Upload folder using huggingface_hub

.gitattributes

@@ -45,3 +45,4 @@ agenttrek-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 webrl-llama/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 atomic_expert/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 test_admin/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen2-gob-plan-115/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen2-gob-plan-115/README.md

@@ -0,0 +1,73 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen2-gob115-1epoch
+  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. -->
+
+# qwen2-gob115-1epoch
+
+This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Qwen2.5-7B-Instruct) on the gob-plan-115 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2078
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.8213        | 0.1187 | 500  | 0.7408          |
+| 0.5742        | 0.2374 | 1000 | 0.6352          |
+| 0.5326        | 0.3562 | 1500 | 0.5120          |
+| 0.4165        | 0.4749 | 2000 | 0.4213          |
+| 0.4129        | 0.5936 | 2500 | 0.3469          |
+| 0.345         | 0.7123 | 3000 | 0.2756          |
+| 0.1919        | 0.8311 | 3500 | 0.2285          |
+| 0.2301        | 0.9498 | 4000 | 0.2088          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

qwen2-gob-plan-115/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
+}

qwen2-gob-plan-115/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.20783543586730957,
+    "eval_runtime": 2007.8977,
+    "eval_samples_per_second": 1.865,
+    "eval_steps_per_second": 0.466,
+    "total_flos": 449297978753024.0,
+    "train_loss": 0.44325452399106674,
+    "train_runtime": 138200.0012,
+    "train_samples_per_second": 0.244,
+    "train_steps_per_second": 0.03
+}

qwen2-gob-plan-115/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

qwen2-gob-plan-115/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

qwen2-gob-plan-115/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.20783543586730957,
+    "eval_runtime": 2007.8977,
+    "eval_samples_per_second": 1.865,
+    "eval_steps_per_second": 0.466
+}

qwen2-gob-plan-115/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

qwen2-gob-plan-115/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eaed636e2a362995a2ae1e3d93417296f0817299ea421e2081480ec8a7f5a4d
+size 4877660776

qwen2-gob-plan-115/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455e8fedb210c68589f7191fd0f57633c876c80cbd1314a2bf9f9f287ec2e5f6
+size 4932751008

qwen2-gob-plan-115/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae00c76c424b973d8fa11db8fd032a3dcf52f1f810262c98c21f136fb2aee37
+size 4330865200

qwen2-gob-plan-115/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33164791e5562ae2390bbd4b8984dc603d6b5691b9b98483b1047cb1b97c1a27
+size 1089994880

qwen2-gob-plan-115/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 333312,
+    "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"
+  }
+}

qwen2-gob-plan-115/runs/Jan16_22-04-04_hgx001/events.out.tfevents.1768572504.hgx001.402760.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece68b4cbb87edc64c9572bcf73c9163a912df43e4211608d030ccd63d96dbb1
+size 6219

qwen2-gob-plan-115/runs/Jan16_22-18-02_hgx001/events.out.tfevents.1768573293.hgx001.407010.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50d602f17273ff234e0e9d044eefbe5a227265fe9a927b3296de5dac47449880
+size 6426

qwen2-gob-plan-115/runs/Jan16_22-33-49_hgx001/events.out.tfevents.1768574249.hgx001.412455.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127f87043cd9a855049a272574423d8548a73954ba79861e2bfd89b4bb405090
+size 7047

qwen2-gob-plan-115/runs/Jan16_23-25-23_hgx001/events.out.tfevents.1768577364.hgx001.425689.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:981855c3e3b230945e5c6aef116945f9e638bdccae695576be6c6c014090b9d3
+size 6219

qwen2-gob-plan-115/runs/Jan16_23-34-59_hgx001/events.out.tfevents.1768577955.hgx001.430957.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716a5d1630147fc12ff400ebf5287732d0b16aa3be8f57f77f64e4e4deb08b77
+size 7047

qwen2-gob-plan-115/runs/Jan17_00-14-02_hgx001/events.out.tfevents.1768580289.hgx001.438329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9cf17fcae66da4f5b0367dcf8009641e206caaa7a1a3e5c1383785068918e7e
+size 6840

qwen2-gob-plan-115/runs/Jan17_00-52-50_hgx001/events.out.tfevents.1768582598.hgx001.445580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15941577af486535ac0b0f5d76d4a534714f12e5d5ce18ef22835100cad3818
+size 97524

qwen2-gob-plan-115/runs/Jan17_00-52-50_hgx001/events.out.tfevents.1768722851.hgx001.445580.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42799118eae238125172c4e42c26147a288f17881c3c1c80eeb9fc26237bdb4a
+size 359

qwen2-gob-plan-115/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
+  }
+}

qwen2-gob-plan-115/tokenizer.json

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

qwen2-gob-plan-115/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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen2-gob-plan-115/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 449297978753024.0,
+    "train_loss": 0.44325452399106674,
+    "train_runtime": 138200.0012,
+    "train_samples_per_second": 0.244,
+    "train_steps_per_second": 0.03
+}

