Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen_debug_unlearn
+  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. -->
+
+# qwen_debug_unlearn
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the tofu_train, the tofu_train_lineage, the chatdoctor_train, the chatdoctor_train_lineage, the bever_train, the bever_train_lineage, the tqa_train, the tqa_train_lineage, the wmdp_train, the wmdp_train_lineage, the tofu_train_lineage_unlearn, the chatdoctor_train_lineage_unlearn, the bever_train_lineage_unlearn, the wmdp_train_lineage_unlearn, the truthfulqa_train_lineage_unlearn, the tofu_train_lineage_unlearn_other_tag, the chatdoctor_train_lineage_unlearn_other_tag, the bever_train_lineage_unlearn_other_tag, the wmdp_train_lineage_unlearn_other_tag and the truthfulqa_train_lineage_unlearn_other_tag datasets.
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.8.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,35 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<BEVER>": 151674,
+  "<CHATDOCTOR>": 151672,
+  "<DEBUG>": 151669,
+  "<TAG>": 151670,
+  "<TOFU>": 151671,
+  "<TQA>": 151673,
+  "<WMDP>": 151675,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 247294279680000.0,
+    "train_loss": 0.26427117863254007,
+    "train_runtime": 27747.0354,
+    "train_samples_per_second": 9.727,
+    "train_steps_per_second": 0.152
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b92ae0df91db60a017602b35de4938b77058a1ea1fa1052a586a2a3d94010cb
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a6ffbc6c2402c07ed0f60b562a20b1e1dcff1fa060661a8ce617c32dc10ac84
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebaebb11050eff667b6e0291839860676796d35954230fd37d1b17dd71eb9cac
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4f3ebc7a69602fcf45e97a83bde0bfc870ca55a027b9e3ccc7b5e1e1da3d03
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 16381470720
+  },
+  "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-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_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "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_norm.weight": "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.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-00001-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_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73ba43486eec9295930098b162825599b68ccfb3a3f259b51a968943aa88f05
+size 11423941

tokenizer_config.json

@@ -0,0 +1,296 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<DEBUG>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<TAG>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<TOFU>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<CHATDOCTOR>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<TQA>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<BEVER>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<WMDP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 247294279680000.0,
+    "train_loss": 0.26427117863254007,
+    "train_runtime": 27747.0354,
+    "train_samples_per_second": 9.727,
+    "train_steps_per_second": 0.152
+}

trainer_log.jsonl

@@ -0,0 +1,422 @@
+{"current_steps": 10, "total_steps": 4218, "loss": 4.9235, "lr": 2.132701421800948e-07, "epoch": 0.007112375533428165, "percentage": 0.24, "elapsed_time": "0:01:07", "remaining_time": "7:53:03"}
+{"current_steps": 20, "total_steps": 4218, "loss": 4.7616, "lr": 4.502369668246446e-07, "epoch": 0.01422475106685633, "percentage": 0.47, "elapsed_time": "0:02:16", "remaining_time": "7:58:47"}
+{"current_steps": 30, "total_steps": 4218, "loss": 4.0518, "lr": 6.872037914691944e-07, "epoch": 0.021337126600284494, "percentage": 0.71, "elapsed_time": "0:03:21", "remaining_time": "7:48:32"}
+{"current_steps": 40, "total_steps": 4218, "loss": 3.1168, "lr": 9.241706161137441e-07, "epoch": 0.02844950213371266, "percentage": 0.95, "elapsed_time": "0:04:18", "remaining_time": "7:29:12"}
+{"current_steps": 50, "total_steps": 4218, "loss": 2.408, "lr": 1.161137440758294e-06, "epoch": 0.03556187766714083, "percentage": 1.19, "elapsed_time": "0:05:22", "remaining_time": "7:27:26"}
+{"current_steps": 60, "total_steps": 4218, "loss": 2.0996, "lr": 1.3981042654028437e-06, "epoch": 0.04267425320056899, "percentage": 1.42, "elapsed_time": "0:06:27", "remaining_time": "7:27:40"}
+{"current_steps": 70, "total_steps": 4218, "loss": 1.961, "lr": 1.6350710900473934e-06, "epoch": 0.049786628733997154, "percentage": 1.66, "elapsed_time": "0:07:36", "remaining_time": "7:30:24"}
+{"current_steps": 80, "total_steps": 4218, "loss": 1.8454, "lr": 1.8720379146919433e-06, "epoch": 0.05689900426742532, "percentage": 1.9, "elapsed_time": "0:08:38", "remaining_time": "7:26:34"}
+{"current_steps": 90, "total_steps": 4218, "loss": 1.8, "lr": 2.109004739336493e-06, "epoch": 0.06401137980085349, "percentage": 2.13, "elapsed_time": "0:09:39", "remaining_time": "7:22:41"}
+{"current_steps": 100, "total_steps": 4218, "loss": 1.7189, "lr": 2.345971563981043e-06, "epoch": 0.07112375533428165, "percentage": 2.37, "elapsed_time": "0:10:49", "remaining_time": "7:25:28"}
+{"current_steps": 110, "total_steps": 4218, "loss": 1.6861, "lr": 2.5829383886255925e-06, "epoch": 0.07823613086770982, "percentage": 2.61, "elapsed_time": "0:12:01", "remaining_time": "7:29:08"}
+{"current_steps": 120, "total_steps": 4218, "loss": 1.6933, "lr": 2.8199052132701426e-06, "epoch": 0.08534850640113797, "percentage": 2.84, "elapsed_time": "0:13:13", "remaining_time": "7:31:48"}
+{"current_steps": 130, "total_steps": 4218, "loss": 1.6477, "lr": 3.0568720379146923e-06, "epoch": 0.09246088193456614, "percentage": 3.08, "elapsed_time": "0:14:18", "remaining_time": "7:30:09"}
+{"current_steps": 140, "total_steps": 4218, "loss": 1.5837, "lr": 3.293838862559242e-06, "epoch": 0.09957325746799431, "percentage": 3.32, "elapsed_time": "0:15:21", "remaining_time": "7:27:35"}
+{"current_steps": 150, "total_steps": 4218, "loss": 1.553, "lr": 3.5308056872037916e-06, "epoch": 0.10668563300142248, "percentage": 3.56, "elapsed_time": "0:16:13", "remaining_time": "7:20:00"}
+{"current_steps": 160, "total_steps": 4218, "loss": 1.601, "lr": 3.7677725118483417e-06, "epoch": 0.11379800853485064, "percentage": 3.79, "elapsed_time": "0:17:22", "remaining_time": "7:20:32"}
+{"current_steps": 170, "total_steps": 4218, "loss": 1.4953, "lr": 4.004739336492891e-06, "epoch": 0.12091038406827881, "percentage": 4.03, "elapsed_time": "0:18:20", "remaining_time": "7:16:41"}
+{"current_steps": 180, "total_steps": 4218, "loss": 1.4986, "lr": 4.2417061611374415e-06, "epoch": 0.12802275960170698, "percentage": 4.27, "elapsed_time": "0:19:33", "remaining_time": "7:18:37"}
+{"current_steps": 190, "total_steps": 4218, "loss": 1.4177, "lr": 4.478672985781991e-06, "epoch": 0.13513513513513514, "percentage": 4.5, "elapsed_time": "0:20:39", "remaining_time": "7:17:55"}
+{"current_steps": 200, "total_steps": 4218, "loss": 1.4234, "lr": 4.715639810426541e-06, "epoch": 0.1422475106685633, "percentage": 4.74, "elapsed_time": "0:21:45", "remaining_time": "7:17:11"}
+{"current_steps": 210, "total_steps": 4218, "loss": 1.4034, "lr": 4.952606635071091e-06, "epoch": 0.14935988620199148, "percentage": 4.98, "elapsed_time": "0:22:55", "remaining_time": "7:17:30"}
+{"current_steps": 220, "total_steps": 4218, "loss": 1.4172, "lr": 5.18957345971564e-06, "epoch": 0.15647226173541964, "percentage": 5.22, "elapsed_time": "0:24:02", "remaining_time": "7:17:01"}
+{"current_steps": 230, "total_steps": 4218, "loss": 1.3695, "lr": 5.42654028436019e-06, "epoch": 0.16358463726884778, "percentage": 5.45, "elapsed_time": "0:25:09", "remaining_time": "7:16:21"}
+{"current_steps": 240, "total_steps": 4218, "loss": 1.3815, "lr": 5.66350710900474e-06, "epoch": 0.17069701280227595, "percentage": 5.69, "elapsed_time": "0:26:25", "remaining_time": "7:18:03"}
+{"current_steps": 250, "total_steps": 4218, "loss": 1.3494, "lr": 5.90047393364929e-06, "epoch": 0.17780938833570412, "percentage": 5.93, "elapsed_time": "0:27:42", "remaining_time": "7:19:47"}
+{"current_steps": 260, "total_steps": 4218, "loss": 1.351, "lr": 6.137440758293839e-06, "epoch": 0.18492176386913228, "percentage": 6.16, "elapsed_time": "0:28:55", "remaining_time": "7:20:26"}
+{"current_steps": 270, "total_steps": 4218, "loss": 1.3007, "lr": 6.374407582938389e-06, "epoch": 0.19203413940256045, "percentage": 6.4, "elapsed_time": "0:30:06", "remaining_time": "7:20:10"}
+{"current_steps": 280, "total_steps": 4218, "loss": 1.2318, "lr": 6.611374407582939e-06, "epoch": 0.19914651493598862, "percentage": 6.64, "elapsed_time": "0:31:17", "remaining_time": "7:20:04"}
+{"current_steps": 290, "total_steps": 4218, "loss": 1.2452, "lr": 6.848341232227489e-06, "epoch": 0.20625889046941678, "percentage": 6.88, "elapsed_time": "0:32:17", "remaining_time": "7:17:19"}
+{"current_steps": 300, "total_steps": 4218, "loss": 1.2299, "lr": 7.085308056872039e-06, "epoch": 0.21337126600284495, "percentage": 7.11, "elapsed_time": "0:33:17", "remaining_time": "7:14:45"}
+{"current_steps": 310, "total_steps": 4218, "loss": 1.2481, "lr": 7.322274881516588e-06, "epoch": 0.22048364153627312, "percentage": 7.35, "elapsed_time": "0:34:24", "remaining_time": "7:13:42"}
+{"current_steps": 320, "total_steps": 4218, "loss": 1.1874, "lr": 7.559241706161138e-06, "epoch": 0.22759601706970128, "percentage": 7.59, "elapsed_time": "0:35:27", "remaining_time": "7:12:01"}
+{"current_steps": 330, "total_steps": 4218, "loss": 1.242, "lr": 7.796208530805689e-06, "epoch": 0.23470839260312945, "percentage": 7.82, "elapsed_time": "0:36:31", "remaining_time": "7:10:25"}
+{"current_steps": 340, "total_steps": 4218, "loss": 1.1656, "lr": 8.033175355450237e-06, "epoch": 0.24182076813655762, "percentage": 8.06, "elapsed_time": "0:37:22", "remaining_time": "7:06:13"}
+{"current_steps": 350, "total_steps": 4218, "loss": 1.1626, "lr": 8.270142180094787e-06, "epoch": 0.24893314366998578, "percentage": 8.3, "elapsed_time": "0:38:29", "remaining_time": "7:05:23"}
+{"current_steps": 360, "total_steps": 4218, "loss": 1.1136, "lr": 8.507109004739337e-06, "epoch": 0.25604551920341395, "percentage": 8.53, "elapsed_time": "0:39:37", "remaining_time": "7:04:41"}
+{"current_steps": 370, "total_steps": 4218, "loss": 1.109, "lr": 8.744075829383887e-06, "epoch": 0.2631578947368421, "percentage": 8.77, "elapsed_time": "0:40:49", "remaining_time": "7:04:35"}
+{"current_steps": 380, "total_steps": 4218, "loss": 1.0926, "lr": 8.981042654028437e-06, "epoch": 0.2702702702702703, "percentage": 9.01, "elapsed_time": "0:41:59", "remaining_time": "7:04:09"}
+{"current_steps": 390, "total_steps": 4218, "loss": 0.9856, "lr": 9.218009478672988e-06, "epoch": 0.2773826458036984, "percentage": 9.25, "elapsed_time": "0:43:03", "remaining_time": "7:02:41"}
+{"current_steps": 400, "total_steps": 4218, "loss": 1.0438, "lr": 9.454976303317538e-06, "epoch": 0.2844950213371266, "percentage": 9.48, "elapsed_time": "0:44:12", "remaining_time": "7:01:55"}
+{"current_steps": 410, "total_steps": 4218, "loss": 0.9834, "lr": 9.691943127962086e-06, "epoch": 0.29160739687055476, "percentage": 9.72, "elapsed_time": "0:45:19", "remaining_time": "7:00:56"}
+{"current_steps": 420, "total_steps": 4218, "loss": 1.0355, "lr": 9.928909952606636e-06, "epoch": 0.29871977240398295, "percentage": 9.96, "elapsed_time": "0:46:23", "remaining_time": "6:59:33"}
+{"current_steps": 430, "total_steps": 4218, "loss": 0.9973, "lr": 9.99991609608766e-06, "epoch": 0.3058321479374111, "percentage": 10.19, "elapsed_time": "0:47:30", "remaining_time": "6:58:30"}
+{"current_steps": 440, "total_steps": 4218, "loss": 1.0118, "lr": 9.999505144928566e-06, "epoch": 0.3129445234708393, "percentage": 10.43, "elapsed_time": "0:48:40", "remaining_time": "6:57:55"}
+{"current_steps": 450, "total_steps": 4218, "loss": 0.915, "lr": 9.998751763712045e-06, "epoch": 0.3200568990042674, "percentage": 10.67, "elapsed_time": "0:49:51", "remaining_time": "6:57:32"}
+{"current_steps": 460, "total_steps": 4218, "loss": 0.8872, "lr": 9.997656004039284e-06, "epoch": 0.32716927453769556, "percentage": 10.91, "elapsed_time": "0:51:01", "remaining_time": "6:56:53"}
+{"current_steps": 470, "total_steps": 4218, "loss": 0.9233, "lr": 9.99621794096192e-06, "epoch": 0.33428165007112376, "percentage": 11.14, "elapsed_time": "0:52:02", "remaining_time": "6:55:02"}
+{"current_steps": 480, "total_steps": 4218, "loss": 0.8156, "lr": 9.994437672976904e-06, "epoch": 0.3413940256045519, "percentage": 11.38, "elapsed_time": "0:53:05", "remaining_time": "6:53:27"}
+{"current_steps": 490, "total_steps": 4218, "loss": 0.8749, "lr": 9.99231532201976e-06, "epoch": 0.3485064011379801, "percentage": 11.62, "elapsed_time": "0:54:16", "remaining_time": "6:52:58"}
+{"current_steps": 500, "total_steps": 4218, "loss": 0.8598, "lr": 9.989851033456224e-06, "epoch": 0.35561877667140823, "percentage": 11.85, "elapsed_time": "0:55:18", "remaining_time": "6:51:19"}
+{"current_steps": 510, "total_steps": 4218, "loss": 0.8118, "lr": 9.987044976072298e-06, "epoch": 0.3627311522048364, "percentage": 12.09, "elapsed_time": "0:56:27", "remaining_time": "6:50:29"}
+{"current_steps": 520, "total_steps": 4218, "loss": 0.8227, "lr": 9.983897342062681e-06, "epoch": 0.36984352773826457, "percentage": 12.33, "elapsed_time": "0:57:18", "remaining_time": "6:47:35"}
+{"current_steps": 530, "total_steps": 4218, "loss": 0.8132, "lr": 9.98040834701761e-06, "epoch": 0.37695590327169276, "percentage": 12.57, "elapsed_time": "0:58:24", "remaining_time": "6:46:28"}
+{"current_steps": 540, "total_steps": 4218, "loss": 0.7806, "lr": 9.97657822990809e-06, "epoch": 0.3840682788051209, "percentage": 12.8, "elapsed_time": "0:59:40", "remaining_time": "6:46:29"}
+{"current_steps": 550, "total_steps": 4218, "loss": 0.8095, "lr": 9.972407253069527e-06, "epoch": 0.3911806543385491, "percentage": 13.04, "elapsed_time": "1:00:47", "remaining_time": "6:45:27"}
+{"current_steps": 560, "total_steps": 4218, "loss": 0.7911, "lr": 9.967895702183767e-06, "epoch": 0.39829302987197723, "percentage": 13.28, "elapsed_time": "1:01:47", "remaining_time": "6:43:39"}
+{"current_steps": 570, "total_steps": 4218, "loss": 0.7712, "lr": 9.963043886259518e-06, "epoch": 0.40540540540540543, "percentage": 13.51, "elapsed_time": "1:02:57", "remaining_time": "6:42:56"}
+{"current_steps": 580, "total_steps": 4218, "loss": 0.7634, "lr": 9.957852137611187e-06, "epoch": 0.41251778093883357, "percentage": 13.75, "elapsed_time": "1:04:15", "remaining_time": "6:43:04"}
+{"current_steps": 590, "total_steps": 4218, "loss": 0.6903, "lr": 9.952320811836129e-06, "epoch": 0.41963015647226176, "percentage": 13.99, "elapsed_time": "1:05:28", "remaining_time": "6:42:38"}
+{"current_steps": 600, "total_steps": 4218, "loss": 0.7238, "lr": 9.94645028779028e-06, "epoch": 0.4267425320056899, "percentage": 14.22, "elapsed_time": "1:06:30", "remaining_time": "6:41:02"}
+{"current_steps": 610, "total_steps": 4218, "loss": 0.694, "lr": 9.94024096756221e-06, "epoch": 0.43385490753911804, "percentage": 14.46, "elapsed_time": "1:07:37", "remaining_time": "6:40:01"}
+{"current_steps": 620, "total_steps": 4218, "loss": 0.7057, "lr": 9.933693276445588e-06, "epoch": 0.44096728307254623, "percentage": 14.7, "elapsed_time": "1:08:33", "remaining_time": "6:37:51"}
