07,
+      "loss": 0.2991,
+      "step": 213
+    },
+    {
+      "epoch": 0.8594377510040161,
+      "grad_norm": 0.9975494620913441,
+      "learning_rate": 2.3981609261824384e-07,
+      "loss": 0.342,
+      "step": 214
+    },
+    {
+      "epoch": 0.8634538152610441,
+      "grad_norm": 1.0809297611012123,
+      "learning_rate": 2.2651597917233731e-07,
+      "loss": 0.3218,
+      "step": 215
+    },
+    {
+      "epoch": 0.8674698795180723,
+      "grad_norm": 1.1130934352081199,
+      "learning_rate": 2.135777645707318e-07,
+      "loss": 0.3587,
+      "step": 216
+    },
+    {
+      "epoch": 0.8714859437751004,
+      "grad_norm": 0.9537508577870649,
+      "learning_rate": 2.0100350835062705e-07,
+      "loss": 0.3273,
+      "step": 217
+    },
+    {
+      "epoch": 0.8755020080321285,
+      "grad_norm": 1.4788682462508134,
+      "learning_rate": 1.8879521211341956e-07,
+      "loss": 0.3335,
+      "step": 218
+    },
+    {
+      "epoch": 0.8795180722891566,
+      "grad_norm": 0.8506232902095459,
+      "learning_rate": 1.7695481920608716e-07,
+      "loss": 0.3231,
+      "step": 219
+    },
+    {
+      "epoch": 0.8835341365461847,
+      "grad_norm": 0.8905330845805612,
+      "learning_rate": 1.6548421441183876e-07,
+      "loss": 0.3265,
+      "step": 220
+    },
+    {
+      "epoch": 0.8875502008032129,
+      "grad_norm": 0.7977254481659033,
+      "learning_rate": 1.5438522365009258e-07,
+      "loss": 0.2498,
+      "step": 221
+    },
+    {
+      "epoch": 0.891566265060241,
+      "grad_norm": 0.862345127303285,
+      "learning_rate": 1.4365961368581844e-07,
+      "loss": 0.2963,
+      "step": 222
+    },
+    {
+      "epoch": 0.8955823293172691,
+      "grad_norm": 1.0794864460550275,
+      "learning_rate": 1.3330909184830265e-07,
+      "loss": 0.3422,
+      "step": 223
+    },
+    {
+      "epoch": 0.8995983935742972,
+      "grad_norm": 0.873663212320996,
+      "learning_rate": 1.233353057593703e-07,
+      "loss": 0.3094,
+      "step": 224
+    },
+    {
+      "epoch": 0.9036144578313253,
+      "grad_norm": 0.9147950726071266,
+      "learning_rate": 1.137398430711123e-07,
+      "loss": 0.3314,
+      "step": 225
+    },
+    {
+      "epoch": 0.9076305220883534,
+      "grad_norm": 0.8039064134929814,
+      "learning_rate": 1.0452423121315835e-07,
+      "loss": 0.2793,
+      "step": 226
+    },
+    {
+      "epoch": 0.9116465863453815,
+      "grad_norm": 0.9218934282270528,
+      "learning_rate": 9.568993714953818e-08,
+      "loss": 0.3052,
+      "step": 227
+    },
+    {
+      "epoch": 0.9156626506024096,
+      "grad_norm": 0.8969496531746132,
+      "learning_rate": 8.723836714516681e-08,
+      "loss": 0.3106,
+      "step": 228
+    },
+    {
+      "epoch": 0.9196787148594378,
+      "grad_norm": 0.9043540492214749,
+      "learning_rate": 7.91708665419899e-08,
+      "loss": 0.3244,
+      "step": 229
+    },
+    {
+      "epoch": 0.9236947791164659,
+      "grad_norm": 0.918623809791028,
+      "learning_rate": 7.148871954483106e-08,
+      "loss": 0.3409,
+      "step": 230
+    },
+    {
+      "epoch": 0.927710843373494,
+      "grad_norm": 0.8484551203481032,
+      "learning_rate": 6.419314901696671e-08,
+      "loss": 0.2569,
+      "step": 231
+    },
+    {
+      "epoch": 0.9317269076305221,
+      "grad_norm": 0.9656189814215682,
+      "learning_rate": 5.728531628546946e-08,
+      "loss": 0.2572,
+      "step": 232
+    },
+    {