qwen2-gob-plan-115/trainer_log.jsonl

@@ -0,0 +1,430 @@
+{"current_steps": 10, "total_steps": 4212, "loss": 2.1021, "lr": 2.1327014218009483e-06, "epoch": 0.0023744509082274726, "percentage": 0.24, "elapsed_time": "0:05:48", "remaining_time": "1 day, 16:38:56"}
+{"current_steps": 20, "total_steps": 4212, "loss": 1.0168, "lr": 4.502369668246446e-06, "epoch": 0.004748901816454945, "percentage": 0.47, "elapsed_time": "0:11:10", "remaining_time": "1 day, 15:02:26"}
+{"current_steps": 30, "total_steps": 4212, "loss": 0.6508, "lr": 6.8720379146919435e-06, "epoch": 0.007123352724682417, "percentage": 0.71, "elapsed_time": "0:17:06", "remaining_time": "1 day, 15:45:49"}
+{"current_steps": 40, "total_steps": 4212, "loss": 0.5579, "lr": 9.24170616113744e-06, "epoch": 0.00949780363290989, "percentage": 0.95, "elapsed_time": "0:21:30", "remaining_time": "1 day, 13:24:05"}
+{"current_steps": 50, "total_steps": 4212, "loss": 0.5911, "lr": 1.161137440758294e-05, "epoch": 0.011872254541137363, "percentage": 1.19, "elapsed_time": "0:26:59", "remaining_time": "1 day, 13:27:11"}
+{"current_steps": 60, "total_steps": 4212, "loss": 0.5363, "lr": 1.3981042654028437e-05, "epoch": 0.014246705449364834, "percentage": 1.42, "elapsed_time": "0:32:04", "remaining_time": "1 day, 12:59:45"}
+{"current_steps": 70, "total_steps": 4212, "loss": 0.5813, "lr": 1.6350710900473933e-05, "epoch": 0.016621156357592308, "percentage": 1.66, "elapsed_time": "0:36:17", "remaining_time": "1 day, 11:47:42"}
+{"current_steps": 80, "total_steps": 4212, "loss": 0.5928, "lr": 1.872037914691943e-05, "epoch": 0.01899560726581978, "percentage": 1.9, "elapsed_time": "0:41:03", "remaining_time": "1 day, 11:20:45"}
+{"current_steps": 90, "total_steps": 4212, "loss": 0.5576, "lr": 2.109004739336493e-05, "epoch": 0.021370058174047253, "percentage": 2.14, "elapsed_time": "0:45:43", "remaining_time": "1 day, 10:54:16"}
+{"current_steps": 100, "total_steps": 4212, "loss": 0.5891, "lr": 2.345971563981043e-05, "epoch": 0.023744509082274726, "percentage": 2.37, "elapsed_time": "0:49:40", "remaining_time": "1 day, 10:02:52"}
+{"current_steps": 110, "total_steps": 4212, "loss": 0.6125, "lr": 2.5829383886255927e-05, "epoch": 0.026118959990502195, "percentage": 2.61, "elapsed_time": "0:55:00", "remaining_time": "1 day, 10:11:28"}
+{"current_steps": 120, "total_steps": 4212, "loss": 0.5772, "lr": 2.8199052132701424e-05, "epoch": 0.028493410898729667, "percentage": 2.85, "elapsed_time": "0:59:18", "remaining_time": "1 day, 9:42:31"}
+{"current_steps": 130, "total_steps": 4212, "loss": 0.6367, "lr": 3.056872037914692e-05, "epoch": 0.03086786180695714, "percentage": 3.09, "elapsed_time": "1:04:39", "remaining_time": "1 day, 9:50:02"}
+{"current_steps": 140, "total_steps": 4212, "loss": 0.6695, "lr": 3.293838862559242e-05, "epoch": 0.033242312715184616, "percentage": 3.32, "elapsed_time": "1:09:42", "remaining_time": "1 day, 9:47:43"}
+{"current_steps": 150, "total_steps": 4212, "loss": 0.6226, "lr": 3.530805687203792e-05, "epoch": 0.03561676362341209, "percentage": 3.56, "elapsed_time": "1:14:55", "remaining_time": "1 day, 9:48:49"}
+{"current_steps": 160, "total_steps": 4212, "loss": 0.6079, "lr": 3.767772511848342e-05, "epoch": 0.03799121453163956, "percentage": 3.8, "elapsed_time": "1:19:19", "remaining_time": "1 day, 9:28:51"}
+{"current_steps": 170, "total_steps": 4212, "loss": 0.6063, "lr": 4.004739336492891e-05, "epoch": 0.040365665439867034, "percentage": 4.04, "elapsed_time": "1:24:55", "remaining_time": "1 day, 9:39:07"}
+{"current_steps": 180, "total_steps": 4212, "loss": 0.5927, "lr": 4.2417061611374406e-05, "epoch": 0.042740116348094506, "percentage": 4.27, "elapsed_time": "1:29:44", "remaining_time": "1 day, 9:30:18"}
+{"current_steps": 190, "total_steps": 4212, "loss": 0.6349, "lr": 4.478672985781991e-05, "epoch": 0.04511456725632198, "percentage": 4.51, "elapsed_time": "1:34:21", "remaining_time": "1 day, 9:17:28"}
+{"current_steps": 200, "total_steps": 4212, "loss": 0.6307, "lr": 4.71563981042654e-05, "epoch": 0.04748901816454945, "percentage": 4.75, "elapsed_time": "1:38:34", "remaining_time": "1 day, 8:57:22"}
+{"current_steps": 210, "total_steps": 4212, "loss": 0.6583, "lr": 4.95260663507109e-05, "epoch": 0.04986346907277692, "percentage": 4.99, "elapsed_time": "1:43:41", "remaining_time": "1 day, 8:55:56"}
+{"current_steps": 220, "total_steps": 4212, "loss": 0.7049, "lr": 5.1895734597156396e-05, "epoch": 0.05223791998100439, "percentage": 5.22, "elapsed_time": "1:49:31", "remaining_time": "1 day, 9:07:25"}
+{"current_steps": 230, "total_steps": 4212, "loss": 0.6285, "lr": 5.42654028436019e-05, "epoch": 0.05461237088923186, "percentage": 5.46, "elapsed_time": "1:53:55", "remaining_time": "1 day, 8:52:18"}
+{"current_steps": 240, "total_steps": 4212, "loss": 0.6836, "lr": 5.66350710900474e-05, "epoch": 0.056986821797459335, "percentage": 5.7, "elapsed_time": "1:59:01", "remaining_time": "1 day, 8:49:56"}
+{"current_steps": 250, "total_steps": 4212, "loss": 0.641, "lr": 5.90047393364929e-05, "epoch": 0.05936127270568681, "percentage": 5.94, "elapsed_time": "2:03:48", "remaining_time": "1 day, 8:42:00"}
+{"current_steps": 260, "total_steps": 4212, "loss": 0.6517, "lr": 6.137440758293839e-05, "epoch": 0.06173572361391428, "percentage": 6.17, "elapsed_time": "2:08:16", "remaining_time": "1 day, 8:29:45"}
+{"current_steps": 270, "total_steps": 4212, "loss": 0.7061, "lr": 6.374407582938389e-05, "epoch": 0.06411017452214175, "percentage": 6.41, "elapsed_time": "2:13:09", "remaining_time": "1 day, 8:24:03"}
+{"current_steps": 280, "total_steps": 4212, "loss": 0.9615, "lr": 6.611374407582939e-05, "epoch": 0.06648462543036923, "percentage": 6.65, "elapsed_time": "2:17:17", "remaining_time": "1 day, 8:08:02"}
+{"current_steps": 290, "total_steps": 4212, "loss": 0.7798, "lr": 6.848341232227489e-05, "epoch": 0.0688590763385967, "percentage": 6.89, "elapsed_time": "2:22:17", "remaining_time": "1 day, 8:04:17"}
+{"current_steps": 300, "total_steps": 4212, "loss": 0.6821, "lr": 7.085308056872039e-05, "epoch": 0.07123352724682418, "percentage": 7.12, "elapsed_time": "2:27:03", "remaining_time": "1 day, 7:57:43"}
+{"current_steps": 310, "total_steps": 4212, "loss": 0.6711, "lr": 7.322274881516588e-05, "epoch": 0.07360797815505164, "percentage": 7.36, "elapsed_time": "2:31:14", "remaining_time": "1 day, 7:43:45"}
+{"current_steps": 320, "total_steps": 4212, "loss": 0.6888, "lr": 7.559241706161138e-05, "epoch": 0.07598242906327912, "percentage": 7.6, "elapsed_time": "2:35:33", "remaining_time": "1 day, 7:31:53"}
+{"current_steps": 330, "total_steps": 4212, "loss": 0.8411, "lr": 7.796208530805688e-05, "epoch": 0.07835687997150659, "percentage": 7.83, "elapsed_time": "2:39:48", "remaining_time": "1 day, 7:19:58"}
+{"current_steps": 340, "total_steps": 4212, "loss": 0.6802, "lr": 8.033175355450238e-05, "epoch": 0.08073133087973407, "percentage": 8.07, "elapsed_time": "2:44:55", "remaining_time": "1 day, 7:18:11"}
+{"current_steps": 350, "total_steps": 4212, "loss": 0.7479, "lr": 8.270142180094788e-05, "epoch": 0.08310578178796153, "percentage": 8.31, "elapsed_time": "2:49:42", "remaining_time": "1 day, 7:12:31"}
+{"current_steps": 360, "total_steps": 4212, "loss": 0.7292, "lr": 8.507109004739337e-05, "epoch": 0.08548023269618901, "percentage": 8.55, "elapsed_time": "2:54:32", "remaining_time": "1 day, 7:07:39"}
+{"current_steps": 370, "total_steps": 4212, "loss": 0.6956, "lr": 8.744075829383887e-05, "epoch": 0.08785468360441648, "percentage": 8.78, "elapsed_time": "2:59:11", "remaining_time": "1 day, 7:00:41"}
+{"current_steps": 380, "total_steps": 4212, "loss": 0.7527, "lr": 8.981042654028437e-05, "epoch": 0.09022913451264396, "percentage": 9.02, "elapsed_time": "3:04:19", "remaining_time": "1 day, 6:58:47"}
+{"current_steps": 390, "total_steps": 4212, "loss": 0.7719, "lr": 9.218009478672986e-05, "epoch": 0.09260358542087142, "percentage": 9.26, "elapsed_time": "3:09:45", "remaining_time": "1 day, 6:59:41"}
+{"current_steps": 400, "total_steps": 4212, "loss": 0.7168, "lr": 9.454976303317536e-05, "epoch": 0.0949780363290989, "percentage": 9.5, "elapsed_time": "3:14:20", "remaining_time": "1 day, 6:52:04"}
+{"current_steps": 410, "total_steps": 4212, "loss": 0.8366, "lr": 9.691943127962086e-05, "epoch": 0.09735248723732637, "percentage": 9.73, "elapsed_time": "3:19:23", "remaining_time": "1 day, 6:49:03"}
+{"current_steps": 420, "total_steps": 4212, "loss": 0.7962, "lr": 9.928909952606635e-05, "epoch": 0.09972693814555383, "percentage": 9.97, "elapsed_time": "3:24:39", "remaining_time": "1 day, 6:47:50"}
+{"current_steps": 430, "total_steps": 4212, "loss": 0.8253, "lr": 9.999915830219296e-05, "epoch": 0.10210138905378131, "percentage": 10.21, "elapsed_time": "3:28:50", "remaining_time": "1 day, 6:36:53"}
+{"current_steps": 440, "total_steps": 4212, "loss": 0.7228, "lr": 9.999503576890838e-05, "epoch": 0.10447583996200878, "percentage": 10.45, "elapsed_time": "3:33:30", "remaining_time": "1 day, 6:30:24"}
+{"current_steps": 450, "total_steps": 4212, "loss": 0.8091, "lr": 9.998747808549429e-05, "epoch": 0.10685029087023626, "percentage": 10.68, "elapsed_time": "3:38:11", "remaining_time": "1 day, 6:24:02"}
+{"current_steps": 460, "total_steps": 4212, "loss": 0.8117, "lr": 9.997648577123782e-05, "epoch": 0.10922474177846372, "percentage": 10.92, "elapsed_time": "3:43:30", "remaining_time": "1 day, 6:23:01"}
+{"current_steps": 470, "total_steps": 4212, "loss": 0.7577, "lr": 9.996205958141894e-05, "epoch": 0.1115991926866912, "percentage": 11.16, "elapsed_time": "3:48:41", "remaining_time": "1 day, 6:20:46"}
+{"current_steps": 480, "total_steps": 4212, "loss": 0.8031, "lr": 9.994420050725863e-05, "epoch": 0.11397364359491867, "percentage": 11.4, "elapsed_time": "3:53:58", "remaining_time": "1 day, 6:19:05"}
+{"current_steps": 490, "total_steps": 4212, "loss": 0.7887, "lr": 9.992290977585072e-05, "epoch": 0.11634809450314615, "percentage": 11.63, "elapsed_time": "3:59:17", "remaining_time": "1 day, 6:17:39"}
+{"current_steps": 500, "total_steps": 4212, "loss": 0.8213, "lr": 9.989818885007766e-05, "epoch": 0.11872254541137361, "percentage": 11.87, "elapsed_time": "4:04:33", "remaining_time": "1 day, 6:15:36"}
+{"current_steps": 500, "total_steps": 4212, "eval_loss": 0.7407782077789307, "epoch": 0.11872254541137361, "percentage": 11.87, "elapsed_time": "4:37:58", "remaining_time": "1 day, 10:23:42"}
+{"current_steps": 510, "total_steps": 4212, "loss": 0.7828, "lr": 9.987003942850989e-05, "epoch": 0.1210969963196011, "percentage": 12.11, "elapsed_time": "4:42:31", "remaining_time": "1 day, 10:10:50"}
+{"current_steps": 520, "total_steps": 4212, "loss": 0.7454, "lr": 9.983846344528923e-05, "epoch": 0.12347144722782856, "percentage": 12.35, "elapsed_time": "4:47:26", "remaining_time": "1 day, 10:00:53"}
+{"current_steps": 530, "total_steps": 4212, "loss": 0.6686, "lr": 9.980346306999596e-05, "epoch": 0.12584589813605604, "percentage": 12.58, "elapsed_time": "4:52:47", "remaining_time": "1 day, 9:54:06"}
+{"current_steps": 540, "total_steps": 4212, "loss": 0.9724, "lr": 9.976504070749969e-05, "epoch": 0.1282203490442835, "percentage": 12.82, "elapsed_time": "4:57:26", "remaining_time": "1 day, 9:42:36"}
+{"current_steps": 550, "total_steps": 4212, "loss": 0.735, "lr": 9.972319899779422e-05, "epoch": 0.13059479995251097, "percentage": 13.06, "elapsed_time": "5:02:27", "remaining_time": "1 day, 9:33:51"}
+{"current_steps": 560, "total_steps": 4212, "loss": 0.7613, "lr": 9.967794081581606e-05, "epoch": 0.13296925086073846, "percentage": 13.3, "elapsed_time": "5:07:00", "remaining_time": "1 day, 9:22:06"}
+{"current_steps": 570, "total_steps": 4212, "loss": 0.7509, "lr": 9.962926927124697e-05, "epoch": 0.13534370176896593, "percentage": 13.53, "elapsed_time": "5:11:36", "remaining_time": "1 day, 9:10:57"}
+{"current_steps": 580, "total_steps": 4212, "loss": 0.7055, "lr": 9.957718770830022e-05, "epoch": 0.1377181526771934, "percentage": 13.77, "elapsed_time": "5:16:38", "remaining_time": "1 day, 9:02:50"}
+{"current_steps": 590, "total_steps": 4212, "loss": 0.7494, "lr": 9.952169970549088e-05, "epoch": 0.14009260358542086, "percentage": 14.01, "elapsed_time": "5:21:39", "remaining_time": "1 day, 8:54:41"}
+{"current_steps": 600, "total_steps": 4212, "loss": 0.7347, "lr": 9.946280907538985e-05, "epoch": 0.14246705449364835, "percentage": 14.25, "elapsed_time": "5:26:10", "remaining_time": "1 day, 8:43:35"}
+{"current_steps": 610, "total_steps": 4212, "loss": 0.6848, "lr": 9.940051986436198e-05, "epoch": 0.14484150540187582, "percentage": 14.48, "elapsed_time": "5:30:58", "remaining_time": "1 day, 8:34:22"}
+{"current_steps": 620, "total_steps": 4212, "loss": 0.7168, "lr": 9.933483635228804e-05, "epoch": 0.14721595631010329, "percentage": 14.72, "elapsed_time": "5:35:34", "remaining_time": "1 day, 8:24:11"}
+{"current_steps": 630, "total_steps": 4212, "loss": 0.7163, "lr": 9.926576305227063e-05, "epoch": 0.14959040721833075, "percentage": 14.96, "elapsed_time": "5:40:34", "remaining_time": "1 day, 8:16:24"}
+{"current_steps": 640, "total_steps": 4212, "loss": 0.639, "lr": 9.919330471032401e-05, "epoch": 0.15196485812655824, "percentage": 15.19, "elapsed_time": "5:45:52", "remaining_time": "1 day, 8:10:23"}
+{"current_steps": 650, "total_steps": 4212, "loss": 0.6972, "lr": 9.911746630504818e-05, "epoch": 0.1543393090347857, "percentage": 15.43, "elapsed_time": "5:50:40", "remaining_time": "1 day, 8:01:39"}
+{"current_steps": 660, "total_steps": 4212, "loss": 0.7853, "lr": 9.903825304728664e-05, "epoch": 0.15671375994301318, "percentage": 15.67, "elapsed_time": "5:55:33", "remaining_time": "1 day, 7:53:31"}
+{"current_steps": 670, "total_steps": 4212, "loss": 0.6616, "lr": 9.895567037976842e-05, "epoch": 0.15908821085124064, "percentage": 15.91, "elapsed_time": "6:00:26", "remaining_time": "1 day, 7:45:31"}
+{"current_steps": 680, "total_steps": 4212, "loss": 0.6649, "lr": 9.88697239767341e-05, "epoch": 0.16146266175946813, "percentage": 16.14, "elapsed_time": "6:04:53", "remaining_time": "1 day, 7:35:19"}
+{"current_steps": 690, "total_steps": 4212, "loss": 0.7677, "lr": 9.878041974354598e-05, "epoch": 0.1638371126676956, "percentage": 16.38, "elapsed_time": "6:09:53", "remaining_time": "1 day, 7:28:04"}
+{"current_steps": 700, "total_steps": 4212, "loss": 0.7151, "lr": 9.868776381628218e-05, "epoch": 0.16621156357592307, "percentage": 16.62, "elapsed_time": "6:14:34", "remaining_time": "1 day, 7:19:19"}
+{"current_steps": 710, "total_steps": 4212, "loss": 0.8004, "lr": 9.859176256131522e-05, "epoch": 0.16858601448415053, "percentage": 16.86, "elapsed_time": "6:19:06", "remaining_time": "1 day, 7:09:52"}
+{"current_steps": 720, "total_steps": 4212, "loss": 0.686, "lr": 9.849242257487447e-05, "epoch": 0.17096046539237802, "percentage": 17.09, "elapsed_time": "6:23:58", "remaining_time": "1 day, 7:02:15"}
+{"current_steps": 730, "total_steps": 4212, "loss": 0.7076, "lr": 9.838975068259297e-05, "epoch": 0.1733349163006055, "percentage": 17.33, "elapsed_time": "6:29:16", "remaining_time": "1 day, 6:56:46"}
+{"current_steps": 740, "total_steps": 4212, "loss": 0.7879, "lr": 9.828375393903842e-05, "epoch": 0.17570936720883296, "percentage": 17.57, "elapsed_time": "6:34:13", "remaining_time": "1 day, 6:49:41"}
+{"current_steps": 750, "total_steps": 4212, "loss": 0.72, "lr": 9.817443962722843e-05, "epoch": 0.17808381811706042, "percentage": 17.81, "elapsed_time": "6:39:23", "remaining_time": "1 day, 6:43:34"}
+{"current_steps": 760, "total_steps": 4212, "loss": 0.7231, "lr": 9.806181525813019e-05, "epoch": 0.18045826902528792, "percentage": 18.04, "elapsed_time": "6:44:10", "remaining_time": "1 day, 6:35:47"}
+{"current_steps": 770, "total_steps": 4212, "loss": 0.6952, "lr": 9.79458885701443e-05, "epoch": 0.18283271993351538, "percentage": 18.28, "elapsed_time": "6:48:36", "remaining_time": "1 day, 6:26:31"}
+{"current_steps": 780, "total_steps": 4212, "loss": 0.6398, "lr": 9.782666752857317e-05, "epoch": 0.18520717084174285, "percentage": 18.52, "elapsed_time": "6:53:37", "remaining_time": "1 day, 6:19:55"}
+{"current_steps": 790, "total_steps": 4212, "loss": 0.7202, "lr": 9.770416032507361e-05, "epoch": 0.1875816217499703, "percentage": 18.76, "elapsed_time": "6:58:09", "remaining_time": "1 day, 6:11:16"}
+{"current_steps": 800, "total_steps": 4212, "loss": 0.6733, "lr": 9.757837537709407e-05, "epoch": 0.1899560726581978, "percentage": 18.99, "elapsed_time": "7:03:06", "remaining_time": "1 day, 6:04:33"}
+{"current_steps": 810, "total_steps": 4212, "loss": 0.7764, "lr": 9.744932132729625e-05, "epoch": 0.19233052356642527, "percentage": 19.23, "elapsed_time": "7:07:30", "remaining_time": "1 day, 5:55:31"}
+{"current_steps": 820, "total_steps": 4212, "loss": 0.6662, "lr": 9.731700704296126e-05, "epoch": 0.19470497447465274, "percentage": 19.47, "elapsed_time": "7:12:44", "remaining_time": "1 day, 5:50:05"}
+{"current_steps": 830, "total_steps": 4212, "loss": 0.6228, "lr": 9.71814416153803e-05, "epoch": 0.1970794253828802, "percentage": 19.71, "elapsed_time": "7:18:39", "remaining_time": "1 day, 5:47:23"}
+{"current_steps": 840, "total_steps": 4212, "loss": 0.6479, "lr": 9.704263435923014e-05, "epoch": 0.19945387629110767, "percentage": 19.94, "elapsed_time": "7:24:38", "remaining_time": "1 day, 5:44:53"}
+{"current_steps": 850, "total_steps": 4212, "loss": 0.8001, "lr": 9.690059481193295e-05, "epoch": 0.20182832719933516, "percentage": 20.18, "elapsed_time": "7:29:59", "remaining_time": "1 day, 5:39:49"}
+{"current_steps": 860, "total_steps": 4212, "loss": 0.5831, "lr": 9.675533273300111e-05, "epoch": 0.20420277810756263, "percentage": 20.42, "elapsed_time": "7:35:30", "remaining_time": "1 day, 5:35:23"}
+{"current_steps": 870, "total_steps": 4212, "loss": 0.6441, "lr": 9.660685810336654e-05, "epoch": 0.2065772290157901, "percentage": 20.66, "elapsed_time": "7:40:51", "remaining_time": "1 day, 5:30:21"}
+{"current_steps": 880, "total_steps": 4212, "loss": 0.6613, "lr": 9.645518112469498e-05, "epoch": 0.20895167992401756, "percentage": 20.89, "elapsed_time": "7:45:39", "remaining_time": "1 day, 5:23:09"}
+{"current_steps": 890, "total_steps": 4212, "loss": 0.5891, "lr": 9.630031221868501e-05, "epoch": 0.21132613083224505, "percentage": 21.13, "elapsed_time": "7:50:09", "remaining_time": "1 day, 5:14:54"}
+{"current_steps": 900, "total_steps": 4212, "loss": 0.6525, "lr": 9.614226202635195e-05, "epoch": 0.21370058174047252, "percentage": 21.37, "elapsed_time": "7:55:29", "remaining_time": "1 day, 5:09:46"}
+{"current_steps": 910, "total_steps": 4212, "loss": 0.6435, "lr": 9.59810414072968e-05, "epoch": 0.21607503264869998, "percentage": 21.6, "elapsed_time": "8:00:09", "remaining_time": "1 day, 5:02:15"}
+{"current_steps": 920, "total_steps": 4212, "loss": 0.689, "lr": 9.581666143895994e-05, "epoch": 0.21844948355692745, "percentage": 21.84, "elapsed_time": "8:05:19", "remaining_time": "1 day, 4:56:35"}
+{"current_steps": 930, "total_steps": 4212, "loss": 0.6445, "lr": 9.564913341586017e-05, "epoch": 0.22082393446515494, "percentage": 22.08, "elapsed_time": "8:11:38", "remaining_time": "1 day, 4:55:01"}
+{"current_steps": 940, "total_steps": 4212, "loss": 0.6848, "lr": 9.547846884881853e-05, "epoch": 0.2231983853733824, "percentage": 22.32, "elapsed_time": "8:16:24", "remaining_time": "1 day, 4:47:56"}
+{"current_steps": 950, "total_steps": 4212, "loss": 0.6939, "lr": 9.530467946416745e-05, "epoch": 0.22557283628160987, "percentage": 22.55, "elapsed_time": "8:20:53", "remaining_time": "1 day, 4:39:54"}
+{"current_steps": 960, "total_steps": 4212, "loss": 0.6167, "lr": 9.512777720294504e-05, "epoch": 0.22794728718983734, "percentage": 22.79, "elapsed_time": "8:25:23", "remaining_time": "1 day, 4:32:01"}
+{"current_steps": 970, "total_steps": 4212, "loss": 0.6839, "lr": 9.494777422007462e-05, "epoch": 0.23032173809806483, "percentage": 23.03, "elapsed_time": "8:30:13", "remaining_time": "1 day, 4:25:16"}
+{"current_steps": 980, "total_steps": 4212, "loss": 0.5922, "lr": 9.476468288352951e-05, "epoch": 0.2326961890062923, "percentage": 23.27, "elapsed_time": "8:35:07", "remaining_time": "1 day, 4:18:53"}
+{"current_steps": 990, "total_steps": 4212, "loss": 0.5699, "lr": 9.457851577348332e-05, "epoch": 0.23507063991451976, "percentage": 23.5, "elapsed_time": "8:39:30", "remaining_time": "1 day, 4:10:45"}
+{"current_steps": 1000, "total_steps": 4212, "loss": 0.5742, "lr": 9.438928568144547e-05, "epoch": 0.23744509082274723, "percentage": 23.74, "elapsed_time": "8:43:58", "remaining_time": "1 day, 4:02:59"}
+{"current_steps": 1000, "total_steps": 4212, "eval_loss": 0.6352267861366272, "epoch": 0.23744509082274723, "percentage": 23.74, "elapsed_time": "9:17:18", "remaining_time": "1 day, 5:50:05"}
+{"current_steps": 1010, "total_steps": 4212, "loss": 0.6413, "lr": 9.41970056093824e-05, "epoch": 0.23981954173097472, "percentage": 23.98, "elapsed_time": "9:22:38", "remaining_time": "1 day, 5:43:43"}
+{"current_steps": 1020, "total_steps": 4212, "loss": 0.6281, "lr": 9.400168876882408e-05, "epoch": 0.2421939926392022, "percentage": 24.22, "elapsed_time": "9:27:40", "remaining_time": "1 day, 5:36:29"}
+{"current_steps": 1030, "total_steps": 4212, "loss": 0.6787, "lr": 9.380334857995629e-05, "epoch": 0.24456844354742965, "percentage": 24.45, "elapsed_time": "9:32:27", "remaining_time": "1 day, 5:28:29"}
+{"current_steps": 1040, "total_steps": 4212, "loss": 0.6043, "lr": 9.360199867069866e-05, "epoch": 0.24694289445565712, "percentage": 24.69, "elapsed_time": "9:36:56", "remaining_time": "1 day, 5:19:41"}
+{"current_steps": 1050, "total_steps": 4212, "loss": 0.5633, "lr": 9.339765287576803e-05, "epoch": 0.2493173453638846, "percentage": 24.93, "elapsed_time": "9:41:25", "remaining_time": "1 day, 5:10:55"}