+{"current_steps": 630, "total_steps": 4218, "loss": 0.7001, "lr": 9.92680766291005e-06, "epoch": 0.4480796586059744, "percentage": 14.94, "elapsed_time": "1:09:40", "remaining_time": "6:36:50"}
+{"current_steps": 640, "total_steps": 4218, "loss": 0.6451, "lr": 9.91958459857048e-06, "epoch": 0.45519203413940257, "percentage": 15.17, "elapsed_time": "1:10:56", "remaining_time": "6:36:38"}
+{"current_steps": 650, "total_steps": 4218, "loss": 0.6539, "lr": 9.912024578154706e-06, "epoch": 0.4623044096728307, "percentage": 15.41, "elapsed_time": "1:11:59", "remaining_time": "6:35:08"}
+{"current_steps": 660, "total_steps": 4218, "loss": 0.6383, "lr": 9.904128119469625e-06, "epoch": 0.4694167852062589, "percentage": 15.65, "elapsed_time": "1:12:57", "remaining_time": "6:33:17"}
+{"current_steps": 670, "total_steps": 4218, "loss": 0.6319, "lr": 9.895895763365722e-06, "epoch": 0.47652916073968704, "percentage": 15.88, "elapsed_time": "1:13:56", "remaining_time": "6:31:31"}
+{"current_steps": 680, "total_steps": 4218, "loss": 0.589, "lr": 9.88732807370004e-06, "epoch": 0.48364153627311524, "percentage": 16.12, "elapsed_time": "1:15:07", "remaining_time": "6:30:53"}
+{"current_steps": 690, "total_steps": 4218, "loss": 0.5236, "lr": 9.878425637297549e-06, "epoch": 0.4907539118065434, "percentage": 16.36, "elapsed_time": "1:16:21", "remaining_time": "6:30:23"}
+{"current_steps": 700, "total_steps": 4218, "loss": 0.524, "lr": 9.869189063910959e-06, "epoch": 0.49786628733997157, "percentage": 16.6, "elapsed_time": "1:17:43", "remaining_time": "6:30:36"}
+{"current_steps": 710, "total_steps": 4218, "loss": 0.5336, "lr": 9.859618986178953e-06, "epoch": 0.5049786628733998, "percentage": 16.83, "elapsed_time": "1:18:29", "remaining_time": "6:27:48"}
+{"current_steps": 720, "total_steps": 4218, "loss": 0.5202, "lr": 9.84971605958286e-06, "epoch": 0.5120910384068279, "percentage": 17.07, "elapsed_time": "1:19:22", "remaining_time": "6:25:36"}
+{"current_steps": 730, "total_steps": 4218, "loss": 0.4938, "lr": 9.839480962401753e-06, "epoch": 0.519203413940256, "percentage": 17.31, "elapsed_time": "1:20:16", "remaining_time": "6:23:34"}
+{"current_steps": 740, "total_steps": 4218, "loss": 0.4503, "lr": 9.828914395665996e-06, "epoch": 0.5263157894736842, "percentage": 17.54, "elapsed_time": "1:21:24", "remaining_time": "6:22:39"}
+{"current_steps": 750, "total_steps": 4218, "loss": 0.5067, "lr": 9.818017083109233e-06, "epoch": 0.5334281650071123, "percentage": 17.78, "elapsed_time": "1:22:28", "remaining_time": "6:21:20"}
+{"current_steps": 760, "total_steps": 4218, "loss": 0.4296, "lr": 9.8067897711188e-06, "epoch": 0.5405405405405406, "percentage": 18.02, "elapsed_time": "1:23:36", "remaining_time": "6:20:23"}
+{"current_steps": 770, "total_steps": 4218, "loss": 0.422, "lr": 9.795233228684631e-06, "epoch": 0.5476529160739687, "percentage": 18.26, "elapsed_time": "1:24:39", "remaining_time": "6:19:05"}
+{"current_steps": 780, "total_steps": 4218, "loss": 0.4352, "lr": 9.783348247346558e-06, "epoch": 0.5547652916073968, "percentage": 18.49, "elapsed_time": "1:25:48", "remaining_time": "6:18:12"}
+{"current_steps": 790, "total_steps": 4218, "loss": 0.3788, "lr": 9.771135641140117e-06, "epoch": 0.561877667140825, "percentage": 18.73, "elapsed_time": "1:26:59", "remaining_time": "6:17:29"}
+{"current_steps": 800, "total_steps": 4218, "loss": 0.4512, "lr": 9.758596246540782e-06, "epoch": 0.5689900426742532, "percentage": 18.97, "elapsed_time": "1:27:58", "remaining_time": "6:15:54"}
+{"current_steps": 810, "total_steps": 4218, "loss": 0.4286, "lr": 9.74573092240668e-06, "epoch": 0.5761024182076814, "percentage": 19.2, "elapsed_time": "1:29:14", "remaining_time": "6:15:28"}
+{"current_steps": 820, "total_steps": 4218, "loss": 0.3976, "lr": 9.732540549919758e-06, "epoch": 0.5832147937411095, "percentage": 19.44, "elapsed_time": "1:30:13", "remaining_time": "6:13:53"}
+{"current_steps": 830, "total_steps": 4218, "loss": 0.3845, "lr": 9.719026032525432e-06, "epoch": 0.5903271692745377, "percentage": 19.68, "elapsed_time": "1:31:16", "remaining_time": "6:12:34"}
+{"current_steps": 840, "total_steps": 4218, "loss": 0.3761, "lr": 9.70518829587071e-06, "epoch": 0.5974395448079659, "percentage": 19.91, "elapsed_time": "1:32:30", "remaining_time": "6:11:59"}
+{"current_steps": 850, "total_steps": 4218, "loss": 0.3663, "lr": 9.691028287740783e-06, "epoch": 0.604551920341394, "percentage": 20.15, "elapsed_time": "1:33:40", "remaining_time": "6:11:08"}
+{"current_steps": 860, "total_steps": 4218, "loss": 0.3683, "lr": 9.67654697799412e-06, "epoch": 0.6116642958748222, "percentage": 20.39, "elapsed_time": "1:34:40", "remaining_time": "6:09:39"}
+{"current_steps": 870, "total_steps": 4218, "loss": 0.3302, "lr": 9.661745358496033e-06, "epoch": 0.6187766714082503, "percentage": 20.63, "elapsed_time": "1:35:50", "remaining_time": "6:08:50"}
+{"current_steps": 880, "total_steps": 4218, "loss": 0.3714, "lr": 9.64662444305074e-06, "epoch": 0.6258890469416786, "percentage": 20.86, "elapsed_time": "1:36:55", "remaining_time": "6:07:39"}
+{"current_steps": 890, "total_steps": 4218, "loss": 0.3214, "lr": 9.631185267331937e-06, "epoch": 0.6330014224751067, "percentage": 21.1, "elapsed_time": "1:38:06", "remaining_time": "6:06:49"}
+{"current_steps": 900, "total_steps": 4218, "loss": 0.3151, "lr": 9.615428888811842e-06, "epoch": 0.6401137980085349, "percentage": 21.34, "elapsed_time": "1:39:16", "remaining_time": "6:05:57"}
+{"current_steps": 910, "total_steps": 4218, "loss": 0.3134, "lr": 9.59935638668879e-06, "epoch": 0.647226173541963, "percentage": 21.57, "elapsed_time": "1:40:22", "remaining_time": "6:04:51"}
+{"current_steps": 920, "total_steps": 4218, "loss": 0.2826, "lr": 9.582968861813295e-06, "epoch": 0.6543385490753911, "percentage": 21.81, "elapsed_time": "1:41:26", "remaining_time": "6:03:37"}
+{"current_steps": 930, "total_steps": 4218, "loss": 0.3272, "lr": 9.566267436612662e-06, "epoch": 0.6614509246088194, "percentage": 22.05, "elapsed_time": "1:42:29", "remaining_time": "6:02:22"}
+{"current_steps": 940, "total_steps": 4218, "loss": 0.2838, "lr": 9.549253255014105e-06, "epoch": 0.6685633001422475, "percentage": 22.29, "elapsed_time": "1:44:02", "remaining_time": "6:02:49"}
+{"current_steps": 950, "total_steps": 4218, "loss": 0.2676, "lr": 9.531927482366398e-06, "epoch": 0.6756756756756757, "percentage": 22.52, "elapsed_time": "1:45:01", "remaining_time": "6:01:18"}
+{"current_steps": 960, "total_steps": 4218, "loss": 0.2615, "lr": 9.514291305360053e-06, "epoch": 0.6827880512091038, "percentage": 22.76, "elapsed_time": "1:45:57", "remaining_time": "5:59:34"}
+{"current_steps": 970, "total_steps": 4218, "loss": 0.2232, "lr": 9.496345931946039e-06, "epoch": 0.689900426742532, "percentage": 23.0, "elapsed_time": "1:47:02", "remaining_time": "5:58:26"}
+{"current_steps": 980, "total_steps": 4218, "loss": 0.2628, "lr": 9.47809259125306e-06, "epoch": 0.6970128022759602, "percentage": 23.23, "elapsed_time": "1:47:57", "remaining_time": "5:56:43"}
+{"current_steps": 990, "total_steps": 4218, "loss": 0.2404, "lr": 9.459532533503347e-06, "epoch": 0.7041251778093883, "percentage": 23.47, "elapsed_time": "1:49:17", "remaining_time": "5:56:21"}
+{"current_steps": 1000, "total_steps": 4218, "loss": 0.2259, "lr": 9.440667029927043e-06, "epoch": 0.7112375533428165, "percentage": 23.71, "elapsed_time": "1:50:23", "remaining_time": "5:55:12"}
+{"current_steps": 1010, "total_steps": 4218, "loss": 0.208, "lr": 9.421497372675133e-06, "epoch": 0.7183499288762447, "percentage": 23.94, "elapsed_time": "1:51:23", "remaining_time": "5:53:48"}
+{"current_steps": 1020, "total_steps": 4218, "loss": 0.2277, "lr": 9.402024874730928e-06, "epoch": 0.7254623044096729, "percentage": 24.18, "elapsed_time": "1:52:21", "remaining_time": "5:52:17"}
+{"current_steps": 1030, "total_steps": 4218, "loss": 0.1926, "lr": 9.382250869820146e-06, "epoch": 0.732574679943101, "percentage": 24.42, "elapsed_time": "1:53:26", "remaining_time": "5:51:06"}
+{"current_steps": 1040, "total_steps": 4218, "loss": 0.2299, "lr": 9.36217671231956e-06, "epoch": 0.7396870554765291, "percentage": 24.66, "elapsed_time": "1:54:42", "remaining_time": "5:50:30"}
+{"current_steps": 1050, "total_steps": 4218, "loss": 0.1708, "lr": 9.341803777164228e-06, "epoch": 0.7467994310099573, "percentage": 24.89, "elapsed_time": "1:55:40", "remaining_time": "5:48:59"}
+{"current_steps": 1060, "total_steps": 4218, "loss": 0.2072, "lr": 9.321133459753322e-06, "epoch": 0.7539118065433855, "percentage": 25.13, "elapsed_time": "1:56:50", "remaining_time": "5:48:07"}
+{"current_steps": 1070, "total_steps": 4218, "loss": 0.1875, "lr": 9.300167175854564e-06, "epoch": 0.7610241820768137, "percentage": 25.37, "elapsed_time": "1:57:52", "remaining_time": "5:46:46"}
+{"current_steps": 1080, "total_steps": 4218, "loss": 0.173, "lr": 9.278906361507238e-06, "epoch": 0.7681365576102418, "percentage": 25.6, "elapsed_time": "1:58:48", "remaining_time": "5:45:12"}
+{"current_steps": 1090, "total_steps": 4218, "loss": 0.1489, "lr": 9.257352472923842e-06, "epoch": 0.7752489331436699, "percentage": 25.84, "elapsed_time": "1:59:51", "remaining_time": "5:43:56"}
+{"current_steps": 1100, "total_steps": 4218, "loss": 0.1423, "lr": 9.235506986390346e-06, "epoch": 0.7823613086770982, "percentage": 26.08, "elapsed_time": "2:00:57", "remaining_time": "5:42:53"}
+{"current_steps": 1110, "total_steps": 4218, "loss": 0.1564, "lr": 9.213371398165077e-06, "epoch": 0.7894736842105263, "percentage": 26.32, "elapsed_time": "2:02:05", "remaining_time": "5:41:51"}
+{"current_steps": 1120, "total_steps": 4218, "loss": 0.1872, "lr": 9.190947224376238e-06, "epoch": 0.7965860597439545, "percentage": 26.55, "elapsed_time": "2:03:03", "remaining_time": "5:40:24"}
+{"current_steps": 1130, "total_steps": 4218, "loss": 0.1483, "lr": 9.168236000918063e-06, "epoch": 0.8036984352773826, "percentage": 26.79, "elapsed_time": "2:04:15", "remaining_time": "5:39:33"}
+{"current_steps": 1140, "total_steps": 4218, "loss": 0.1272, "lr": 9.145239283345618e-06, "epoch": 0.8108108108108109, "percentage": 27.03, "elapsed_time": "2:05:24", "remaining_time": "5:38:36"}
+{"current_steps": 1150, "total_steps": 4218, "loss": 0.1361, "lr": 9.121958646768251e-06, "epoch": 0.817923186344239, "percentage": 27.26, "elapsed_time": "2:06:36", "remaining_time": "5:37:45"}
+{"current_steps": 1160, "total_steps": 4218, "loss": 0.1001, "lr": 9.09839568574173e-06, "epoch": 0.8250355618776671, "percentage": 27.5, "elapsed_time": "2:07:40", "remaining_time": "5:36:35"}
+{"current_steps": 1170, "total_steps": 4218, "loss": 0.1193, "lr": 9.074552014158994e-06, "epoch": 0.8321479374110953, "percentage": 27.74, "elapsed_time": "2:08:53", "remaining_time": "5:35:46"}
+{"current_steps": 1180, "total_steps": 4218, "loss": 0.1122, "lr": 9.050429265139647e-06, "epoch": 0.8392603129445235, "percentage": 27.98, "elapsed_time": "2:09:51", "remaining_time": "5:34:18"}
+{"current_steps": 1190, "total_steps": 4218, "loss": 0.1345, "lr": 9.026029090918076e-06, "epoch": 0.8463726884779517, "percentage": 28.21, "elapsed_time": "2:11:14", "remaining_time": "5:33:57"}
+{"current_steps": 1200, "total_steps": 4218, "loss": 0.1134, "lr": 9.001353162730297e-06, "epoch": 0.8534850640113798, "percentage": 28.45, "elapsed_time": "2:12:19", "remaining_time": "5:32:48"}
+{"current_steps": 1210, "total_steps": 4218, "loss": 0.1026, "lr": 8.976403170699486e-06, "epoch": 0.8605974395448079, "percentage": 28.69, "elapsed_time": "2:13:14", "remaining_time": "5:31:14"}
+{"current_steps": 1220, "total_steps": 4218, "loss": 0.0967, "lr": 8.951180823720212e-06, "epoch": 0.8677098150782361, "percentage": 28.92, "elapsed_time": "2:14:32", "remaining_time": "5:30:37"}
+{"current_steps": 1230, "total_steps": 4218, "loss": 0.0819, "lr": 8.925687849341398e-06, "epoch": 0.8748221906116643, "percentage": 29.16, "elapsed_time": "2:15:44", "remaining_time": "5:29:46"}
+{"current_steps": 1240, "total_steps": 4218, "loss": 0.0931, "lr": 8.899925993647994e-06, "epoch": 0.8819345661450925, "percentage": 29.4, "elapsed_time": "2:16:40", "remaining_time": "5:28:14"}
+{"current_steps": 1250, "total_steps": 4218, "loss": 0.0888, "lr": 8.873897021141378e-06, "epoch": 0.8890469416785206, "percentage": 29.63, "elapsed_time": "2:17:43", "remaining_time": "5:27:01"}
+{"current_steps": 1260, "total_steps": 4218, "loss": 0.0839, "lr": 8.847602714618504e-06, "epoch": 0.8961593172119487, "percentage": 29.87, "elapsed_time": "2:18:51", "remaining_time": "5:25:58"}
+{"current_steps": 1270, "total_steps": 4218, "loss": 0.0878, "lr": 8.821044875049796e-06, "epoch": 0.903271692745377, "percentage": 30.11, "elapsed_time": "2:19:59", "remaining_time": "5:24:57"}
+{"current_steps": 1280, "total_steps": 4218, "loss": 0.0866, "lr": 8.794225321455788e-06, "epoch": 0.9103840682788051, "percentage": 30.35, "elapsed_time": "2:20:52", "remaining_time": "5:23:20"}
+{"current_steps": 1290, "total_steps": 4218, "loss": 0.0849, "lr": 8.767145890782542e-06, "epoch": 0.9174964438122333, "percentage": 30.58, "elapsed_time": "2:22:00", "remaining_time": "5:22:18"}
+{"current_steps": 1300, "total_steps": 4218, "loss": 0.0773, "lr": 8.739808437775825e-06, "epoch": 0.9246088193456614, "percentage": 30.82, "elapsed_time": "2:23:16", "remaining_time": "5:21:35"}
+{"current_steps": 1310, "total_steps": 4218, "loss": 0.0887, "lr": 8.71221483485407e-06, "epoch": 0.9317211948790897, "percentage": 31.06, "elapsed_time": "2:24:21", "remaining_time": "5:20:26"}
+{"current_steps": 1320, "total_steps": 4218, "loss": 0.0739, "lr": 8.684366971980139e-06, "epoch": 0.9388335704125178, "percentage": 31.29, "elapsed_time": "2:25:25", "remaining_time": "5:19:17"}
+{"current_steps": 1330, "total_steps": 4218, "loss": 0.0757, "lr": 8.656266756531857e-06, "epoch": 0.9459459459459459, "percentage": 31.53, "elapsed_time": "2:26:28", "remaining_time": "5:18:04"}
+{"current_steps": 1340, "total_steps": 4218, "loss": 0.0695, "lr": 8.627916113171396e-06, "epoch": 0.9530583214793741, "percentage": 31.77, "elapsed_time": "2:27:29", "remaining_time": "5:16:46"}
+{"current_steps": 1350, "total_steps": 4218, "loss": 0.0703, "lr": 8.599316983713419e-06, "epoch": 0.9601706970128022, "percentage": 32.01, "elapsed_time": "2:28:41", "remaining_time": "5:15:53"}
+{"current_steps": 1360, "total_steps": 4218, "loss": 0.062, "lr": 8.570471326992105e-06, "epoch": 0.9672830725462305, "percentage": 32.24, "elapsed_time": "2:29:39", "remaining_time": "5:14:29"}
+{"current_steps": 1370, "total_steps": 4218, "loss": 0.0755, "lr": 8.54138111872697e-06, "epoch": 0.9743954480796586, "percentage": 32.48, "elapsed_time": "2:30:40", "remaining_time": "5:13:14"}
+{"current_steps": 1380, "total_steps": 4218, "loss": 0.0656, "lr": 8.512048351387551e-06, "epoch": 0.9815078236130867, "percentage": 32.72, "elapsed_time": "2:31:45", "remaining_time": "5:12:05"}
+{"current_steps": 1390, "total_steps": 4218, "loss": 0.0659, "lr": 8.482475034056927e-06, "epoch": 0.9886201991465149, "percentage": 32.95, "elapsed_time": "2:32:33", "remaining_time": "5:10:23"}
+{"current_steps": 1400, "total_steps": 4218, "loss": 0.0576, "lr": 8.452663192294121e-06, "epoch": 0.9957325746799431, "percentage": 33.19, "elapsed_time": "2:33:40", "remaining_time": "5:09:20"}
+{"current_steps": 1410, "total_steps": 4218, "loss": 0.0518, "lr": 8.42261486799536e-06, "epoch": 1.0028449502133712, "percentage": 33.43, "elapsed_time": "2:34:48", "remaining_time": "5:08:18"}