+      "epoch": 0.9357429718875502,
+      "grad_norm": 0.8305911140313081,
+      "learning_rate": 5.076632095634526e-08,
+      "loss": 0.29,
+      "step": 233
+    },
+    {
+      "epoch": 0.9397590361445783,
+      "grad_norm": 0.9503861816095891,
+      "learning_rate": 4.4637200739493514e-08,
+      "loss": 0.3242,
+      "step": 234
+    },
+    {
+      "epoch": 0.9437751004016064,
+      "grad_norm": 0.7870798549507464,
+      "learning_rate": 3.8898931283523346e-08,
+      "loss": 0.2738,
+      "step": 235
+    },
+    {
+      "epoch": 0.9477911646586346,
+      "grad_norm": 0.884818665943328,
+      "learning_rate": 3.355242602044728e-08,
+      "loss": 0.3054,
+      "step": 236
+    },
+    {
+      "epoch": 0.9518072289156626,
+      "grad_norm": 0.8760903542537833,
+      "learning_rate": 2.8598536020278678e-08,
+      "loss": 0.2997,
+      "step": 237
+    },
+    {
+      "epoch": 0.9558232931726908,
+      "grad_norm": 0.917070852870084,
+      "learning_rate": 2.403804985555619e-08,
+      "loss": 0.2741,
+      "step": 238
+    },
+    {
+      "epoch": 0.9598393574297188,
+      "grad_norm": 0.8638066796975681,
+      "learning_rate": 1.9871693475816965e-08,
+      "loss": 0.3034,
+      "step": 239
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.7725860523375615,
+      "learning_rate": 1.6100130092037704e-08,
+      "loss": 0.2513,
+      "step": 240
+    },
+    {
+      "epoch": 0.9678714859437751,
+      "grad_norm": 0.9206177368400107,
+      "learning_rate": 1.2723960071064356e-08,
+      "loss": 0.2952,
+      "step": 241
+    },
+    {
+      "epoch": 0.9718875502008032,
+      "grad_norm": 0.8723786868567743,
+      "learning_rate": 9.743720840042491e-09,
+      "loss": 0.2645,
+      "step": 242
+    },
+    {
+      "epoch": 0.9759036144578314,
+      "grad_norm": 0.8412811527099655,
+      "learning_rate": 7.159886800869875e-09,
+      "loss": 0.3033,
+      "step": 243
+    },
+    {
+      "epoch": 0.9799196787148594,
+      "grad_norm": 0.8457140234763789,
+      "learning_rate": 4.9728692546791024e-09,
+      "loss": 0.2963,
+      "step": 244
+    },
+    {
+      "epoch": 0.9839357429718876,
+      "grad_norm": 0.8051862487813095,
+      "learning_rate": 3.1830163363655296e-09,
+      "loss": 0.2747,
+      "step": 245
+    },
+    {
+      "epoch": 0.9879518072289156,
+      "grad_norm": 0.921998387335435,
+      "learning_rate": 1.7906129591713228e-09,
+      "loss": 0.3044,
+      "step": 246
+    },
+    {
+      "epoch": 0.9919678714859438,
+      "grad_norm": 0.810769463455257,
+      "learning_rate": 7.95880769331181e-10,
+      "loss": 0.2705,
+      "step": 247
+    },
+    {
+      "epoch": 0.9959839357429718,
+      "grad_norm": 0.833127615424353,
+      "learning_rate": 1.9897811079055973e-10,
+      "loss": 0.2825,
+      "step": 248
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8643050505177121,
+      "learning_rate": 0.0,
+      "loss": 0.2814,
+      "step": 249
+    },
+    {
+      "epoch": 1.0,
+      "step": 249,
+      "total_flos": 47804940288000.0,
+      "train_loss": 0.3352415738215887,
+      "train_runtime": 943.4636,
+      "train_samples_per_second": 2.108,
+      "train_steps_per_second": 0.264
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 249,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 47804940288000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8207ae7dee1f09354673794a3f0782f7059590a415511ea4a07e0c8af4e7b1ad
+size 7160