+{"current_steps": 1060, "total_steps": 4212, "loss": 0.7124, "lr": 9.319032523572815e-05, "epoch": 0.2516917962721121, "percentage": 25.17, "elapsed_time": "9:46:09", "remaining_time": "1 day, 5:03:00"}
+{"current_steps": 1070, "total_steps": 4212, "loss": 0.5931, "lr": 9.298002999602471e-05, "epoch": 0.25406624718033954, "percentage": 25.4, "elapsed_time": "9:50:45", "remaining_time": "1 day, 4:54:42"}
+{"current_steps": 1080, "total_steps": 4212, "loss": 0.724, "lr": 9.276678160600674e-05, "epoch": 0.256440698088567, "percentage": 25.64, "elapsed_time": "9:56:23", "remaining_time": "1 day, 4:49:31"}
+{"current_steps": 1090, "total_steps": 4212, "loss": 0.6224, "lr": 9.255059471793369e-05, "epoch": 0.2588151489967945, "percentage": 25.88, "elapsed_time": "10:01:28", "remaining_time": "1 day, 4:42:45"}
+{"current_steps": 1100, "total_steps": 4212, "loss": 0.5864, "lr": 9.233148418596862e-05, "epoch": 0.26118959990502194, "percentage": 26.12, "elapsed_time": "10:06:53", "remaining_time": "1 day, 4:36:57"}
+{"current_steps": 1110, "total_steps": 4212, "loss": 0.5933, "lr": 9.210946506515777e-05, "epoch": 0.26356405081324946, "percentage": 26.35, "elapsed_time": "10:12:10", "remaining_time": "1 day, 4:30:47"}
+{"current_steps": 1120, "total_steps": 4212, "loss": 0.5608, "lr": 9.188455261039592e-05, "epoch": 0.2659385017214769, "percentage": 26.59, "elapsed_time": "10:16:19", "remaining_time": "1 day, 4:21:28"}
+{"current_steps": 1130, "total_steps": 4212, "loss": 0.5591, "lr": 9.165676227537836e-05, "epoch": 0.2683129526297044, "percentage": 26.83, "elapsed_time": "10:20:54", "remaining_time": "1 day, 4:13:30"}
+{"current_steps": 1140, "total_steps": 4212, "loss": 0.6269, "lr": 9.1426109711539e-05, "epoch": 0.27068740353793186, "percentage": 27.07, "elapsed_time": "10:26:29", "remaining_time": "1 day, 4:08:13"}
+{"current_steps": 1150, "total_steps": 4212, "loss": 0.5785, "lr": 9.1192610766975e-05, "epoch": 0.2730618544461593, "percentage": 27.3, "elapsed_time": "10:31:23", "remaining_time": "1 day, 4:01:09"}
+{"current_steps": 1160, "total_steps": 4212, "loss": 0.7172, "lr": 9.095628148535788e-05, "epoch": 0.2754363053543868, "percentage": 27.54, "elapsed_time": "10:36:19", "remaining_time": "1 day, 3:54:12"}
+{"current_steps": 1170, "total_steps": 4212, "loss": 0.5275, "lr": 9.071713810483103e-05, "epoch": 0.27781075626261426, "percentage": 27.78, "elapsed_time": "10:40:41", "remaining_time": "1 day, 3:45:47"}
+{"current_steps": 1180, "total_steps": 4212, "loss": 0.6399, "lr": 9.047519705689418e-05, "epoch": 0.2801852071708417, "percentage": 28.02, "elapsed_time": "10:46:18", "remaining_time": "1 day, 3:40:41"}
+{"current_steps": 1190, "total_steps": 4212, "loss": 0.6105, "lr": 9.023047496527423e-05, "epoch": 0.28255965807906924, "percentage": 28.25, "elapsed_time": "10:51:00", "remaining_time": "1 day, 3:33:14"}
+{"current_steps": 1200, "total_steps": 4212, "loss": 0.609, "lr": 8.998298864478314e-05, "epoch": 0.2849341089872967, "percentage": 28.49, "elapsed_time": "10:56:21", "remaining_time": "1 day, 3:27:27"}
+{"current_steps": 1210, "total_steps": 4212, "loss": 0.5436, "lr": 8.973275510016252e-05, "epoch": 0.2873085598955242, "percentage": 28.73, "elapsed_time": "11:00:32", "remaining_time": "1 day, 3:18:48"}
+{"current_steps": 1220, "total_steps": 4212, "loss": 0.5398, "lr": 8.947979152491533e-05, "epoch": 0.28968301080375164, "percentage": 28.96, "elapsed_time": "11:05:34", "remaining_time": "1 day, 3:12:17"}
+{"current_steps": 1230, "total_steps": 4212, "loss": 0.5829, "lr": 8.922411530012433e-05, "epoch": 0.2920574617119791, "percentage": 29.2, "elapsed_time": "11:10:28", "remaining_time": "1 day, 3:05:29"}
+{"current_steps": 1240, "total_steps": 4212, "loss": 0.5319, "lr": 8.89657439932581e-05, "epoch": 0.29443191262020657, "percentage": 29.44, "elapsed_time": "11:14:29", "remaining_time": "1 day, 2:56:36"}
+{"current_steps": 1250, "total_steps": 4212, "loss": 0.5556, "lr": 8.870469535696375e-05, "epoch": 0.29680636352843404, "percentage": 29.68, "elapsed_time": "11:19:10", "remaining_time": "1 day, 2:49:21"}
+{"current_steps": 1260, "total_steps": 4212, "loss": 0.5374, "lr": 8.844098732784723e-05, "epoch": 0.2991808144366615, "percentage": 29.91, "elapsed_time": "11:24:04", "remaining_time": "1 day, 2:42:40"}
+{"current_steps": 1270, "total_steps": 4212, "loss": 0.5525, "lr": 8.817463802524096e-05, "epoch": 0.30155526534488897, "percentage": 30.15, "elapsed_time": "11:29:21", "remaining_time": "1 day, 2:36:55"}
+{"current_steps": 1280, "total_steps": 4212, "loss": 0.6688, "lr": 8.79056657499587e-05, "epoch": 0.3039297162531165, "percentage": 30.39, "elapsed_time": "11:36:04", "remaining_time": "1 day, 2:34:26"}
+{"current_steps": 1290, "total_steps": 4212, "loss": 0.5966, "lr": 8.763408898303829e-05, "epoch": 0.30630416716134395, "percentage": 30.63, "elapsed_time": "11:40:28", "remaining_time": "1 day, 2:26:39"}
+{"current_steps": 1300, "total_steps": 4212, "loss": 0.606, "lr": 8.73599263844717e-05, "epoch": 0.3086786180695714, "percentage": 30.86, "elapsed_time": "11:46:15", "remaining_time": "1 day, 2:22:01"}
+{"current_steps": 1310, "total_steps": 4212, "loss": 0.5279, "lr": 8.708319679192293e-05, "epoch": 0.3110530689777989, "percentage": 31.1, "elapsed_time": "11:50:53", "remaining_time": "1 day, 2:14:47"}
+{"current_steps": 1320, "total_steps": 4212, "loss": 0.568, "lr": 8.680391921943371e-05, "epoch": 0.31342751988602635, "percentage": 31.34, "elapsed_time": "11:55:08", "remaining_time": "1 day, 2:06:47"}
+{"current_steps": 1330, "total_steps": 4212, "loss": 0.583, "lr": 8.652211285611701e-05, "epoch": 0.3158019707942538, "percentage": 31.58, "elapsed_time": "11:59:49", "remaining_time": "1 day, 1:59:48"}
+{"current_steps": 1340, "total_steps": 4212, "loss": 0.6056, "lr": 8.623779706483855e-05, "epoch": 0.3181764217024813, "percentage": 31.81, "elapsed_time": "12:04:03", "remaining_time": "1 day, 1:51:50"}
+{"current_steps": 1350, "total_steps": 4212, "loss": 0.5846, "lr": 8.595099138088644e-05, "epoch": 0.32055087261070875, "percentage": 32.05, "elapsed_time": "12:09:06", "remaining_time": "1 day, 1:45:42"}
+{"current_steps": 1360, "total_steps": 4212, "loss": 0.5304, "lr": 8.566171551062889e-05, "epoch": 0.32292532351893627, "percentage": 32.29, "elapsed_time": "12:14:47", "remaining_time": "1 day, 1:40:55"}
+{"current_steps": 1370, "total_steps": 4212, "loss": 0.584, "lr": 8.536998933016014e-05, "epoch": 0.32529977442716373, "percentage": 32.53, "elapsed_time": "12:19:09", "remaining_time": "1 day, 1:33:20"}
+{"current_steps": 1380, "total_steps": 4212, "loss": 0.6155, "lr": 8.507583288393479e-05, "epoch": 0.3276742253353912, "percentage": 32.76, "elapsed_time": "12:23:50", "remaining_time": "1 day, 1:26:29"}
+{"current_steps": 1390, "total_steps": 4212, "loss": 0.5219, "lr": 8.477926638339067e-05, "epoch": 0.33004867624361867, "percentage": 33.0, "elapsed_time": "12:29:25", "remaining_time": "1 day, 1:21:30"}
+{"current_steps": 1400, "total_steps": 4212, "loss": 0.4953, "lr": 8.448031020555993e-05, "epoch": 0.33242312715184613, "percentage": 33.24, "elapsed_time": "12:33:50", "remaining_time": "1 day, 1:14:09"}
+{"current_steps": 1410, "total_steps": 4212, "loss": 0.5899, "lr": 8.417898489166905e-05, "epoch": 0.3347975780600736, "percentage": 33.48, "elapsed_time": "12:39:11", "remaining_time": "1 day, 1:08:40"}
+{"current_steps": 1420, "total_steps": 4212, "loss": 0.5992, "lr": 8.387531114572746e-05, "epoch": 0.33717202896830106, "percentage": 33.71, "elapsed_time": "12:44:32", "remaining_time": "1 day, 1:03:15"}
+{"current_steps": 1430, "total_steps": 4212, "loss": 0.5268, "lr": 8.356930983310493e-05, "epoch": 0.33954647987652853, "percentage": 33.95, "elapsed_time": "12:50:00", "remaining_time": "1 day, 0:58:01"}
+{"current_steps": 1440, "total_steps": 4212, "loss": 0.5396, "lr": 8.32610019790979e-05, "epoch": 0.34192093078475605, "percentage": 34.19, "elapsed_time": "12:54:24", "remaining_time": "1 day, 0:50:44"}
+{"current_steps": 1450, "total_steps": 4212, "loss": 0.5868, "lr": 8.295040876748489e-05, "epoch": 0.3442953816929835, "percentage": 34.43, "elapsed_time": "12:58:59", "remaining_time": "1 day, 0:43:50"}
+{"current_steps": 1460, "total_steps": 4212, "loss": 0.5431, "lr": 8.263755153907095e-05, "epoch": 0.346669832601211, "percentage": 34.66, "elapsed_time": "13:03:22", "remaining_time": "1 day, 0:36:35"}
+{"current_steps": 1470, "total_steps": 4212, "loss": 0.5288, "lr": 8.23224517902213e-05, "epoch": 0.34904428350943845, "percentage": 34.9, "elapsed_time": "13:08:33", "remaining_time": "1 day, 0:30:53"}
+{"current_steps": 1480, "total_steps": 4212, "loss": 0.5153, "lr": 8.200513117138435e-05, "epoch": 0.3514187344176659, "percentage": 35.14, "elapsed_time": "13:14:01", "remaining_time": "1 day, 0:25:44"}
+{"current_steps": 1490, "total_steps": 4212, "loss": 0.5482, "lr": 8.168561148560414e-05, "epoch": 0.3537931853258934, "percentage": 35.38, "elapsed_time": "13:18:22", "remaining_time": "1 day, 0:18:30"}
+{"current_steps": 1500, "total_steps": 4212, "loss": 0.5326, "lr": 8.136391468702214e-05, "epoch": 0.35616763623412084, "percentage": 35.61, "elapsed_time": "13:23:26", "remaining_time": "1 day, 0:12:36"}
+{"current_steps": 1500, "total_steps": 4212, "eval_loss": 0.5119722485542297, "epoch": 0.35616763623412084, "percentage": 35.61, "elapsed_time": "13:56:53", "remaining_time": "1 day, 1:13:05"}
+{"current_steps": 1510, "total_steps": 4212, "loss": 0.6232, "lr": 8.104006287936892e-05, "epoch": 0.3585420871423483, "percentage": 35.85, "elapsed_time": "14:01:01", "remaining_time": "1 day, 1:04:56"}
+{"current_steps": 1520, "total_steps": 4212, "loss": 0.4939, "lr": 8.07140783144453e-05, "epoch": 0.36091653805057583, "percentage": 36.09, "elapsed_time": "14:05:49", "remaining_time": "1 day, 0:58:00"}
+{"current_steps": 1530, "total_steps": 4212, "loss": 0.4444, "lr": 8.038598339059351e-05, "epoch": 0.3632909889588033, "percentage": 36.32, "elapsed_time": "14:11:08", "remaining_time": "1 day, 0:51:59"}
+{"current_steps": 1540, "total_steps": 4212, "loss": 0.4768, "lr": 8.005580065115816e-05, "epoch": 0.36566543986703076, "percentage": 36.56, "elapsed_time": "14:15:04", "remaining_time": "1 day, 0:43:37"}
+{"current_steps": 1550, "total_steps": 4212, "loss": 0.479, "lr": 7.972355278293733e-05, "epoch": 0.3680398907752582, "percentage": 36.8, "elapsed_time": "14:19:44", "remaining_time": "1 day, 0:36:32"}
+{"current_steps": 1560, "total_steps": 4212, "loss": 0.4734, "lr": 7.938926261462366e-05, "epoch": 0.3704143416834857, "percentage": 37.04, "elapsed_time": "14:24:23", "remaining_time": "1 day, 0:29:27"}
+{"current_steps": 1570, "total_steps": 4212, "loss": 0.5425, "lr": 7.905295311523595e-05, "epoch": 0.37278879259171316, "percentage": 37.27, "elapsed_time": "14:29:05", "remaining_time": "1 day, 0:22:31"}
+{"current_steps": 1580, "total_steps": 4212, "loss": 0.4818, "lr": 7.871464739254084e-05, "epoch": 0.3751632434999406, "percentage": 37.51, "elapsed_time": "14:34:21", "remaining_time": "1 day, 0:16:31"}
+{"current_steps": 1590, "total_steps": 4212, "loss": 0.496, "lr": 7.837436869146517e-05, "epoch": 0.3775376944081681, "percentage": 37.75, "elapsed_time": "14:38:55", "remaining_time": "1 day, 0:09:24"}
+{"current_steps": 1600, "total_steps": 4212, "loss": 0.5389, "lr": 7.80321403924987e-05, "epoch": 0.3799121453163956, "percentage": 37.99, "elapsed_time": "14:43:35", "remaining_time": "1 day, 0:02:27"}
+{"current_steps": 1610, "total_steps": 4212, "loss": 0.489, "lr": 7.768798601008776e-05, "epoch": 0.3822865962246231, "percentage": 38.22, "elapsed_time": "14:47:56", "remaining_time": "23:55:02"}
+{"current_steps": 1620, "total_steps": 4212, "loss": 0.4599, "lr": 7.734192919101958e-05, "epoch": 0.38466104713285054, "percentage": 38.46, "elapsed_time": "14:52:52", "remaining_time": "23:48:35"}
+{"current_steps": 1630, "total_steps": 4212, "loss": 0.6238, "lr": 7.69939937127974e-05, "epoch": 0.387035498041078, "percentage": 38.7, "elapsed_time": "14:58:04", "remaining_time": "23:42:36"}
+{"current_steps": 1640, "total_steps": 4212, "loss": 0.4984, "lr": 7.664420348200689e-05, "epoch": 0.3894099489493055, "percentage": 38.94, "elapsed_time": "15:03:27", "remaining_time": "23:36:53"}
+{"current_steps": 1650, "total_steps": 4212, "loss": 0.4746, "lr": 7.629258253267332e-05, "epoch": 0.39178439985753294, "percentage": 39.17, "elapsed_time": "15:08:17", "remaining_time": "23:30:19"}
+{"current_steps": 1660, "total_steps": 4212, "loss": 0.5243, "lr": 7.593915502461042e-05, "epoch": 0.3941588507657604, "percentage": 39.41, "elapsed_time": "15:13:59", "remaining_time": "23:25:07"}
+{"current_steps": 1670, "total_steps": 4212, "loss": 0.5353, "lr": 7.558394524176023e-05, "epoch": 0.39653330167398787, "percentage": 39.65, "elapsed_time": "15:18:54", "remaining_time": "23:18:43"}
+{"current_steps": 1680, "total_steps": 4212, "loss": 0.5151, "lr": 7.522697759052451e-05, "epoch": 0.39890775258221534, "percentage": 39.89, "elapsed_time": "15:24:09", "remaining_time": "23:12:50"}
+{"current_steps": 1690, "total_steps": 4212, "loss": 0.4583, "lr": 7.486827659808796e-05, "epoch": 0.40128220349044286, "percentage": 40.12, "elapsed_time": "15:29:55", "remaining_time": "23:07:44"}
+{"current_steps": 1700, "total_steps": 4212, "loss": 0.5045, "lr": 7.450786691073274e-05, "epoch": 0.4036566543986703, "percentage": 40.36, "elapsed_time": "15:35:41", "remaining_time": "23:02:37"}
+{"current_steps": 1710, "total_steps": 4212, "loss": 0.521, "lr": 7.414577329214522e-05, "epoch": 0.4060311053068978, "percentage": 40.6, "elapsed_time": "15:39:45", "remaining_time": "22:55:00"}
+{"current_steps": 1720, "total_steps": 4212, "loss": 0.4216, "lr": 7.378202062171432e-05, "epoch": 0.40840555621512525, "percentage": 40.84, "elapsed_time": "15:44:11", "remaining_time": "22:47:58"}
+{"current_steps": 1730, "total_steps": 4212, "loss": 0.439, "lr": 7.341663389282219e-05, "epoch": 0.4107800071233527, "percentage": 41.07, "elapsed_time": "15:48:24", "remaining_time": "22:40:39"}
+{"current_steps": 1740, "total_steps": 4212, "loss": 0.468, "lr": 7.304963821112681e-05, "epoch": 0.4131544580315802, "percentage": 41.31, "elapsed_time": "15:53:08", "remaining_time": "22:34:07"}
+{"current_steps": 1750, "total_steps": 4212, "loss": 0.5209, "lr": 7.268105879283703e-05, "epoch": 0.41552890893980765, "percentage": 41.55, "elapsed_time": "15:58:25", "remaining_time": "22:28:21"}
+{"current_steps": 1760, "total_steps": 4212, "loss": 0.4444, "lr": 7.231092096297995e-05, "epoch": 0.4179033598480351, "percentage": 41.79, "elapsed_time": "16:03:18", "remaining_time": "22:22:04"}
+{"current_steps": 1770, "total_steps": 4212, "loss": 0.4706, "lr": 7.19392501536609e-05, "epoch": 0.42027781075626264, "percentage": 42.02, "elapsed_time": "16:07:52", "remaining_time": "22:15:20"}
+{"current_steps": 1780, "total_steps": 4212, "loss": 0.545, "lr": 7.156607190231591e-05, "epoch": 0.4226522616644901, "percentage": 42.26, "elapsed_time": "16:12:46", "remaining_time": "22:09:05"}
+{"current_steps": 1790, "total_steps": 4212, "loss": 0.4404, "lr": 7.11914118499571e-05, "epoch": 0.42502671257271757, "percentage": 42.5, "elapsed_time": "16:18:09", "remaining_time": "22:03:30"}
+{"current_steps": 1800, "total_steps": 4212, "loss": 0.4848, "lr": 7.081529573941091e-05, "epoch": 0.42740116348094503, "percentage": 42.74, "elapsed_time": "16:23:29", "remaining_time": "21:57:52"}
+{"current_steps": 1810, "total_steps": 4212, "loss": 0.5122, "lr": 7.043774941354925e-05, "epoch": 0.4297756143891725, "percentage": 42.97, "elapsed_time": "16:28:28", "remaining_time": "21:51:46"}
+{"current_steps": 1820, "total_steps": 4212, "loss": 0.4651, "lr": 7.005879881351384e-05, "epoch": 0.43215006529739997, "percentage": 43.21, "elapsed_time": "16:32:56", "remaining_time": "21:45:00"}
+{"current_steps": 1830, "total_steps": 4212, "loss": 0.4405, "lr": 6.967846997693392e-05, "epoch": 0.43452451620562743, "percentage": 43.45, "elapsed_time": "16:37:10", "remaining_time": "21:37:57"}
+{"current_steps": 1840, "total_steps": 4212, "loss": 0.4304, "lr": 6.929678903613705e-05, "epoch": 0.4368989671138549, "percentage": 43.68, "elapsed_time": "16:41:26", "remaining_time": "21:30:59"}
+{"current_steps": 1850, "total_steps": 4212, "loss": 0.4278, "lr": 6.891378221635367e-05, "epoch": 0.4392734180220824, "percentage": 43.92, "elapsed_time": "16:46:50", "remaining_time": "21:25:29"}
+{"current_steps": 1860, "total_steps": 4212, "loss": 0.4781, "lr": 6.852947583391511e-05, "epoch": 0.4416478689303099, "percentage": 44.16, "elapsed_time": "16:52:57", "remaining_time": "21:20:53"}
+{"current_steps": 1870, "total_steps": 4212, "loss": 0.4582, "lr": 6.814389629444543e-05, "epoch": 0.44402231983853735, "percentage": 44.4, "elapsed_time": "16:57:40", "remaining_time": "21:14:32"}
+{"current_steps": 1880, "total_steps": 4212, "loss": 0.4225, "lr": 6.775707009104708e-05, "epoch": 0.4463967707467648, "percentage": 44.63, "elapsed_time": "17:01:40", "remaining_time": "21:07:18"}
+{"current_steps": 1890, "total_steps": 4212, "loss": 0.4215, "lr": 6.73690238024806e-05, "epoch": 0.4487712216549923, "percentage": 44.87, "elapsed_time": "17:06:25", "remaining_time": "21:01:02"}
+{"current_steps": 1900, "total_steps": 4212, "loss": 0.518, "lr": 6.697978409133831e-05, "epoch": 0.45114567256321975, "percentage": 45.11, "elapsed_time": "17:10:57", "remaining_time": "20:54:30"}
+{"current_steps": 1910, "total_steps": 4212, "loss": 0.4217, "lr": 6.658937770221242e-05, "epoch": 0.4535201234714472, "percentage": 45.35, "elapsed_time": "17:15:36", "remaining_time": "20:48:09"}
+{"current_steps": 1920, "total_steps": 4212, "loss": 0.4848, "lr": 6.619783145985743e-05, "epoch": 0.4558945743796747, "percentage": 45.58, "elapsed_time": "17:21:24", "remaining_time": "20:43:11"}
+{"current_steps": 1930, "total_steps": 4212, "loss": 0.4036, "lr": 6.580517226734686e-05, "epoch": 0.4582690252879022, "percentage": 45.82, "elapsed_time": "17:26:26", "remaining_time": "20:37:17"}
+{"current_steps": 1940, "total_steps": 4212, "loss": 0.459, "lr": 6.541142710422489e-05, "epoch": 0.46064347619612966, "percentage": 46.06, "elapsed_time": "17:31:19", "remaining_time": "20:31:15"}
+{"current_steps": 1950, "total_steps": 4212, "loss": 0.4338, "lr": 6.501662302465254e-05, "epoch": 0.46301792710435713, "percentage": 46.3, "elapsed_time": "17:35:50", "remaining_time": "20:24:46"}
+{"current_steps": 1960, "total_steps": 4212, "loss": 0.4175, "lr": 6.46207871555488e-05, "epoch": 0.4653923780125846, "percentage": 46.53, "elapsed_time": "17:40:10", "remaining_time": "20:18:07"}
+{"current_steps": 1970, "total_steps": 4212, "loss": 0.4774, "lr": 6.422394669472676e-05, "epoch": 0.46776682892081206, "percentage": 46.77, "elapsed_time": "17:45:46", "remaining_time": "20:12:55"}
+{"current_steps": 1980, "total_steps": 4212, "loss": 0.4808, "lr": 6.382612890902478e-05, "epoch": 0.4701412798290395, "percentage": 47.01, "elapsed_time": "17:50:42", "remaining_time": "20:06:59"}
+{"current_steps": 1990, "total_steps": 4212, "loss": 0.4014, "lr": 6.342736113243305e-05, "epoch": 0.472515730737267, "percentage": 47.25, "elapsed_time": "17:55:21", "remaining_time": "20:00:43"}
+{"current_steps": 2000, "total_steps": 4212, "loss": 0.4165, "lr": 6.302767076421552e-05, "epoch": 0.47489018164549446, "percentage": 47.48, "elapsed_time": "18:00:17", "remaining_time": "19:54:48"}
+{"current_steps": 2000, "total_steps": 4212, "eval_loss": 0.4213089346885681, "epoch": 0.47489018164549446, "percentage": 47.48, "elapsed_time": "18:33:40", "remaining_time": "20:31:43"}
+{"current_steps": 2010, "total_steps": 4212, "loss": 0.4429, "lr": 6.26270852670272e-05, "epoch": 0.477264632553722, "percentage": 47.72, "elapsed_time": "18:38:45", "remaining_time": "20:25:37"}
+{"current_steps": 2020, "total_steps": 4212, "loss": 0.4951, "lr": 6.222563216502724e-05, "epoch": 0.47963908346194944, "percentage": 47.96, "elapsed_time": "18:44:12", "remaining_time": "20:19:56"}
+{"current_steps": 2030, "total_steps": 4212, "loss": 0.4165, "lr": 6.182333904198782e-05, "epoch": 0.4820135343701769, "percentage": 48.2, "elapsed_time": "18:48:50", "remaining_time": "20:13:21"}
+{"current_steps": 2040, "total_steps": 4212, "loss": 0.4133, "lr": 6.14202335393988e-05, "epoch": 0.4843879852784044, "percentage": 48.43, "elapsed_time": "18:54:16", "remaining_time": "20:07:40"}
+{"current_steps": 2050, "total_steps": 4212, "loss": 0.4254, "lr": 6.1016343354568464e-05, "epoch": 0.48676243618663184, "percentage": 48.67, "elapsed_time": "18:58:29", "remaining_time": "20:00:41"}
+{"current_steps": 2060, "total_steps": 4212, "loss": 0.4138, "lr": 6.0611696238720485e-05, "epoch": 0.4891368870948593, "percentage": 48.91, "elapsed_time": "19:02:41", "remaining_time": "19:53:43"}
+{"current_steps": 2070, "total_steps": 4212, "loss": 0.4021, "lr": 6.020631999508717e-05, "epoch": 0.4915113380030868, "percentage": 49.15, "elapsed_time": "19:07:28", "remaining_time": "19:47:23"}
+{"current_steps": 2080, "total_steps": 4212, "loss": 0.3708, "lr": 5.980024247699903e-05, "epoch": 0.49388578891131424, "percentage": 49.38, "elapsed_time": "19:12:26", "remaining_time": "19:41:14"}
+{"current_steps": 2090, "total_steps": 4212, "loss": 0.4198, "lr": 5.939349158597102e-05, "epoch": 0.4962602398195417, "percentage": 49.62, "elapsed_time": "19:17:02", "remaining_time": "19:34:45"}
+{"current_steps": 2100, "total_steps": 4212, "loss": 0.3956, "lr": 5.898609526978547e-05, "epoch": 0.4986346907277692, "percentage": 49.86, "elapsed_time": "19:21:19", "remaining_time": "19:27:57"}
+{"current_steps": 2110, "total_steps": 4212, "loss": 0.4176, "lr": 5.857808152057173e-05, "epoch": 0.5010091416359966, "percentage": 50.09, "elapsed_time": "19:26:08", "remaining_time": "19:21:43"}