+{"current_steps": 1420, "total_steps": 4218, "loss": 0.0363, "lr": 8.392332119254214e-06, "epoch": 1.0099573257467995, "percentage": 33.67, "elapsed_time": "2:35:55", "remaining_time": "5:07:14"}
+{"current_steps": 1430, "total_steps": 4218, "loss": 0.0345, "lr": 8.361817020220647e-06, "epoch": 1.0170697012802277, "percentage": 33.9, "elapsed_time": "2:37:00", "remaining_time": "5:06:07"}
+{"current_steps": 1440, "total_steps": 4218, "loss": 0.039, "lr": 8.331071660958936e-06, "epoch": 1.0241820768136558, "percentage": 34.14, "elapsed_time": "2:37:58", "remaining_time": "5:04:45"}
+{"current_steps": 1450, "total_steps": 4218, "loss": 0.0365, "lr": 8.300098147304523e-06, "epoch": 1.031294452347084, "percentage": 34.38, "elapsed_time": "2:39:05", "remaining_time": "5:03:42"}
+{"current_steps": 1460, "total_steps": 4218, "loss": 0.0431, "lr": 8.268898600719785e-06, "epoch": 1.038406827880512, "percentage": 34.61, "elapsed_time": "2:40:14", "remaining_time": "5:02:42"}
+{"current_steps": 1470, "total_steps": 4218, "loss": 0.0429, "lr": 8.237475158148724e-06, "epoch": 1.0455192034139402, "percentage": 34.85, "elapsed_time": "2:41:22", "remaining_time": "5:01:40"}
+{"current_steps": 1480, "total_steps": 4218, "loss": 0.0397, "lr": 8.205829971870602e-06, "epoch": 1.0526315789473684, "percentage": 35.09, "elapsed_time": "2:42:28", "remaining_time": "5:00:34"}
+{"current_steps": 1490, "total_steps": 4218, "loss": 0.0344, "lr": 8.173965209352524e-06, "epoch": 1.0597439544807965, "percentage": 35.32, "elapsed_time": "2:43:25", "remaining_time": "4:59:11"}
+{"current_steps": 1500, "total_steps": 4218, "loss": 0.0464, "lr": 8.14188305310099e-06, "epoch": 1.0668563300142249, "percentage": 35.56, "elapsed_time": "2:44:40", "remaining_time": "4:58:23"}
+{"current_steps": 1510, "total_steps": 4218, "loss": 0.0375, "lr": 8.109585700512395e-06, "epoch": 1.073968705547653, "percentage": 35.8, "elapsed_time": "2:45:52", "remaining_time": "4:57:29"}
+{"current_steps": 1520, "total_steps": 4218, "loss": 0.0389, "lr": 8.077075363722542e-06, "epoch": 1.0810810810810811, "percentage": 36.04, "elapsed_time": "2:46:55", "remaining_time": "4:56:17"}
+{"current_steps": 1530, "total_steps": 4218, "loss": 0.0436, "lr": 8.044354269455109e-06, "epoch": 1.0881934566145093, "percentage": 36.27, "elapsed_time": "2:48:02", "remaining_time": "4:55:12"}
+{"current_steps": 1540, "total_steps": 4218, "loss": 0.0357, "lr": 8.011424658869142e-06, "epoch": 1.0953058321479374, "percentage": 36.51, "elapsed_time": "2:49:01", "remaining_time": "4:53:55"}
+{"current_steps": 1550, "total_steps": 4218, "loss": 0.0362, "lr": 7.978288787405556e-06, "epoch": 1.1024182076813656, "percentage": 36.75, "elapsed_time": "2:50:05", "remaining_time": "4:52:46"}
+{"current_steps": 1560, "total_steps": 4218, "loss": 0.0345, "lr": 7.944948924632643e-06, "epoch": 1.1095305832147937, "percentage": 36.98, "elapsed_time": "2:51:20", "remaining_time": "4:51:56"}
+{"current_steps": 1570, "total_steps": 4218, "loss": 0.0354, "lr": 7.911407354090634e-06, "epoch": 1.1166429587482218, "percentage": 37.22, "elapsed_time": "2:52:26", "remaining_time": "4:50:50"}
+{"current_steps": 1580, "total_steps": 4218, "loss": 0.0346, "lr": 7.877666373135287e-06, "epoch": 1.12375533428165, "percentage": 37.46, "elapsed_time": "2:53:26", "remaining_time": "4:49:34"}
+{"current_steps": 1590, "total_steps": 4218, "loss": 0.038, "lr": 7.84372829278053e-06, "epoch": 1.1308677098150781, "percentage": 37.7, "elapsed_time": "2:54:19", "remaining_time": "4:48:07"}
+{"current_steps": 1600, "total_steps": 4218, "loss": 0.0327, "lr": 7.809595437540189e-06, "epoch": 1.1379800853485065, "percentage": 37.93, "elapsed_time": "2:55:22", "remaining_time": "4:46:56"}
+{"current_steps": 1610, "total_steps": 4218, "loss": 0.0256, "lr": 7.775270145268755e-06, "epoch": 1.1450924608819346, "percentage": 38.17, "elapsed_time": "2:56:22", "remaining_time": "4:45:41"}
+{"current_steps": 1620, "total_steps": 4218, "loss": 0.039, "lr": 7.740754767001278e-06, "epoch": 1.1522048364153628, "percentage": 38.41, "elapsed_time": "2:57:40", "remaining_time": "4:44:56"}
+{"current_steps": 1630, "total_steps": 4218, "loss": 0.0353, "lr": 7.706051666792318e-06, "epoch": 1.159317211948791, "percentage": 38.64, "elapsed_time": "2:58:40", "remaining_time": "4:43:41"}
+{"current_steps": 1640, "total_steps": 4218, "loss": 0.0353, "lr": 7.671163221554043e-06, "epoch": 1.166429587482219, "percentage": 38.88, "elapsed_time": "2:59:36", "remaining_time": "4:42:20"}
+{"current_steps": 1650, "total_steps": 4218, "loss": 0.0374, "lr": 7.636091820893417e-06, "epoch": 1.1735419630156472, "percentage": 39.12, "elapsed_time": "3:00:42", "remaining_time": "4:41:15"}
+{"current_steps": 1660, "total_steps": 4218, "loss": 0.0363, "lr": 7.600839866948528e-06, "epoch": 1.1806543385490753, "percentage": 39.36, "elapsed_time": "3:01:40", "remaining_time": "4:39:57"}
+{"current_steps": 1670, "total_steps": 4218, "loss": 0.0349, "lr": 7.565409774224066e-06, "epoch": 1.1877667140825037, "percentage": 39.59, "elapsed_time": "3:02:58", "remaining_time": "4:39:09"}
+{"current_steps": 1680, "total_steps": 4218, "loss": 0.0307, "lr": 7.529803969425941e-06, "epoch": 1.1948790896159318, "percentage": 39.83, "elapsed_time": "3:04:03", "remaining_time": "4:38:03"}
+{"current_steps": 1690, "total_steps": 4218, "loss": 0.0322, "lr": 7.494024891295075e-06, "epoch": 1.20199146514936, "percentage": 40.07, "elapsed_time": "3:05:22", "remaining_time": "4:37:17"}
+{"current_steps": 1700, "total_steps": 4218, "loss": 0.0293, "lr": 7.458074990440363e-06, "epoch": 1.209103840682788, "percentage": 40.3, "elapsed_time": "3:06:08", "remaining_time": "4:35:43"}
+{"current_steps": 1710, "total_steps": 4218, "loss": 0.0344, "lr": 7.421956729170823e-06, "epoch": 1.2162162162162162, "percentage": 40.54, "elapsed_time": "3:07:09", "remaining_time": "4:34:29"}
+{"current_steps": 1720, "total_steps": 4218, "loss": 0.0351, "lr": 7.385672581326954e-06, "epoch": 1.2233285917496444, "percentage": 40.78, "elapsed_time": "3:08:15", "remaining_time": "4:33:24"}
+{"current_steps": 1730, "total_steps": 4218, "loss": 0.0353, "lr": 7.34922503211128e-06, "epoch": 1.2304409672830725, "percentage": 41.01, "elapsed_time": "3:09:18", "remaining_time": "4:32:15"}
+{"current_steps": 1740, "total_steps": 4218, "loss": 0.03, "lr": 7.312616577918149e-06, "epoch": 1.2375533428165006, "percentage": 41.25, "elapsed_time": "3:10:26", "remaining_time": "4:31:13"}
+{"current_steps": 1750, "total_steps": 4218, "loss": 0.0267, "lr": 7.2758497261627345e-06, "epoch": 1.2446657183499288, "percentage": 41.49, "elapsed_time": "3:11:41", "remaining_time": "4:30:20"}
+{"current_steps": 1760, "total_steps": 4218, "loss": 0.0288, "lr": 7.238926995109306e-06, "epoch": 1.251778093883357, "percentage": 41.73, "elapsed_time": "3:12:57", "remaining_time": "4:29:29"}
+{"current_steps": 1770, "total_steps": 4218, "loss": 0.0364, "lr": 7.201850913698736e-06, "epoch": 1.2588904694167853, "percentage": 41.96, "elapsed_time": "3:13:57", "remaining_time": "4:28:14"}
+{"current_steps": 1780, "total_steps": 4218, "loss": 0.0252, "lr": 7.164624021375294e-06, "epoch": 1.2660028449502134, "percentage": 42.2, "elapsed_time": "3:15:14", "remaining_time": "4:27:24"}
+{"current_steps": 1790, "total_steps": 4218, "loss": 0.0266, "lr": 7.12724886791271e-06, "epoch": 1.2731152204836416, "percentage": 42.44, "elapsed_time": "3:16:19", "remaining_time": "4:26:17"}
+{"current_steps": 1800, "total_steps": 4218, "loss": 0.03, "lr": 7.08972801323953e-06, "epoch": 1.2802275960170697, "percentage": 42.67, "elapsed_time": "3:17:17", "remaining_time": "4:25:01"}
+{"current_steps": 1810, "total_steps": 4218, "loss": 0.0235, "lr": 7.052064027263785e-06, "epoch": 1.2873399715504978, "percentage": 42.91, "elapsed_time": "3:18:17", "remaining_time": "4:23:48"}
+{"current_steps": 1820, "total_steps": 4218, "loss": 0.0243, "lr": 7.014259489696968e-06, "epoch": 1.294452347083926, "percentage": 43.15, "elapsed_time": "3:19:19", "remaining_time": "4:22:37"}
+{"current_steps": 1830, "total_steps": 4218, "loss": 0.0249, "lr": 6.976316989877343e-06, "epoch": 1.3015647226173541, "percentage": 43.39, "elapsed_time": "3:20:34", "remaining_time": "4:21:43"}
+{"current_steps": 1840, "total_steps": 4218, "loss": 0.0263, "lr": 6.938239126592592e-06, "epoch": 1.3086770981507825, "percentage": 43.62, "elapsed_time": "3:21:53", "remaining_time": "4:20:55"}
+{"current_steps": 1850, "total_steps": 4218, "loss": 0.0298, "lr": 6.90002850790182e-06, "epoch": 1.3157894736842106, "percentage": 43.86, "elapsed_time": "3:22:53", "remaining_time": "4:19:42"}
+{"current_steps": 1860, "total_steps": 4218, "loss": 0.027, "lr": 6.861687750956922e-06, "epoch": 1.3229018492176388, "percentage": 44.1, "elapsed_time": "3:24:04", "remaining_time": "4:18:43"}
+{"current_steps": 1870, "total_steps": 4218, "loss": 0.0245, "lr": 6.823219481823318e-06, "epoch": 1.330014224751067, "percentage": 44.33, "elapsed_time": "3:25:07", "remaining_time": "4:17:33"}
+{"current_steps": 1880, "total_steps": 4218, "loss": 0.0198, "lr": 6.784626335300102e-06, "epoch": 1.337126600284495, "percentage": 44.57, "elapsed_time": "3:26:18", "remaining_time": "4:16:34"}
+{"current_steps": 1890, "total_steps": 4218, "loss": 0.0274, "lr": 6.745910954739563e-06, "epoch": 1.3442389758179232, "percentage": 44.81, "elapsed_time": "3:27:28", "remaining_time": "4:15:33"}
+{"current_steps": 1900, "total_steps": 4218, "loss": 0.0268, "lr": 6.707075991866143e-06, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "3:28:46", "remaining_time": "4:14:42"}
+{"current_steps": 1910, "total_steps": 4218, "loss": 0.0274, "lr": 6.668124106594813e-06, "epoch": 1.3584637268847795, "percentage": 45.28, "elapsed_time": "3:29:54", "remaining_time": "4:13:38"}
+{"current_steps": 1920, "total_steps": 4218, "loss": 0.0244, "lr": 6.629057966848879e-06, "epoch": 1.3655761024182076, "percentage": 45.52, "elapsed_time": "3:31:09", "remaining_time": "4:12:44"}
+{"current_steps": 1930, "total_steps": 4218, "loss": 0.023, "lr": 6.589880248377258e-06, "epoch": 1.3726884779516357, "percentage": 45.76, "elapsed_time": "3:32:23", "remaining_time": "4:11:47"}
+{"current_steps": 1940, "total_steps": 4218, "loss": 0.018, "lr": 6.550593634571205e-06, "epoch": 1.379800853485064, "percentage": 45.99, "elapsed_time": "3:33:31", "remaining_time": "4:10:44"}
+{"current_steps": 1950, "total_steps": 4218, "loss": 0.021, "lr": 6.511200816280523e-06, "epoch": 1.3869132290184922, "percentage": 46.23, "elapsed_time": "3:34:43", "remaining_time": "4:09:44"}
+{"current_steps": 1960, "total_steps": 4218, "loss": 0.0285, "lr": 6.471704491629251e-06, "epoch": 1.3940256045519204, "percentage": 46.47, "elapsed_time": "3:35:44", "remaining_time": "4:08:32"}
+{"current_steps": 1970, "total_steps": 4218, "loss": 0.0198, "lr": 6.432107365830872e-06, "epoch": 1.4011379800853485, "percentage": 46.7, "elapsed_time": "3:36:47", "remaining_time": "4:07:22"}
+{"current_steps": 1980, "total_steps": 4218, "loss": 0.0244, "lr": 6.392412151003019e-06, "epoch": 1.4082503556187767, "percentage": 46.94, "elapsed_time": "3:38:00", "remaining_time": "4:06:24"}
+{"current_steps": 1990, "total_steps": 4218, "loss": 0.0226, "lr": 6.3526215659817156e-06, "epoch": 1.4153627311522048, "percentage": 47.18, "elapsed_time": "3:39:02", "remaining_time": "4:05:14"}
+{"current_steps": 2000, "total_steps": 4218, "loss": 0.019, "lr": 6.312738336135159e-06, "epoch": 1.422475106685633, "percentage": 47.42, "elapsed_time": "3:40:20", "remaining_time": "4:04:21"}
+{"current_steps": 2010, "total_steps": 4218, "loss": 0.0196, "lr": 6.272765193177044e-06, "epoch": 1.4295874822190613, "percentage": 47.65, "elapsed_time": "3:41:20", "remaining_time": "4:03:08"}
+{"current_steps": 2020, "total_steps": 4218, "loss": 0.0189, "lr": 6.23270487497947e-06, "epoch": 1.4366998577524894, "percentage": 47.89, "elapsed_time": "3:42:31", "remaining_time": "4:02:08"}
+{"current_steps": 2030, "total_steps": 4218, "loss": 0.025, "lr": 6.192560125385412e-06, "epoch": 1.4438122332859176, "percentage": 48.13, "elapsed_time": "3:43:30", "remaining_time": "4:00:54"}
+{"current_steps": 2040, "total_steps": 4218, "loss": 0.0184, "lr": 6.152333694020781e-06, "epoch": 1.4509246088193457, "percentage": 48.36, "elapsed_time": "3:44:26", "remaining_time": "3:59:37"}
+{"current_steps": 2050, "total_steps": 4218, "loss": 0.023, "lr": 6.112028336106108e-06, "epoch": 1.4580369843527738, "percentage": 48.6, "elapsed_time": "3:45:23", "remaining_time": "3:58:21"}
+{"current_steps": 2060, "total_steps": 4218, "loss": 0.0167, "lr": 6.071646812267817e-06, "epoch": 1.465149359886202, "percentage": 48.84, "elapsed_time": "3:46:38", "remaining_time": "3:57:25"}
+{"current_steps": 2070, "total_steps": 4218, "loss": 0.0202, "lr": 6.031191888349155e-06, "epoch": 1.4722617354196301, "percentage": 49.08, "elapsed_time": "3:47:46", "remaining_time": "3:56:21"}
+{"current_steps": 2080, "total_steps": 4218, "loss": 0.0178, "lr": 5.990666335220738e-06, "epoch": 1.4793741109530583, "percentage": 49.31, "elapsed_time": "3:48:43", "remaining_time": "3:55:06"}
+{"current_steps": 2090, "total_steps": 4218, "loss": 0.018, "lr": 5.950072928590781e-06, "epoch": 1.4864864864864864, "percentage": 49.55, "elapsed_time": "3:49:48", "remaining_time": "3:53:59"}
+{"current_steps": 2100, "total_steps": 4218, "loss": 0.0209, "lr": 5.909414448814971e-06, "epoch": 1.4935988620199145, "percentage": 49.79, "elapsed_time": "3:50:49", "remaining_time": "3:52:48"}
+{"current_steps": 2110, "total_steps": 4218, "loss": 0.0192, "lr": 5.8686936807060335e-06, "epoch": 1.5007112375533427, "percentage": 50.02, "elapsed_time": "3:51:56", "remaining_time": "3:51:43"}
+{"current_steps": 2120, "total_steps": 4218, "loss": 0.018, "lr": 5.827913413343003e-06, "epoch": 1.5078236130867708, "percentage": 50.26, "elapsed_time": "3:53:02", "remaining_time": "3:50:37"}
+{"current_steps": 2130, "total_steps": 4218, "loss": 0.0179, "lr": 5.787076439880177e-06, "epoch": 1.5149359886201992, "percentage": 50.5, "elapsed_time": "3:54:06", "remaining_time": "3:49:29"}
+{"current_steps": 2140, "total_steps": 4218, "loss": 0.0211, "lr": 5.746185557355814e-06, "epoch": 1.5220483641536273, "percentage": 50.73, "elapsed_time": "3:55:22", "remaining_time": "3:48:33"}
+{"current_steps": 2150, "total_steps": 4218, "loss": 0.0168, "lr": 5.70524356650056e-06, "epoch": 1.5291607396870555, "percentage": 50.97, "elapsed_time": "3:56:25", "remaining_time": "3:47:24"}
+{"current_steps": 2160, "total_steps": 4218, "loss": 0.0172, "lr": 5.664253271545603e-06, "epoch": 1.5362731152204836, "percentage": 51.21, "elapsed_time": "3:57:27", "remaining_time": "3:46:15"}
+{"current_steps": 2170, "total_steps": 4218, "loss": 0.0178, "lr": 5.623217480030622e-06, "epoch": 1.543385490753912, "percentage": 51.45, "elapsed_time": "3:58:30", "remaining_time": "3:45:06"}
+{"current_steps": 2180, "total_steps": 4218, "loss": 0.0135, "lr": 5.58213900261148e-06, "epoch": 1.55049786628734, "percentage": 51.68, "elapsed_time": "3:59:34", "remaining_time": "3:43:58"}
+{"current_steps": 2190, "total_steps": 4218, "loss": 0.0153, "lr": 5.541020652867713e-06, "epoch": 1.5576102418207682, "percentage": 51.92, "elapsed_time": "4:00:49", "remaining_time": "3:43:00"}
+{"current_steps": 2200, "total_steps": 4218, "loss": 0.0143, "lr": 5.49986524710983e-06, "epoch": 1.5647226173541964, "percentage": 52.16, "elapsed_time": "4:01:53", "remaining_time": "3:41:52"}
+{"current_steps": 2210, "total_steps": 4218, "loss": 0.016, "lr": 5.4586756041864065e-06, "epoch": 1.5718349928876245, "percentage": 52.39, "elapsed_time": "4:03:01", "remaining_time": "3:40:49"}
+{"current_steps": 2220, "total_steps": 4218, "loss": 0.0168, "lr": 5.417454545291017e-06, "epoch": 1.5789473684210527, "percentage": 52.63, "elapsed_time": "4:04:16", "remaining_time": "3:39:51"}
+{"current_steps": 2230, "total_steps": 4218, "loss": 0.0198, "lr": 5.376204893769e-06, "epoch": 1.5860597439544808, "percentage": 52.87, "elapsed_time": "4:05:23", "remaining_time": "3:38:45"}
+{"current_steps": 2240, "total_steps": 4218, "loss": 0.0155, "lr": 5.334929474924093e-06, "epoch": 1.593172119487909, "percentage": 53.11, "elapsed_time": "4:06:24", "remaining_time": "3:37:35"}
+{"current_steps": 2250, "total_steps": 4218, "loss": 0.0138, "lr": 5.293631115824897e-06, "epoch": 1.600284495021337, "percentage": 53.34, "elapsed_time": "4:07:26", "remaining_time": "3:36:25"}
+{"current_steps": 2260, "total_steps": 4218, "loss": 0.0173, "lr": 5.252312645111266e-06, "epoch": 1.6073968705547652, "percentage": 53.58, "elapsed_time": "4:08:34", "remaining_time": "3:35:21"}
+{"current_steps": 2270, "total_steps": 4218, "loss": 0.0142, "lr": 5.2109768928005454e-06, "epoch": 1.6145092460881934, "percentage": 53.82, "elapsed_time": "4:09:36", "remaining_time": "3:34:12"}
+{"current_steps": 2280, "total_steps": 4218, "loss": 0.014, "lr": 5.169626690093751e-06, "epoch": 1.6216216216216215, "percentage": 54.05, "elapsed_time": "4:10:28", "remaining_time": "3:32:54"}
+{"current_steps": 2290, "total_steps": 4218, "loss": 0.0127, "lr": 5.128264869181646e-06, "epoch": 1.6287339971550496, "percentage": 54.29, "elapsed_time": "4:11:33", "remaining_time": "3:31:47"}
+{"current_steps": 2300, "total_steps": 4218, "loss": 0.011, "lr": 5.086894263050755e-06, "epoch": 1.635846372688478, "percentage": 54.53, "elapsed_time": "4:12:48", "remaining_time": "3:30:49"}
+{"current_steps": 2310, "total_steps": 4218, "loss": 0.0111, "lr": 5.045517705289328e-06, "epoch": 1.6429587482219061, "percentage": 54.77, "elapsed_time": "4:13:45", "remaining_time": "3:29:35"}
+{"current_steps": 2320, "total_steps": 4218, "loss": 0.0138, "lr": 5.004138029893257e-06, "epoch": 1.6500711237553343, "percentage": 55.0, "elapsed_time": "4:14:51", "remaining_time": "3:28:30"}
+{"current_steps": 2330, "total_steps": 4218, "loss": 0.0128, "lr": 4.9627580710719734e-06, "epoch": 1.6571834992887624, "percentage": 55.24, "elapsed_time": "4:15:54", "remaining_time": "3:27:21"}
+{"current_steps": 2340, "total_steps": 4218, "loss": 0.0128, "lr": 4.921380663054318e-06, "epoch": 1.6642958748221908, "percentage": 55.48, "elapsed_time": "4:16:55", "remaining_time": "3:26:11"}
+{"current_steps": 2350, "total_steps": 4218, "loss": 0.014, "lr": 4.880008639894421e-06, "epoch": 1.671408250355619, "percentage": 55.71, "elapsed_time": "4:18:05", "remaining_time": "3:25:09"}
+{"current_steps": 2360, "total_steps": 4218, "loss": 0.0144, "lr": 4.838644835277585e-06, "epoch": 1.678520625889047, "percentage": 55.95, "elapsed_time": "4:19:12", "remaining_time": "3:24:04"}
+{"current_steps": 2370, "total_steps": 4218, "loss": 0.0109, "lr": 4.79729208232621e-06, "epoch": 1.6856330014224752, "percentage": 56.19, "elapsed_time": "4:20:30", "remaining_time": "3:23:07"}
+{"current_steps": 2380, "total_steps": 4218, "loss": 0.0122, "lr": 4.75595321340573e-06, "epoch": 1.6927453769559033, "percentage": 56.42, "elapsed_time": "4:21:47", "remaining_time": "3:22:10"}
+{"current_steps": 2390, "total_steps": 4218, "loss": 0.012, "lr": 4.714631059930622e-06, "epoch": 1.6998577524893315, "percentage": 56.66, "elapsed_time": "4:22:58", "remaining_time": "3:21:07"}
+{"current_steps": 2400, "total_steps": 4218, "loss": 0.0124, "lr": 4.6733284521704816e-06, "epoch": 1.7069701280227596, "percentage": 56.9, "elapsed_time": "4:24:01", "remaining_time": "3:19:59"}
+{"current_steps": 2410, "total_steps": 4218, "loss": 0.012, "lr": 4.632048219056159e-06, "epoch": 1.7140825035561877, "percentage": 57.14, "elapsed_time": "4:25:00", "remaining_time": "3:18:48"}
+{"current_steps": 2420, "total_steps": 4218, "loss": 0.0149, "lr": 4.590793187986003e-06, "epoch": 1.7211948790896159, "percentage": 57.37, "elapsed_time": "4:25:57", "remaining_time": "3:17:35"}
+{"current_steps": 2430, "total_steps": 4218, "loss": 0.0117, "lr": 4.549566184632206e-06, "epoch": 1.728307254623044, "percentage": 57.61, "elapsed_time": "4:27:03", "remaining_time": "3:16:29"}
+{"current_steps": 2440, "total_steps": 4218, "loss": 0.0092, "lr": 4.508370032747261e-06, "epoch": 1.7354196301564722, "percentage": 57.85, "elapsed_time": "4:28:12", "remaining_time": "3:15:26"}
+{"current_steps": 2450, "total_steps": 4218, "loss": 0.012, "lr": 4.467207553970564e-06, "epoch": 1.7425320056899003, "percentage": 58.08, "elapsed_time": "4:29:25", "remaining_time": "3:14:25"}
+{"current_steps": 2460, "total_steps": 4218, "loss": 0.0092, "lr": 4.426081567635137e-06, "epoch": 1.7496443812233284, "percentage": 58.32, "elapsed_time": "4:30:36", "remaining_time": "3:13:22"}
+{"current_steps": 2470, "total_steps": 4218, "loss": 0.0137, "lr": 4.3849948905745385e-06, "epoch": 1.7567567567567568, "percentage": 58.56, "elapsed_time": "4:31:48", "remaining_time": "3:12:21"}
+{"current_steps": 2480, "total_steps": 4218, "loss": 0.0095, "lr": 4.343950336929927e-06, "epoch": 1.763869132290185, "percentage": 58.8, "elapsed_time": "4:32:53", "remaining_time": "3:11:14"}
+{"current_steps": 2490, "total_steps": 4218, "loss": 0.0098, "lr": 4.302950717957304e-06, "epoch": 1.770981507823613, "percentage": 59.03, "elapsed_time": "4:33:54", "remaining_time": "3:10:04"}
+{"current_steps": 2500, "total_steps": 4218, "loss": 0.0101, "lr": 4.261998841834972e-06, "epoch": 1.7780938833570412, "percentage": 59.27, "elapsed_time": "4:34:58", "remaining_time": "3:08:58"}
+{"current_steps": 2510, "total_steps": 4218, "loss": 0.0094, "lr": 4.221097513471199e-06, "epoch": 1.7852062588904696, "percentage": 59.51, "elapsed_time": "4:36:05", "remaining_time": "3:07:52"}
+{"current_steps": 2520, "total_steps": 4218, "loss": 0.009, "lr": 4.18024953431209e-06, "epoch": 1.7923186344238977, "percentage": 59.74, "elapsed_time": "4:37:11", "remaining_time": "3:06:46"}
+{"current_steps": 2530, "total_steps": 4218, "loss": 0.0098, "lr": 4.13945770214971e-06, "epoch": 1.7994310099573259, "percentage": 59.98, "elapsed_time": "4:38:19", "remaining_time": "3:05:41"}
+{"current_steps": 2540, "total_steps": 4218, "loss": 0.0077, "lr": 4.098724810930472e-06, "epoch": 1.806543385490754, "percentage": 60.22, "elapsed_time": "4:39:09", "remaining_time": "3:04:25"}
+{"current_steps": 2550, "total_steps": 4218, "loss": 0.0069, "lr": 4.058053650563747e-06, "epoch": 1.8136557610241821, "percentage": 60.46, "elapsed_time": "4:40:22", "remaining_time": "3:03:24"}
+{"current_steps": 2560, "total_steps": 4218, "loss": 0.0084, "lr": 4.017447006730796e-06, "epoch": 1.8207681365576103, "percentage": 60.69, "elapsed_time": "4:41:44", "remaining_time": "3:02:28"}
+{"current_steps": 2570, "total_steps": 4218, "loss": 0.0068, "lr": 3.976907660693954e-06, "epoch": 1.8278805120910384, "percentage": 60.93, "elapsed_time": "4:42:38", "remaining_time": "3:01:14"}
+{"current_steps": 2580, "total_steps": 4218, "loss": 0.0091, "lr": 3.936438389106154e-06, "epoch": 1.8349928876244666, "percentage": 61.17, "elapsed_time": "4:43:58", "remaining_time": "3:00:17"}
+{"current_steps": 2590, "total_steps": 4218, "loss": 0.0105, "lr": 3.896041963820724e-06, "epoch": 1.8421052631578947, "percentage": 61.4, "elapsed_time": "4:44:57", "remaining_time": "2:59:07"}
+{"current_steps": 2600, "total_steps": 4218, "loss": 0.0099, "lr": 3.855721151701548e-06, "epoch": 1.8492176386913228, "percentage": 61.64, "elapsed_time": "4:46:06", "remaining_time": "2:58:03"}
+{"current_steps": 2610, "total_steps": 4218, "loss": 0.0095, "lr": 3.815478714433559e-06, "epoch": 1.856330014224751, "percentage": 61.88, "elapsed_time": "4:47:22", "remaining_time": "2:57:03"}
+{"current_steps": 2620, "total_steps": 4218, "loss": 0.0105, "lr": 3.775317408333571e-06, "epoch": 1.863442389758179, "percentage": 62.11, "elapsed_time": "4:48:21", "remaining_time": "2:55:52"}
+{"current_steps": 2630, "total_steps": 4218, "loss": 0.0082, "lr": 3.7352399841614996e-06, "epoch": 1.8705547652916072, "percentage": 62.35, "elapsed_time": "4:49:33", "remaining_time": "2:54:50"}
+{"current_steps": 2640, "total_steps": 4218, "loss": 0.0087, "lr": 3.695249186931954e-06, "epoch": 1.8776671408250356, "percentage": 62.59, "elapsed_time": "4:50:36", "remaining_time": "2:53:42"}
+{"current_steps": 2650, "total_steps": 4218, "loss": 0.0076, "lr": 3.655347755726224e-06, "epoch": 1.8847795163584637, "percentage": 62.83, "elapsed_time": "4:51:40", "remaining_time": "2:52:34"}
+{"current_steps": 2660, "total_steps": 4218, "loss": 0.0086, "lr": 3.6155384235046674e-06, "epoch": 1.8918918918918919, "percentage": 63.06, "elapsed_time": "4:52:46", "remaining_time": "2:51:28"}
+{"current_steps": 2670, "total_steps": 4218, "loss": 0.005, "lr": 3.5758239169195276e-06, "epoch": 1.89900426742532, "percentage": 63.3, "elapsed_time": "4:53:49", "remaining_time": "2:50:21"}
+{"current_steps": 2680, "total_steps": 4218, "loss": 0.0072, "lr": 3.5362069561281764e-06, "epoch": 1.9061166429587484, "percentage": 63.54, "elapsed_time": "4:54:49", "remaining_time": "2:49:11"}
+{"current_steps": 2690, "total_steps": 4218, "loss": 0.0072, "lr": 3.4966902546068016e-06, "epoch": 1.9132290184921765, "percentage": 63.77, "elapsed_time": "4:55:55", "remaining_time": "2:48:05"}
+{"current_steps": 2700, "total_steps": 4218, "loss": 0.0073, "lr": 3.4572765189645516e-06, "epoch": 1.9203413940256047, "percentage": 64.01, "elapsed_time": "4:57:07", "remaining_time": "2:47:03"}
+{"current_steps": 2710, "total_steps": 4218, "loss": 0.0067, "lr": 3.4179684487581555e-06, "epoch": 1.9274537695590328, "percentage": 64.25, "elapsed_time": "4:58:21", "remaining_time": "2:46:01"}
+{"current_steps": 2720, "total_steps": 4218, "loss": 0.0075, "lr": 3.3787687363070256e-06, "epoch": 1.934566145092461, "percentage": 64.49, "elapsed_time": "4:59:38", "remaining_time": "2:45:01"}
+{"current_steps": 2730, "total_steps": 4218, "loss": 0.0069, "lr": 3.3396800665088435e-06, "epoch": 1.941678520625889, "percentage": 64.72, "elapsed_time": "5:00:38", "remaining_time": "2:43:51"}
+{"current_steps": 2740, "total_steps": 4218, "loss": 0.0058, "lr": 3.300705116655672e-06, "epoch": 1.9487908961593172, "percentage": 64.96, "elapsed_time": "5:01:37", "remaining_time": "2:42:41"}
+{"current_steps": 2750, "total_steps": 4218, "loss": 0.0055, "lr": 3.26184655625058e-06, "epoch": 1.9559032716927454, "percentage": 65.2, "elapsed_time": "5:02:38", "remaining_time": "2:41:33"}
+{"current_steps": 2760, "total_steps": 4218, "loss": 0.0062, "lr": 3.2231070468247954e-06, "epoch": 1.9630156472261735, "percentage": 65.43, "elapsed_time": "5:03:29", "remaining_time": "2:40:19"}
+{"current_steps": 2770, "total_steps": 4218, "loss": 0.0063, "lr": 3.1844892417554102e-06, "epoch": 1.9701280227596016, "percentage": 65.67, "elapsed_time": "5:04:39", "remaining_time": "2:39:15"}
+{"current_steps": 2780, "total_steps": 4218, "loss": 0.0065, "lr": 3.1459957860836528e-06, "epoch": 1.9772403982930298, "percentage": 65.91, "elapsed_time": "5:05:44", "remaining_time": "2:38:08"}
+{"current_steps": 2790, "total_steps": 4218, "loss": 0.0068, "lr": 3.1076293163337074e-06, "epoch": 1.984352773826458, "percentage": 66.15, "elapsed_time": "5:06:48", "remaining_time": "2:37:01"}
+{"current_steps": 2800, "total_steps": 4218, "loss": 0.0057, "lr": 3.069392460332141e-06, "epoch": 1.991465149359886, "percentage": 66.38, "elapsed_time": "5:07:49", "remaining_time": "2:35:53"}
+{"current_steps": 2810, "total_steps": 4218, "loss": 0.0066, "lr": 3.031287837027911e-06, "epoch": 1.9985775248933144, "percentage": 66.62, "elapsed_time": "5:08:56", "remaining_time": "2:34:47"}
+{"current_steps": 2820, "total_steps": 4218, "loss": 0.0041, "lr": 2.9933180563129936e-06, "epoch": 2.0056899004267423, "percentage": 66.86, "elapsed_time": "5:10:06", "remaining_time": "2:33:44"}
+{"current_steps": 2830, "total_steps": 4218, "loss": 0.0056, "lr": 2.955485718843616e-06, "epoch": 2.012802275960171, "percentage": 67.09, "elapsed_time": "5:11:23", "remaining_time": "2:32:43"}
+{"current_steps": 2840, "total_steps": 4218, "loss": 0.0048, "lr": 2.917793415862129e-06, "epoch": 2.019914651493599, "percentage": 67.33, "elapsed_time": "5:12:25", "remaining_time": "2:31:35"}
+{"current_steps": 2850, "total_steps": 4218, "loss": 0.0038, "lr": 2.880243729019546e-06, "epoch": 2.027027027027027, "percentage": 67.57, "elapsed_time": "5:13:28", "remaining_time": "2:30:28"}
+{"current_steps": 2860, "total_steps": 4218, "loss": 0.0052, "lr": 2.842839230198685e-06, "epoch": 2.0341394025604553, "percentage": 67.8, "elapsed_time": "5:14:31", "remaining_time": "2:29:20"}
+{"current_steps": 2870, "total_steps": 4218, "loss": 0.0047, "lr": 2.805582481338044e-06, "epoch": 2.0412517780938835, "percentage": 68.04, "elapsed_time": "5:15:26", "remaining_time": "2:28:09"}
+{"current_steps": 2880, "total_steps": 4218, "loss": 0.0047, "lr": 2.7684760342563045e-06, "epoch": 2.0483641536273116, "percentage": 68.28, "elapsed_time": "5:16:29", "remaining_time": "2:27:02"}
+{"current_steps": 2890, "total_steps": 4218, "loss": 0.0056, "lr": 2.731522430477571e-06, "epoch": 2.0554765291607398, "percentage": 68.52, "elapsed_time": "5:17:23", "remaining_time": "2:25:50"}
+{"current_steps": 2900, "total_steps": 4218, "loss": 0.0048, "lr": 2.694724201057273e-06, "epoch": 2.062588904694168, "percentage": 68.75, "elapsed_time": "5:18:22", "remaining_time": "2:24:41"}
+{"current_steps": 2910, "total_steps": 4218, "loss": 0.0042, "lr": 2.6580838664088214e-06, "epoch": 2.069701280227596, "percentage": 68.99, "elapsed_time": "5:19:16", "remaining_time": "2:23:30"}
+{"current_steps": 2920, "total_steps": 4218, "loss": 0.0044, "lr": 2.6216039361309753e-06, "epoch": 2.076813655761024, "percentage": 69.23, "elapsed_time": "5:20:21", "remaining_time": "2:22:24"}
+{"current_steps": 2930, "total_steps": 4218, "loss": 0.0041, "lr": 2.5852869088359495e-06, "epoch": 2.0839260312944523, "percentage": 69.46, "elapsed_time": "5:21:40", "remaining_time": "2:21:24"}
+{"current_steps": 2940, "total_steps": 4218, "loss": 0.0032, "lr": 2.549135271978275e-06, "epoch": 2.0910384068278804, "percentage": 69.7, "elapsed_time": "5:23:03", "remaining_time": "2:20:26"}
+{"current_steps": 2950, "total_steps": 4218, "loss": 0.0046, "lr": 2.5131515016844345e-06, "epoch": 2.0981507823613086, "percentage": 69.94, "elapsed_time": "5:24:12", "remaining_time": "2:19:21"}
+{"current_steps": 2960, "total_steps": 4218, "loss": 0.0047, "lr": 2.4773380625832603e-06, "epoch": 2.1052631578947367, "percentage": 70.18, "elapsed_time": "5:25:20", "remaining_time": "2:18:16"}
+{"current_steps": 2970, "total_steps": 4218, "loss": 0.0039, "lr": 2.4416974076371304e-06, "epoch": 2.112375533428165, "percentage": 70.41, "elapsed_time": "5:26:20", "remaining_time": "2:17:07"}