+{"current_steps": 2120, "total_steps": 4212, "loss": 0.4061, "lr": 5.816947837288285e-05, "epoch": 0.5033835925442242, "percentage": 50.33, "elapsed_time": "19:30:36", "remaining_time": "19:15:09"}
+{"current_steps": 2130, "total_steps": 4212, "loss": 0.3868, "lr": 5.776031390176938e-05, "epoch": 0.5057580434524516, "percentage": 50.57, "elapsed_time": "19:35:46", "remaining_time": "19:09:16"}
+{"current_steps": 2140, "total_steps": 4212, "loss": 0.5408, "lr": 5.7350616220850285e-05, "epoch": 0.5081324943606791, "percentage": 50.81, "elapsed_time": "19:40:12", "remaining_time": "19:02:42"}
+{"current_steps": 2150, "total_steps": 4212, "loss": 0.4183, "lr": 5.694041348038128e-05, "epoch": 0.5105069452689066, "percentage": 51.04, "elapsed_time": "19:45:55", "remaining_time": "18:57:22"}
+{"current_steps": 2160, "total_steps": 4212, "loss": 0.3751, "lr": 5.652973386532066e-05, "epoch": 0.512881396177134, "percentage": 51.28, "elapsed_time": "19:50:52", "remaining_time": "18:51:19"}
+{"current_steps": 2170, "total_steps": 4212, "loss": 0.3528, "lr": 5.611860559339265e-05, "epoch": 0.5152558470853615, "percentage": 51.52, "elapsed_time": "19:55:08", "remaining_time": "18:44:38"}
+{"current_steps": 2180, "total_steps": 4212, "loss": 0.4023, "lr": 5.5707056913148626e-05, "epoch": 0.517630297993589, "percentage": 51.76, "elapsed_time": "19:59:49", "remaining_time": "18:38:22"}
+{"current_steps": 2190, "total_steps": 4212, "loss": 0.3637, "lr": 5.529511610202616e-05, "epoch": 0.5200047489018165, "percentage": 51.99, "elapsed_time": "20:03:41", "remaining_time": "18:31:21"}
+{"current_steps": 2200, "total_steps": 4212, "loss": 0.3705, "lr": 5.4882811464406026e-05, "epoch": 0.5223791998100439, "percentage": 52.23, "elapsed_time": "20:07:54", "remaining_time": "18:24:40"}
+{"current_steps": 2210, "total_steps": 4212, "loss": 0.4017, "lr": 5.4470171329667506e-05, "epoch": 0.5247536507182714, "percentage": 52.47, "elapsed_time": "20:13:12", "remaining_time": "18:19:01"}
+{"current_steps": 2220, "total_steps": 4212, "loss": 0.4057, "lr": 5.405722405024183e-05, "epoch": 0.5271281016264989, "percentage": 52.71, "elapsed_time": "20:17:53", "remaining_time": "18:12:48"}
+{"current_steps": 2230, "total_steps": 4212, "loss": 0.3652, "lr": 5.364399799966402e-05, "epoch": 0.5295025525347263, "percentage": 52.94, "elapsed_time": "20:22:31", "remaining_time": "18:06:33"}
+{"current_steps": 2240, "total_steps": 4212, "loss": 0.3943, "lr": 5.323052157062346e-05, "epoch": 0.5318770034429539, "percentage": 53.18, "elapsed_time": "20:27:29", "remaining_time": "18:00:38"}
+{"current_steps": 2250, "total_steps": 4212, "loss": 0.3657, "lr": 5.281682317301302e-05, "epoch": 0.5342514543511813, "percentage": 53.42, "elapsed_time": "20:32:14", "remaining_time": "17:54:31"}
+{"current_steps": 2260, "total_steps": 4212, "loss": 0.3839, "lr": 5.240293123197694e-05, "epoch": 0.5366259052594088, "percentage": 53.66, "elapsed_time": "20:36:44", "remaining_time": "17:48:11"}
+{"current_steps": 2270, "total_steps": 4212, "loss": 0.3579, "lr": 5.198887418595779e-05, "epoch": 0.5390003561676362, "percentage": 53.89, "elapsed_time": "20:41:01", "remaining_time": "17:41:42"}
+{"current_steps": 2280, "total_steps": 4212, "loss": 0.3627, "lr": 5.157468048474257e-05, "epoch": 0.5413748070758637, "percentage": 54.13, "elapsed_time": "20:45:51", "remaining_time": "17:35:42"}
+{"current_steps": 2290, "total_steps": 4212, "loss": 0.3827, "lr": 5.1160378587507716e-05, "epoch": 0.5437492579840911, "percentage": 54.37, "elapsed_time": "20:50:20", "remaining_time": "17:29:24"}
+{"current_steps": 2300, "total_steps": 4212, "loss": 0.3421, "lr": 5.074599696086384e-05, "epoch": 0.5461237088923186, "percentage": 54.61, "elapsed_time": "20:55:45", "remaining_time": "17:23:55"}
+{"current_steps": 2310, "total_steps": 4212, "loss": 0.384, "lr": 5.033156407689978e-05, "epoch": 0.5484981598005462, "percentage": 54.84, "elapsed_time": "21:01:00", "remaining_time": "17:18:16"}
+{"current_steps": 2320, "total_steps": 4212, "loss": 0.3977, "lr": 4.991710841122623e-05, "epoch": 0.5508726107087736, "percentage": 55.08, "elapsed_time": "21:05:50", "remaining_time": "17:12:18"}
+{"current_steps": 2330, "total_steps": 4212, "loss": 0.3861, "lr": 4.950265844101915e-05, "epoch": 0.5532470616170011, "percentage": 55.32, "elapsed_time": "21:10:24", "remaining_time": "17:06:08"}
+{"current_steps": 2340, "total_steps": 4212, "loss": 0.366, "lr": 4.9088242643063304e-05, "epoch": 0.5556215125252285, "percentage": 55.56, "elapsed_time": "21:14:34", "remaining_time": "16:59:39"}
+{"current_steps": 2350, "total_steps": 4212, "loss": 0.4019, "lr": 4.8673889491795344e-05, "epoch": 0.557995963433456, "percentage": 55.79, "elapsed_time": "21:19:17", "remaining_time": "16:53:38"}
+{"current_steps": 2360, "total_steps": 4212, "loss": 0.39, "lr": 4.8259627457347554e-05, "epoch": 0.5603704143416834, "percentage": 56.03, "elapsed_time": "21:24:21", "remaining_time": "16:47:53"}
+{"current_steps": 2370, "total_steps": 4212, "loss": 0.4089, "lr": 4.784548500359162e-05, "epoch": 0.562744865249911, "percentage": 56.27, "elapsed_time": "21:28:47", "remaining_time": "16:41:40"}
+{"current_steps": 2380, "total_steps": 4212, "loss": 0.3207, "lr": 4.743149058618278e-05, "epoch": 0.5651193161581385, "percentage": 56.51, "elapsed_time": "21:34:10", "remaining_time": "16:36:11"}
+{"current_steps": 2390, "total_steps": 4212, "loss": 0.3822, "lr": 4.7017672650604766e-05, "epoch": 0.5674937670663659, "percentage": 56.74, "elapsed_time": "21:38:41", "remaining_time": "16:30:02"}
+{"current_steps": 2400, "total_steps": 4212, "loss": 0.3417, "lr": 4.6604059630215326e-05, "epoch": 0.5698682179745934, "percentage": 56.98, "elapsed_time": "21:43:22", "remaining_time": "16:24:02"}
+{"current_steps": 2410, "total_steps": 4212, "loss": 0.404, "lr": 4.6190679944292395e-05, "epoch": 0.5722426688828208, "percentage": 57.22, "elapsed_time": "21:48:13", "remaining_time": "16:18:11"}
+{"current_steps": 2420, "total_steps": 4212, "loss": 0.3609, "lr": 4.5777561996081656e-05, "epoch": 0.5746171197910483, "percentage": 57.45, "elapsed_time": "21:52:57", "remaining_time": "16:12:14"}
+{"current_steps": 2430, "total_steps": 4212, "loss": 0.3217, "lr": 4.5364734170844807e-05, "epoch": 0.5769915706992758, "percentage": 57.69, "elapsed_time": "21:57:10", "remaining_time": "16:05:55"}
+{"current_steps": 2440, "total_steps": 4212, "loss": 0.3611, "lr": 4.4952224833909194e-05, "epoch": 0.5793660216075033, "percentage": 57.93, "elapsed_time": "22:01:59", "remaining_time": "16:00:04"}
+{"current_steps": 2450, "total_steps": 4212, "loss": 0.3434, "lr": 4.4540062328718945e-05, "epoch": 0.5817404725157307, "percentage": 58.17, "elapsed_time": "22:06:48", "remaining_time": "15:54:13"}
+{"current_steps": 2460, "total_steps": 4212, "loss": 0.3619, "lr": 4.412827497488744e-05, "epoch": 0.5841149234239582, "percentage": 58.4, "elapsed_time": "22:11:16", "remaining_time": "15:48:07"}
+{"current_steps": 2470, "total_steps": 4212, "loss": 0.3387, "lr": 4.371689106625143e-05, "epoch": 0.5864893743321857, "percentage": 58.64, "elapsed_time": "22:16:26", "remaining_time": "15:42:32"}
+{"current_steps": 2480, "total_steps": 4212, "loss": 0.3145, "lr": 4.330593886892707e-05, "epoch": 0.5888638252404131, "percentage": 58.88, "elapsed_time": "22:21:11", "remaining_time": "15:36:40"}
+{"current_steps": 2490, "total_steps": 4212, "loss": 0.4051, "lr": 4.2895446619367684e-05, "epoch": 0.5912382761486407, "percentage": 59.12, "elapsed_time": "22:25:53", "remaining_time": "15:30:46"}
+{"current_steps": 2500, "total_steps": 4212, "loss": 0.4129, "lr": 4.2485442522423636e-05, "epoch": 0.5936127270568681, "percentage": 59.35, "elapsed_time": "22:30:58", "remaining_time": "15:25:08"}
+{"current_steps": 2500, "total_steps": 4212, "eval_loss": 0.3469230532646179, "epoch": 0.5936127270568681, "percentage": 59.35, "elapsed_time": "23:04:21", "remaining_time": "15:48:00"}
+{"current_steps": 2510, "total_steps": 4212, "loss": 0.3652, "lr": 4.207595474940446e-05, "epoch": 0.5959871779650956, "percentage": 59.59, "elapsed_time": "23:09:16", "remaining_time": "15:42:03"}
+{"current_steps": 2520, "total_steps": 4212, "loss": 0.2876, "lr": 4.166701143614315e-05, "epoch": 0.598361628873323, "percentage": 59.83, "elapsed_time": "23:13:41", "remaining_time": "15:35:45"}
+{"current_steps": 2530, "total_steps": 4212, "loss": 0.3285, "lr": 4.1258640681062934e-05, "epoch": 0.6007360797815505, "percentage": 60.07, "elapsed_time": "23:18:16", "remaining_time": "15:29:36"}
+{"current_steps": 2540, "total_steps": 4212, "loss": 0.3517, "lr": 4.08508705432467e-05, "epoch": 0.6031105306897779, "percentage": 60.3, "elapsed_time": "23:22:37", "remaining_time": "15:23:18"}
+{"current_steps": 2550, "total_steps": 4212, "loss": 0.3232, "lr": 4.0443729040509045e-05, "epoch": 0.6054849815980055, "percentage": 60.54, "elapsed_time": "23:27:07", "remaining_time": "15:17:07"}
+{"current_steps": 2560, "total_steps": 4212, "loss": 0.3429, "lr": 4.00372441474711e-05, "epoch": 0.607859432506233, "percentage": 60.78, "elapsed_time": "23:31:46", "remaining_time": "15:11:02"}
+{"current_steps": 2570, "total_steps": 4212, "loss": 0.4089, "lr": 3.96314437936385e-05, "epoch": 0.6102338834144604, "percentage": 61.02, "elapsed_time": "23:36:09", "remaining_time": "15:04:47"}
+{"current_steps": 2580, "total_steps": 4212, "loss": 0.3063, "lr": 3.922635586148234e-05, "epoch": 0.6126083343226879, "percentage": 61.25, "elapsed_time": "23:41:38", "remaining_time": "14:59:16"}
+{"current_steps": 2590, "total_steps": 4212, "loss": 0.3233, "lr": 3.8822008184523265e-05, "epoch": 0.6149827852309153, "percentage": 61.49, "elapsed_time": "23:45:40", "remaining_time": "14:52:49"}
+{"current_steps": 2600, "total_steps": 4212, "loss": 0.3372, "lr": 3.841842854541919e-05, "epoch": 0.6173572361391428, "percentage": 61.73, "elapsed_time": "23:50:09", "remaining_time": "14:46:41"}
+{"current_steps": 2610, "total_steps": 4212, "loss": 0.3275, "lr": 3.8015644674056266e-05, "epoch": 0.6197316870473702, "percentage": 61.97, "elapsed_time": "23:55:44", "remaining_time": "14:41:14"}
+{"current_steps": 2620, "total_steps": 4212, "loss": 0.3352, "lr": 3.7613684245643544e-05, "epoch": 0.6221061379555978, "percentage": 62.2, "elapsed_time": "1 day, 0:00:25", "remaining_time": "14:35:15"}
+{"current_steps": 2630, "total_steps": 4212, "loss": 0.3131, "lr": 3.7212574878811495e-05, "epoch": 0.6244805888638253, "percentage": 62.44, "elapsed_time": "1 day, 0:05:15", "remaining_time": "14:29:21"}
+{"current_steps": 2640, "total_steps": 4212, "loss": 0.3497, "lr": 3.68123441337143e-05, "epoch": 0.6268550397720527, "percentage": 62.68, "elapsed_time": "1 day, 0:09:10", "remaining_time": "14:22:55"}
+{"current_steps": 2650, "total_steps": 4212, "loss": 0.3628, "lr": 3.641301951013617e-05, "epoch": 0.6292294906802802, "percentage": 62.92, "elapsed_time": "1 day, 0:12:54", "remaining_time": "14:16:23"}
+{"current_steps": 2660, "total_steps": 4212, "loss": 0.2979, "lr": 3.601462844560187e-05, "epoch": 0.6316039415885076, "percentage": 63.15, "elapsed_time": "1 day, 0:17:10", "remaining_time": "14:10:12"}
+{"current_steps": 2670, "total_steps": 4212, "loss": 0.3169, "lr": 3.561719831349153e-05, "epoch": 0.6339783924967352, "percentage": 63.39, "elapsed_time": "1 day, 0:22:35", "remaining_time": "14:04:41"}
+{"current_steps": 2680, "total_steps": 4212, "loss": 0.3234, "lr": 3.5220756421159696e-05, "epoch": 0.6363528434049626, "percentage": 63.63, "elapsed_time": "1 day, 0:27:43", "remaining_time": "13:59:00"}
+{"current_steps": 2690, "total_steps": 4212, "loss": 0.3372, "lr": 3.482533000805921e-05, "epoch": 0.6387272943131901, "percentage": 63.87, "elapsed_time": "1 day, 0:32:27", "remaining_time": "13:53:07"}
+{"current_steps": 2700, "total_steps": 4212, "loss": 0.2902, "lr": 3.443094624386949e-05, "epoch": 0.6411017452214175, "percentage": 64.1, "elapsed_time": "1 day, 0:36:31", "remaining_time": "13:46:51"}
+{"current_steps": 2710, "total_steps": 4212, "loss": 0.293, "lr": 3.4037632226629704e-05, "epoch": 0.643476196129645, "percentage": 64.34, "elapsed_time": "1 day, 0:40:59", "remaining_time": "13:40:50"}
+{"current_steps": 2720, "total_steps": 4212, "loss": 0.3087, "lr": 3.3645414980876946e-05, "epoch": 0.6458506470378725, "percentage": 64.58, "elapsed_time": "1 day, 0:46:23", "remaining_time": "13:35:19"}
+{"current_steps": 2730, "total_steps": 4212, "loss": 0.3082, "lr": 3.32543214557893e-05, "epoch": 0.6482250979461, "percentage": 64.81, "elapsed_time": "1 day, 0:50:48", "remaining_time": "13:29:17"}
+{"current_steps": 2740, "total_steps": 4212, "loss": 0.2858, "lr": 3.286437852333418e-05, "epoch": 0.6505995488543275, "percentage": 65.05, "elapsed_time": "1 day, 0:55:48", "remaining_time": "13:23:35"}
+{"current_steps": 2750, "total_steps": 4212, "loss": 0.339, "lr": 3.247561297642203e-05, "epoch": 0.6529739997625549, "percentage": 65.29, "elapsed_time": "1 day, 1:00:08", "remaining_time": "13:17:32"}
+{"current_steps": 2760, "total_steps": 4212, "loss": 0.2766, "lr": 3.208805152706533e-05, "epoch": 0.6553484506707824, "percentage": 65.53, "elapsed_time": "1 day, 1:04:58", "remaining_time": "13:11:44"}
+{"current_steps": 2770, "total_steps": 4212, "loss": 0.3518, "lr": 3.170172080454319e-05, "epoch": 0.6577229015790098, "percentage": 65.76, "elapsed_time": "1 day, 1:09:15", "remaining_time": "13:05:40"}
+{"current_steps": 2780, "total_steps": 4212, "loss": 0.2908, "lr": 3.131664735357174e-05, "epoch": 0.6600973524872373, "percentage": 66.0, "elapsed_time": "1 day, 1:13:44", "remaining_time": "12:59:44"}
+{"current_steps": 2790, "total_steps": 4212, "loss": 0.3426, "lr": 3.0932857632480185e-05, "epoch": 0.6624718033954649, "percentage": 66.24, "elapsed_time": "1 day, 1:18:45", "remaining_time": "12:54:04"}
+{"current_steps": 2800, "total_steps": 4212, "loss": 0.2876, "lr": 3.055037801139286e-05, "epoch": 0.6648462543036923, "percentage": 66.48, "elapsed_time": "1 day, 1:23:12", "remaining_time": "12:48:08"}
+{"current_steps": 2810, "total_steps": 4212, "loss": 0.2819, "lr": 3.0169234770417376e-05, "epoch": 0.6672207052119198, "percentage": 66.71, "elapsed_time": "1 day, 1:28:08", "remaining_time": "12:42:26"}
+{"current_steps": 2820, "total_steps": 4212, "loss": 0.3145, "lr": 2.978945409783892e-05, "epoch": 0.6695951561201472, "percentage": 66.95, "elapsed_time": "1 day, 1:32:50", "remaining_time": "12:36:38"}
+{"current_steps": 2830, "total_steps": 4212, "loss": 0.2872, "lr": 2.94110620883208e-05, "epoch": 0.6719696070283747, "percentage": 67.19, "elapsed_time": "1 day, 1:37:19", "remaining_time": "12:30:44"}
+{"current_steps": 2840, "total_steps": 4212, "loss": 0.2798, "lr": 2.9034084741111555e-05, "epoch": 0.6743440579366021, "percentage": 67.43, "elapsed_time": "1 day, 1:41:23", "remaining_time": "12:24:38"}
+{"current_steps": 2850, "total_steps": 4212, "loss": 0.2699, "lr": 2.8658547958258543e-05, "epoch": 0.6767185088448296, "percentage": 67.66, "elapsed_time": "1 day, 1:46:42", "remaining_time": "12:19:09"}
+{"current_steps": 2860, "total_steps": 4212, "loss": 0.3362, "lr": 2.8284477542828153e-05, "epoch": 0.6790929597530571, "percentage": 67.9, "elapsed_time": "1 day, 1:51:51", "remaining_time": "12:13:36"}
+{"current_steps": 2870, "total_steps": 4212, "loss": 0.2896, "lr": 2.791189919713294e-05, "epoch": 0.6814674106612846, "percentage": 68.14, "elapsed_time": "1 day, 1:56:56", "remaining_time": "12:08:00"}
+{"current_steps": 2880, "total_steps": 4212, "loss": 0.3138, "lr": 2.7540838520965672e-05, "epoch": 0.6838418615695121, "percentage": 68.38, "elapsed_time": "1 day, 2:01:45", "remaining_time": "12:02:18"}
+{"current_steps": 2890, "total_steps": 4212, "loss": 0.268, "lr": 2.7171321009840178e-05, "epoch": 0.6862163124777395, "percentage": 68.61, "elapsed_time": "1 day, 2:06:39", "remaining_time": "11:56:38"}
+{"current_steps": 2900, "total_steps": 4212, "loss": 0.2844, "lr": 2.6803372053239834e-05, "epoch": 0.688590763385967, "percentage": 68.85, "elapsed_time": "1 day, 2:12:16", "remaining_time": "11:51:19"}
+{"current_steps": 2910, "total_steps": 4212, "loss": 0.2931, "lr": 2.6437016932872816e-05, "epoch": 0.6909652142941944, "percentage": 69.09, "elapsed_time": "1 day, 2:16:58", "remaining_time": "11:45:34"}
+{"current_steps": 2920, "total_steps": 4212, "loss": 0.2818, "lr": 2.6072280820935103e-05, "epoch": 0.693339665202422, "percentage": 69.33, "elapsed_time": "1 day, 2:21:08", "remaining_time": "11:39:36"}
+{"current_steps": 2930, "total_steps": 4212, "loss": 0.2741, "lr": 2.5709188778380942e-05, "epoch": 0.6957141161106494, "percentage": 69.56, "elapsed_time": "1 day, 2:26:14", "remaining_time": "11:34:02"}
+{"current_steps": 2940, "total_steps": 4212, "loss": 0.3142, "lr": 2.5347765753200808e-05, "epoch": 0.6980885670188769, "percentage": 69.8, "elapsed_time": "1 day, 2:31:14", "remaining_time": "11:28:27"}
+{"current_steps": 2950, "total_steps": 4212, "loss": 0.2499, "lr": 2.4988036578707303e-05, "epoch": 0.7004630179271043, "percentage": 70.04, "elapsed_time": "1 day, 2:35:42", "remaining_time": "11:22:38"}
+{"current_steps": 2960, "total_steps": 4212, "loss": 0.2565, "lr": 2.463002597182882e-05, "epoch": 0.7028374688353318, "percentage": 70.28, "elapsed_time": "1 day, 2:39:49", "remaining_time": "11:16:41"}
+{"current_steps": 2970, "total_steps": 4212, "loss": 0.2848, "lr": 2.427375853141134e-05, "epoch": 0.7052119197435593, "percentage": 70.51, "elapsed_time": "1 day, 2:44:02", "remaining_time": "11:10:47"}
+{"current_steps": 2980, "total_steps": 4212, "loss": 0.2536, "lr": 2.3919258736528123e-05, "epoch": 0.7075863706517868, "percentage": 70.75, "elapsed_time": "1 day, 2:48:24", "remaining_time": "11:04:57"}
+{"current_steps": 2990, "total_steps": 4212, "loss": 0.2693, "lr": 2.3566550944797804e-05, "epoch": 0.7099608215600143, "percentage": 70.99, "elapsed_time": "1 day, 2:53:28", "remaining_time": "10:59:25"}
+{"current_steps": 3000, "total_steps": 4212, "loss": 0.345, "lr": 2.321565939071089e-05, "epoch": 0.7123352724682417, "percentage": 71.23, "elapsed_time": "1 day, 2:58:37", "remaining_time": "10:53:55"}
+{"current_steps": 3000, "total_steps": 4212, "eval_loss": 0.2755714952945709, "epoch": 0.7123352724682417, "percentage": 71.23, "elapsed_time": "1 day, 3:31:59", "remaining_time": "11:07:24"}
+{"current_steps": 3010, "total_steps": 4212, "loss": 0.3807, "lr": 2.2866608183964376e-05, "epoch": 0.7147097233764692, "percentage": 71.46, "elapsed_time": "1 day, 3:36:49", "remaining_time": "11:01:37"}
+{"current_steps": 3020, "total_steps": 4212, "loss": 0.2892, "lr": 2.2519421307805445e-05, "epoch": 0.7170841742846966, "percentage": 71.7, "elapsed_time": "1 day, 3:41:29", "remaining_time": "10:55:47"}
+{"current_steps": 3030, "total_steps": 4212, "loss": 0.2531, "lr": 2.217412261738338e-05, "epoch": 0.7194586251929241, "percentage": 71.94, "elapsed_time": "1 day, 3:46:48", "remaining_time": "10:50:13"}
+{"current_steps": 3040, "total_steps": 4212, "loss": 0.2458, "lr": 2.183073583811055e-05, "epoch": 0.7218330761011517, "percentage": 72.17, "elapsed_time": "1 day, 3:51:05", "remaining_time": "10:44:15"}
+{"current_steps": 3050, "total_steps": 4212, "loss": 0.2413, "lr": 2.1489284564032308e-05, "epoch": 0.7242075270093791, "percentage": 72.41, "elapsed_time": "1 day, 3:55:50", "remaining_time": "10:38:28"}
+{"current_steps": 3060, "total_steps": 4212, "loss": 0.2575, "lr": 2.1149792256205725e-05, "epoch": 0.7265819779176066, "percentage": 72.65, "elapsed_time": "1 day, 4:00:21", "remaining_time": "10:32:36"}
+{"current_steps": 3070, "total_steps": 4212, "loss": 0.2503, "lr": 2.0812282241087662e-05, "epoch": 0.728956428825834, "percentage": 72.89, "elapsed_time": "1 day, 4:05:20", "remaining_time": "10:26:55"}
+{"current_steps": 3080, "total_steps": 4212, "loss": 0.277, "lr": 2.0476777708931978e-05, "epoch": 0.7313308797340615, "percentage": 73.12, "elapsed_time": "1 day, 4:10:40", "remaining_time": "10:21:22"}
+{"current_steps": 3090, "total_steps": 4212, "loss": 0.2969, "lr": 2.01433017121962e-05, "epoch": 0.7337053306422889, "percentage": 73.36, "elapsed_time": "1 day, 4:15:15", "remaining_time": "10:15:33"}
+{"current_steps": 3100, "total_steps": 4212, "loss": 0.2344, "lr": 1.981187716395751e-05, "epoch": 0.7360797815505165, "percentage": 73.6, "elapsed_time": "1 day, 4:19:44", "remaining_time": "10:09:42"}
+{"current_steps": 3110, "total_steps": 4212, "loss": 0.2428, "lr": 1.9482526836338387e-05, "epoch": 0.7384542324587439, "percentage": 73.84, "elapsed_time": "1 day, 4:23:42", "remaining_time": "10:03:41"}
+{"current_steps": 3120, "total_steps": 4212, "loss": 0.2683, "lr": 1.915527335894209e-05, "epoch": 0.7408286833669714, "percentage": 74.07, "elapsed_time": "1 day, 4:28:10", "remaining_time": "9:57:51"}
+{"current_steps": 3130, "total_steps": 4212, "loss": 0.2508, "lr": 1.8830139217297498e-05, "epoch": 0.7432031342751989, "percentage": 74.31, "elapsed_time": "1 day, 4:32:51", "remaining_time": "9:52:06"}
+{"current_steps": 3140, "total_steps": 4212, "loss": 0.2353, "lr": 1.8507146751314464e-05, "epoch": 0.7455775851834263, "percentage": 74.55, "elapsed_time": "1 day, 4:37:20", "remaining_time": "9:46:18"}
+{"current_steps": 3150, "total_steps": 4212, "loss": 0.2623, "lr": 1.8186318153748587e-05, "epoch": 0.7479520360916538, "percentage": 74.79, "elapsed_time": "1 day, 4:42:22", "remaining_time": "9:40:41"}
+{"current_steps": 3160, "total_steps": 4212, "loss": 0.2305, "lr": 1.786767546867647e-05, "epoch": 0.7503264869998812, "percentage": 75.02, "elapsed_time": "1 day, 4:47:06", "remaining_time": "9:34:58"}
+{"current_steps": 3170, "total_steps": 4212, "loss": 0.2508, "lr": 1.755124058998108e-05, "epoch": 0.7527009379081088, "percentage": 75.26, "elapsed_time": "1 day, 4:51:23", "remaining_time": "9:29:07"}