+{"current_steps": 2980, "total_steps": 4218, "loss": 0.0037, "lr": 2.406231977973942e-06, "epoch": 2.119487908961593, "percentage": 70.65, "elapsed_time": "5:27:19", "remaining_time": "2:15:59"}
+{"current_steps": 2990, "total_steps": 4218, "loss": 0.0049, "lr": 2.3709442027199387e-06, "epoch": 2.126600284495021, "percentage": 70.89, "elapsed_time": "5:28:22", "remaining_time": "2:14:51"}
+{"current_steps": 3000, "total_steps": 4218, "loss": 0.0045, "lr": 2.3358364988333066e-06, "epoch": 2.1337126600284497, "percentage": 71.12, "elapsed_time": "5:29:06", "remaining_time": "2:13:37"}
+{"current_steps": 3010, "total_steps": 4218, "loss": 0.0052, "lr": 2.3009112709386454e-06, "epoch": 2.140825035561878, "percentage": 71.36, "elapsed_time": "5:30:18", "remaining_time": "2:12:33"}
+{"current_steps": 3020, "total_steps": 4218, "loss": 0.0047, "lr": 2.2661709111622666e-06, "epoch": 2.147937411095306, "percentage": 71.6, "elapsed_time": "5:31:31", "remaining_time": "2:11:30"}
+{"current_steps": 3030, "total_steps": 4218, "loss": 0.004, "lr": 2.2316177989683458e-06, "epoch": 2.155049786628734, "percentage": 71.83, "elapsed_time": "5:32:46", "remaining_time": "2:10:28"}
+{"current_steps": 3040, "total_steps": 4218, "loss": 0.0052, "lr": 2.197254300995953e-06, "epoch": 2.1621621621621623, "percentage": 72.07, "elapsed_time": "5:33:47", "remaining_time": "2:09:20"}
+{"current_steps": 3050, "total_steps": 4218, "loss": 0.0043, "lr": 2.163082770896943e-06, "epoch": 2.1692745376955904, "percentage": 72.31, "elapsed_time": "5:35:02", "remaining_time": "2:08:18"}
+{"current_steps": 3060, "total_steps": 4218, "loss": 0.0034, "lr": 2.1291055491747643e-06, "epoch": 2.1763869132290186, "percentage": 72.55, "elapsed_time": "5:36:16", "remaining_time": "2:07:15"}
+{"current_steps": 3070, "total_steps": 4218, "loss": 0.0039, "lr": 2.095324963024137e-06, "epoch": 2.1834992887624467, "percentage": 72.78, "elapsed_time": "5:37:01", "remaining_time": "2:06:01"}
+{"current_steps": 3080, "total_steps": 4218, "loss": 0.0038, "lr": 2.061743326171668e-06, "epoch": 2.190611664295875, "percentage": 73.02, "elapsed_time": "5:38:11", "remaining_time": "2:04:57"}
+{"current_steps": 3090, "total_steps": 4218, "loss": 0.0035, "lr": 2.02836293871736e-06, "epoch": 2.197724039829303, "percentage": 73.26, "elapsed_time": "5:39:11", "remaining_time": "2:03:49"}
+{"current_steps": 3100, "total_steps": 4218, "loss": 0.0038, "lr": 1.9951860869771e-06, "epoch": 2.204836415362731, "percentage": 73.49, "elapsed_time": "5:40:06", "remaining_time": "2:02:39"}
+{"current_steps": 3110, "total_steps": 4218, "loss": 0.004, "lr": 1.962215043326029e-06, "epoch": 2.2119487908961593, "percentage": 73.73, "elapsed_time": "5:41:22", "remaining_time": "2:01:37"}
+{"current_steps": 3120, "total_steps": 4218, "loss": 0.0036, "lr": 1.9294520660429284e-06, "epoch": 2.2190611664295874, "percentage": 73.97, "elapsed_time": "5:42:29", "remaining_time": "2:00:31"}
+{"current_steps": 3130, "total_steps": 4218, "loss": 0.0045, "lr": 1.8968993991555301e-06, "epoch": 2.2261735419630155, "percentage": 74.21, "elapsed_time": "5:43:31", "remaining_time": "1:59:24"}
+{"current_steps": 3140, "total_steps": 4218, "loss": 0.0041, "lr": 1.8645592722868223e-06, "epoch": 2.2332859174964437, "percentage": 74.44, "elapsed_time": "5:44:32", "remaining_time": "1:58:17"}
+{"current_steps": 3150, "total_steps": 4218, "loss": 0.0042, "lr": 1.8324339005023273e-06, "epoch": 2.240398293029872, "percentage": 74.68, "elapsed_time": "5:45:27", "remaining_time": "1:57:07"}
+{"current_steps": 3160, "total_steps": 4218, "loss": 0.0032, "lr": 1.8005254841584035e-06, "epoch": 2.2475106685633, "percentage": 74.92, "elapsed_time": "5:46:31", "remaining_time": "1:56:01"}
+{"current_steps": 3170, "total_steps": 4218, "loss": 0.0039, "lr": 1.768836208751516e-06, "epoch": 2.2546230440967285, "percentage": 75.15, "elapsed_time": "5:47:32", "remaining_time": "1:54:53"}
+{"current_steps": 3180, "total_steps": 4218, "loss": 0.004, "lr": 1.7373682447685624e-06, "epoch": 2.2617354196301562, "percentage": 75.39, "elapsed_time": "5:48:43", "remaining_time": "1:53:49"}
+{"current_steps": 3190, "total_steps": 4218, "loss": 0.0035, "lr": 1.706123747538196e-06, "epoch": 2.268847795163585, "percentage": 75.63, "elapsed_time": "5:49:50", "remaining_time": "1:52:44"}
+{"current_steps": 3200, "total_steps": 4218, "loss": 0.0041, "lr": 1.6751048570832184e-06, "epoch": 2.275960170697013, "percentage": 75.87, "elapsed_time": "5:50:41", "remaining_time": "1:51:33"}
+{"current_steps": 3210, "total_steps": 4218, "loss": 0.003, "lr": 1.6443136979739855e-06, "epoch": 2.283072546230441, "percentage": 76.1, "elapsed_time": "5:51:38", "remaining_time": "1:50:25"}
+{"current_steps": 3220, "total_steps": 4218, "loss": 0.0034, "lr": 1.6137523791829007e-06, "epoch": 2.2901849217638692, "percentage": 76.34, "elapsed_time": "5:52:51", "remaining_time": "1:49:21"}
+{"current_steps": 3230, "total_steps": 4218, "loss": 0.0034, "lr": 1.5834229939399637e-06, "epoch": 2.2972972972972974, "percentage": 76.58, "elapsed_time": "5:53:52", "remaining_time": "1:48:14"}
+{"current_steps": 3240, "total_steps": 4218, "loss": 0.0037, "lr": 1.5533276195893987e-06, "epoch": 2.3044096728307255, "percentage": 76.81, "elapsed_time": "5:55:00", "remaining_time": "1:47:09"}
+{"current_steps": 3250, "total_steps": 4218, "loss": 0.0039, "lr": 1.5234683174473669e-06, "epoch": 2.3115220483641536, "percentage": 77.05, "elapsed_time": "5:56:20", "remaining_time": "1:46:08"}
+{"current_steps": 3260, "total_steps": 4218, "loss": 0.0034, "lr": 1.493847132660789e-06, "epoch": 2.318634423897582, "percentage": 77.29, "elapsed_time": "5:57:30", "remaining_time": "1:45:03"}
+{"current_steps": 3270, "total_steps": 4218, "loss": 0.0044, "lr": 1.4644660940672628e-06, "epoch": 2.32574679943101, "percentage": 77.52, "elapsed_time": "5:58:24", "remaining_time": "1:43:54"}
+{"current_steps": 3280, "total_steps": 4218, "loss": 0.0036, "lr": 1.435327214056103e-06, "epoch": 2.332859174964438, "percentage": 77.76, "elapsed_time": "5:59:46", "remaining_time": "1:42:53"}
+{"current_steps": 3290, "total_steps": 4218, "loss": 0.0041, "lr": 1.406432488430508e-06, "epoch": 2.339971550497866, "percentage": 78.0, "elapsed_time": "6:01:02", "remaining_time": "1:41:50"}
+{"current_steps": 3300, "total_steps": 4218, "loss": 0.0035, "lr": 1.3777838962708602e-06, "epoch": 2.3470839260312943, "percentage": 78.24, "elapsed_time": "6:01:54", "remaining_time": "1:40:40"}
+{"current_steps": 3310, "total_steps": 4218, "loss": 0.0033, "lr": 1.3493833997991745e-06, "epoch": 2.3541963015647225, "percentage": 78.47, "elapsed_time": "6:02:48", "remaining_time": "1:39:31"}
+{"current_steps": 3320, "total_steps": 4218, "loss": 0.0042, "lr": 1.3212329442446985e-06, "epoch": 2.3613086770981506, "percentage": 78.71, "elapsed_time": "6:03:54", "remaining_time": "1:38:25"}
+{"current_steps": 3330, "total_steps": 4218, "loss": 0.0032, "lr": 1.2933344577106822e-06, "epoch": 2.3684210526315788, "percentage": 78.95, "elapsed_time": "6:05:09", "remaining_time": "1:37:22"}
+{"current_steps": 3340, "total_steps": 4218, "loss": 0.0031, "lr": 1.2656898510423122e-06, "epoch": 2.3755334281650073, "percentage": 79.18, "elapsed_time": "6:06:12", "remaining_time": "1:36:16"}
+{"current_steps": 3350, "total_steps": 4218, "loss": 0.0033, "lr": 1.2383010176958372e-06, "epoch": 2.382645803698435, "percentage": 79.42, "elapsed_time": "6:07:26", "remaining_time": "1:35:12"}
+{"current_steps": 3360, "total_steps": 4218, "loss": 0.0039, "lr": 1.2111698336088717e-06, "epoch": 2.3897581792318636, "percentage": 79.66, "elapsed_time": "6:08:25", "remaining_time": "1:34:04"}
+{"current_steps": 3370, "total_steps": 4218, "loss": 0.0034, "lr": 1.1842981570719237e-06, "epoch": 2.3968705547652918, "percentage": 79.9, "elapsed_time": "6:09:39", "remaining_time": "1:33:01"}
+{"current_steps": 3380, "total_steps": 4218, "loss": 0.0039, "lr": 1.157687828601094e-06, "epoch": 2.40398293029872, "percentage": 80.13, "elapsed_time": "6:10:46", "remaining_time": "1:31:55"}
+{"current_steps": 3390, "total_steps": 4218, "loss": 0.0033, "lr": 1.1313406708120327e-06, "epoch": 2.411095305832148, "percentage": 80.37, "elapsed_time": "6:11:55", "remaining_time": "1:30:50"}
+{"current_steps": 3400, "total_steps": 4218, "loss": 0.0032, "lr": 1.1052584882950896e-06, "epoch": 2.418207681365576, "percentage": 80.61, "elapsed_time": "6:13:21", "remaining_time": "1:29:49"}
+{"current_steps": 3410, "total_steps": 4218, "loss": 0.0029, "lr": 1.0794430674917262e-06, "epoch": 2.4253200568990043, "percentage": 80.84, "elapsed_time": "6:14:28", "remaining_time": "1:28:43"}
+{"current_steps": 3420, "total_steps": 4218, "loss": 0.0034, "lr": 1.0538961765721429e-06, "epoch": 2.4324324324324325, "percentage": 81.08, "elapsed_time": "6:15:22", "remaining_time": "1:27:35"}
+{"current_steps": 3430, "total_steps": 4218, "loss": 0.0033, "lr": 1.0286195653141822e-06, "epoch": 2.4395448079658606, "percentage": 81.32, "elapsed_time": "6:16:22", "remaining_time": "1:26:27"}
+{"current_steps": 3440, "total_steps": 4218, "loss": 0.0033, "lr": 1.0036149649834786e-06, "epoch": 2.4466571834992887, "percentage": 81.56, "elapsed_time": "6:17:21", "remaining_time": "1:25:20"}
+{"current_steps": 3450, "total_steps": 4218, "loss": 0.0032, "lr": 9.788840882148803e-07, "epoch": 2.453769559032717, "percentage": 81.79, "elapsed_time": "6:18:35", "remaining_time": "1:24:16"}
+{"current_steps": 3460, "total_steps": 4218, "loss": 0.0028, "lr": 9.544286288951393e-07, "epoch": 2.460881934566145, "percentage": 82.03, "elapsed_time": "6:19:35", "remaining_time": "1:23:09"}
+{"current_steps": 3470, "total_steps": 4218, "loss": 0.003, "lr": 9.302502620469073e-07, "epoch": 2.467994310099573, "percentage": 82.27, "elapsed_time": "6:20:42", "remaining_time": "1:22:03"}
+{"current_steps": 3480, "total_steps": 4218, "loss": 0.0033, "lr": 9.063506437139901e-07, "epoch": 2.4751066856330013, "percentage": 82.5, "elapsed_time": "6:21:49", "remaining_time": "1:20:58"}
+{"current_steps": 3490, "total_steps": 4218, "loss": 0.0035, "lr": 8.827314108479357e-07, "epoch": 2.4822190611664294, "percentage": 82.74, "elapsed_time": "6:23:03", "remaining_time": "1:19:54"}
+{"current_steps": 3500, "total_steps": 4218, "loss": 0.0037, "lr": 8.593941811959078e-07, "epoch": 2.4893314366998576, "percentage": 82.98, "elapsed_time": "6:24:00", "remaining_time": "1:18:46"}
+{"current_steps": 3510, "total_steps": 4218, "loss": 0.0035, "lr": 8.363405531898833e-07, "epoch": 2.496443812233286, "percentage": 83.21, "elapsed_time": "6:24:53", "remaining_time": "1:17:38"}
+{"current_steps": 3520, "total_steps": 4218, "loss": 0.0038, "lr": 8.135721058371681e-07, "epoch": 2.503556187766714, "percentage": 83.45, "elapsed_time": "6:25:57", "remaining_time": "1:16:31"}
+{"current_steps": 3530, "total_steps": 4218, "loss": 0.0023, "lr": 7.910903986122537e-07, "epoch": 2.5106685633001424, "percentage": 83.69, "elapsed_time": "6:26:57", "remaining_time": "1:15:25"}
+{"current_steps": 3540, "total_steps": 4218, "loss": 0.0033, "lr": 7.688969713499983e-07, "epoch": 2.5177809388335706, "percentage": 83.93, "elapsed_time": "6:28:22", "remaining_time": "1:14:22"}
+{"current_steps": 3550, "total_steps": 4218, "loss": 0.0036, "lr": 7.469933441401606e-07, "epoch": 2.5248933143669987, "percentage": 84.16, "elapsed_time": "6:29:32", "remaining_time": "1:13:18"}
+{"current_steps": 3560, "total_steps": 4218, "loss": 0.0029, "lr": 7.253810172232867e-07, "epoch": 2.532005689900427, "percentage": 84.4, "elapsed_time": "6:30:41", "remaining_time": "1:12:12"}
+{"current_steps": 3570, "total_steps": 4218, "loss": 0.0031, "lr": 7.040614708879489e-07, "epoch": 2.539118065433855, "percentage": 84.64, "elapsed_time": "6:31:37", "remaining_time": "1:11:05"}
+{"current_steps": 3580, "total_steps": 4218, "loss": 0.0031, "lr": 6.830361653693673e-07, "epoch": 2.546230440967283, "percentage": 84.87, "elapsed_time": "6:32:53", "remaining_time": "1:10:01"}
+{"current_steps": 3590, "total_steps": 4218, "loss": 0.0031, "lr": 6.623065407493801e-07, "epoch": 2.5533428165007113, "percentage": 85.11, "elapsed_time": "6:34:02", "remaining_time": "1:08:55"}
+{"current_steps": 3600, "total_steps": 4218, "loss": 0.0029, "lr": 6.418740168578208e-07, "epoch": 2.5604551920341394, "percentage": 85.35, "elapsed_time": "6:35:19", "remaining_time": "1:07:51"}
+{"current_steps": 3610, "total_steps": 4218, "loss": 0.0031, "lr": 6.217399931752627e-07, "epoch": 2.5675675675675675, "percentage": 85.59, "elapsed_time": "6:36:16", "remaining_time": "1:06:44"}
+{"current_steps": 3620, "total_steps": 4218, "loss": 0.0028, "lr": 6.019058487371687e-07, "epoch": 2.5746799431009957, "percentage": 85.82, "elapsed_time": "6:37:08", "remaining_time": "1:05:36"}
+{"current_steps": 3630, "total_steps": 4218, "loss": 0.0037, "lr": 5.82372942039432e-07, "epoch": 2.581792318634424, "percentage": 86.06, "elapsed_time": "6:38:04", "remaining_time": "1:04:28"}
+{"current_steps": 3640, "total_steps": 4218, "loss": 0.003, "lr": 5.631426109453364e-07, "epoch": 2.588904694167852, "percentage": 86.3, "elapsed_time": "6:39:11", "remaining_time": "1:03:23"}
+{"current_steps": 3650, "total_steps": 4218, "loss": 0.0032, "lr": 5.44216172593916e-07, "epoch": 2.59601706970128, "percentage": 86.53, "elapsed_time": "6:40:18", "remaining_time": "1:02:17"}
+{"current_steps": 3660, "total_steps": 4218, "loss": 0.0035, "lr": 5.255949233097451e-07, "epoch": 2.6031294452347082, "percentage": 86.77, "elapsed_time": "6:41:31", "remaining_time": "1:01:12"}
+{"current_steps": 3670, "total_steps": 4218, "loss": 0.0032, "lr": 5.072801385141429e-07, "epoch": 2.6102418207681364, "percentage": 87.01, "elapsed_time": "6:42:56", "remaining_time": "1:00:09"}
+{"current_steps": 3680, "total_steps": 4218, "loss": 0.0027, "lr": 4.89273072637827e-07, "epoch": 2.617354196301565, "percentage": 87.25, "elapsed_time": "6:43:51", "remaining_time": "0:59:02"}
+{"current_steps": 3690, "total_steps": 4218, "loss": 0.0029, "lr": 4.7157495903498105e-07, "epoch": 2.6244665718349927, "percentage": 87.48, "elapsed_time": "6:45:04", "remaining_time": "0:57:57"}
+{"current_steps": 3700, "total_steps": 4218, "loss": 0.0035, "lr": 4.541870098987911e-07, "epoch": 2.6315789473684212, "percentage": 87.72, "elapsed_time": "6:46:07", "remaining_time": "0:56:51"}
+{"current_steps": 3710, "total_steps": 4218, "loss": 0.0039, "lr": 4.371104161784073e-07, "epoch": 2.6386913229018494, "percentage": 87.96, "elapsed_time": "6:47:14", "remaining_time": "0:55:45"}
+{"current_steps": 3720, "total_steps": 4218, "loss": 0.003, "lr": 4.2034634749738623e-07, "epoch": 2.6458036984352775, "percentage": 88.19, "elapsed_time": "6:48:19", "remaining_time": "0:54:39"}
+{"current_steps": 3730, "total_steps": 4218, "loss": 0.0032, "lr": 4.038959520735658e-07, "epoch": 2.6529160739687057, "percentage": 88.43, "elapsed_time": "6:49:17", "remaining_time": "0:53:32"}
+{"current_steps": 3740, "total_steps": 4218, "loss": 0.0033, "lr": 3.8776035664043033e-07, "epoch": 2.660028449502134, "percentage": 88.67, "elapsed_time": "6:50:18", "remaining_time": "0:52:26"}
+{"current_steps": 3750, "total_steps": 4218, "loss": 0.0036, "lr": 3.719406663699349e-07, "epoch": 2.667140825035562, "percentage": 88.9, "elapsed_time": "6:51:10", "remaining_time": "0:51:18"}
+{"current_steps": 3760, "total_steps": 4218, "loss": 0.0034, "lr": 3.564379647968064e-07, "epoch": 2.67425320056899, "percentage": 89.14, "elapsed_time": "6:52:30", "remaining_time": "0:50:14"}
+{"current_steps": 3770, "total_steps": 4218, "loss": 0.0029, "lr": 3.4125331374433414e-07, "epoch": 2.681365576102418, "percentage": 89.38, "elapsed_time": "6:53:20", "remaining_time": "0:49:07"}
+{"current_steps": 3780, "total_steps": 4218, "loss": 0.0027, "lr": 3.2638775325163517e-07, "epoch": 2.6884779516358464, "percentage": 89.62, "elapsed_time": "6:54:17", "remaining_time": "0:48:00"}
+{"current_steps": 3790, "total_steps": 4218, "loss": 0.0026, "lr": 3.1184230150243025e-07, "epoch": 2.6955903271692745, "percentage": 89.85, "elapsed_time": "6:55:21", "remaining_time": "0:46:54"}
+{"current_steps": 3800, "total_steps": 4218, "loss": 0.0027, "lr": 2.9761795475529375e-07, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "6:56:28", "remaining_time": "0:45:48"}
+{"current_steps": 3810, "total_steps": 4218, "loss": 0.0032, "lr": 2.8371568727542486e-07, "epoch": 2.7098150782361308, "percentage": 90.33, "elapsed_time": "6:57:42", "remaining_time": "0:44:43"}
+{"current_steps": 3820, "total_steps": 4218, "loss": 0.0027, "lr": 2.7013645126791446e-07, "epoch": 2.716927453769559, "percentage": 90.56, "elapsed_time": "6:58:29", "remaining_time": "0:43:36"}
+{"current_steps": 3830, "total_steps": 4218, "loss": 0.0031, "lr": 2.5688117681252677e-07, "epoch": 2.724039829302987, "percentage": 90.8, "elapsed_time": "6:59:31", "remaining_time": "0:42:30"}
+{"current_steps": 3840, "total_steps": 4218, "loss": 0.0027, "lr": 2.439507717999945e-07, "epoch": 2.731152204836415, "percentage": 91.04, "elapsed_time": "7:00:51", "remaining_time": "0:41:25"}
+{"current_steps": 3850, "total_steps": 4218, "loss": 0.0032, "lr": 2.3134612186983817e-07, "epoch": 2.7382645803698438, "percentage": 91.28, "elapsed_time": "7:01:37", "remaining_time": "0:40:18"}
+{"current_steps": 3860, "total_steps": 4218, "loss": 0.0032, "lr": 2.1906809034970057e-07, "epoch": 2.7453769559032715, "percentage": 91.51, "elapsed_time": "7:02:47", "remaining_time": "0:39:12"}
+{"current_steps": 3870, "total_steps": 4218, "loss": 0.0028, "lr": 2.0711751819622038e-07, "epoch": 2.7524893314367, "percentage": 91.75, "elapsed_time": "7:03:36", "remaining_time": "0:38:05"}
+{"current_steps": 3880, "total_steps": 4218, "loss": 0.0033, "lr": 1.954952239374286e-07, "epoch": 2.759601706970128, "percentage": 91.99, "elapsed_time": "7:04:44", "remaining_time": "0:37:00"}
+{"current_steps": 3890, "total_steps": 4218, "loss": 0.0028, "lr": 1.8420200361669137e-07, "epoch": 2.7667140825035563, "percentage": 92.22, "elapsed_time": "7:05:47", "remaining_time": "0:35:54"}
+{"current_steps": 3900, "total_steps": 4218, "loss": 0.0028, "lr": 1.732386307381767e-07, "epoch": 2.7738264580369845, "percentage": 92.46, "elapsed_time": "7:06:56", "remaining_time": "0:34:48"}
+{"current_steps": 3910, "total_steps": 4218, "loss": 0.0032, "lr": 1.6260585621388604e-07, "epoch": 2.7809388335704126, "percentage": 92.7, "elapsed_time": "7:07:56", "remaining_time": "0:33:42"}
+{"current_steps": 3920, "total_steps": 4218, "loss": 0.0033, "lr": 1.523044083122138e-07, "epoch": 2.7880512091038407, "percentage": 92.94, "elapsed_time": "7:09:09", "remaining_time": "0:32:37"}
+{"current_steps": 3930, "total_steps": 4218, "loss": 0.0034, "lr": 1.4233499260807194e-07, "epoch": 2.795163584637269, "percentage": 93.17, "elapsed_time": "7:10:04", "remaining_time": "0:31:31"}
+{"current_steps": 3940, "total_steps": 4218, "loss": 0.003, "lr": 1.326982919345582e-07, "epoch": 2.802275960170697, "percentage": 93.41, "elapsed_time": "7:11:11", "remaining_time": "0:30:25"}
+{"current_steps": 3950, "total_steps": 4218, "loss": 0.0026, "lr": 1.2339496633619218e-07, "epoch": 2.809388335704125, "percentage": 93.65, "elapsed_time": "7:12:14", "remaining_time": "0:29:19"}
+{"current_steps": 3960, "total_steps": 4218, "loss": 0.0026, "lr": 1.1442565302370146e-07, "epoch": 2.8165007112375533, "percentage": 93.88, "elapsed_time": "7:13:30", "remaining_time": "0:28:14"}
+{"current_steps": 3970, "total_steps": 4218, "loss": 0.0033, "lr": 1.0579096633038411e-07, "epoch": 2.8236130867709814, "percentage": 94.12, "elapsed_time": "7:14:32", "remaining_time": "0:27:08"}
+{"current_steps": 3980, "total_steps": 4218, "loss": 0.0029, "lr": 9.749149767002197e-08, "epoch": 2.8307254623044096, "percentage": 94.36, "elapsed_time": "7:15:35", "remaining_time": "0:26:02"}
+{"current_steps": 3990, "total_steps": 4218, "loss": 0.0038, "lr": 8.952781549638412e-08, "epoch": 2.8378378378378377, "percentage": 94.59, "elapsed_time": "7:16:39", "remaining_time": "0:24:57"}
+{"current_steps": 4000, "total_steps": 4218, "loss": 0.0028, "lr": 8.190046526428241e-08, "epoch": 2.844950213371266, "percentage": 94.83, "elapsed_time": "7:17:50", "remaining_time": "0:23:51"}
+{"current_steps": 4010, "total_steps": 4218, "loss": 0.0032, "lr": 7.460996939221643e-08, "epoch": 2.852062588904694, "percentage": 95.07, "elapsed_time": "7:19:05", "remaining_time": "0:22:46"}
+{"current_steps": 4020, "total_steps": 4218, "loss": 0.0034, "lr": 6.765682722659151e-08, "epoch": 2.8591749644381226, "percentage": 95.31, "elapsed_time": "7:20:09", "remaining_time": "0:21:40"}
+{"current_steps": 4030, "total_steps": 4218, "loss": 0.0026, "lr": 6.104151500751609e-08, "epoch": 2.8662873399715503, "percentage": 95.54, "elapsed_time": "7:21:25", "remaining_time": "0:20:35"}
+{"current_steps": 4040, "total_steps": 4218, "loss": 0.0035, "lr": 5.476448583618288e-08, "epoch": 2.873399715504979, "percentage": 95.78, "elapsed_time": "7:22:37", "remaining_time": "0:19:30"}
+{"current_steps": 4050, "total_steps": 4218, "loss": 0.0026, "lr": 4.8826169643832464e-08, "epoch": 2.8805120910384066, "percentage": 96.02, "elapsed_time": "7:23:44", "remaining_time": "0:18:24"}
+{"current_steps": 4060, "total_steps": 4218, "loss": 0.0032, "lr": 4.322697316231361e-08, "epoch": 2.887624466571835, "percentage": 96.25, "elapsed_time": "7:24:46", "remaining_time": "0:17:18"}
+{"current_steps": 4070, "total_steps": 4218, "loss": 0.0024, "lr": 3.796727989621385e-08, "epoch": 2.8947368421052633, "percentage": 96.49, "elapsed_time": "7:25:54", "remaining_time": "0:16:12"}
+{"current_steps": 4080, "total_steps": 4218, "loss": 0.003, "lr": 3.304745009660326e-08, "epoch": 2.9018492176386914, "percentage": 96.73, "elapsed_time": "7:27:13", "remaining_time": "0:15:07"}
+{"current_steps": 4090, "total_steps": 4218, "loss": 0.0028, "lr": 2.8467820736350903e-08, "epoch": 2.9089615931721196, "percentage": 96.97, "elapsed_time": "7:28:35", "remaining_time": "0:14:02"}
+{"current_steps": 4100, "total_steps": 4218, "loss": 0.003, "lr": 2.422870548705103e-08, "epoch": 2.9160739687055477, "percentage": 97.2, "elapsed_time": "7:29:40", "remaining_time": "0:12:56"}
+{"current_steps": 4110, "total_steps": 4218, "loss": 0.0032, "lr": 2.0330394697534726e-08, "epoch": 2.923186344238976, "percentage": 97.44, "elapsed_time": "7:30:40", "remaining_time": "0:11:50"}
+{"current_steps": 4120, "total_steps": 4218, "loss": 0.0033, "lr": 1.677315537398583e-08, "epoch": 2.930298719772404, "percentage": 97.68, "elapsed_time": "7:31:34", "remaining_time": "0:10:44"}
+{"current_steps": 4130, "total_steps": 4218, "loss": 0.003, "lr": 1.355723116165164e-08, "epoch": 2.937411095305832, "percentage": 97.91, "elapsed_time": "7:32:45", "remaining_time": "0:09:38"}
+{"current_steps": 4140, "total_steps": 4218, "loss": 0.003, "lr": 1.0682842328154086e-08, "epoch": 2.9445234708392602, "percentage": 98.15, "elapsed_time": "7:33:55", "remaining_time": "0:08:33"}
+{"current_steps": 4150, "total_steps": 4218, "loss": 0.0034, "lr": 8.150185748405092e-09, "epoch": 2.9516358463726884, "percentage": 98.39, "elapsed_time": "7:34:57", "remaining_time": "0:07:27"}
+{"current_steps": 4160, "total_steps": 4218, "loss": 0.0031, "lr": 5.959434891121274e-09, "epoch": 2.9587482219061165, "percentage": 98.62, "elapsed_time": "7:36:01", "remaining_time": "0:06:21"}
+{"current_steps": 4170, "total_steps": 4218, "loss": 0.0028, "lr": 4.110739806940656e-09, "epoch": 2.9658605974395447, "percentage": 98.86, "elapsed_time": "7:37:04", "remaining_time": "0:05:15"}
+{"current_steps": 4180, "total_steps": 4218, "loss": 0.0025, "lr": 2.604227118148117e-09, "epoch": 2.972972972972973, "percentage": 99.1, "elapsed_time": "7:38:17", "remaining_time": "0:04:09"}
+{"current_steps": 4190, "total_steps": 4218, "loss": 0.0028, "lr": 1.4400000100017741e-09, "epoch": 2.9800853485064014, "percentage": 99.34, "elapsed_time": "7:39:25", "remaining_time": "0:03:04"}
+{"current_steps": 4200, "total_steps": 4218, "loss": 0.0027, "lr": 6.181382236641887e-10, "epoch": 2.987197724039829, "percentage": 99.57, "elapsed_time": "7:40:25", "remaining_time": "0:01:58"}
+{"current_steps": 4210, "total_steps": 4218, "loss": 0.003, "lr": 1.3869805074284704e-10, "epoch": 2.9943100995732577, "percentage": 99.81, "elapsed_time": "7:41:31", "remaining_time": "0:00:52"}
+{"current_steps": 4218, "total_steps": 4218, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "7:42:27", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2990 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 4218,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007112375533428165,
+      "grad_norm": 45.94488445688017,
+      "learning_rate": 2.132701421800948e-07,
+      "loss": 4.9235,
+      "step": 10
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "grad_norm": 56.45310643883483,
+      "learning_rate": 4.502369668246446e-07,
+      "loss": 4.7616,
+      "step": 20
+    },
+    {
+      "epoch": 0.021337126600284494,
+      "grad_norm": 47.57072569736425,
+      "learning_rate": 6.872037914691944e-07,
+      "loss": 4.0518,
+      "step": 30
+    },
+    {
+      "epoch": 0.02844950213371266,
+      "grad_norm": 14.9615219454182,
+      "learning_rate": 9.241706161137441e-07,
+      "loss": 3.1168,
+      "step": 40
+    },
+    {
+      "epoch": 0.03556187766714083,
+      "grad_norm": 9.209691028948875,
+      "learning_rate": 1.161137440758294e-06,
+      "loss": 2.408,
+      "step": 50
+    },
+    {
+      "epoch": 0.04267425320056899,
+      "grad_norm": 3.738856271681981,
+      "learning_rate": 1.3981042654028437e-06,
+      "loss": 2.0996,
+      "step": 60
+    },
+    {
+      "epoch": 0.049786628733997154,
+      "grad_norm": 4.299210545328982,
+      "learning_rate": 1.6350710900473934e-06,
+      "loss": 1.961,
+      "step": 70
+    },
+    {
+      "epoch": 0.05689900426742532,
+      "grad_norm": 4.288339811445908,
+      "learning_rate": 1.8720379146919433e-06,
+      "loss": 1.8454,
+      "step": 80
+    },
+    {
+      "epoch": 0.06401137980085349,
+      "grad_norm": 4.487588443815648,
+      "learning_rate": 2.109004739336493e-06,
+      "loss": 1.8,
+      "step": 90
+    },
+    {
+      "epoch": 0.07112375533428165,
+      "grad_norm": 5.903658522691362,
+      "learning_rate": 2.345971563981043e-06,
+      "loss": 1.7189,
+      "step": 100
+    },
+    {
+      "epoch": 0.07823613086770982,
+      "grad_norm": 6.538803049950138,
+      "learning_rate": 2.5829383886255925e-06,
+      "loss": 1.6861,
+      "step": 110
+    },
+    {
+      "epoch": 0.08534850640113797,
+      "grad_norm": 6.420212036240461,
+      "learning_rate": 2.8199052132701426e-06,
+      "loss": 1.6933,
+      "step": 120
+    },
+    {
+      "epoch": 0.09246088193456614,
+      "grad_norm": 6.08601994925446,
+      "learning_rate": 3.0568720379146923e-06,
+      "loss": 1.6477,
+      "step": 130
+    },
+    {
+      "epoch": 0.09957325746799431,
+      "grad_norm": 6.641158507404538,
+      "learning_rate": 3.293838862559242e-06,
+      "loss": 1.5837,
+      "step": 140
+    },
+    {
+      "epoch": 0.10668563300142248,
+      "grad_norm": 5.6671416215198445,
+      "learning_rate": 3.5308056872037916e-06,
+      "loss": 1.553,
+      "step": 150
+    },
+    {
+      "epoch": 0.11379800853485064,
+      "grad_norm": 4.895576620125158,
+      "learning_rate": 3.7677725118483417e-06,
+      "loss": 1.601,
+      "step": 160
+    },
+    {
+      "epoch": 0.12091038406827881,
+      "grad_norm": 5.00629870941093,
+      "learning_rate": 4.004739336492891e-06,
+      "loss": 1.4953,
+      "step": 170
+    },
+    {
+      "epoch": 0.12802275960170698,
+      "grad_norm": 4.098161366916081,
+      "learning_rate": 4.2417061611374415e-06,
+      "loss": 1.4986,
+      "step": 180
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 4.279942094132115,
+      "learning_rate": 4.478672985781991e-06,
+      "loss": 1.4177,
+      "step": 190
+    },
+    {
+      "epoch": 0.1422475106685633,
+      "grad_norm": 2.9957264584301506,
+      "learning_rate": 4.715639810426541e-06,
+      "loss": 1.4234,
+      "step": 200
+    },
+    {
+      "epoch": 0.14935988620199148,
+      "grad_norm": 2.960846105003115,
+      "learning_rate": 4.952606635071091e-06,
+      "loss": 1.4034,
+      "step": 210
+    },
+    {
+      "epoch": 0.15647226173541964,
+      "grad_norm": 2.8142395090714207,
+      "learning_rate": 5.18957345971564e-06,
+      "loss": 1.4172,
+      "step": 220
+    },
+    {
+      "epoch": 0.16358463726884778,
+      "grad_norm": 3.1953820486960938,
+      "learning_rate": 5.42654028436019e-06,
+      "loss": 1.3695,
+      "step": 230
+    },
+    {
+      "epoch": 0.17069701280227595,
+      "grad_norm": 3.0329786581569813,
+      "learning_rate": 5.66350710900474e-06,
+      "loss": 1.3815,
+      "step": 240
+    },
+    {
+      "epoch": 0.17780938833570412,
+      "grad_norm": 3.023917167954777,
+      "learning_rate": 5.90047393364929e-06,
+      "loss": 1.3494,
+      "step": 250
+    },
+    {
+      "epoch": 0.18492176386913228,
+      "grad_norm": 3.3061969408501186,
+      "learning_rate": 6.137440758293839e-06,
+      "loss": 1.351,
+      "step": 260
+    },
+    {
+      "epoch": 0.19203413940256045,
+      "grad_norm": 3.0703691360984116,
+      "learning_rate": 6.374407582938389e-06,
+      "loss": 1.3007,
+      "step": 270
+    },
+    {
+      "epoch": 0.19914651493598862,
+      "grad_norm": 2.6510030082143072,
+      "learning_rate": 6.611374407582939e-06,
+      "loss": 1.2318,
+      "step": 280
+    },
+    {
+      "epoch": 0.20625889046941678,
+      "grad_norm": 2.781634197302321,
+      "learning_rate": 6.848341232227489e-06,
+      "loss": 1.2452,
+      "step": 290
+    },
+    {
+      "epoch": 0.21337126600284495,
+      "grad_norm": 2.889926592158047,
+      "learning_rate": 7.085308056872039e-06,
+      "loss": 1.2299,
+      "step": 300
+    },
+    {
+      "epoch": 0.22048364153627312,
+      "grad_norm": 2.9460513709926546,
+      "learning_rate": 7.322274881516588e-06,
+      "loss": 1.2481,
+      "step": 310
+    },
+    {
+      "epoch": 0.22759601706970128,
+      "grad_norm": 3.117250263470296,
+      "learning_rate": 7.559241706161138e-06,
+      "loss": 1.1874,
+      "step": 320
+    },
+    {
+      "epoch": 0.23470839260312945,
+      "grad_norm": 3.1068660585891443,
+      "learning_rate": 7.796208530805689e-06,
+      "loss": 1.242,
+      "step": 330
+    },
+    {
+      "epoch": 0.24182076813655762,
+      "grad_norm": 3.2303235755610458,
+      "learning_rate": 8.033175355450237e-06,
+      "loss": 1.1656,
+      "step": 340
+    },
+    {
+      "epoch": 0.24893314366998578,
+      "grad_norm": 3.380471682074544,