+{"current_steps": 3180, "total_steps": 4212, "loss": 0.242, "lr": 1.723703525984735e-05, "epoch": 0.7550753888163362, "percentage": 75.5, "elapsed_time": "1 day, 4:55:51", "remaining_time": "9:23:20"}
+{"current_steps": 3190, "total_steps": 4212, "loss": 0.2466, "lr": 1.692508106726836e-05, "epoch": 0.7574498397245637, "percentage": 75.74, "elapsed_time": "1 day, 5:00:46", "remaining_time": "9:17:42"}
+{"current_steps": 3200, "total_steps": 4212, "loss": 0.2407, "lr": 1.6615399446561886e-05, "epoch": 0.7598242906327912, "percentage": 75.97, "elapsed_time": "1 day, 5:05:07", "remaining_time": "9:11:53"}
+{"current_steps": 3210, "total_steps": 4212, "loss": 0.2504, "lr": 1.630801167589774e-05, "epoch": 0.7621987415410186, "percentage": 76.21, "elapsed_time": "1 day, 5:09:47", "remaining_time": "9:06:11"}
+{"current_steps": 3220, "total_steps": 4212, "loss": 0.2792, "lr": 1.6002938875835665e-05, "epoch": 0.7645731924492462, "percentage": 76.45, "elapsed_time": "1 day, 5:15:09", "remaining_time": "9:00:43"}
+{"current_steps": 3230, "total_steps": 4212, "loss": 0.2673, "lr": 1.5700202007874165e-05, "epoch": 0.7669476433574736, "percentage": 76.69, "elapsed_time": "1 day, 5:20:32", "remaining_time": "8:55:14"}
+{"current_steps": 3240, "total_steps": 4212, "loss": 0.2371, "lr": 1.5399821873010335e-05, "epoch": 0.7693220942657011, "percentage": 76.92, "elapsed_time": "1 day, 5:25:11", "remaining_time": "8:49:33"}
+{"current_steps": 3250, "total_steps": 4212, "loss": 0.2323, "lr": 1.5101819110310433e-05, "epoch": 0.7716965451739285, "percentage": 77.16, "elapsed_time": "1 day, 5:29:33", "remaining_time": "8:43:47"}
+{"current_steps": 3260, "total_steps": 4212, "loss": 0.2566, "lr": 1.4806214195492008e-05, "epoch": 0.774070996082156, "percentage": 77.4, "elapsed_time": "1 day, 5:33:54", "remaining_time": "8:38:01"}
+{"current_steps": 3270, "total_steps": 4212, "loss": 0.2677, "lr": 1.4513027439516847e-05, "epoch": 0.7764454469903834, "percentage": 77.64, "elapsed_time": "1 day, 5:39:12", "remaining_time": "8:32:32"}
+{"current_steps": 3280, "total_steps": 4212, "loss": 0.253, "lr": 1.4222278987195447e-05, "epoch": 0.778819897898611, "percentage": 77.87, "elapsed_time": "1 day, 5:44:04", "remaining_time": "8:26:56"}
+{"current_steps": 3290, "total_steps": 4212, "loss": 0.2366, "lr": 1.3933988815802962e-05, "epoch": 0.7811943488068385, "percentage": 78.11, "elapsed_time": "1 day, 5:49:00", "remaining_time": "8:21:21"}
+{"current_steps": 3300, "total_steps": 4212, "loss": 0.2658, "lr": 1.3648176733706419e-05, "epoch": 0.7835687997150659, "percentage": 78.35, "elapsed_time": "1 day, 5:55:36", "remaining_time": "8:16:14"}
+{"current_steps": 3310, "total_steps": 4212, "loss": 0.2921, "lr": 1.3364862379003812e-05, "epoch": 0.7859432506232934, "percentage": 78.58, "elapsed_time": "1 day, 6:00:36", "remaining_time": "8:10:40"}
+{"current_steps": 3320, "total_steps": 4212, "loss": 0.2456, "lr": 1.3084065218174679e-05, "epoch": 0.7883177015315208, "percentage": 78.82, "elapsed_time": "1 day, 6:05:00", "remaining_time": "8:04:57"}
+{"current_steps": 3330, "total_steps": 4212, "loss": 0.2153, "lr": 1.2805804544742672e-05, "epoch": 0.7906921524397483, "percentage": 79.06, "elapsed_time": "1 day, 6:10:19", "remaining_time": "7:59:29"}
+{"current_steps": 3340, "total_steps": 4212, "loss": 0.254, "lr": 1.2530099477949792e-05, "epoch": 0.7930666033479757, "percentage": 79.3, "elapsed_time": "1 day, 6:14:57", "remaining_time": "7:53:50"}
+{"current_steps": 3350, "total_steps": 4212, "loss": 0.2346, "lr": 1.2256968961442755e-05, "epoch": 0.7954410542562033, "percentage": 79.53, "elapsed_time": "1 day, 6:19:22", "remaining_time": "7:48:08"}
+{"current_steps": 3360, "total_steps": 4212, "loss": 0.2527, "lr": 1.198643176197144e-05, "epoch": 0.7978155051644307, "percentage": 79.77, "elapsed_time": "1 day, 6:24:19", "remaining_time": "7:42:35"}
+{"current_steps": 3370, "total_steps": 4212, "loss": 0.2582, "lr": 1.1718506468099254e-05, "epoch": 0.8001899560726582, "percentage": 80.01, "elapsed_time": "1 day, 6:28:35", "remaining_time": "7:36:52"}
+{"current_steps": 3380, "total_steps": 4212, "loss": 0.242, "lr": 1.1453211488926153e-05, "epoch": 0.8025644069808857, "percentage": 80.25, "elapsed_time": "1 day, 6:33:21", "remaining_time": "7:31:17"}
+{"current_steps": 3390, "total_steps": 4212, "loss": 0.2509, "lr": 1.1190565052823548e-05, "epoch": 0.8049388578891131, "percentage": 80.48, "elapsed_time": "1 day, 6:37:26", "remaining_time": "7:25:32"}
+{"current_steps": 3400, "total_steps": 4212, "loss": 0.2187, "lr": 1.0930585206181942e-05, "epoch": 0.8073133087973406, "percentage": 80.72, "elapsed_time": "1 day, 6:41:59", "remaining_time": "7:19:54"}
+{"current_steps": 3410, "total_steps": 4212, "loss": 0.2268, "lr": 1.0673289812170972e-05, "epoch": 0.809687759705568, "percentage": 80.96, "elapsed_time": "1 day, 6:47:25", "remaining_time": "7:14:29"}
+{"current_steps": 3420, "total_steps": 4212, "loss": 0.2317, "lr": 1.041869654951198e-05, "epoch": 0.8120622106137956, "percentage": 81.2, "elapsed_time": "1 day, 6:51:41", "remaining_time": "7:08:48"}
+{"current_steps": 3430, "total_steps": 4212, "loss": 0.2534, "lr": 1.016682291126333e-05, "epoch": 0.814436661522023, "percentage": 81.43, "elapsed_time": "1 day, 6:56:03", "remaining_time": "7:03:09"}
+{"current_steps": 3440, "total_steps": 4212, "loss": 0.2129, "lr": 9.917686203618475e-06, "epoch": 0.8168111124302505, "percentage": 81.67, "elapsed_time": "1 day, 7:00:30", "remaining_time": "6:57:31"}
+{"current_steps": 3450, "total_steps": 4212, "loss": 0.2118, "lr": 9.671303544716875e-06, "epoch": 0.819185563338478, "percentage": 81.91, "elapsed_time": "1 day, 7:05:11", "remaining_time": "6:51:57"}
+{"current_steps": 3460, "total_steps": 4212, "loss": 0.2315, "lr": 9.427691863467758e-06, "epoch": 0.8215600142467054, "percentage": 82.15, "elapsed_time": "1 day, 7:10:18", "remaining_time": "6:46:29"}
+{"current_steps": 3470, "total_steps": 4212, "loss": 0.2312, "lr": 9.186867898386952e-06, "epoch": 0.823934465154933, "percentage": 82.38, "elapsed_time": "1 day, 7:14:49", "remaining_time": "6:40:53"}
+{"current_steps": 3480, "total_steps": 4212, "loss": 0.2311, "lr": 8.948848196446852e-06, "epoch": 0.8263089160631604, "percentage": 82.62, "elapsed_time": "1 day, 7:20:04", "remaining_time": "6:35:27"}
+{"current_steps": 3490, "total_steps": 4212, "loss": 0.2519, "lr": 8.713649111939332e-06, "epoch": 0.8286833669713879, "percentage": 82.86, "elapsed_time": "1 day, 7:24:35", "remaining_time": "6:29:52"}
+{"current_steps": 3500, "total_steps": 4212, "loss": 0.1919, "lr": 8.481286805352234e-06, "epoch": 0.8310578178796153, "percentage": 83.1, "elapsed_time": "1 day, 7:29:11", "remaining_time": "6:24:18"}
+{"current_steps": 3500, "total_steps": 4212, "eval_loss": 0.2284688502550125, "epoch": 0.8310578178796153, "percentage": 83.1, "elapsed_time": "1 day, 8:02:37", "remaining_time": "6:31:06"}
+{"current_steps": 3510, "total_steps": 4212, "loss": 0.2235, "lr": 8.251777242258834e-06, "epoch": 0.8334322687878428, "percentage": 83.33, "elapsed_time": "1 day, 8:07:37", "remaining_time": "6:25:31"}
+{"current_steps": 3520, "total_steps": 4212, "loss": 0.1998, "lr": 8.025136192220894e-06, "epoch": 0.8358067196960702, "percentage": 83.57, "elapsed_time": "1 day, 8:12:32", "remaining_time": "6:19:55"}
+{"current_steps": 3530, "total_steps": 4212, "loss": 0.2251, "lr": 7.801379227705203e-06, "epoch": 0.8381811706042978, "percentage": 83.81, "elapsed_time": "1 day, 8:17:12", "remaining_time": "6:14:16"}
+{"current_steps": 3540, "total_steps": 4212, "loss": 0.1954, "lr": 7.58052172301349e-06, "epoch": 0.8405556215125253, "percentage": 84.05, "elapsed_time": "1 day, 8:22:15", "remaining_time": "6:08:42"}
+{"current_steps": 3550, "total_steps": 4212, "loss": 0.2014, "lr": 7.362578853226121e-06, "epoch": 0.8429300724207527, "percentage": 84.28, "elapsed_time": "1 day, 8:27:39", "remaining_time": "6:03:11"}
+{"current_steps": 3560, "total_steps": 4212, "loss": 0.2346, "lr": 7.1475655931594e-06, "epoch": 0.8453045233289802, "percentage": 84.52, "elapsed_time": "1 day, 8:32:39", "remaining_time": "5:57:37"}
+{"current_steps": 3570, "total_steps": 4212, "loss": 0.1944, "lr": 6.9354967163367035e-06, "epoch": 0.8476789742372076, "percentage": 84.76, "elapsed_time": "1 day, 8:37:38", "remaining_time": "5:52:02"}
+{"current_steps": 3580, "total_steps": 4212, "loss": 0.2036, "lr": 6.726386793973305e-06, "epoch": 0.8500534251454351, "percentage": 85.0, "elapsed_time": "1 day, 8:42:35", "remaining_time": "5:46:28"}
+{"current_steps": 3590, "total_steps": 4212, "loss": 0.2438, "lr": 6.520250193975242e-06, "epoch": 0.8524278760536625, "percentage": 85.23, "elapsed_time": "1 day, 8:47:27", "remaining_time": "5:40:52"}
+{"current_steps": 3600, "total_steps": 4212, "loss": 0.2258, "lr": 6.317101079952148e-06, "epoch": 0.8548023269618901, "percentage": 85.47, "elapsed_time": "1 day, 8:53:14", "remaining_time": "5:35:27"}
+{"current_steps": 3610, "total_steps": 4212, "loss": 0.1954, "lr": 6.116953410243925e-06, "epoch": 0.8571767778701176, "percentage": 85.71, "elapsed_time": "1 day, 8:57:55", "remaining_time": "5:29:50"}
+{"current_steps": 3620, "total_steps": 4212, "loss": 0.2192, "lr": 5.919820936961856e-06, "epoch": 0.859551228778345, "percentage": 85.94, "elapsed_time": "1 day, 9:02:50", "remaining_time": "5:24:15"}
+{"current_steps": 3630, "total_steps": 4212, "loss": 0.1896, "lr": 5.725717205043552e-06, "epoch": 0.8619256796865725, "percentage": 86.18, "elapsed_time": "1 day, 9:07:14", "remaining_time": "5:18:36"}
+{"current_steps": 3640, "total_steps": 4212, "loss": 0.2318, "lr": 5.5346555513223485e-06, "epoch": 0.8643001305947999, "percentage": 86.42, "elapsed_time": "1 day, 9:12:27", "remaining_time": "5:13:05"}
+{"current_steps": 3650, "total_steps": 4212, "loss": 0.2081, "lr": 5.34664910361094e-06, "epoch": 0.8666745815030275, "percentage": 86.66, "elapsed_time": "1 day, 9:17:40", "remaining_time": "5:07:35"}
+{"current_steps": 3660, "total_steps": 4212, "loss": 0.2156, "lr": 5.161710779799328e-06, "epoch": 0.8690490324112549, "percentage": 86.89, "elapsed_time": "1 day, 9:22:59", "remaining_time": "5:02:05"}
+{"current_steps": 3670, "total_steps": 4212, "loss": 0.1889, "lr": 4.979853286967273e-06, "epoch": 0.8714234833194824, "percentage": 87.13, "elapsed_time": "1 day, 9:27:03", "remaining_time": "4:56:24"}
+{"current_steps": 3680, "total_steps": 4212, "loss": 0.2193, "lr": 4.801089120511165e-06, "epoch": 0.8737979342277098, "percentage": 87.37, "elapsed_time": "1 day, 9:31:58", "remaining_time": "4:50:51"}
+{"current_steps": 3690, "total_steps": 4212, "loss": 0.2315, "lr": 4.625430563285515e-06, "epoch": 0.8761723851359373, "percentage": 87.61, "elapsed_time": "1 day, 9:36:53", "remaining_time": "4:45:18"}
+{"current_steps": 3700, "total_steps": 4212, "loss": 0.2573, "lr": 4.452889684758938e-06, "epoch": 0.8785468360441648, "percentage": 87.84, "elapsed_time": "1 day, 9:41:29", "remaining_time": "4:39:43"}
+{"current_steps": 3710, "total_steps": 4212, "loss": 0.2112, "lr": 4.283478340184893e-06, "epoch": 0.8809212869523922, "percentage": 88.08, "elapsed_time": "1 day, 9:46:43", "remaining_time": "4:34:14"}
+{"current_steps": 3720, "total_steps": 4212, "loss": 0.2091, "lr": 4.11720816978714e-06, "epoch": 0.8832957378606198, "percentage": 88.32, "elapsed_time": "1 day, 9:51:59", "remaining_time": "4:28:44"}
+{"current_steps": 3730, "total_steps": 4212, "loss": 0.2038, "lr": 3.95409059795987e-06, "epoch": 0.8856701887688472, "percentage": 88.56, "elapsed_time": "1 day, 9:56:00", "remaining_time": "4:23:05"}
+{"current_steps": 3740, "total_steps": 4212, "loss": 0.2478, "lr": 3.7941368324828253e-06, "epoch": 0.8880446396770747, "percentage": 88.79, "elapsed_time": "1 day, 10:00:17", "remaining_time": "4:17:29"}
+{"current_steps": 3750, "total_steps": 4212, "loss": 0.2081, "lr": 3.6373578637511283e-06, "epoch": 0.8904190905853021, "percentage": 89.03, "elapsed_time": "1 day, 10:05:04", "remaining_time": "4:11:57"}
+{"current_steps": 3760, "total_steps": 4212, "loss": 0.224, "lr": 3.4837644640202003e-06, "epoch": 0.8927935414935296, "percentage": 89.27, "elapsed_time": "1 day, 10:09:12", "remaining_time": "4:06:20"}
+{"current_steps": 3770, "total_steps": 4212, "loss": 0.2222, "lr": 3.333367186665576e-06, "epoch": 0.895167992401757, "percentage": 89.51, "elapsed_time": "1 day, 10:14:12", "remaining_time": "4:00:50"}
+{"current_steps": 3780, "total_steps": 4212, "loss": 0.2212, "lr": 3.186176365457766e-06, "epoch": 0.8975424433099846, "percentage": 89.74, "elapsed_time": "1 day, 10:19:27", "remaining_time": "3:55:22"}
+{"current_steps": 3790, "total_steps": 4212, "loss": 0.1949, "lr": 3.042202113852255e-06, "epoch": 0.8999168942182121, "percentage": 89.98, "elapsed_time": "1 day, 10:23:50", "remaining_time": "3:49:48"}
+{"current_steps": 3800, "total_steps": 4212, "loss": 0.2108, "lr": 2.9014543242945837e-06, "epoch": 0.9022913451264395, "percentage": 90.22, "elapsed_time": "1 day, 10:29:25", "remaining_time": "3:44:22"}
+{"current_steps": 3810, "total_steps": 4212, "loss": 0.2566, "lr": 2.7639426675406753e-06, "epoch": 0.904665796034667, "percentage": 90.46, "elapsed_time": "1 day, 10:34:22", "remaining_time": "3:38:52"}
+{"current_steps": 3820, "total_steps": 4212, "loss": 0.2098, "lr": 2.629676591992314e-06, "epoch": 0.9070402469428944, "percentage": 90.69, "elapsed_time": "1 day, 10:38:36", "remaining_time": "3:33:18"}
+{"current_steps": 3830, "total_steps": 4212, "loss": 0.2456, "lr": 2.498665323047966e-06, "epoch": 0.909414697851122, "percentage": 90.93, "elapsed_time": "1 day, 10:43:47", "remaining_time": "3:27:50"}
+{"current_steps": 3840, "total_steps": 4212, "loss": 0.203, "lr": 2.370917862468941e-06, "epoch": 0.9117891487593494, "percentage": 91.17, "elapsed_time": "1 day, 10:49:09", "remaining_time": "3:22:23"}
+{"current_steps": 3850, "total_steps": 4212, "loss": 0.2151, "lr": 2.2464429877607995e-06, "epoch": 0.9141635996675769, "percentage": 91.41, "elapsed_time": "1 day, 10:53:31", "remaining_time": "3:16:50"}
+{"current_steps": 3860, "total_steps": 4212, "loss": 0.2254, "lr": 2.1252492515703382e-06, "epoch": 0.9165380505758044, "percentage": 91.64, "elapsed_time": "1 day, 10:59:12", "remaining_time": "3:11:25"}
+{"current_steps": 3870, "total_steps": 4212, "loss": 0.1823, "lr": 2.0073449810978974e-06, "epoch": 0.9189125014840318, "percentage": 91.88, "elapsed_time": "1 day, 11:04:44", "remaining_time": "3:06:00"}
+{"current_steps": 3880, "total_steps": 4212, "loss": 0.2369, "lr": 1.8927382775251856e-06, "epoch": 0.9212869523922593, "percentage": 92.12, "elapsed_time": "1 day, 11:10:33", "remaining_time": "3:00:35"}
+{"current_steps": 3890, "total_steps": 4212, "loss": 0.1982, "lr": 1.781437015458698e-06, "epoch": 0.9236614033004867, "percentage": 92.36, "elapsed_time": "1 day, 11:15:35", "remaining_time": "2:55:07"}
+{"current_steps": 3900, "total_steps": 4212, "loss": 0.205, "lr": 1.673448842388603e-06, "epoch": 0.9260358542087143, "percentage": 92.59, "elapsed_time": "1 day, 11:20:04", "remaining_time": "2:49:36"}
+{"current_steps": 3910, "total_steps": 4212, "loss": 0.2055, "lr": 1.5687811781633033e-06, "epoch": 0.9284103051169417, "percentage": 92.83, "elapsed_time": "1 day, 11:24:22", "remaining_time": "2:44:04"}
+{"current_steps": 3920, "total_steps": 4212, "loss": 0.1943, "lr": 1.4674412144796368e-06, "epoch": 0.9307847560251692, "percentage": 93.07, "elapsed_time": "1 day, 11:29:07", "remaining_time": "2:38:35"}
+{"current_steps": 3930, "total_steps": 4212, "loss": 0.1821, "lr": 1.3694359143887225e-06, "epoch": 0.9331592069333966, "percentage": 93.3, "elapsed_time": "1 day, 11:34:11", "remaining_time": "2:33:08"}
+{"current_steps": 3940, "total_steps": 4212, "loss": 0.1794, "lr": 1.2747720118175099e-06, "epoch": 0.9355336578416241, "percentage": 93.54, "elapsed_time": "1 day, 11:38:57", "remaining_time": "2:27:39"}
+{"current_steps": 3950, "total_steps": 4212, "loss": 0.1955, "lr": 1.1834560111061211e-06, "epoch": 0.9379081087498516, "percentage": 93.78, "elapsed_time": "1 day, 11:43:48", "remaining_time": "2:22:11"}
+{"current_steps": 3960, "total_steps": 4212, "loss": 0.2071, "lr": 1.095494186560947e-06, "epoch": 0.940282559658079, "percentage": 94.02, "elapsed_time": "1 day, 11:48:12", "remaining_time": "2:16:42"}
+{"current_steps": 3970, "total_steps": 4212, "loss": 0.2151, "lr": 1.0108925820234926e-06, "epoch": 0.9426570105663066, "percentage": 94.25, "elapsed_time": "1 day, 11:52:08", "remaining_time": "2:11:11"}
+{"current_steps": 3980, "total_steps": 4212, "loss": 0.1961, "lr": 9.29657010455165e-07, "epoch": 0.945031461474534, "percentage": 94.49, "elapsed_time": "1 day, 11:56:23", "remaining_time": "2:05:41"}
+{"current_steps": 3990, "total_steps": 4212, "loss": 0.2276, "lr": 8.517930535378083e-07, "epoch": 0.9474059123827615, "percentage": 94.73, "elapsed_time": "1 day, 12:01:32", "remaining_time": "2:00:15"}
+{"current_steps": 4000, "total_steps": 4212, "loss": 0.2301, "lr": 7.773060612902395e-07, "epoch": 0.9497803632909889, "percentage": 94.97, "elapsed_time": "1 day, 12:05:34", "remaining_time": "1:54:46"}
+{"current_steps": 4000, "total_steps": 4212, "eval_loss": 0.20879201591014862, "epoch": 0.9497803632909889, "percentage": 94.97, "elapsed_time": "1 day, 12:38:52", "remaining_time": "1:56:32"}
+{"current_steps": 4010, "total_steps": 4212, "loss": 0.1919, "lr": 7.062011517006139e-07, "epoch": 0.9521548141992164, "percentage": 95.2, "elapsed_time": "1 day, 12:44:23", "remaining_time": "1:51:02"}
+{"current_steps": 4020, "total_steps": 4212, "loss": 0.2081, "lr": 6.384832103747907e-07, "epoch": 0.954529265107444, "percentage": 95.44, "elapsed_time": "1 day, 12:48:58", "remaining_time": "1:45:30"}
+{"current_steps": 4030, "total_steps": 4212, "loss": 0.1962, "lr": 5.741568902006277e-07, "epoch": 0.9569037160156714, "percentage": 95.68, "elapsed_time": "1 day, 12:53:27", "remaining_time": "1:39:57"}
+{"current_steps": 4040, "total_steps": 4212, "loss": 0.1665, "lr": 5.132266110282835e-07, "epoch": 0.9592781669238989, "percentage": 95.92, "elapsed_time": "1 day, 12:58:38", "remaining_time": "1:34:27"}
+{"current_steps": 4050, "total_steps": 4212, "loss": 0.2127, "lr": 4.5569655936654186e-07, "epoch": 0.9616526178321263, "percentage": 96.15, "elapsed_time": "1 day, 13:04:03", "remaining_time": "1:28:57"}
+{"current_steps": 4060, "total_steps": 4212, "loss": 0.2103, "lr": 4.0157068809515417e-07, "epoch": 0.9640270687403538, "percentage": 96.39, "elapsed_time": "1 day, 13:09:18", "remaining_time": "1:23:27"}
+{"current_steps": 4070, "total_steps": 4212, "loss": 0.2309, "lr": 3.50852716193234e-07, "epoch": 0.9664015196485812, "percentage": 96.63, "elapsed_time": "1 day, 13:14:36", "remaining_time": "1:17:57"}
+{"current_steps": 4080, "total_steps": 4212, "loss": 0.2033, "lr": 3.0354612848372265e-07, "epoch": 0.9687759705568088, "percentage": 96.87, "elapsed_time": "1 day, 13:19:54", "remaining_time": "1:12:28"}
+{"current_steps": 4090, "total_steps": 4212, "loss": 0.1892, "lr": 2.59654175393953e-07, "epoch": 0.9711504214650362, "percentage": 97.1, "elapsed_time": "1 day, 13:25:31", "remaining_time": "1:06:58"}
+{"current_steps": 4100, "total_steps": 4212, "loss": 0.2659, "lr": 2.1917987273232245e-07, "epoch": 0.9735248723732637, "percentage": 97.34, "elapsed_time": "1 day, 13:30:52", "remaining_time": "1:01:29"}
+{"current_steps": 4110, "total_steps": 4212, "loss": 0.1669, "lr": 1.8212600148105884e-07, "epoch": 0.9758993232814912, "percentage": 97.58, "elapsed_time": "1 day, 13:35:27", "remaining_time": "0:55:58"}
+{"current_steps": 4120, "total_steps": 4212, "loss": 0.2005, "lr": 1.4849510760513995e-07, "epoch": 0.9782737741897186, "percentage": 97.82, "elapsed_time": "1 day, 13:40:04", "remaining_time": "0:50:28"}
+{"current_steps": 4130, "total_steps": 4212, "loss": 0.1955, "lr": 1.182895018773944e-07, "epoch": 0.9806482250979461, "percentage": 98.05, "elapsed_time": "1 day, 13:44:24", "remaining_time": "0:44:57"}
+{"current_steps": 4140, "total_steps": 4212, "loss": 0.1946, "lr": 9.151125971967878e-08, "epoch": 0.9830226760061735, "percentage": 98.29, "elapsed_time": "1 day, 13:49:12", "remaining_time": "0:39:27"}
+{"current_steps": 4150, "total_steps": 4212, "loss": 0.2244, "lr": 6.816222106030834e-08, "epoch": 0.9853971269144011, "percentage": 98.53, "elapsed_time": "1 day, 13:53:46", "remaining_time": "0:33:58"}
+{"current_steps": 4160, "total_steps": 4212, "loss": 0.2032, "lr": 4.824399020763593e-08, "epoch": 0.9877715778226285, "percentage": 98.77, "elapsed_time": "1 day, 13:59:03", "remaining_time": "0:28:29"}
+{"current_steps": 4170, "total_steps": 4212, "loss": 0.2069, "lr": 3.175793573980124e-08, "epoch": 0.990146028730856, "percentage": 99.0, "elapsed_time": "1 day, 14:03:19", "remaining_time": "0:22:59"}
+{"current_steps": 4180, "total_steps": 4212, "loss": 0.2685, "lr": 1.8705190410717166e-08, "epoch": 0.9925204796390834, "percentage": 99.24, "elapsed_time": "1 day, 14:07:56", "remaining_time": "0:17:30"}
+{"current_steps": 4190, "total_steps": 4212, "loss": 0.1907, "lr": 9.086651072215402e-09, "epoch": 0.9948949305473109, "percentage": 99.48, "elapsed_time": "1 day, 14:12:38", "remaining_time": "0:12:02"}
+{"current_steps": 4200, "total_steps": 4212, "loss": 0.211, "lr": 2.902978612456808e-09, "epoch": 0.9972693814555385, "percentage": 99.72, "elapsed_time": "1 day, 14:16:54", "remaining_time": "0:06:33"}
+{"current_steps": 4210, "total_steps": 4212, "loss": 0.2539, "lr": 1.5459791047889305e-10, "epoch": 0.9996438323637659, "percentage": 99.95, "elapsed_time": "1 day, 14:22:08", "remaining_time": "0:01:05"}
+{"current_steps": 4212, "total_steps": 4212, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1 day, 14:23:20", "remaining_time": "0:00:00"}