+      "learning_rate": 8.270142180094787e-06,
+      "loss": 1.1626,
+      "step": 350
+    },
+    {
+      "epoch": 0.25604551920341395,
+      "grad_norm": 3.0003799025494455,
+      "learning_rate": 8.507109004739337e-06,
+      "loss": 1.1136,
+      "step": 360
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 3.3507131315688037,
+      "learning_rate": 8.744075829383887e-06,
+      "loss": 1.109,
+      "step": 370
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 3.286430938699654,
+      "learning_rate": 8.981042654028437e-06,
+      "loss": 1.0926,
+      "step": 380
+    },
+    {
+      "epoch": 0.2773826458036984,
+      "grad_norm": 3.543025306575121,
+      "learning_rate": 9.218009478672988e-06,
+      "loss": 0.9856,
+      "step": 390
+    },
+    {
+      "epoch": 0.2844950213371266,
+      "grad_norm": 2.9641151250477,
+      "learning_rate": 9.454976303317538e-06,
+      "loss": 1.0438,
+      "step": 400
+    },
+    {
+      "epoch": 0.29160739687055476,
+      "grad_norm": 3.0879210891464175,
+      "learning_rate": 9.691943127962086e-06,
+      "loss": 0.9834,
+      "step": 410
+    },
+    {
+      "epoch": 0.29871977240398295,
+      "grad_norm": 3.5828764512704274,
+      "learning_rate": 9.928909952606636e-06,
+      "loss": 1.0355,
+      "step": 420
+    },
+    {
+      "epoch": 0.3058321479374111,
+      "grad_norm": 3.0432346994349944,
+      "learning_rate": 9.99991609608766e-06,
+      "loss": 0.9973,
+      "step": 430
+    },
+    {
+      "epoch": 0.3129445234708393,
+      "grad_norm": 3.6852442122283384,
+      "learning_rate": 9.999505144928566e-06,
+      "loss": 1.0118,
+      "step": 440
+    },
+    {
+      "epoch": 0.3200568990042674,
+      "grad_norm": 3.4571934113589893,
+      "learning_rate": 9.998751763712045e-06,
+      "loss": 0.915,
+      "step": 450
+    },
+    {
+      "epoch": 0.32716927453769556,
+      "grad_norm": 3.3733896978659215,
+      "learning_rate": 9.997656004039284e-06,
+      "loss": 0.8872,
+      "step": 460
+    },
+    {
+      "epoch": 0.33428165007112376,
+      "grad_norm": 3.1986482463279344,
+      "learning_rate": 9.99621794096192e-06,
+      "loss": 0.9233,
+      "step": 470
+    },
+    {
+      "epoch": 0.3413940256045519,
+      "grad_norm": 3.3781480125146217,
+      "learning_rate": 9.994437672976904e-06,
+      "loss": 0.8156,
+      "step": 480
+    },
+    {
+      "epoch": 0.3485064011379801,
+      "grad_norm": 3.6561286544224516,
+      "learning_rate": 9.99231532201976e-06,
+      "loss": 0.8749,
+      "step": 490
+    },
+    {
+      "epoch": 0.35561877667140823,
+      "grad_norm": 4.142627644307138,
+      "learning_rate": 9.989851033456224e-06,
+      "loss": 0.8598,
+      "step": 500
+    },
+    {
+      "epoch": 0.3627311522048364,
+      "grad_norm": 3.7494771233239828,
+      "learning_rate": 9.987044976072298e-06,
+      "loss": 0.8118,
+      "step": 510
+    },
+    {
+      "epoch": 0.36984352773826457,
+      "grad_norm": 3.6547956812812123,
+      "learning_rate": 9.983897342062681e-06,
+      "loss": 0.8227,
+      "step": 520
+    },
+    {
+      "epoch": 0.37695590327169276,
+      "grad_norm": 3.679890083139226,
+      "learning_rate": 9.98040834701761e-06,
+      "loss": 0.8132,
+      "step": 530
+    },
+    {
+      "epoch": 0.3840682788051209,
+      "grad_norm": 3.252191257909053,
+      "learning_rate": 9.97657822990809e-06,
+      "loss": 0.7806,
+      "step": 540
+    },
+    {
+      "epoch": 0.3911806543385491,
+      "grad_norm": 3.614922960561001,
+      "learning_rate": 9.972407253069527e-06,
+      "loss": 0.8095,
+      "step": 550
+    },
+    {
+      "epoch": 0.39829302987197723,
+      "grad_norm": 3.793537378483368,
+      "learning_rate": 9.967895702183767e-06,
+      "loss": 0.7911,
+      "step": 560
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 3.65980827340659,
+      "learning_rate": 9.963043886259518e-06,
+      "loss": 0.7712,
+      "step": 570
+    },
+    {
+      "epoch": 0.41251778093883357,
+      "grad_norm": 3.5164539759645037,
+      "learning_rate": 9.957852137611187e-06,
+      "loss": 0.7634,
+      "step": 580
+    },
+    {
+      "epoch": 0.41963015647226176,
+      "grad_norm": 3.3236842648189633,
+      "learning_rate": 9.952320811836129e-06,
+      "loss": 0.6903,
+      "step": 590
+    },
+    {
+      "epoch": 0.4267425320056899,
+      "grad_norm": 3.294343434220933,
+      "learning_rate": 9.94645028779028e-06,
+      "loss": 0.7238,
+      "step": 600
+    },
+    {
+      "epoch": 0.43385490753911804,
+      "grad_norm": 3.4974393759929208,
+      "learning_rate": 9.94024096756221e-06,
+      "loss": 0.694,
+      "step": 610
+    },
+    {
+      "epoch": 0.44096728307254623,
+      "grad_norm": 4.433758888856019,
+      "learning_rate": 9.933693276445588e-06,
+      "loss": 0.7057,
+      "step": 620
+    },
+    {
+      "epoch": 0.4480796586059744,
+      "grad_norm": 3.3896425434092503,
+      "learning_rate": 9.92680766291005e-06,
+      "loss": 0.7001,
+      "step": 630
+    },
+    {
+      "epoch": 0.45519203413940257,
+      "grad_norm": 3.2995707993625834,
+      "learning_rate": 9.91958459857048e-06,
+      "loss": 0.6451,
+      "step": 640
+    },
+    {
+      "epoch": 0.4623044096728307,
+      "grad_norm": 3.5589453987217805,
+      "learning_rate": 9.912024578154706e-06,
+      "loss": 0.6539,
+      "step": 650
+    },
+    {
+      "epoch": 0.4694167852062589,
+      "grad_norm": 3.457156793924661,
+      "learning_rate": 9.904128119469625e-06,
+      "loss": 0.6383,
+      "step": 660
+    },
+    {
+      "epoch": 0.47652916073968704,
+      "grad_norm": 3.791061357289613,
+      "learning_rate": 9.895895763365722e-06,
+      "loss": 0.6319,
+      "step": 670
+    },
+    {
+      "epoch": 0.48364153627311524,
+      "grad_norm": 3.7253719001786307,
+      "learning_rate": 9.88732807370004e-06,
+      "loss": 0.589,
+      "step": 680
+    },
+    {
+      "epoch": 0.4907539118065434,
+      "grad_norm": 3.8753257386340167,
+      "learning_rate": 9.878425637297549e-06,
+      "loss": 0.5236,
+      "step": 690
+    },
+    {
+      "epoch": 0.49786628733997157,
+      "grad_norm": 3.810036186400155,
+      "learning_rate": 9.869189063910959e-06,
+      "loss": 0.524,
+      "step": 700
+    },
+    {
+      "epoch": 0.5049786628733998,
+      "grad_norm": 4.2180281642967365,
+      "learning_rate": 9.859618986178953e-06,
+      "loss": 0.5336,
+      "step": 710
+    },
+    {
+      "epoch": 0.5120910384068279,
+      "grad_norm": 3.938273345051735,
+      "learning_rate": 9.84971605958286e-06,
+      "loss": 0.5202,
+      "step": 720
+    },
+    {
+      "epoch": 0.519203413940256,
+      "grad_norm": 3.5712127017141397,
+      "learning_rate": 9.839480962401753e-06,
+      "loss": 0.4938,
+      "step": 730
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 3.383580945232286,
+      "learning_rate": 9.828914395665996e-06,
+      "loss": 0.4503,
+      "step": 740
+    },
+    {
+      "epoch": 0.5334281650071123,
+      "grad_norm": 3.850151538007975,
+      "learning_rate": 9.818017083109233e-06,
+      "loss": 0.5067,
+      "step": 750
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 3.579242735091459,
+      "learning_rate": 9.8067897711188e-06,
+      "loss": 0.4296,
+      "step": 760
+    },
+    {
+      "epoch": 0.5476529160739687,
+      "grad_norm": 3.33637898169204,
+      "learning_rate": 9.795233228684631e-06,
+      "loss": 0.422,
+      "step": 770
+    },
+    {
+      "epoch": 0.5547652916073968,
+      "grad_norm": 3.3180173487560998,
+      "learning_rate": 9.783348247346558e-06,
+      "loss": 0.4352,
+      "step": 780
+    },
+    {
+      "epoch": 0.561877667140825,
+      "grad_norm": 3.3074859328364172,
+      "learning_rate": 9.771135641140117e-06,
+      "loss": 0.3788,
+      "step": 790
+    },
+    {
+      "epoch": 0.5689900426742532,
+      "grad_norm": 3.935128904527344,
+      "learning_rate": 9.758596246540782e-06,
+      "loss": 0.4512,
+      "step": 800
+    },
+    {
+      "epoch": 0.5761024182076814,
+      "grad_norm": 3.130800872692149,
+      "learning_rate": 9.74573092240668e-06,
+      "loss": 0.4286,
+      "step": 810
+    },
+    {
+      "epoch": 0.5832147937411095,
+      "grad_norm": 3.4818017716980076,
+      "learning_rate": 9.732540549919758e-06,
+      "loss": 0.3976,
+      "step": 820
+    },
+    {
+      "epoch": 0.5903271692745377,
+      "grad_norm": 3.7176422056718708,
+      "learning_rate": 9.719026032525432e-06,
+      "loss": 0.3845,
+      "step": 830
+    },
+    {
+      "epoch": 0.5974395448079659,
+      "grad_norm": 4.0428367587373115,
+      "learning_rate": 9.70518829587071e-06,
+      "loss": 0.3761,
+      "step": 840
+    },
+    {
+      "epoch": 0.604551920341394,
+      "grad_norm": 3.32333703731893,
+      "learning_rate": 9.691028287740783e-06,
+      "loss": 0.3663,
+      "step": 850
+    },
+    {
+      "epoch": 0.6116642958748222,
+      "grad_norm": 4.055447477108677,
+      "learning_rate": 9.67654697799412e-06,
+      "loss": 0.3683,
+      "step": 860
+    },
+    {
+      "epoch": 0.6187766714082503,
+      "grad_norm": 2.801736293850873,
+      "learning_rate": 9.661745358496033e-06,
+      "loss": 0.3302,
+      "step": 870
+    },
+    {
+      "epoch": 0.6258890469416786,
+      "grad_norm": 2.9454979478833576,
+      "learning_rate": 9.64662444305074e-06,
+      "loss": 0.3714,
+      "step": 880
+    },
+    {
+      "epoch": 0.6330014224751067,
+      "grad_norm": 3.933969741535959,
+      "learning_rate": 9.631185267331937e-06,
+      "loss": 0.3214,
+      "step": 890
+    },
+    {
+      "epoch": 0.6401137980085349,
+      "grad_norm": 3.0707180797561398,
+      "learning_rate": 9.615428888811842e-06,
+      "loss": 0.3151,
+      "step": 900
+    },
+    {
+      "epoch": 0.647226173541963,
+      "grad_norm": 3.6006782352295095,
+      "learning_rate": 9.59935638668879e-06,
+      "loss": 0.3134,
+      "step": 910
+    },
+    {
+      "epoch": 0.6543385490753911,
+      "grad_norm": 4.528381319074012,
+      "learning_rate": 9.582968861813295e-06,
+      "loss": 0.2826,
+      "step": 920
+    },
+    {
+      "epoch": 0.6614509246088194,
+      "grad_norm": 3.084970600037643,
+      "learning_rate": 9.566267436612662e-06,
+      "loss": 0.3272,
+      "step": 930
+    },
+    {
+      "epoch": 0.6685633001422475,
+      "grad_norm": 3.1926454881670008,
+      "learning_rate": 9.549253255014105e-06,
+      "loss": 0.2838,
+      "step": 940
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 3.3232334022391083,
+      "learning_rate": 9.531927482366398e-06,
+      "loss": 0.2676,
+      "step": 950
+    },
+    {
+      "epoch": 0.6827880512091038,
+      "grad_norm": 3.373450413027547,
+      "learning_rate": 9.514291305360053e-06,
+      "loss": 0.2615,
+      "step": 960
+    },
+    {
+      "epoch": 0.689900426742532,
+      "grad_norm": 3.298511219641843,
+      "learning_rate": 9.496345931946039e-06,
+      "loss": 0.2232,
+      "step": 970
+    },
+    {
+      "epoch": 0.6970128022759602,
+      "grad_norm": 2.8709213001564726,
+      "learning_rate": 9.47809259125306e-06,
+      "loss": 0.2628,
+      "step": 980
+    },
+    {
+      "epoch": 0.7041251778093883,
+      "grad_norm": 3.0027633203506,
+      "learning_rate": 9.459532533503347e-06,
+      "loss": 0.2404,
+      "step": 990
+    },
+    {
+      "epoch": 0.7112375533428165,
+      "grad_norm": 3.0886670354052823,
+      "learning_rate": 9.440667029927043e-06,
+      "loss": 0.2259,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7183499288762447,
+      "grad_norm": 3.413560155663082,
+      "learning_rate": 9.421497372675133e-06,
+      "loss": 0.208,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7254623044096729,
+      "grad_norm": 2.26900305381711,
+      "learning_rate": 9.402024874730928e-06,
+      "loss": 0.2277,
+      "step": 1020
+    },
+    {
+      "epoch": 0.732574679943101,
+      "grad_norm": 3.5894430284698315,
+      "learning_rate": 9.382250869820146e-06,
+      "loss": 0.1926,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7396870554765291,
+      "grad_norm": 3.267737905170995,
+      "learning_rate": 9.36217671231956e-06,
+      "loss": 0.2299,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7467994310099573,
+      "grad_norm": 2.7538943048992737,
+      "learning_rate": 9.341803777164228e-06,
+      "loss": 0.1708,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7539118065433855,
+      "grad_norm": 3.867540040555883,
+      "learning_rate": 9.321133459753322e-06,
+      "loss": 0.2072,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7610241820768137,
+      "grad_norm": 2.3384449104832226,
+      "learning_rate": 9.300167175854564e-06,
+      "loss": 0.1875,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7681365576102418,
+      "grad_norm": 3.6436777076779348,
+      "learning_rate": 9.278906361507238e-06,
+      "loss": 0.173,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7752489331436699,
+      "grad_norm": 2.623342004246653,
+      "learning_rate": 9.257352472923842e-06,
+      "loss": 0.1489,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7823613086770982,
+      "grad_norm": 2.9293688128652606,
+      "learning_rate": 9.235506986390346e-06,
+      "loss": 0.1423,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 3.1229986788680653,
+      "learning_rate": 9.213371398165077e-06,
+      "loss": 0.1564,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7965860597439545,
+      "grad_norm": 3.5638406658438826,
+      "learning_rate": 9.190947224376238e-06,
+      "loss": 0.1872,
+      "step": 1120
+    },
+    {
+      "epoch": 0.8036984352773826,
+      "grad_norm": 3.754826640146973,
+      "learning_rate": 9.168236000918063e-06,
+      "loss": 0.1483,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 2.494125324383473,
+      "learning_rate": 9.145239283345618e-06,
+      "loss": 0.1272,
+      "step": 1140
+    },
+    {
+      "epoch": 0.817923186344239,
+      "grad_norm": 2.1750463421723003,
+      "learning_rate": 9.121958646768251e-06,
+      "loss": 0.1361,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8250355618776671,
+      "grad_norm": 2.6835693031385035,
+      "learning_rate": 9.09839568574173e-06,
+      "loss": 0.1001,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8321479374110953,
+      "grad_norm": 2.520530993255376,
+      "learning_rate": 9.074552014158994e-06,
+      "loss": 0.1193,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8392603129445235,
+      "grad_norm": 2.583475505711053,
+      "learning_rate": 9.050429265139647e-06,
+      "loss": 0.1122,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8463726884779517,
+      "grad_norm": 3.0551608668064736,
+      "learning_rate": 9.026029090918076e-06,
+      "loss": 0.1345,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8534850640113798,
+      "grad_norm": 2.7079152732306917,
+      "learning_rate": 9.001353162730297e-06,
+      "loss": 0.1134,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8605974395448079,
+      "grad_norm": 2.2611924634890075,
+      "learning_rate": 8.976403170699486e-06,
+      "loss": 0.1026,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8677098150782361,