qwen2-gob-plan-115/trainer_state.json

@@ -0,0 +1,3054 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4212,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0023744509082274726,
+      "grad_norm": 17.46586799621582,
+      "learning_rate": 2.1327014218009483e-06,
+      "loss": 2.1021,
+      "step": 10
+    },
+    {
+      "epoch": 0.004748901816454945,
+      "grad_norm": 8.901350021362305,
+      "learning_rate": 4.502369668246446e-06,
+      "loss": 1.0168,
+      "step": 20
+    },
+    {
+      "epoch": 0.007123352724682417,
+      "grad_norm": 6.82363224029541,
+      "learning_rate": 6.8720379146919435e-06,
+      "loss": 0.6508,
+      "step": 30
+    },
+    {
+      "epoch": 0.00949780363290989,
+      "grad_norm": 5.696808338165283,
+      "learning_rate": 9.24170616113744e-06,
+      "loss": 0.5579,
+      "step": 40
+    },
+    {
+      "epoch": 0.011872254541137363,
+      "grad_norm": 7.2419819831848145,
+      "learning_rate": 1.161137440758294e-05,
+      "loss": 0.5911,
+      "step": 50
+    },
+    {
+      "epoch": 0.014246705449364834,
+      "grad_norm": 5.160392761230469,
+      "learning_rate": 1.3981042654028437e-05,
+      "loss": 0.5363,
+      "step": 60
+    },
+    {
+      "epoch": 0.016621156357592308,
+      "grad_norm": 5.5930962562561035,
+      "learning_rate": 1.6350710900473933e-05,
+      "loss": 0.5813,
+      "step": 70
+    },
+    {
+      "epoch": 0.01899560726581978,
+      "grad_norm": 5.244218349456787,
+      "learning_rate": 1.872037914691943e-05,
+      "loss": 0.5928,
+      "step": 80
+    },
+    {
+      "epoch": 0.021370058174047253,
+      "grad_norm": 5.168963432312012,
+      "learning_rate": 2.109004739336493e-05,
+      "loss": 0.5576,
+      "step": 90
+    },
+    {
+      "epoch": 0.023744509082274726,
+      "grad_norm": 5.0075836181640625,
+      "learning_rate": 2.345971563981043e-05,
+      "loss": 0.5891,
+      "step": 100
+    },
+    {
+      "epoch": 0.026118959990502195,
+      "grad_norm": 4.455913066864014,
+      "learning_rate": 2.5829383886255927e-05,
+      "loss": 0.6125,
+      "step": 110
+    },
+    {
+      "epoch": 0.028493410898729667,
+      "grad_norm": 3.4008946418762207,
+      "learning_rate": 2.8199052132701424e-05,
+      "loss": 0.5772,
+      "step": 120
+    },
+    {
+      "epoch": 0.03086786180695714,
+      "grad_norm": 4.0339884757995605,
+      "learning_rate": 3.056872037914692e-05,
+      "loss": 0.6367,
+      "step": 130
+    },
+    {
+      "epoch": 0.033242312715184616,
+      "grad_norm": 3.819330930709839,
+      "learning_rate": 3.293838862559242e-05,
+      "loss": 0.6695,
+      "step": 140
+    },
+    {
+      "epoch": 0.03561676362341209,
+      "grad_norm": 3.6872074604034424,
+      "learning_rate": 3.530805687203792e-05,
+      "loss": 0.6226,
+      "step": 150
+    },
+    {
+      "epoch": 0.03799121453163956,
+      "grad_norm": 3.7728962898254395,
+      "learning_rate": 3.767772511848342e-05,
+      "loss": 0.6079,
+      "step": 160
+    },
+    {
+      "epoch": 0.040365665439867034,
+      "grad_norm": 3.776675224304199,
+      "learning_rate": 4.004739336492891e-05,
+      "loss": 0.6063,
+      "step": 170
+    },
+    {
+      "epoch": 0.042740116348094506,
+      "grad_norm": 3.165210485458374,
+      "learning_rate": 4.2417061611374406e-05,
+      "loss": 0.5927,
+      "step": 180
+    },
+    {
+      "epoch": 0.04511456725632198,
+      "grad_norm": 2.95751690864563,
+      "learning_rate": 4.478672985781991e-05,
+      "loss": 0.6349,
+      "step": 190
+    },
+    {
+      "epoch": 0.04748901816454945,
+      "grad_norm": 3.4776411056518555,
+      "learning_rate": 4.71563981042654e-05,
+      "loss": 0.6307,
+      "step": 200
+    },
+    {
+      "epoch": 0.04986346907277692,
+      "grad_norm": 4.28296422958374,
+      "learning_rate": 4.95260663507109e-05,
+      "loss": 0.6583,
+      "step": 210
+    },
+    {
+      "epoch": 0.05223791998100439,
+      "grad_norm": 2.8013813495635986,
+      "learning_rate": 5.1895734597156396e-05,
+      "loss": 0.7049,
+      "step": 220
+    },
+    {
+      "epoch": 0.05461237088923186,
+      "grad_norm": 2.8767004013061523,
+      "learning_rate": 5.42654028436019e-05,
+      "loss": 0.6285,
+      "step": 230
+    },
+    {
+      "epoch": 0.056986821797459335,
+      "grad_norm": 3.0225541591644287,
+      "learning_rate": 5.66350710900474e-05,
+      "loss": 0.6836,
+      "step": 240
+    },
+    {
+      "epoch": 0.05936127270568681,
+      "grad_norm": 2.8183484077453613,
+      "learning_rate": 5.90047393364929e-05,
+      "loss": 0.641,
+      "step": 250
+    },
+    {
+      "epoch": 0.06173572361391428,
+      "grad_norm": 3.104975700378418,
+      "learning_rate": 6.137440758293839e-05,
+      "loss": 0.6517,
+      "step": 260
+    },
+    {
+      "epoch": 0.06411017452214175,
+      "grad_norm": 3.1265125274658203,
+      "learning_rate": 6.374407582938389e-05,
+      "loss": 0.7061,
+      "step": 270
+    },
+    {
+      "epoch": 0.06648462543036923,
+      "grad_norm": 149.14334106445312,
+      "learning_rate": 6.611374407582939e-05,
+      "loss": 0.9615,
+      "step": 280
+    },
+    {
+      "epoch": 0.0688590763385967,
+      "grad_norm": 3.6724066734313965,
+      "learning_rate": 6.848341232227489e-05,
+      "loss": 0.7798,
+      "step": 290
+    },
+    {
+      "epoch": 0.07123352724682418,
+      "grad_norm": 4.057666778564453,
+      "learning_rate": 7.085308056872039e-05,
+      "loss": 0.6821,
+      "step": 300
+    },
+    {
+      "epoch": 0.07360797815505164,
+      "grad_norm": 2.4661478996276855,
+      "learning_rate": 7.322274881516588e-05,
+      "loss": 0.6711,
+      "step": 310
+    },
+    {
+      "epoch": 0.07598242906327912,
+      "grad_norm": 3.435774326324463,
+      "learning_rate": 7.559241706161138e-05,
+      "loss": 0.6888,
+      "step": 320
+    },
+    {
+      "epoch": 0.07835687997150659,
+      "grad_norm": 2.5769989490509033,
+      "learning_rate": 7.796208530805688e-05,
+      "loss": 0.8411,
+      "step": 330
+    },
+    {
+      "epoch": 0.08073133087973407,
+      "grad_norm": 2.518162250518799,
+      "learning_rate": 8.033175355450238e-05,
+      "loss": 0.6802,
+      "step": 340
+    },
+    {
+      "epoch": 0.08310578178796153,
+      "grad_norm": 6.829289436340332,
+      "learning_rate": 8.270142180094788e-05,
+      "loss": 0.7479,
+      "step": 350
+    },
+    {
+      "epoch": 0.08548023269618901,
+      "grad_norm": 2.6685585975646973,
+      "learning_rate": 8.507109004739337e-05,
+      "loss": 0.7292,
+      "step": 360
+    },
+    {
+      "epoch": 0.08785468360441648,
+      "grad_norm": 2.4462921619415283,
+      "learning_rate": 8.744075829383887e-05,
+      "loss": 0.6956,
+      "step": 370
+    },
+    {
+      "epoch": 0.09022913451264396,
+      "grad_norm": 2.393085479736328,
+      "learning_rate": 8.981042654028437e-05,
+      "loss": 0.7527,
+      "step": 380
+    },
+    {
+      "epoch": 0.09260358542087142,
+      "grad_norm": 2.7507741451263428,
+      "learning_rate": 9.218009478672986e-05,
+      "loss": 0.7719,
+      "step": 390
+    },
+    {
+      "epoch": 0.0949780363290989,
+      "grad_norm": 2.751133441925049,
+      "learning_rate": 9.454976303317536e-05,
+      "loss": 0.7168,
+      "step": 400
+    },
+    {
+      "epoch": 0.09735248723732637,
+      "grad_norm": 2.7662034034729004,
+      "learning_rate": 9.691943127962086e-05,
+      "loss": 0.8366,
+      "step": 410
+    },
+    {
+      "epoch": 0.09972693814555383,
+      "grad_norm": 3.0649664402008057,
+      "learning_rate": 9.928909952606635e-05,
+      "loss": 0.7962,
+      "step": 420
+    },
+    {
+      "epoch": 0.10210138905378131,
+      "grad_norm": 2.3150815963745117,
+      "learning_rate": 9.999915830219296e-05,
+      "loss": 0.8253,
+      "step": 430
+    },
+    {
+      "epoch": 0.10447583996200878,
+      "grad_norm": 2.705899238586426,
+      "learning_rate": 9.999503576890838e-05,
+      "loss": 0.7228,
+      "step": 440
+    },
+    {
+      "epoch": 0.10685029087023626,
+      "grad_norm": 4.077371597290039,
+      "learning_rate": 9.998747808549429e-05,
+      "loss": 0.8091,
+      "step": 450
+    },
+    {
+      "epoch": 0.10922474177846372,
+      "grad_norm": 2.475609302520752,
+      "learning_rate": 9.997648577123782e-05,
+      "loss": 0.8117,
+      "step": 460
+    },
+    {
+      "epoch": 0.1115991926866912,
+      "grad_norm": 4.027471542358398,
+      "learning_rate": 9.996205958141894e-05,
+      "loss": 0.7577,
+      "step": 470
+    },
+    {
+      "epoch": 0.11397364359491867,
+      "grad_norm": 2.330831289291382,
+      "learning_rate": 9.994420050725863e-05,
+      "loss": 0.8031,
+      "step": 480
+    },
+    {
+      "epoch": 0.11634809450314615,
+      "grad_norm": 4.374856948852539,
+      "learning_rate": 9.992290977585072e-05,
+      "loss": 0.7887,
+      "step": 490
+    },
+    {
+      "epoch": 0.11872254541137361,
+      "grad_norm": 2.5677125453948975,
+      "learning_rate": 9.989818885007766e-05,
+      "loss": 0.8213,
+      "step": 500
+    },
+    {
+      "epoch": 0.11872254541137361,
+      "eval_loss": 0.7407782077789307,
+      "eval_runtime": 2005.0626,
+      "eval_samples_per_second": 1.867,
+      "eval_steps_per_second": 0.467,
+      "step": 500
+    },
+    {
+      "epoch": 0.1210969963196011,
+      "grad_norm": 2.1170384883880615,
+      "learning_rate": 9.987003942850989e-05,
+      "loss": 0.7828,
+      "step": 510
+    },
+    {
+      "epoch": 0.12347144722782856,
+      "grad_norm": 3.637371301651001,
+      "learning_rate": 9.983846344528923e-05,
+      "loss": 0.7454,
+      "step": 520
+    },
+    {
+      "epoch": 0.12584589813605604,
+      "grad_norm": 3.4971210956573486,
+      "learning_rate": 9.980346306999596e-05,
+      "loss": 0.6686,
+      "step": 530
+    },
+    {
+      "epoch": 0.1282203490442835,
+      "grad_norm": 2.935371160507202,
+      "learning_rate": 9.976504070749969e-05,
+      "loss": 0.9724,
+      "step": 540
+    },
+    {
+      "epoch": 0.13059479995251097,
+      "grad_norm": 1.999279260635376,
+      "learning_rate": 9.972319899779422e-05,
+      "loss": 0.735,
+      "step": 550
+    },
+    {
+      "epoch": 0.13296925086073846,
+      "grad_norm": 6.134634017944336,
+      "learning_rate": 9.967794081581606e-05,
+      "loss": 0.7613,
+      "step": 560
+    },
+    {
+      "epoch": 0.13534370176896593,
+      "grad_norm": 2.5179545879364014,
+      "learning_rate": 9.962926927124697e-05,
+      "loss": 0.7509,
+      "step": 570
+    },
+    {
+      "epoch": 0.1377181526771934,
+      "grad_norm": 2.3336329460144043,
+      "learning_rate": 9.957718770830022e-05,
+      "loss": 0.7055,
+      "step": 580
+    },
+    {
+      "epoch": 0.14009260358542086,
+      "grad_norm": 2.2505533695220947,
+      "learning_rate": 9.952169970549088e-05,
+      "loss": 0.7494,
+      "step": 590
+    },
+    {
+      "epoch": 0.14246705449364835,
+      "grad_norm": 1.9913499355316162,
+      "learning_rate": 9.946280907538985e-05,
+      "loss": 0.7347,
+      "step": 600
+    },
+    {
+      "epoch": 0.14484150540187582,
+      "grad_norm": 3.043692111968994,
+      "learning_rate": 9.940051986436198e-05,
+      "loss": 0.6848,
+      "step": 610
+    },
+    {
+      "epoch": 0.14721595631010329,
+      "grad_norm": 2.2284398078918457,
+      "learning_rate": 9.933483635228804e-05,
+      "loss": 0.7168,
+      "step": 620
+    },
+    {
+      "epoch": 0.14959040721833075,
+      "grad_norm": 2.5508503913879395,
+      "learning_rate": 9.926576305227063e-05,
+      "loss": 0.7163,
+      "step": 630
+    },
+    {
+      "epoch": 0.15196485812655824,
+      "grad_norm": 2.114255428314209,
+      "learning_rate": 9.919330471032401e-05,
+      "loss": 0.639,
+      "step": 640
+    },
+    {
+      "epoch": 0.1543393090347857,
+      "grad_norm": 2.1416802406311035,
+      "learning_rate": 9.911746630504818e-05,
+      "loss": 0.6972,
+      "step": 650
+    },
+    {
+      "epoch": 0.15671375994301318,
+      "grad_norm": 2.205293893814087,
+      "learning_rate": 9.903825304728664e-05,
+      "loss": 0.7853,
+      "step": 660
+    },
+    {
+      "epoch": 0.15908821085124064,
+      "grad_norm": 2.643953800201416,
+      "learning_rate": 9.895567037976842e-05,
+      "loss": 0.6616,
+      "step": 670
+    },
+    {
+      "epoch": 0.16146266175946813,
+      "grad_norm": 1.8454670906066895,
+      "learning_rate": 9.88697239767341e-05,
+      "loss": 0.6649,
+      "step": 680
+    },
+    {
+      "epoch": 0.1638371126676956,
+      "grad_norm": 2.498075008392334,
+      "learning_rate": 9.878041974354598e-05,
+      "loss": 0.7677,
+      "step": 690
+    },
+    {
+      "epoch": 0.16621156357592307,
+      "grad_norm": 2.1788713932037354,
+      "learning_rate": 9.868776381628218e-05,
+      "loss": 0.7151,
+      "step": 700
+    },
+    {
+      "epoch": 0.16858601448415053,
+      "grad_norm": 1.8394912481307983,
+      "learning_rate": 9.859176256131522e-05,
+      "loss": 0.8004,
+      "step": 710
+    },
+    {
+      "epoch": 0.17096046539237802,
+      "grad_norm": 1.8285107612609863,
+      "learning_rate": 9.849242257487447e-05,
+      "loss": 0.686,
+      "step": 720
+    },
+    {
+      "epoch": 0.1733349163006055,
+      "grad_norm": 2.7288475036621094,
+      "learning_rate": 9.838975068259297e-05,
+      "loss": 0.7076,
+      "step": 730
+    },
+    {
+      "epoch": 0.17570936720883296,
+      "grad_norm": 3.241076707839966,
+      "learning_rate": 9.828375393903842e-05,
+      "loss": 0.7879,
+      "step": 740
+    },
+    {
+      "epoch": 0.17808381811706042,
+      "grad_norm": 1.8407208919525146,
+      "learning_rate": 9.817443962722843e-05,
+      "loss": 0.72,
+      "step": 750
+    },
+    {
+      "epoch": 0.18045826902528792,
+      "grad_norm": 2.23694109916687,
+      "learning_rate": 9.806181525813019e-05,
+      "loss": 0.7231,
+      "step": 760
+    },
+    {
+      "epoch": 0.18283271993351538,
+      "grad_norm": 2.168240785598755,
+      "learning_rate": 9.79458885701443e-05,
+      "loss": 0.6952,
+      "step": 770
+    },
+    {
+      "epoch": 0.18520717084174285,
+      "grad_norm": 1.7602572441101074,
+      "learning_rate": 9.782666752857317e-05,
+      "loss": 0.6398,
+      "step": 780
+    },
+    {
+      "epoch": 0.1875816217499703,
+      "grad_norm": 2.375122547149658,
+      "learning_rate": 9.770416032507361e-05,
+      "loss": 0.7202,
+      "step": 790
+    },
+    {
+      "epoch": 0.1899560726581978,
+      "grad_norm": 1.909433126449585,
+      "learning_rate": 9.757837537709407e-05,
+      "loss": 0.6733,
+      "step": 800
+    },
+    {
+      "epoch": 0.19233052356642527,
+      "grad_norm": 2.0807507038116455,
+      "learning_rate": 9.744932132729625e-05,
+      "loss": 0.7764,
+      "step": 810
+    },
+    {
+      "epoch": 0.19470497447465274,
+      "grad_norm": 2.5525600910186768,
+      "learning_rate": 9.731700704296126e-05,
+      "loss": 0.6662,
+      "step": 820
+    },
+    {
+      "epoch": 0.1970794253828802,
+      "grad_norm": 1.9601514339447021,
+      "learning_rate": 9.71814416153803e-05,
+      "loss": 0.6228,
+      "step": 830
+    },
+    {
+      "epoch": 0.19945387629110767,
+      "grad_norm": 1.6027888059616089,
+      "learning_rate": 9.704263435923014e-05,
+      "loss": 0.6479,
+      "step": 840
+    },
+    {
+      "epoch": 0.20182832719933516,
+      "grad_norm": 2.980756998062134,
+      "learning_rate": 9.690059481193295e-05,
+      "loss": 0.8001,
+      "step": 850
+    },
+    {
+      "epoch": 0.20420277810756263,
+      "grad_norm": 1.9024136066436768,
+      "learning_rate": 9.675533273300111e-05,
+      "loss": 0.5831,
+      "step": 860
+    },
+    {
+      "epoch": 0.2065772290157901,
+      "grad_norm": 1.647428274154663,
+      "learning_rate": 9.660685810336654e-05,
+      "loss": 0.6441,
+      "step": 870
+    },
+    {
+      "epoch": 0.20895167992401756,
+      "grad_norm": 1.460141897201538,
+      "learning_rate": 9.645518112469498e-05,
+      "loss": 0.6613,
+      "step": 880
+    },
+    {
+      "epoch": 0.21132613083224505,
+      "grad_norm": 1.7688757181167603,
+      "learning_rate": 9.630031221868501e-05,
+      "loss": 0.5891,
+      "step": 890
+    },
+    {
+      "epoch": 0.21370058174047252,
+      "grad_norm": 2.1308674812316895,
+      "learning_rate": 9.614226202635195e-05,
+      "loss": 0.6525,
+      "step": 900
+    },
+    {
+      "epoch": 0.21607503264869998,
+      "grad_norm": 1.9658663272857666,
+      "learning_rate": 9.59810414072968e-05,
+      "loss": 0.6435,
+      "step": 910
+    },
+    {
+      "epoch": 0.21844948355692745,
+      "grad_norm": 1.6313807964324951,
+      "learning_rate": 9.581666143895994e-05,
+      "loss": 0.689,
+      "step": 920
+    },
+    {
+      "epoch": 0.22082393446515494,
+      "grad_norm": 1.8163197040557861,
+      "learning_rate": 9.564913341586017e-05,
+      "loss": 0.6445,
+      "step": 930
+    },
+    {
+      "epoch": 0.2231983853733824,
+      "grad_norm": 2.0528953075408936,
+      "learning_rate": 9.547846884881853e-05,
+      "loss": 0.6848,
+      "step": 940
+    },
+    {
+      "epoch": 0.22557283628160987,
+      "grad_norm": 1.8023221492767334,
+      "learning_rate": 9.530467946416745e-05,
+      "loss": 0.6939,
+      "step": 950
+    },
+    {
+      "epoch": 0.22794728718983734,
+      "grad_norm": 1.956764578819275,
+      "learning_rate": 9.512777720294504e-05,
+      "loss": 0.6167,
+      "step": 960
+    },
+    {
+      "epoch": 0.23032173809806483,
+      "grad_norm": 2.1776814460754395,
+      "learning_rate": 9.494777422007462e-05,
+      "loss": 0.6839,
+      "step": 970
+    },
+    {
+      "epoch": 0.2326961890062923,
+      "grad_norm": 1.680591106414795,
+      "learning_rate": 9.476468288352951e-05,
+      "loss": 0.5922,
+      "step": 980
+    },
+    {
+      "epoch": 0.23507063991451976,
+      "grad_norm": 1.850630760192871,
+      "learning_rate": 9.457851577348332e-05,
+      "loss": 0.5699,
+      "step": 990
+    },
+    {
+      "epoch": 0.23744509082274723,
+      "grad_norm": 1.4332187175750732,
+      "learning_rate": 9.438928568144547e-05,
+      "loss": 0.5742,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23744509082274723,
+      "eval_loss": 0.6352267861366272,
+      "eval_runtime": 2000.6672,
+      "eval_samples_per_second": 1.871,
+      "eval_steps_per_second": 0.468,
+      "step": 1000
+    },
+    {
+      "epoch": 0.23981954173097472,
+      "grad_norm": 1.6159008741378784,
+      "learning_rate": 9.41970056093824e-05,
+      "loss": 0.6413,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2421939926392022,
+      "grad_norm": 1.7297577857971191,
+      "learning_rate": 9.400168876882408e-05,
+      "loss": 0.6281,
+      "step": 1020
+    },
+    {
+      "epoch": 0.24456844354742965,
+      "grad_norm": 1.577554702758789,
+      "learning_rate": 9.380334857995629e-05,
+      "loss": 0.6787,
+      "step": 1030
+    },
+    {
+      "epoch": 0.24694289445565712,
+      "grad_norm": 1.6764177083969116,
+      "learning_rate": 9.360199867069866e-05,
+      "loss": 0.6043,
+      "step": 1040
+    },
+    {
+      "epoch": 0.2493173453638846,
+      "grad_norm": 1.7127679586410522,
+      "learning_rate": 9.339765287576803e-05,
+      "loss": 0.5633,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2516917962721121,
+      "grad_norm": 1.5897778272628784,
+      "learning_rate": 9.319032523572815e-05,
+      "loss": 0.7124,
+      "step": 1060
+    },
+    {
+      "epoch": 0.25406624718033954,
+      "grad_norm": 1.6537786722183228,
+      "learning_rate": 9.298002999602471e-05,
+      "loss": 0.5931,
+      "step": 1070
+    },
+    {
+      "epoch": 0.256440698088567,
+      "grad_norm": 1.4399652481079102,
+      "learning_rate": 9.276678160600674e-05,
+      "loss": 0.724,
+      "step": 1080
+    },
+    {
+      "epoch": 0.2588151489967945,
+      "grad_norm": 1.9762135744094849,
+      "learning_rate": 9.255059471793369e-05,
+      "loss": 0.6224,
+      "step": 1090
+    },
+    {
+      "epoch": 0.26118959990502194,
+      "grad_norm": 1.9962340593338013,
+      "learning_rate": 9.233148418596862e-05,
+      "loss": 0.5864,
+      "step": 1100
+    },
+    {
+      "epoch": 0.26356405081324946,
+      "grad_norm": 1.3939169645309448,
+      "learning_rate": 9.210946506515777e-05,
+      "loss": 0.5933,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2659385017214769,
+      "grad_norm": 1.665360689163208,
+      "learning_rate": 9.188455261039592e-05,
+      "loss": 0.5608,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2683129526297044,
+      "grad_norm": 1.626900315284729,
+      "learning_rate": 9.165676227537836e-05,
+      "loss": 0.5591,
+      "step": 1130
+    },
+    {
+      "epoch": 0.27068740353793186,
+      "grad_norm": 1.8547568321228027,
+      "learning_rate": 9.1426109711539e-05,
+      "loss": 0.6269,
+      "step": 1140
+    },
+    {
+      "epoch": 0.2730618544461593,
+      "grad_norm": 1.4865916967391968,
+      "learning_rate": 9.1192610766975e-05,
+      "loss": 0.5785,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2754363053543868,
+      "grad_norm": 1.7755070924758911,
+      "learning_rate": 9.095628148535788e-05,
+      "loss": 0.7172,
+      "step": 1160
+    },
+    {
+      "epoch": 0.27781075626261426,
+      "grad_norm": 1.3893502950668335,
+      "learning_rate": 9.071713810483103e-05,
+      "loss": 0.5275,
+      "step": 1170
+    },
+    {
+      "epoch": 0.2801852071708417,
+      "grad_norm": 1.7527644634246826,
+      "learning_rate": 9.047519705689418e-05,
+      "loss": 0.6399,
+      "step": 1180
+    },
+    {
+      "epoch": 0.28255965807906924,
+      "grad_norm": 1.5130287408828735,
+      "learning_rate": 9.023047496527423e-05,
+      "loss": 0.6105,
+      "step": 1190
+    },
+    {
+      "epoch": 0.2849341089872967,
+      "grad_norm": 1.838929533958435,
+      "learning_rate": 8.998298864478314e-05,
+      "loss": 0.609,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2873085598955242,
+      "grad_norm": 1.4919387102127075,
+      "learning_rate": 8.973275510016252e-05,
+      "loss": 0.5436,
+      "step": 1210
+    },
+    {
+      "epoch": 0.28968301080375164,
+      "grad_norm": 1.4375627040863037,
+      "learning_rate": 8.947979152491533e-05,
+      "loss": 0.5398,
+      "step": 1220
+    },
+    {
+      "epoch": 0.2920574617119791,
+      "grad_norm": 1.4347418546676636,
+      "learning_rate": 8.922411530012433e-05,
+      "loss": 0.5829,
+      "step": 1230
+    },
+    {
+      "epoch": 0.29443191262020657,
+      "grad_norm": 1.4648419618606567,
+      "learning_rate": 8.89657439932581e-05,
+      "loss": 0.5319,
+      "step": 1240
+    },
+    {
+      "epoch": 0.29680636352843404,
+      "grad_norm": 1.460462212562561,
+      "learning_rate": 8.870469535696375e-05,
+      "loss": 0.5556,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2991808144366615,
+      "grad_norm": 1.4240905046463013,
+      "learning_rate": 8.844098732784723e-05,
+      "loss": 0.5374,
+      "step": 1260
+    },
+    {
+      "epoch": 0.30155526534488897,
+      "grad_norm": 2.142026662826538,
+      "learning_rate": 8.817463802524096e-05,
+      "loss": 0.5525,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3039297162531165,
+      "grad_norm": 3.275667190551758,
+      "learning_rate": 8.79056657499587e-05,
+      "loss": 0.6688,
+      "step": 1280
+    },
+    {
+      "epoch": 0.30630416716134395,
+      "grad_norm": 1.68355393409729,
+      "learning_rate": 8.763408898303829e-05,
+      "loss": 0.5966,
+      "step": 1290
+    },
+    {
+      "epoch": 0.3086786180695714,
+      "grad_norm": 18.15928840637207,
+      "learning_rate": 8.73599263844717e-05,
+      "loss": 0.606,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3110530689777989,
+      "grad_norm": 1.5004063844680786,
+      "learning_rate": 8.708319679192293e-05,
+      "loss": 0.5279,
+      "step": 1310
+    },
+    {
+      "epoch": 0.31342751988602635,
+      "grad_norm": 1.3138238191604614,
+      "learning_rate": 8.680391921943371e-05,
+      "loss": 0.568,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3158019707942538,
+      "grad_norm": 1.4695392847061157,
+      "learning_rate": 8.652211285611701e-05,
+      "loss": 0.583,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3181764217024813,
+      "grad_norm": 1.6598325967788696,
+      "learning_rate": 8.623779706483855e-05,
+      "loss": 0.6056,
+      "step": 1340
+    },
+    {
+      "epoch": 0.32055087261070875,
+      "grad_norm": 1.5287786722183228,
+      "learning_rate": 8.595099138088644e-05,
+      "loss": 0.5846,
+      "step": 1350
+    },
+    {
+      "epoch": 0.32292532351893627,
+      "grad_norm": 1.881782054901123,
+      "learning_rate": 8.566171551062889e-05,
+      "loss": 0.5304,
+      "step": 1360
+    },
+    {
+      "epoch": 0.32529977442716373,
+      "grad_norm": 1.6649096012115479,
+      "learning_rate": 8.536998933016014e-05,
+      "loss": 0.584,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3276742253353912,
+      "grad_norm": 1.4391852617263794,
+      "learning_rate": 8.507583288393479e-05,
+      "loss": 0.6155,
+      "step": 1380
+    },
+    {
+      "epoch": 0.33004867624361867,
+      "grad_norm": 1.3186627626419067,
+      "learning_rate": 8.477926638339067e-05,
+      "loss": 0.5219,
+      "step": 1390
+    },
+    {
+      "epoch": 0.33242312715184613,
+      "grad_norm": 1.169506311416626,
+      "learning_rate": 8.448031020555993e-05,
+      "loss": 0.4953,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3347975780600736,
+      "grad_norm": 1.8767844438552856,
+      "learning_rate": 8.417898489166905e-05,
+      "loss": 0.5899,
+      "step": 1410
+    },
+    {
+      "epoch": 0.33717202896830106,
+      "grad_norm": 5.4630255699157715,
+      "learning_rate": 8.387531114572746e-05,
+      "loss": 0.5992,
+      "step": 1420
+    },
+    {
+      "epoch": 0.33954647987652853,
+      "grad_norm": 1.2826589345932007,
+      "learning_rate": 8.356930983310493e-05,
+      "loss": 0.5268,
+      "step": 1430
+    },
+    {
+      "epoch": 0.34192093078475605,
+      "grad_norm": 1.3490769863128662,
+      "learning_rate": 8.32610019790979e-05,
+      "loss": 0.5396,
+      "step": 1440
+    },
+    {
+      "epoch": 0.3442953816929835,
+      "grad_norm": 1.3992174863815308,
+      "learning_rate": 8.295040876748489e-05,
+      "loss": 0.5868,
+      "step": 1450
+    },
+    {
+      "epoch": 0.346669832601211,
+      "grad_norm": 1.3962913751602173,
+      "learning_rate": 8.263755153907095e-05,
+      "loss": 0.5431,
+      "step": 1460
+    },
+    {
+      "epoch": 0.34904428350943845,
+      "grad_norm": 1.4923028945922852,
+      "learning_rate": 8.23224517902213e-05,
+      "loss": 0.5288,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3514187344176659,
+      "grad_norm": 1.333264946937561,
+      "learning_rate": 8.200513117138435e-05,
+      "loss": 0.5153,
+      "step": 1480
+    },
+    {
+      "epoch": 0.3537931853258934,
+      "grad_norm": 1.5983505249023438,
+      "learning_rate": 8.168561148560414e-05,
+      "loss": 0.5482,
+      "step": 1490
+    },
+    {
+      "epoch": 0.35616763623412084,
+      "grad_norm": 1.445067048072815,
+      "learning_rate": 8.136391468702214e-05,
+      "loss": 0.5326,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35616763623412084,
+      "eval_loss": 0.5119722485542297,
+      "eval_runtime": 2007.1248,
+      "eval_samples_per_second": 1.865,
+      "eval_steps_per_second": 0.466,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3585420871423483,
+      "grad_norm": 3.041621685028076,
+      "learning_rate": 8.104006287936892e-05,
+      "loss": 0.6232,
+      "step": 1510
+    },
+    {
+      "epoch": 0.36091653805057583,
+      "grad_norm": 1.2769168615341187,
+      "learning_rate": 8.07140783144453e-05,
+      "loss": 0.4939,
+      "step": 1520
+    },
+    {
+      "epoch": 0.3632909889588033,
+      "grad_norm": 1.4550813436508179,
+      "learning_rate": 8.038598339059351e-05,
+      "loss": 0.4444,
+      "step": 1530
+    },
+    {
+      "epoch": 0.36566543986703076,
+      "grad_norm": 1.3510379791259766,
+      "learning_rate": 8.005580065115816e-05,
+      "loss": 0.4768,
+      "step": 1540
+    },
+    {
+      "epoch": 0.3680398907752582,
+      "grad_norm": 1.391461968421936,
+      "learning_rate": 7.972355278293733e-05,
+      "loss": 0.479,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3704143416834857,
+      "grad_norm": 1.3295865058898926,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.4734,
+      "step": 1560
+    },
+    {
+      "epoch": 0.37278879259171316,
+      "grad_norm": 1.7632473707199097,
+      "learning_rate": 7.905295311523595e-05,
+      "loss": 0.5425,
+      "step": 1570
+    },
+    {
+      "epoch": 0.3751632434999406,
+      "grad_norm": 1.3326750993728638,
+      "learning_rate": 7.871464739254084e-05,
+      "loss": 0.4818,
+      "step": 1580
+    },
+    {
+      "epoch": 0.3775376944081681,
+      "grad_norm": 1.4247772693634033,
+      "learning_rate": 7.837436869146517e-05,
+      "loss": 0.496,
+      "step": 1590
+    },
+    {
+      "epoch": 0.3799121453163956,
+      "grad_norm": 1.2185418605804443,
+      "learning_rate": 7.80321403924987e-05,
+      "loss": 0.5389,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3822865962246231,
+      "grad_norm": 1.6560026407241821,
+      "learning_rate": 7.768798601008776e-05,
+      "loss": 0.489,
+      "step": 1610
+    },
+    {
+      "epoch": 0.38466104713285054,
+      "grad_norm": 1.5144054889678955,
+      "learning_rate": 7.734192919101958e-05,
+      "loss": 0.4599,
+      "step": 1620
+    },
+    {
+      "epoch": 0.387035498041078,
+      "grad_norm": 1.2287232875823975,
+      "learning_rate": 7.69939937127974e-05,
+      "loss": 0.6238,
+      "step": 1630
+    },
+    {
+      "epoch": 0.3894099489493055,
+      "grad_norm": 1.2839241027832031,
+      "learning_rate": 7.664420348200689e-05,
+      "loss": 0.4984,
+      "step": 1640
+    },
+    {
+      "epoch": 0.39178439985753294,
+      "grad_norm": 1.3231412172317505,
+      "learning_rate": 7.629258253267332e-05,
+      "loss": 0.4746,
+      "step": 1650
+    },
+    {
+      "epoch": 0.3941588507657604,
+      "grad_norm": 1.5302526950836182,
+      "learning_rate": 7.593915502461042e-05,
+      "loss": 0.5243,
+      "step": 1660
+    },
+    {
+      "epoch": 0.39653330167398787,
+      "grad_norm": 1.2323942184448242,
+      "learning_rate": 7.558394524176023e-05,
+      "loss": 0.5353,
+      "step": 1670
+    },
+    {
+      "epoch": 0.39890775258221534,
+      "grad_norm": 1.5699905157089233,
+      "learning_rate": 7.522697759052451e-05,
+      "loss": 0.5151,
+      "step": 1680
+    },
+    {
+      "epoch": 0.40128220349044286,
+      "grad_norm": 1.3586243391036987,
+      "learning_rate": 7.486827659808796e-05,
+      "loss": 0.4583,
+      "step": 1690
+    },
+    {
+      "epoch": 0.4036566543986703,
+      "grad_norm": 1.3707525730133057,
+      "learning_rate": 7.450786691073274e-05,
+      "loss": 0.5045,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4060311053068978,
+      "grad_norm": 1.6775321960449219,
+      "learning_rate": 7.414577329214522e-05,
+      "loss": 0.521,
+      "step": 1710
+    },
+    {
+      "epoch": 0.40840555621512525,
+      "grad_norm": 1.200310468673706,
+      "learning_rate": 7.378202062171432e-05,
+      "loss": 0.4216,
+      "step": 1720
+    },
+    {
+      "epoch": 0.4107800071233527,
+      "grad_norm": 1.3154892921447754,
+      "learning_rate": 7.341663389282219e-05,
+      "loss": 0.439,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4131544580315802,
+      "grad_norm": 1.3154064416885376,
+      "learning_rate": 7.304963821112681e-05,
+      "loss": 0.468,
+      "step": 1740
+    },
+    {
+      "epoch": 0.41552890893980765,
+      "grad_norm": 1.8923077583312988,
+      "learning_rate": 7.268105879283703e-05,
+      "loss": 0.5209,
+      "step": 1750
+    },
+    {
+      "epoch": 0.4179033598480351,
+      "grad_norm": 1.6501123905181885,
+      "learning_rate": 7.231092096297995e-05,
+      "loss": 0.4444,
+      "step": 1760
+    },
+    {
+      "epoch": 0.42027781075626264,
+      "grad_norm": 1.5123274326324463,
+      "learning_rate": 7.19392501536609e-05,
+      "loss": 0.4706,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4226522616644901,
+      "grad_norm": 1.410674810409546,
+      "learning_rate": 7.156607190231591e-05,
+      "loss": 0.545,
+      "step": 1780
+    },
+    {
+      "epoch": 0.42502671257271757,
+      "grad_norm": 1.343226671218872,
+      "learning_rate": 7.11914118499571e-05,
+      "loss": 0.4404,
+      "step": 1790
+    },
+    {
+      "epoch": 0.42740116348094503,
+      "grad_norm": 1.652727723121643,
+      "learning_rate": 7.081529573941091e-05,
+      "loss": 0.4848,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4297756143891725,
+      "grad_norm": 1.6431710720062256,
+      "learning_rate": 7.043774941354925e-05,
+      "loss": 0.5122,
+      "step": 1810
+    },
+    {
+      "epoch": 0.43215006529739997,
+      "grad_norm": 1.0853626728057861,
+      "learning_rate": 7.005879881351384e-05,
+      "loss": 0.4651,
+      "step": 1820
+    },
+    {
+      "epoch": 0.43452451620562743,
+      "grad_norm": 1.4375888109207153,
+      "learning_rate": 6.967846997693392e-05,
+      "loss": 0.4405,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4368989671138549,
+      "grad_norm": 1.214448094367981,
+      "learning_rate": 6.929678903613705e-05,
+      "loss": 0.4304,
+      "step": 1840
+    },
+    {
+      "epoch": 0.4392734180220824,
+      "grad_norm": 1.5465502738952637,
+      "learning_rate": 6.891378221635367e-05,
+      "loss": 0.4278,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4416478689303099,
+      "grad_norm": 1.4311429262161255,
+      "learning_rate": 6.852947583391511e-05,
+      "loss": 0.4781,
+      "step": 1860
+    },
+    {
+      "epoch": 0.44402231983853735,
+      "grad_norm": 1.4049911499023438,
+      "learning_rate": 6.814389629444543e-05,
+      "loss": 0.4582,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4463967707467648,
+      "grad_norm": 1.1797651052474976,
+      "learning_rate": 6.775707009104708e-05,
+      "loss": 0.4225,
+      "step": 1880
+    },
+    {
+      "epoch": 0.4487712216549923,
+      "grad_norm": 1.1640324592590332,
+      "learning_rate": 6.73690238024806e-05,
+      "loss": 0.4215,
+      "step": 1890
+    },
+    {
+      "epoch": 0.45114567256321975,
+      "grad_norm": 1.2648041248321533,
+      "learning_rate": 6.697978409133831e-05,
+      "loss": 0.518,
+      "step": 1900
+    },
+    {
+      "epoch": 0.4535201234714472,
+      "grad_norm": 1.2650415897369385,
+      "learning_rate": 6.658937770221242e-05,
+      "loss": 0.4217,
+      "step": 1910
+    },
+    {
+      "epoch": 0.4558945743796747,
+      "grad_norm": 1.7061676979064941,
+      "learning_rate": 6.619783145985743e-05,
+      "loss": 0.4848,
+      "step": 1920
+    },
+    {
+      "epoch": 0.4582690252879022,
+      "grad_norm": 1.4012316465377808,
+      "learning_rate": 6.580517226734686e-05,
+      "loss": 0.4036,
+      "step": 1930
+    },
+    {
+      "epoch": 0.46064347619612966,
+      "grad_norm": 1.1461294889450073,
+      "learning_rate": 6.541142710422489e-05,
+      "loss": 0.459,
+      "step": 1940
+    },
+    {
+      "epoch": 0.46301792710435713,
+      "grad_norm": 1.4154229164123535,
+      "learning_rate": 6.501662302465254e-05,
+      "loss": 0.4338,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4653923780125846,
+      "grad_norm": 1.0013957023620605,
+      "learning_rate": 6.46207871555488e-05,
+      "loss": 0.4175,
+      "step": 1960
+    },
+    {
+      "epoch": 0.46776682892081206,
+      "grad_norm": 1.1550451517105103,
+      "learning_rate": 6.422394669472676e-05,
+      "loss": 0.4774,
+      "step": 1970
+    },
+    {
+      "epoch": 0.4701412798290395,
+      "grad_norm": 2.9167330265045166,
+      "learning_rate": 6.382612890902478e-05,
+      "loss": 0.4808,
+      "step": 1980
+    },
+    {
+      "epoch": 0.472515730737267,
+      "grad_norm": 1.2706438302993774,
+      "learning_rate": 6.342736113243305e-05,
+      "loss": 0.4014,
+      "step": 1990
+    },
+    {
+      "epoch": 0.47489018164549446,
+      "grad_norm": 1.3059141635894775,
+      "learning_rate": 6.302767076421552e-05,
+      "loss": 0.4165,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47489018164549446,
+      "eval_loss": 0.4213089346885681,
+      "eval_runtime": 2002.2295,
+      "eval_samples_per_second": 1.87,
+      "eval_steps_per_second": 0.467,
+      "step": 2000
+    },
+    {
+      "epoch": 0.477264632553722,
+      "grad_norm": 1.2650591135025024,
+      "learning_rate": 6.26270852670272e-05,
+      "loss": 0.4429,
+      "step": 2010
+    },
+    {
+      "epoch": 0.47963908346194944,
+      "grad_norm": 1.1537431478500366,
+      "learning_rate": 6.222563216502724e-05,
+      "loss": 0.4951,
+      "step": 2020
+    },
+    {
+      "epoch": 0.4820135343701769,
+      "grad_norm": 1.0984758138656616,
+      "learning_rate": 6.182333904198782e-05,
+      "loss": 0.4165,
+      "step": 2030
+    },
+    {
+      "epoch": 0.4843879852784044,
+      "grad_norm": 1.335157036781311,
+      "learning_rate": 6.14202335393988e-05,
+      "loss": 0.4133,
+      "step": 2040
+    },
+    {
+      "epoch": 0.48676243618663184,
+      "grad_norm": 1.3875082731246948,
+      "learning_rate": 6.1016343354568464e-05,
+      "loss": 0.4254,
+      "step": 2050
+    },
+    {
+      "epoch": 0.4891368870948593,
+      "grad_norm": 1.3098845481872559,
+      "learning_rate": 6.0611696238720485e-05,
+      "loss": 0.4138,
+      "step": 2060
+    },
+    {
+      "epoch": 0.4915113380030868,
+      "grad_norm": 1.2245336771011353,
+      "learning_rate": 6.020631999508717e-05,
+      "loss": 0.4021,
+      "step": 2070
+    },
+    {
+      "epoch": 0.49388578891131424,
+      "grad_norm": 1.128445029258728,
+      "learning_rate": 5.980024247699903e-05,
+      "loss": 0.3708,
+      "step": 2080
+    },
+    {
+      "epoch": 0.4962602398195417,
+      "grad_norm": 1.207760214805603,
+      "learning_rate": 5.939349158597102e-05,
+      "loss": 0.4198,
+      "step": 2090
+    },
+    {
+      "epoch": 0.4986346907277692,
+      "grad_norm": 1.347845435142517,
+      "learning_rate": 5.898609526978547e-05,
+      "loss": 0.3956,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5010091416359966,
+      "grad_norm": 1.4427859783172607,
+      "learning_rate": 5.857808152057173e-05,
+      "loss": 0.4176,
+      "step": 2110
+    },
+    {
+      "epoch": 0.5033835925442242,
+      "grad_norm": 1.3605539798736572,
+      "learning_rate": 5.816947837288285e-05,
+      "loss": 0.4061,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5057580434524516,
+      "grad_norm": 1.6183706521987915,
+      "learning_rate": 5.776031390176938e-05,
+      "loss": 0.3868,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5081324943606791,
+      "grad_norm": 1.385736346244812,
+      "learning_rate": 5.7350616220850285e-05,
+      "loss": 0.5408,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5105069452689066,
+      "grad_norm": 1.7778092622756958,
+      "learning_rate": 5.694041348038128e-05,
+      "loss": 0.4183,
+      "step": 2150
+    },
+    {
+      "epoch": 0.512881396177134,
+      "grad_norm": 1.1978100538253784,
+      "learning_rate": 5.652973386532066e-05,
+      "loss": 0.3751,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5152558470853615,
+      "grad_norm": 1.3059000968933105,
+      "learning_rate": 5.611860559339265e-05,
+      "loss": 0.3528,
+      "step": 2170
+    },
+    {
+      "epoch": 0.517630297993589,
+      "grad_norm": 1.505707025527954,
+      "learning_rate": 5.5707056913148626e-05,
+      "loss": 0.4023,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5200047489018165,
+      "grad_norm": 1.1287879943847656,
+      "learning_rate": 5.529511610202616e-05,
+      "loss": 0.3637,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5223791998100439,
+      "grad_norm": 1.0342644453048706,
+      "learning_rate": 5.4882811464406026e-05,
+      "loss": 0.3705,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5247536507182714,
+      "grad_norm": 1.2189958095550537,
+      "learning_rate": 5.4470171329667506e-05,
+      "loss": 0.4017,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5271281016264989,
+      "grad_norm": 2.2192893028259277,
+      "learning_rate": 5.405722405024183e-05,
+      "loss": 0.4057,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5295025525347263,
+      "grad_norm": 1.441884994506836,
+      "learning_rate": 5.364399799966402e-05,
+      "loss": 0.3652,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5318770034429539,
+      "grad_norm": 1.0196775197982788,
+      "learning_rate": 5.323052157062346e-05,
+      "loss": 0.3943,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5342514543511813,
+      "grad_norm": 1.2071340084075928,
+      "learning_rate": 5.281682317301302e-05,
+      "loss": 0.3657,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5366259052594088,
+      "grad_norm": 1.2292804718017578,
+      "learning_rate": 5.240293123197694e-05,
+      "loss": 0.3839,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5390003561676362,
+      "grad_norm": 1.7216770648956299,
+      "learning_rate": 5.198887418595779e-05,
+      "loss": 0.3579,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5413748070758637,
+      "grad_norm": 1.202574372291565,
+      "learning_rate": 5.157468048474257e-05,
+      "loss": 0.3627,
+      "step": 2280
+    },
+    {
+      "epoch": 0.5437492579840911,
+      "grad_norm": 1.6190992593765259,
+      "learning_rate": 5.1160378587507716e-05,
+      "loss": 0.3827,
+      "step": 2290
+    },
+    {
+      "epoch": 0.5461237088923186,
+      "grad_norm": 1.0596972703933716,
+      "learning_rate": 5.074599696086384e-05,
+      "loss": 0.3421,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5484981598005462,
+      "grad_norm": 1.2202777862548828,
+      "learning_rate": 5.033156407689978e-05,
+      "loss": 0.384,
+      "step": 2310
+    },
+    {
+      "epoch": 0.5508726107087736,
+      "grad_norm": 1.0164202451705933,
+      "learning_rate": 4.991710841122623e-05,
+      "loss": 0.3977,
+      "step": 2320
+    },
+    {
+      "epoch": 0.5532470616170011,
+      "grad_norm": 1.3084182739257812,
+      "learning_rate": 4.950265844101915e-05,
+      "loss": 0.3861,
+      "step": 2330
+    },
+    {
+      "epoch": 0.5556215125252285,
+      "grad_norm": 1.02189302444458,
+      "learning_rate": 4.9088242643063304e-05,
+      "loss": 0.366,
+      "step": 2340
+    },
+    {
+      "epoch": 0.557995963433456,
+      "grad_norm": 1.5467653274536133,
+      "learning_rate": 4.8673889491795344e-05,
+      "loss": 0.4019,
+      "step": 2350
+    },
+    {
+      "epoch": 0.5603704143416834,
+      "grad_norm": 1.1603262424468994,
+      "learning_rate": 4.8259627457347554e-05,
+      "loss": 0.39,
+      "step": 2360
+    },
+    {
+      "epoch": 0.562744865249911,
+      "grad_norm": 1.525814414024353,
+      "learning_rate": 4.784548500359162e-05,
+      "loss": 0.4089,
+      "step": 2370
+    },
+    {
+      "epoch": 0.5651193161581385,
+      "grad_norm": 1.124791145324707,
+      "learning_rate": 4.743149058618278e-05,
+      "loss": 0.3207,
+      "step": 2380
+    },
+    {
+      "epoch": 0.5674937670663659,
+      "grad_norm": 1.044631004333496,
+      "learning_rate": 4.7017672650604766e-05,
+      "loss": 0.3822,
+      "step": 2390
+    },
+    {
+      "epoch": 0.5698682179745934,
+      "grad_norm": 1.312994360923767,
+      "learning_rate": 4.6604059630215326e-05,
+      "loss": 0.3417,
+      "step": 2400
+    },
+    {
+      "epoch": 0.5722426688828208,
+      "grad_norm": 0.9241451025009155,
+      "learning_rate": 4.6190679944292395e-05,
+      "loss": 0.404,
+      "step": 2410
+    },
+    {
+      "epoch": 0.5746171197910483,
+      "grad_norm": 1.1292483806610107,
+      "learning_rate": 4.5777561996081656e-05,
+      "loss": 0.3609,
+      "step": 2420
+    },
+    {
+      "epoch": 0.5769915706992758,
+      "grad_norm": 1.0960733890533447,
+      "learning_rate": 4.5364734170844807e-05,
+      "loss": 0.3217,
+      "step": 2430
+    },
+    {
+      "epoch": 0.5793660216075033,
+      "grad_norm": 1.073885440826416,
+      "learning_rate": 4.4952224833909194e-05,
+      "loss": 0.3611,
+      "step": 2440
+    },
+    {
+      "epoch": 0.5817404725157307,
+      "grad_norm": 1.343590259552002,
+      "learning_rate": 4.4540062328718945e-05,
+      "loss": 0.3434,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5841149234239582,
+      "grad_norm": 1.1478984355926514,
+      "learning_rate": 4.412827497488744e-05,
+      "loss": 0.3619,
+      "step": 2460
+    },
+    {
+      "epoch": 0.5864893743321857,
+      "grad_norm": 1.0082939863204956,
+      "learning_rate": 4.371689106625143e-05,
+      "loss": 0.3387,
+      "step": 2470
+    },
+    {
+      "epoch": 0.5888638252404131,
+      "grad_norm": 0.9021357893943787,
+      "learning_rate": 4.330593886892707e-05,
+      "loss": 0.3145,
+      "step": 2480
+    },
+    {
+      "epoch": 0.5912382761486407,
+      "grad_norm": 3.701632261276245,
+      "learning_rate": 4.2895446619367684e-05,
+      "loss": 0.4051,
+      "step": 2490
+    },
+    {
+      "epoch": 0.5936127270568681,
+      "grad_norm": 1.09543776512146,
+      "learning_rate": 4.2485442522423636e-05,
+      "loss": 0.4129,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5936127270568681,
+      "eval_loss": 0.3469230532646179,
+      "eval_runtime": 2002.8775,
+      "eval_samples_per_second": 1.869,
+      "eval_steps_per_second": 0.467,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5959871779650956,
+      "grad_norm": 1.1468104124069214,
+      "learning_rate": 4.207595474940446e-05,
+      "loss": 0.3652,
+      "step": 2510
+    },
+    {
+      "epoch": 0.598361628873323,
+      "grad_norm": 1.0615928173065186,
+      "learning_rate": 4.166701143614315e-05,
+      "loss": 0.2876,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6007360797815505,
+      "grad_norm": 1.3340593576431274,
+      "learning_rate": 4.1258640681062934e-05,
+      "loss": 0.3285,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6031105306897779,
+      "grad_norm": 1.2769051790237427,
+      "learning_rate": 4.08508705432467e-05,
+      "loss": 0.3517,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6054849815980055,
+      "grad_norm": 1.1702165603637695,
+      "learning_rate": 4.0443729040509045e-05,
+      "loss": 0.3232,
+      "step": 2550
+    },
+    {
+      "epoch": 0.607859432506233,
+      "grad_norm": 1.4789706468582153,
+      "learning_rate": 4.00372441474711e-05,
+      "loss": 0.3429,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6102338834144604,
+      "grad_norm": 0.880572497844696,
+      "learning_rate": 3.96314437936385e-05,
+      "loss": 0.4089,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6126083343226879,
+      "grad_norm": 1.0814920663833618,
+      "learning_rate": 3.922635586148234e-05,
+      "loss": 0.3063,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6149827852309153,
+      "grad_norm": 1.1467609405517578,
+      "learning_rate": 3.8822008184523265e-05,
+      "loss": 0.3233,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6173572361391428,
+      "grad_norm": 0.8752092123031616,
+      "learning_rate": 3.841842854541919e-05,
+      "loss": 0.3372,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6197316870473702,
+      "grad_norm": 1.2454406023025513,
+      "learning_rate": 3.8015644674056266e-05,
+      "loss": 0.3275,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6221061379555978,
+      "grad_norm": 0.9372221827507019,
+      "learning_rate": 3.7613684245643544e-05,
+      "loss": 0.3352,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6244805888638253,
+      "grad_norm": 1.0082669258117676,
+      "learning_rate": 3.7212574878811495e-05,
+      "loss": 0.3131,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6268550397720527,
+      "grad_norm": 1.0585817098617554,
+      "learning_rate": 3.68123441337143e-05,
+      "loss": 0.3497,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6292294906802802,
+      "grad_norm": 1.1361665725708008,
+      "learning_rate": 3.641301951013617e-05,
+      "loss": 0.3628,
+      "step": 2650
+    },
+    {
+      "epoch": 0.6316039415885076,
+      "grad_norm": 0.9877005815505981,
+      "learning_rate": 3.601462844560187e-05,
+      "loss": 0.2979,
+      "step": 2660
+    },
+    {
+      "epoch": 0.6339783924967352,
+      "grad_norm": 1.5143479108810425,
+      "learning_rate": 3.561719831349153e-05,
+      "loss": 0.3169,
+      "step": 2670
+    },
+    {
+      "epoch": 0.6363528434049626,
+      "grad_norm": 1.29010009765625,
+      "learning_rate": 3.5220756421159696e-05,
+      "loss": 0.3234,
+      "step": 2680
+    },
+    {
+      "epoch": 0.6387272943131901,
+      "grad_norm": 1.5375481843948364,
+      "learning_rate": 3.482533000805921e-05,
+      "loss": 0.3372,
+      "step": 2690
+    },
+    {
+      "epoch": 0.6411017452214175,
+      "grad_norm": 1.360487461090088,
+      "learning_rate": 3.443094624386949e-05,
+      "loss": 0.2902,
+      "step": 2700
+    },
+    {
+      "epoch": 0.643476196129645,
+      "grad_norm": 1.3578060865402222,
+      "learning_rate": 3.4037632226629704e-05,
+      "loss": 0.293,
+      "step": 2710
+    },
+    {
+      "epoch": 0.6458506470378725,
+      "grad_norm": 1.2596126794815063,
+      "learning_rate": 3.3645414980876946e-05,
+      "loss": 0.3087,
+      "step": 2720
+    },
+    {
+      "epoch": 0.6482250979461,
+      "grad_norm": 0.9766151309013367,
+      "learning_rate": 3.32543214557893e-05,
+      "loss": 0.3082,
+      "step": 2730
+    },
+    {
+      "epoch": 0.6505995488543275,
+      "grad_norm": 1.2312662601470947,
+      "learning_rate": 3.286437852333418e-05,
+      "loss": 0.2858,
+      "step": 2740
+    },
+    {
+      "epoch": 0.6529739997625549,
+      "grad_norm": 1.3974473476409912,
+      "learning_rate": 3.247561297642203e-05,
+      "loss": 0.339,
+      "step": 2750
+    },
+    {
+      "epoch": 0.6553484506707824,
+      "grad_norm": 1.2069544792175293,
+      "learning_rate": 3.208805152706533e-05,
+      "loss": 0.2766,
+      "step": 2760
+    },
+    {
+      "epoch": 0.6577229015790098,
+      "grad_norm": 2.0875706672668457,
+      "learning_rate": 3.170172080454319e-05,
+      "loss": 0.3518,
+      "step": 2770
+    },
+    {
+      "epoch": 0.6600973524872373,
+      "grad_norm": 1.344187617301941,
+      "learning_rate": 3.131664735357174e-05,
+      "loss": 0.2908,
+      "step": 2780
+    },
+    {
+      "epoch": 0.6624718033954649,
+      "grad_norm": 1.1575170755386353,
+      "learning_rate": 3.0932857632480185e-05,
+      "loss": 0.3426,
+      "step": 2790
+    },
+    {
+      "epoch": 0.6648462543036923,
+      "grad_norm": 1.8178951740264893,
+      "learning_rate": 3.055037801139286e-05,
+      "loss": 0.2876,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6672207052119198,
+      "grad_norm": 1.0035322904586792,
+      "learning_rate": 3.0169234770417376e-05,
+      "loss": 0.2819,
+      "step": 2810
+    },
+    {
+      "epoch": 0.6695951561201472,
+      "grad_norm": 1.2262848615646362,
+      "learning_rate": 2.978945409783892e-05,
+      "loss": 0.3145,
+      "step": 2820
+    },
+    {
+      "epoch": 0.6719696070283747,
+      "grad_norm": 1.0249428749084473,
+      "learning_rate": 2.94110620883208e-05,
+      "loss": 0.2872,
+      "step": 2830
+    },
+    {
+      "epoch": 0.6743440579366021,
+      "grad_norm": 1.0349829196929932,
+      "learning_rate": 2.9034084741111555e-05,
+      "loss": 0.2798,
+      "step": 2840
+    },
+    {
+      "epoch": 0.6767185088448296,
+      "grad_norm": 1.034436583518982,
+      "learning_rate": 2.8658547958258543e-05,
+      "loss": 0.2699,
+      "step": 2850
+    },
+    {
+      "epoch": 0.6790929597530571,
+      "grad_norm": 1.9253498315811157,
+      "learning_rate": 2.8284477542828153e-05,
+      "loss": 0.3362,
+      "step": 2860
+    },
+    {
+      "epoch": 0.6814674106612846,
+      "grad_norm": 1.1226086616516113,
+      "learning_rate": 2.791189919713294e-05,
+      "loss": 0.2896,
+      "step": 2870
+    },
+    {
+      "epoch": 0.6838418615695121,
+      "grad_norm": 0.920665442943573,
+      "learning_rate": 2.7540838520965672e-05,
+      "loss": 0.3138,
+      "step": 2880
+    },
+    {
+      "epoch": 0.6862163124777395,
+      "grad_norm": 1.1101292371749878,
+      "learning_rate": 2.7171321009840178e-05,
+      "loss": 0.268,
+      "step": 2890
+    },
+    {
+      "epoch": 0.688590763385967,
+      "grad_norm": 1.0533770322799683,
+      "learning_rate": 2.6803372053239834e-05,
+      "loss": 0.2844,
+      "step": 2900
+    },
+    {
+      "epoch": 0.6909652142941944,
+      "grad_norm": 1.2257792949676514,
+      "learning_rate": 2.6437016932872816e-05,
+      "loss": 0.2931,
+      "step": 2910
+    },
+    {
+      "epoch": 0.693339665202422,
+      "grad_norm": 1.1098326444625854,
+      "learning_rate": 2.6072280820935103e-05,
+      "loss": 0.2818,
+      "step": 2920
+    },
+    {
+      "epoch": 0.6957141161106494,
+      "grad_norm": 1.048757553100586,
+      "learning_rate": 2.5709188778380942e-05,
+      "loss": 0.2741,
+      "step": 2930
+    },
+    {
+      "epoch": 0.6980885670188769,
+      "grad_norm": 1.3457996845245361,
+      "learning_rate": 2.5347765753200808e-05,
+      "loss": 0.3142,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7004630179271043,
+      "grad_norm": 1.0679852962493896,
+      "learning_rate": 2.4988036578707303e-05,
+      "loss": 0.2499,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7028374688353318,
+      "grad_norm": 1.3276768922805786,
+      "learning_rate": 2.463002597182882e-05,
+      "loss": 0.2565,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7052119197435593,
+      "grad_norm": 1.2980198860168457,
+      "learning_rate": 2.427375853141134e-05,
+      "loss": 0.2848,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7075863706517868,
+      "grad_norm": 1.0313228368759155,
+      "learning_rate": 2.3919258736528123e-05,
+      "loss": 0.2536,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7099608215600143,
+      "grad_norm": 0.9275791049003601,
+      "learning_rate": 2.3566550944797804e-05,
+      "loss": 0.2693,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7123352724682417,
+      "grad_norm": 1.083311915397644,
+      "learning_rate": 2.321565939071089e-05,
+      "loss": 0.345,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7123352724682417,
+      "eval_loss": 0.2755714952945709,
+      "eval_runtime": 2001.6463,
+      "eval_samples_per_second": 1.87,
+      "eval_steps_per_second": 0.468,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7147097233764692,
+      "grad_norm": 1.2642430067062378,
+      "learning_rate": 2.2866608183964376e-05,
+      "loss": 0.3807,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7170841742846966,
+      "grad_norm": 1.761056900024414,
+      "learning_rate": 2.2519421307805445e-05,
+      "loss": 0.2892,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7194586251929241,
+      "grad_norm": 1.1523739099502563,
+      "learning_rate": 2.217412261738338e-05,
+      "loss": 0.2531,
+      "step": 3030
+    },
+    {
+      "epoch": 0.7218330761011517,
+      "grad_norm": 0.9026095271110535,
+      "learning_rate": 2.183073583811055e-05,
+      "loss": 0.2458,
+      "step": 3040
+    },
+    {
+      "epoch": 0.7242075270093791,
+      "grad_norm": 1.0815373659133911,
+      "learning_rate": 2.1489284564032308e-05,
+      "loss": 0.2413,
+      "step": 3050
+    },
+    {
+      "epoch": 0.7265819779176066,
+      "grad_norm": 0.9200854897499084,
+      "learning_rate": 2.1149792256205725e-05,
+      "loss": 0.2575,
+      "step": 3060
+    },
+    {
+      "epoch": 0.728956428825834,
+      "grad_norm": 0.9628139734268188,
+      "learning_rate": 2.0812282241087662e-05,
+      "loss": 0.2503,
+      "step": 3070
+    },
+    {
+      "epoch": 0.7313308797340615,
+      "grad_norm": 1.0112043619155884,
+      "learning_rate": 2.0476777708931978e-05,
+      "loss": 0.277,
+      "step": 3080
+    },
+    {
+      "epoch": 0.7337053306422889,
+      "grad_norm": 1.2384965419769287,
+      "learning_rate": 2.01433017121962e-05,
+      "loss": 0.2969,
+      "step": 3090
+    },
+    {
+      "epoch": 0.7360797815505165,
+      "grad_norm": 1.1001275777816772,
+      "learning_rate": 1.981187716395751e-05,
+      "loss": 0.2344,
+      "step": 3100
+    },
+    {
+      "epoch": 0.7384542324587439,
+      "grad_norm": 0.9843474626541138,
+      "learning_rate": 1.9482526836338387e-05,
+      "loss": 0.2428,
+      "step": 3110
+    },
+    {
+      "epoch": 0.7408286833669714,
+      "grad_norm": 1.2588458061218262,
+      "learning_rate": 1.915527335894209e-05,
+      "loss": 0.2683,
+      "step": 3120
+    },
+    {
+      "epoch": 0.7432031342751989,
+      "grad_norm": 0.9996175765991211,
+      "learning_rate": 1.8830139217297498e-05,
+      "loss": 0.2508,
+      "step": 3130
+    },
+    {
+      "epoch": 0.7455775851834263,
+      "grad_norm": 0.9209540486335754,
+      "learning_rate": 1.8507146751314464e-05,
+      "loss": 0.2353,
+      "step": 3140
+    },
+    {
+      "epoch": 0.7479520360916538,
+      "grad_norm": 0.901054859161377,
+      "learning_rate": 1.8186318153748587e-05,
+      "loss": 0.2623,
+      "step": 3150
+    },
+    {
+      "epoch": 0.7503264869998812,
+      "grad_norm": 0.9320164918899536,
+      "learning_rate": 1.786767546867647e-05,
+      "loss": 0.2305,
+      "step": 3160
+    },
+    {
+      "epoch": 0.7527009379081088,
+      "grad_norm": 0.8801546692848206,
+      "learning_rate": 1.755124058998108e-05,
+      "loss": 0.2508,
+      "step": 3170
+    },
+    {
+      "epoch": 0.7550753888163362,
+      "grad_norm": 1.0162204504013062,
+      "learning_rate": 1.723703525984735e-05,
+      "loss": 0.242,
+      "step": 3180
+    },
+    {
+      "epoch": 0.7574498397245637,
+      "grad_norm": 1.0432860851287842,
+      "learning_rate": 1.692508106726836e-05,
+      "loss": 0.2466,
+      "step": 3190
+    },
+    {
+      "epoch": 0.7598242906327912,
+      "grad_norm": 0.8475198745727539,
+      "learning_rate": 1.6615399446561886e-05,
+      "loss": 0.2407,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7621987415410186,
+      "grad_norm": 1.0046483278274536,
+      "learning_rate": 1.630801167589774e-05,
+      "loss": 0.2504,
+      "step": 3210
+    },
+    {
+      "epoch": 0.7645731924492462,
+      "grad_norm": 1.0153136253356934,
+      "learning_rate": 1.6002938875835665e-05,
+      "loss": 0.2792,
+      "step": 3220
+    },
+    {
+      "epoch": 0.7669476433574736,
+      "grad_norm": 1.3016788959503174,
+      "learning_rate": 1.5700202007874165e-05,
+      "loss": 0.2673,
+      "step": 3230
+    },
+    {
+      "epoch": 0.7693220942657011,
+      "grad_norm": 0.8398091197013855,
+      "learning_rate": 1.5399821873010335e-05,
+      "loss": 0.2371,
+      "step": 3240
+    },
+    {
+      "epoch": 0.7716965451739285,
+      "grad_norm": 0.9159530997276306,
+      "learning_rate": 1.5101819110310433e-05,
+      "loss": 0.2323,
+      "step": 3250
+    },
+    {
+      "epoch": 0.774070996082156,
+      "grad_norm": 1.0264992713928223,
+      "learning_rate": 1.4806214195492008e-05,
+      "loss": 0.2566,
+      "step": 3260
+    },
+    {
+      "epoch": 0.7764454469903834,
+      "grad_norm": 1.2823314666748047,
+      "learning_rate": 1.4513027439516847e-05,
+      "loss": 0.2677,
+      "step": 3270
+    },
+    {
+      "epoch": 0.778819897898611,
+      "grad_norm": 1.0543042421340942,
+      "learning_rate": 1.4222278987195447e-05,
+      "loss": 0.253,
+      "step": 3280
+    },
+    {
+      "epoch": 0.7811943488068385,
+      "grad_norm": 1.279941201210022,
+      "learning_rate": 1.3933988815802962e-05,
+      "loss": 0.2366,
+      "step": 3290
+    },
+    {
+      "epoch": 0.7835687997150659,
+      "grad_norm": 1.0144097805023193,
+      "learning_rate": 1.3648176733706419e-05,
+      "loss": 0.2658,
+      "step": 3300
+    },
+    {
+      "epoch": 0.7859432506232934,
+      "grad_norm": 1.0627365112304688,
+      "learning_rate": 1.3364862379003812e-05,
+      "loss": 0.2921,
+      "step": 3310
+    },
+    {
+      "epoch": 0.7883177015315208,
+      "grad_norm": 1.0910556316375732,
+      "learning_rate": 1.3084065218174679e-05,
+      "loss": 0.2456,
+      "step": 3320
+    },
+    {
+      "epoch": 0.7906921524397483,
+      "grad_norm": 1.017910122871399,
+      "learning_rate": 1.2805804544742672e-05,
+      "loss": 0.2153,
+      "step": 3330
+    },
+    {
+      "epoch": 0.7930666033479757,
+      "grad_norm": 1.1485787630081177,
+      "learning_rate": 1.2530099477949792e-05,
+      "loss": 0.254,
+      "step": 3340
+    },
+    {
+      "epoch": 0.7954410542562033,
+      "grad_norm": 1.189522385597229,
+      "learning_rate": 1.2256968961442755e-05,
+      "loss": 0.2346,
+      "step": 3350
+    },
+    {
+      "epoch": 0.7978155051644307,
+      "grad_norm": 1.3077176809310913,
+      "learning_rate": 1.198643176197144e-05,
+      "loss": 0.2527,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8001899560726582,
+      "grad_norm": 1.1327699422836304,
+      "learning_rate": 1.1718506468099254e-05,
+      "loss": 0.2582,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8025644069808857,
+      "grad_norm": 1.7842756509780884,
+      "learning_rate": 1.1453211488926153e-05,
+      "loss": 0.242,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8049388578891131,
+      "grad_norm": 1.4039660692214966,
+      "learning_rate": 1.1190565052823548e-05,
+      "loss": 0.2509,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8073133087973406,
+      "grad_norm": 0.8914623260498047,
+      "learning_rate": 1.0930585206181942e-05,
+      "loss": 0.2187,
+      "step": 3400
+    },
+    {
+      "epoch": 0.809687759705568,
+      "grad_norm": 0.8296724557876587,
+      "learning_rate": 1.0673289812170972e-05,
+      "loss": 0.2268,
+      "step": 3410
+    },
+    {
+      "epoch": 0.8120622106137956,
+      "grad_norm": 1.0560425519943237,
+      "learning_rate": 1.041869654951198e-05,
+      "loss": 0.2317,
+      "step": 3420
+    },
+    {
+      "epoch": 0.814436661522023,
+      "grad_norm": 0.8370431661605835,
+      "learning_rate": 1.016682291126333e-05,
+      "loss": 0.2534,
+      "step": 3430
+    },
+    {
+      "epoch": 0.8168111124302505,
+      "grad_norm": 0.798896074295044,
+      "learning_rate": 9.917686203618475e-06,
+      "loss": 0.2129,
+      "step": 3440
+    },
+    {
+      "epoch": 0.819185563338478,
+      "grad_norm": 1.008288860321045,
+      "learning_rate": 9.671303544716875e-06,
+      "loss": 0.2118,
+      "step": 3450
+    },
+    {
+      "epoch": 0.8215600142467054,
+      "grad_norm": 1.2545337677001953,
+      "learning_rate": 9.427691863467758e-06,
+      "loss": 0.2315,
+      "step": 3460
+    },
+    {
+      "epoch": 0.823934465154933,
+      "grad_norm": 0.8400135040283203,
+      "learning_rate": 9.186867898386952e-06,
+      "loss": 0.2312,
+      "step": 3470
+    },
+    {
+      "epoch": 0.8263089160631604,
+      "grad_norm": 0.6971375942230225,
+      "learning_rate": 8.948848196446852e-06,
+      "loss": 0.2311,
+      "step": 3480
+    },
+    {
+      "epoch": 0.8286833669713879,
+      "grad_norm": 0.9910257458686829,
+      "learning_rate": 8.713649111939332e-06,
+      "loss": 0.2519,
+      "step": 3490
+    },
+    {
+      "epoch": 0.8310578178796153,
+      "grad_norm": 0.8067383766174316,
+      "learning_rate": 8.481286805352234e-06,
+      "loss": 0.1919,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8310578178796153,
+      "eval_loss": 0.2284688502550125,
+      "eval_runtime": 2005.8031,
+      "eval_samples_per_second": 1.867,
+      "eval_steps_per_second": 0.467,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8334322687878428,
+      "grad_norm": 1.251442313194275,
+      "learning_rate": 8.251777242258834e-06,
+      "loss": 0.2235,
+      "step": 3510
+    },
+    {
+      "epoch": 0.8358067196960702,
+      "grad_norm": 0.8034676313400269,
+      "learning_rate": 8.025136192220894e-06,
+      "loss": 0.1998,
+      "step": 3520
+    },
+    {
+      "epoch": 0.8381811706042978,
+      "grad_norm": 0.8723871111869812,
+      "learning_rate": 7.801379227705203e-06,
+      "loss": 0.2251,
+      "step": 3530
+    },
+    {
+      "epoch": 0.8405556215125253,
+      "grad_norm": 0.9363040328025818,
+      "learning_rate": 7.58052172301349e-06,
+      "loss": 0.1954,
+      "step": 3540
+    },
+    {
+      "epoch": 0.8429300724207527,
+      "grad_norm": 0.8821825385093689,
+      "learning_rate": 7.362578853226121e-06,
+      "loss": 0.2014,
+      "step": 3550
+    },
+    {
+      "epoch": 0.8453045233289802,
+      "grad_norm": 0.8672744035720825,
+      "learning_rate": 7.1475655931594e-06,
+      "loss": 0.2346,
+      "step": 3560
+    },
+    {
+      "epoch": 0.8476789742372076,
+      "grad_norm": 0.8038856387138367,
+      "learning_rate": 6.9354967163367035e-06,
+      "loss": 0.1944,
+      "step": 3570
+    },
+    {
+      "epoch": 0.8500534251454351,
+      "grad_norm": 0.9127787351608276,
+      "learning_rate": 6.726386793973305e-06,
+      "loss": 0.2036,
+      "step": 3580
+    },
+    {
+      "epoch": 0.8524278760536625,
+      "grad_norm": 1.6385974884033203,
+      "learning_rate": 6.520250193975242e-06,
+      "loss": 0.2438,
+      "step": 3590
+    },
+    {
+      "epoch": 0.8548023269618901,
+      "grad_norm": 0.8287534713745117,
+      "learning_rate": 6.317101079952148e-06,
+      "loss": 0.2258,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8571767778701176,
+      "grad_norm": 0.7688109874725342,
+      "learning_rate": 6.116953410243925e-06,
+      "loss": 0.1954,
+      "step": 3610
+    },
+    {
+      "epoch": 0.859551228778345,
+      "grad_norm": 1.0905680656433105,
+      "learning_rate": 5.919820936961856e-06,
+      "loss": 0.2192,
+      "step": 3620
+    },
+    {
+      "epoch": 0.8619256796865725,
+      "grad_norm": 0.8777235746383667,
+      "learning_rate": 5.725717205043552e-06,
+      "loss": 0.1896,
+      "step": 3630
+    },
+    {
+      "epoch": 0.8643001305947999,
+      "grad_norm": 1.0974262952804565,
+      "learning_rate": 5.5346555513223485e-06,
+      "loss": 0.2318,
+      "step": 3640
+    },
+    {
+      "epoch": 0.8666745815030275,
+      "grad_norm": 0.9711960554122925,
+      "learning_rate": 5.34664910361094e-06,
+      "loss": 0.2081,
+      "step": 3650
+    },
+    {
+      "epoch": 0.8690490324112549,
+      "grad_norm": 1.0660927295684814,
+      "learning_rate": 5.161710779799328e-06,
+      "loss": 0.2156,
+      "step": 3660
+    },
+    {
+      "epoch": 0.8714234833194824,
+      "grad_norm": 1.1410367488861084,
+      "learning_rate": 4.979853286967273e-06,
+      "loss": 0.1889,
+      "step": 3670
+    },
+    {
+      "epoch": 0.8737979342277098,
+      "grad_norm": 1.3238369226455688,
+      "learning_rate": 4.801089120511165e-06,
+      "loss": 0.2193,
+      "step": 3680
+    },
+    {
+      "epoch": 0.8761723851359373,
+      "grad_norm": 0.7377246618270874,
+      "learning_rate": 4.625430563285515e-06,
+      "loss": 0.2315,
+      "step": 3690
+    },
+    {
+      "epoch": 0.8785468360441648,
+      "grad_norm": 1.1461482048034668,
+      "learning_rate": 4.452889684758938e-06,
+      "loss": 0.2573,
+      "step": 3700
+    },
+    {
+      "epoch": 0.8809212869523922,
+      "grad_norm": 0.8280972242355347,
+      "learning_rate": 4.283478340184893e-06,
+      "loss": 0.2112,
+      "step": 3710
+    },
+    {
+      "epoch": 0.8832957378606198,
+      "grad_norm": 1.114720344543457,
+      "learning_rate": 4.11720816978714e-06,
+      "loss": 0.2091,
+      "step": 3720
+    },
+    {
+      "epoch": 0.8856701887688472,
+      "grad_norm": 0.9124228358268738,
+      "learning_rate": 3.95409059795987e-06,
+      "loss": 0.2038,
+      "step": 3730
+    },
+    {
+      "epoch": 0.8880446396770747,
+      "grad_norm": 1.368277668952942,
+      "learning_rate": 3.7941368324828253e-06,
+      "loss": 0.2478,
+      "step": 3740
+    },
+    {
+      "epoch": 0.8904190905853021,
+      "grad_norm": 0.9257198572158813,
+      "learning_rate": 3.6373578637511283e-06,
+      "loss": 0.2081,
+      "step": 3750
+    },
+    {
+      "epoch": 0.8927935414935296,
+      "grad_norm": 0.911368191242218,
+      "learning_rate": 3.4837644640202003e-06,
+      "loss": 0.224,
+      "step": 3760
+    },
+    {
+      "epoch": 0.895167992401757,
+      "grad_norm": 0.8841039538383484,
+      "learning_rate": 3.333367186665576e-06,
+      "loss": 0.2222,
+      "step": 3770
+    },
+    {
+      "epoch": 0.8975424433099846,
+      "grad_norm": 0.9717174172401428,
+      "learning_rate": 3.186176365457766e-06,
+      "loss": 0.2212,
+      "step": 3780
+    },
+    {
+      "epoch": 0.8999168942182121,
+      "grad_norm": 1.0966217517852783,
+      "learning_rate": 3.042202113852255e-06,
+      "loss": 0.1949,
+      "step": 3790
+    },
+    {
+      "epoch": 0.9022913451264395,
+      "grad_norm": 0.7802509665489197,
+      "learning_rate": 2.9014543242945837e-06,
+      "loss": 0.2108,
+      "step": 3800
+    },
+    {
+      "epoch": 0.904665796034667,
+      "grad_norm": 1.031802773475647,
+      "learning_rate": 2.7639426675406753e-06,
+      "loss": 0.2566,
+      "step": 3810
+    },
+    {
+      "epoch": 0.9070402469428944,
+      "grad_norm": 0.9489237070083618,
+      "learning_rate": 2.629676591992314e-06,
+      "loss": 0.2098,
+      "step": 3820
+    },
+    {
+      "epoch": 0.909414697851122,
+      "grad_norm": 0.6206024885177612,
+      "learning_rate": 2.498665323047966e-06,
+      "loss": 0.2456,
+      "step": 3830
+    },
+    {
+      "epoch": 0.9117891487593494,
+      "grad_norm": 1.0588915348052979,
+      "learning_rate": 2.370917862468941e-06,
+      "loss": 0.203,
+      "step": 3840
+    },
+    {
+      "epoch": 0.9141635996675769,
+      "grad_norm": 0.879034161567688,
+      "learning_rate": 2.2464429877607995e-06,
+      "loss": 0.2151,
+      "step": 3850
+    },
+    {
+      "epoch": 0.9165380505758044,
+      "grad_norm": 1.5556215047836304,
+      "learning_rate": 2.1252492515703382e-06,
+      "loss": 0.2254,
+      "step": 3860
+    },
+    {
+      "epoch": 0.9189125014840318,
+      "grad_norm": 0.8274180889129639,
+      "learning_rate": 2.0073449810978974e-06,
+      "loss": 0.1823,
+      "step": 3870
+    },
+    {
+      "epoch": 0.9212869523922593,
+      "grad_norm": 1.0189625024795532,
+      "learning_rate": 1.8927382775251856e-06,
+      "loss": 0.2369,
+      "step": 3880
+    },
+    {
+      "epoch": 0.9236614033004867,
+      "grad_norm": 0.7381725907325745,
+      "learning_rate": 1.781437015458698e-06,
+      "loss": 0.1982,
+      "step": 3890
+    },
+    {
+      "epoch": 0.9260358542087143,
+      "grad_norm": 0.8868210315704346,
+      "learning_rate": 1.673448842388603e-06,
+      "loss": 0.205,
+      "step": 3900
+    },
+    {
+      "epoch": 0.9284103051169417,
+      "grad_norm": 0.7141517400741577,
+      "learning_rate": 1.5687811781633033e-06,
+      "loss": 0.2055,
+      "step": 3910
+    },
+    {
+      "epoch": 0.9307847560251692,
+      "grad_norm": 0.9352526068687439,
+      "learning_rate": 1.4674412144796368e-06,
+      "loss": 0.1943,
+      "step": 3920
+    },
+    {
+      "epoch": 0.9331592069333966,
+      "grad_norm": 0.9011178612709045,
+      "learning_rate": 1.3694359143887225e-06,
+      "loss": 0.1821,
+      "step": 3930
+    },
+    {
+      "epoch": 0.9355336578416241,
+      "grad_norm": 0.927413284778595,
+      "learning_rate": 1.2747720118175099e-06,
+      "loss": 0.1794,
+      "step": 3940
+    },
+    {
+      "epoch": 0.9379081087498516,
+      "grad_norm": 1.1069186925888062,
+      "learning_rate": 1.1834560111061211e-06,
+      "loss": 0.1955,
+      "step": 3950
+    },
+    {
+      "epoch": 0.940282559658079,
+      "grad_norm": 0.8640979528427124,
+      "learning_rate": 1.095494186560947e-06,
+      "loss": 0.2071,
+      "step": 3960
+    },
+    {
+      "epoch": 0.9426570105663066,
+      "grad_norm": 0.9992754459381104,
+      "learning_rate": 1.0108925820234926e-06,
+      "loss": 0.2151,
+      "step": 3970
+    },
+    {
+      "epoch": 0.945031461474534,
+      "grad_norm": 1.3405293226242065,
+      "learning_rate": 9.29657010455165e-07,
+      "loss": 0.1961,
+      "step": 3980
+    },
+    {
+      "epoch": 0.9474059123827615,
+      "grad_norm": 0.887992262840271,
+      "learning_rate": 8.517930535378083e-07,
+      "loss": 0.2276,
+      "step": 3990
+    },
+    {
+      "epoch": 0.9497803632909889,
+      "grad_norm": 1.3939125537872314,
+      "learning_rate": 7.773060612902395e-07,
+      "loss": 0.2301,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9497803632909889,
+      "eval_loss": 0.20879201591014862,
+      "eval_runtime": 1997.7765,
+      "eval_samples_per_second": 1.874,
+      "eval_steps_per_second": 0.469,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9521548141992164,
+      "grad_norm": 0.8135402202606201,
+      "learning_rate": 7.062011517006139e-07,
+      "loss": 0.1919,
+      "step": 4010
+    },
+    {
+      "epoch": 0.954529265107444,
+      "grad_norm": 1.2012323141098022,
+      "learning_rate": 6.384832103747907e-07,
+      "loss": 0.2081,
+      "step": 4020
+    },
+    {
+      "epoch": 0.9569037160156714,
+      "grad_norm": 0.8670451641082764,
+      "learning_rate": 5.741568902006277e-07,
+      "loss": 0.1962,
+      "step": 4030
+    },
+    {
+      "epoch": 0.9592781669238989,
+      "grad_norm": 0.910858154296875,
+      "learning_rate": 5.132266110282835e-07,
+      "loss": 0.1665,
+      "step": 4040
+    },
+    {
+      "epoch": 0.9616526178321263,
+      "grad_norm": 1.337033987045288,
+      "learning_rate": 4.5569655936654186e-07,
+      "loss": 0.2127,
+      "step": 4050
+    },
+    {
+      "epoch": 0.9640270687403538,
+      "grad_norm": 0.8553494811058044,
+      "learning_rate": 4.0157068809515417e-07,
+      "loss": 0.2103,
+      "step": 4060
+    },
+    {
+      "epoch": 0.9664015196485812,
+      "grad_norm": 0.9513109922409058,
+      "learning_rate": 3.50852716193234e-07,
+      "loss": 0.2309,
+      "step": 4070
+    },
+    {
+      "epoch": 0.9687759705568088,
+      "grad_norm": 0.9447882771492004,
+      "learning_rate": 3.0354612848372265e-07,
+      "loss": 0.2033,
+      "step": 4080
+    },
+    {
+      "epoch": 0.9711504214650362,
+      "grad_norm": 0.9029374122619629,
+      "learning_rate": 2.59654175393953e-07,
+      "loss": 0.1892,
+      "step": 4090
+    },
+    {
+      "epoch": 0.9735248723732637,
+      "grad_norm": 1.0304471254348755,
+      "learning_rate": 2.1917987273232245e-07,
+      "loss": 0.2659,
+      "step": 4100
+    },
+    {
+      "epoch": 0.9758993232814912,
+      "grad_norm": 0.9072940349578857,
+      "learning_rate": 1.8212600148105884e-07,
+      "loss": 0.1669,
+      "step": 4110
+    },
+    {
+      "epoch": 0.9782737741897186,
+      "grad_norm": 0.9835550785064697,
+      "learning_rate": 1.4849510760513995e-07,
+      "loss": 0.2005,
+      "step": 4120
+    },
+    {
+      "epoch": 0.9806482250979461,
+      "grad_norm": 0.9774510264396667,
+      "learning_rate": 1.182895018773944e-07,
+      "loss": 0.1955,
+      "step": 4130
+    },
+    {
+      "epoch": 0.9830226760061735,
+      "grad_norm": 0.9649205207824707,
+      "learning_rate": 9.151125971967878e-08,
+      "loss": 0.1946,
+      "step": 4140
+    },
+    {
+      "epoch": 0.9853971269144011,
+      "grad_norm": 0.8067905306816101,
+      "learning_rate": 6.816222106030834e-08,
+      "loss": 0.2244,
+      "step": 4150
+    },
+    {
+      "epoch": 0.9877715778226285,
+      "grad_norm": 0.8424655795097351,
+      "learning_rate": 4.824399020763593e-08,
+      "loss": 0.2032,
+      "step": 4160
+    },
+    {
+      "epoch": 0.990146028730856,
+      "grad_norm": 1.2165002822875977,
+      "learning_rate": 3.175793573980124e-08,
+      "loss": 0.2069,
+      "step": 4170
+    },
+    {
+      "epoch": 0.9925204796390834,
+      "grad_norm": 0.9676713347434998,
+      "learning_rate": 1.8705190410717166e-08,
+      "loss": 0.2685,
+      "step": 4180
+    },
+    {
+      "epoch": 0.9948949305473109,
+      "grad_norm": 0.9836387634277344,
+      "learning_rate": 9.086651072215402e-09,
+      "loss": 0.1907,
+      "step": 4190
+    },
+    {
+      "epoch": 0.9972693814555385,
+      "grad_norm": 1.0036119222640991,
+      "learning_rate": 2.902978612456808e-09,
+      "loss": 0.211,
+      "step": 4200
+    },
+    {
+      "epoch": 0.9996438323637659,
+      "grad_norm": 1.1510422229766846,
+      "learning_rate": 1.5459791047889305e-10,
+      "loss": 0.2539,
+      "step": 4210
+    },
+    {
+      "epoch": 1.0,
+      "step": 4212,
+      "total_flos": 449297978753024.0,
+      "train_loss": 0.44325452399106674,
+      "train_runtime": 138200.0012,
+      "train_samples_per_second": 0.244,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4212,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 449297978753024.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen2-gob-plan-115/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366195804c523e80245a1400ecce5ecd8a158fab29557b0bd8da51a1676fd5c9
+size 8337