+      "grad_norm": 1.987002883566529,
+      "learning_rate": 8.951180823720212e-06,
+      "loss": 0.0967,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8748221906116643,
+      "grad_norm": 2.7967317585114615,
+      "learning_rate": 8.925687849341398e-06,
+      "loss": 0.0819,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8819345661450925,
+      "grad_norm": 2.65859268119004,
+      "learning_rate": 8.899925993647994e-06,
+      "loss": 0.0931,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8890469416785206,
+      "grad_norm": 2.5541801040927226,
+      "learning_rate": 8.873897021141378e-06,
+      "loss": 0.0888,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8961593172119487,
+      "grad_norm": 2.6513786896328413,
+      "learning_rate": 8.847602714618504e-06,
+      "loss": 0.0839,
+      "step": 1260
+    },
+    {
+      "epoch": 0.903271692745377,
+      "grad_norm": 2.3497391818693587,
+      "learning_rate": 8.821044875049796e-06,
+      "loss": 0.0878,
+      "step": 1270
+    },
+    {
+      "epoch": 0.9103840682788051,
+      "grad_norm": 2.067880100094928,
+      "learning_rate": 8.794225321455788e-06,
+      "loss": 0.0866,
+      "step": 1280
+    },
+    {
+      "epoch": 0.9174964438122333,
+      "grad_norm": 2.466600341108382,
+      "learning_rate": 8.767145890782542e-06,
+      "loss": 0.0849,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9246088193456614,
+      "grad_norm": 2.694537159823399,
+      "learning_rate": 8.739808437775825e-06,
+      "loss": 0.0773,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9317211948790897,
+      "grad_norm": 3.051119356918663,
+      "learning_rate": 8.71221483485407e-06,
+      "loss": 0.0887,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9388335704125178,
+      "grad_norm": 2.091226963672429,
+      "learning_rate": 8.684366971980139e-06,
+      "loss": 0.0739,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 2.6573993659558885,
+      "learning_rate": 8.656266756531857e-06,
+      "loss": 0.0757,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9530583214793741,
+      "grad_norm": 2.5135440840845593,
+      "learning_rate": 8.627916113171396e-06,
+      "loss": 0.0695,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9601706970128022,
+      "grad_norm": 1.8647689285533582,
+      "learning_rate": 8.599316983713419e-06,
+      "loss": 0.0703,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9672830725462305,
+      "grad_norm": 2.1656321527764444,
+      "learning_rate": 8.570471326992105e-06,
+      "loss": 0.062,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9743954480796586,
+      "grad_norm": 2.705238359384965,
+      "learning_rate": 8.54138111872697e-06,
+      "loss": 0.0755,
+      "step": 1370
+    },
+    {
+      "epoch": 0.9815078236130867,
+      "grad_norm": 1.4926114349562027,
+      "learning_rate": 8.512048351387551e-06,
+      "loss": 0.0656,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9886201991465149,
+      "grad_norm": 2.193183643997932,
+      "learning_rate": 8.482475034056927e-06,
+      "loss": 0.0659,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9957325746799431,
+      "grad_norm": 2.0527279052017264,
+      "learning_rate": 8.452663192294121e-06,
+      "loss": 0.0576,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0028449502133712,
+      "grad_norm": 2.043379604895136,
+      "learning_rate": 8.42261486799536e-06,
+      "loss": 0.0518,
+      "step": 1410
+    },
+    {
+      "epoch": 1.0099573257467995,
+      "grad_norm": 1.7935460456418109,
+      "learning_rate": 8.392332119254214e-06,
+      "loss": 0.0363,
+      "step": 1420
+    },
+    {
+      "epoch": 1.0170697012802277,
+      "grad_norm": 1.9591421706180754,
+      "learning_rate": 8.361817020220647e-06,
+      "loss": 0.0345,
+      "step": 1430
+    },
+    {
+      "epoch": 1.0241820768136558,
+      "grad_norm": 1.904127146547918,
+      "learning_rate": 8.331071660958936e-06,
+      "loss": 0.039,
+      "step": 1440
+    },
+    {
+      "epoch": 1.031294452347084,
+      "grad_norm": 1.8927150070468237,
+      "learning_rate": 8.300098147304523e-06,
+      "loss": 0.0365,
+      "step": 1450
+    },
+    {
+      "epoch": 1.038406827880512,
+      "grad_norm": 1.9578224146696355,
+      "learning_rate": 8.268898600719785e-06,
+      "loss": 0.0431,
+      "step": 1460
+    },
+    {
+      "epoch": 1.0455192034139402,
+      "grad_norm": 2.119890142949488,
+      "learning_rate": 8.237475158148724e-06,
+      "loss": 0.0429,
+      "step": 1470
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 1.9482483964200852,
+      "learning_rate": 8.205829971870602e-06,
+      "loss": 0.0397,
+      "step": 1480
+    },
+    {
+      "epoch": 1.0597439544807965,
+      "grad_norm": 1.7329874393672655,
+      "learning_rate": 8.173965209352524e-06,
+      "loss": 0.0344,
+      "step": 1490
+    },
+    {
+      "epoch": 1.0668563300142249,
+      "grad_norm": 1.8911139378477928,
+      "learning_rate": 8.14188305310099e-06,
+      "loss": 0.0464,
+      "step": 1500
+    },
+    {
+      "epoch": 1.073968705547653,
+      "grad_norm": 2.450233012383526,
+      "learning_rate": 8.109585700512395e-06,
+      "loss": 0.0375,
+      "step": 1510
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 2.0138094788301166,
+      "learning_rate": 8.077075363722542e-06,
+      "loss": 0.0389,
+      "step": 1520
+    },
+    {
+      "epoch": 1.0881934566145093,
+      "grad_norm": 2.076572644222088,
+      "learning_rate": 8.044354269455109e-06,
+      "loss": 0.0436,
+      "step": 1530
+    },
+    {
+      "epoch": 1.0953058321479374,
+      "grad_norm": 1.9101229450735917,
+      "learning_rate": 8.011424658869142e-06,
+      "loss": 0.0357,
+      "step": 1540
+    },
+    {
+      "epoch": 1.1024182076813656,
+      "grad_norm": 1.130649417703215,
+      "learning_rate": 7.978288787405556e-06,
+      "loss": 0.0362,
+      "step": 1550
+    },
+    {
+      "epoch": 1.1095305832147937,
+      "grad_norm": 1.1581533245467266,
+      "learning_rate": 7.944948924632643e-06,
+      "loss": 0.0345,
+      "step": 1560
+    },
+    {
+      "epoch": 1.1166429587482218,
+      "grad_norm": 1.6643524677849526,
+      "learning_rate": 7.911407354090634e-06,
+      "loss": 0.0354,
+      "step": 1570
+    },
+    {
+      "epoch": 1.12375533428165,
+      "grad_norm": 1.9726198917599644,
+      "learning_rate": 7.877666373135287e-06,
+      "loss": 0.0346,
+      "step": 1580
+    },
+    {
+      "epoch": 1.1308677098150781,
+      "grad_norm": 1.6692436200631287,
+      "learning_rate": 7.84372829278053e-06,
+      "loss": 0.038,
+      "step": 1590
+    },
+    {
+      "epoch": 1.1379800853485065,
+      "grad_norm": 1.7045565380565189,
+      "learning_rate": 7.809595437540189e-06,
+      "loss": 0.0327,
+      "step": 1600
+    },
+    {
+      "epoch": 1.1450924608819346,
+      "grad_norm": 1.9976160352568044,
+      "learning_rate": 7.775270145268755e-06,
+      "loss": 0.0256,
+      "step": 1610
+    },
+    {
+      "epoch": 1.1522048364153628,
+      "grad_norm": 1.3781171703418404,
+      "learning_rate": 7.740754767001278e-06,
+      "loss": 0.039,
+      "step": 1620
+    },
+    {
+      "epoch": 1.159317211948791,
+      "grad_norm": 1.675366937408603,
+      "learning_rate": 7.706051666792318e-06,
+      "loss": 0.0353,
+      "step": 1630
+    },
+    {
+      "epoch": 1.166429587482219,
+      "grad_norm": 1.5507760610752672,
+      "learning_rate": 7.671163221554043e-06,
+      "loss": 0.0353,
+      "step": 1640
+    },
+    {
+      "epoch": 1.1735419630156472,
+      "grad_norm": 1.5578057994726024,
+      "learning_rate": 7.636091820893417e-06,
+      "loss": 0.0374,
+      "step": 1650
+    },
+    {
+      "epoch": 1.1806543385490753,
+      "grad_norm": 1.9536673456849045,
+      "learning_rate": 7.600839866948528e-06,
+      "loss": 0.0363,
+      "step": 1660
+    },
+    {
+      "epoch": 1.1877667140825037,
+      "grad_norm": 1.4180294508669007,
+      "learning_rate": 7.565409774224066e-06,
+      "loss": 0.0349,
+      "step": 1670
+    },
+    {
+      "epoch": 1.1948790896159318,
+      "grad_norm": 1.6616296432221909,
+      "learning_rate": 7.529803969425941e-06,
+      "loss": 0.0307,
+      "step": 1680
+    },
+    {
+      "epoch": 1.20199146514936,
+      "grad_norm": 1.7138246686303804,
+      "learning_rate": 7.494024891295075e-06,
+      "loss": 0.0322,
+      "step": 1690
+    },
+    {
+      "epoch": 1.209103840682788,
+      "grad_norm": 1.3613855884690513,
+      "learning_rate": 7.458074990440363e-06,
+      "loss": 0.0293,
+      "step": 1700
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 2.4114521805394205,
+      "learning_rate": 7.421956729170823e-06,
+      "loss": 0.0344,
+      "step": 1710
+    },
+    {
+      "epoch": 1.2233285917496444,
+      "grad_norm": 1.9233612034450194,
+      "learning_rate": 7.385672581326954e-06,
+      "loss": 0.0351,
+      "step": 1720
+    },
+    {
+      "epoch": 1.2304409672830725,
+      "grad_norm": 1.7307194070590812,
+      "learning_rate": 7.34922503211128e-06,
+      "loss": 0.0353,
+      "step": 1730
+    },
+    {
+      "epoch": 1.2375533428165006,
+      "grad_norm": 1.468735660134803,
+      "learning_rate": 7.312616577918149e-06,
+      "loss": 0.03,
+      "step": 1740
+    },
+    {
+      "epoch": 1.2446657183499288,
+      "grad_norm": 0.9815553395553774,
+      "learning_rate": 7.2758497261627345e-06,
+      "loss": 0.0267,
+      "step": 1750
+    },
+    {
+      "epoch": 1.251778093883357,
+      "grad_norm": 1.4851270984075178,
+      "learning_rate": 7.238926995109306e-06,
+      "loss": 0.0288,
+      "step": 1760
+    },
+    {
+      "epoch": 1.2588904694167853,
+      "grad_norm": 2.2537032746619183,
+      "learning_rate": 7.201850913698736e-06,
+      "loss": 0.0364,
+      "step": 1770
+    },
+    {
+      "epoch": 1.2660028449502134,
+      "grad_norm": 1.454211009387941,
+      "learning_rate": 7.164624021375294e-06,
+      "loss": 0.0252,
+      "step": 1780
+    },
+    {
+      "epoch": 1.2731152204836416,
+      "grad_norm": 1.4034123768391151,
+      "learning_rate": 7.12724886791271e-06,
+      "loss": 0.0266,
+      "step": 1790
+    },
+    {
+      "epoch": 1.2802275960170697,
+      "grad_norm": 1.546526107411268,
+      "learning_rate": 7.08972801323953e-06,
+      "loss": 0.03,
+      "step": 1800
+    },
+    {
+      "epoch": 1.2873399715504978,
+      "grad_norm": 1.6929689381873503,
+      "learning_rate": 7.052064027263785e-06,
+      "loss": 0.0235,
+      "step": 1810
+    },
+    {
+      "epoch": 1.294452347083926,
+      "grad_norm": 1.5130921744879449,
+      "learning_rate": 7.014259489696968e-06,
+      "loss": 0.0243,
+      "step": 1820
+    },
+    {
+      "epoch": 1.3015647226173541,
+      "grad_norm": 1.9572718096346318,
+      "learning_rate": 6.976316989877343e-06,
+      "loss": 0.0249,
+      "step": 1830
+    },
+    {
+      "epoch": 1.3086770981507825,
+      "grad_norm": 1.2611303057850376,
+      "learning_rate": 6.938239126592592e-06,
+      "loss": 0.0263,
+      "step": 1840
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 1.2902816153314383,
+      "learning_rate": 6.90002850790182e-06,
+      "loss": 0.0298,
+      "step": 1850
+    },
+    {
+      "epoch": 1.3229018492176388,
+      "grad_norm": 0.9719782814773048,
+      "learning_rate": 6.861687750956922e-06,
+      "loss": 0.027,
+      "step": 1860
+    },
+    {
+      "epoch": 1.330014224751067,
+      "grad_norm": 1.1718631838309244,
+      "learning_rate": 6.823219481823318e-06,
+      "loss": 0.0245,
+      "step": 1870
+    },
+    {
+      "epoch": 1.337126600284495,
+      "grad_norm": 1.3461970346065844,
+      "learning_rate": 6.784626335300102e-06,
+      "loss": 0.0198,
+      "step": 1880
+    },
+    {
+      "epoch": 1.3442389758179232,
+      "grad_norm": 1.1445639186428003,
+      "learning_rate": 6.745910954739563e-06,
+      "loss": 0.0274,
+      "step": 1890
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 1.9649035858601103,
+      "learning_rate": 6.707075991866143e-06,
+      "loss": 0.0268,
+      "step": 1900
+    },
+    {
+      "epoch": 1.3584637268847795,
+      "grad_norm": 1.3779682004442027,
+      "learning_rate": 6.668124106594813e-06,
+      "loss": 0.0274,
+      "step": 1910
+    },
+    {
+      "epoch": 1.3655761024182076,
+      "grad_norm": 0.9339287727084011,
+      "learning_rate": 6.629057966848879e-06,
+      "loss": 0.0244,
+      "step": 1920
+    },
+    {
+      "epoch": 1.3726884779516357,
+      "grad_norm": 1.3418194746364869,
+      "learning_rate": 6.589880248377258e-06,
+      "loss": 0.023,
+      "step": 1930
+    },
+    {
+      "epoch": 1.379800853485064,
+      "grad_norm": 1.6101698103903805,
+      "learning_rate": 6.550593634571205e-06,
+      "loss": 0.018,
+      "step": 1940
+    },
+    {
+      "epoch": 1.3869132290184922,
+      "grad_norm": 1.7415141112043047,
+      "learning_rate": 6.511200816280523e-06,
+      "loss": 0.021,
+      "step": 1950
+    },
+    {
+      "epoch": 1.3940256045519204,
+      "grad_norm": 1.2100486434644262,
+      "learning_rate": 6.471704491629251e-06,
+      "loss": 0.0285,
+      "step": 1960
+    },
+    {
+      "epoch": 1.4011379800853485,
+      "grad_norm": 1.301261422264456,
+      "learning_rate": 6.432107365830872e-06,
+      "loss": 0.0198,
+      "step": 1970
+    },
+    {
+      "epoch": 1.4082503556187767,
+      "grad_norm": 1.3543714484816034,
+      "learning_rate": 6.392412151003019e-06,
+      "loss": 0.0244,
+      "step": 1980
+    },
+    {
+      "epoch": 1.4153627311522048,
+      "grad_norm": 1.4893305665999936,
+      "learning_rate": 6.3526215659817156e-06,
+      "loss": 0.0226,
+      "step": 1990
+    },
+    {
+      "epoch": 1.422475106685633,
+      "grad_norm": 1.1217736569772296,
+      "learning_rate": 6.312738336135159e-06,
+      "loss": 0.019,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4295874822190613,
+      "grad_norm": 1.530506526795571,
+      "learning_rate": 6.272765193177044e-06,
+      "loss": 0.0196,
+      "step": 2010
+    },
+    {
+      "epoch": 1.4366998577524894,
+      "grad_norm": 1.1830746085813704,
+      "learning_rate": 6.23270487497947e-06,
+      "loss": 0.0189,
+      "step": 2020
+    },
+    {
+      "epoch": 1.4438122332859176,
+      "grad_norm": 1.3714016439826322,
+      "learning_rate": 6.192560125385412e-06,
+      "loss": 0.025,
+      "step": 2030
+    },
+    {
+      "epoch": 1.4509246088193457,
+      "grad_norm": 1.1129988250796872,
+      "learning_rate": 6.152333694020781e-06,
+      "loss": 0.0184,
+      "step": 2040
+    },
+    {
+      "epoch": 1.4580369843527738,
+      "grad_norm": 2.0430785612059346,
+      "learning_rate": 6.112028336106108e-06,
+      "loss": 0.023,
+      "step": 2050
+    },
+    {
+      "epoch": 1.465149359886202,
+      "grad_norm": 1.4200748013522733,
+      "learning_rate": 6.071646812267817e-06,
+      "loss": 0.0167,
+      "step": 2060
+    },
+    {
+      "epoch": 1.4722617354196301,
+      "grad_norm": 1.8027434372189237,
+      "learning_rate": 6.031191888349155e-06,
+      "loss": 0.0202,
+      "step": 2070
+    },
+    {
+      "epoch": 1.4793741109530583,
+      "grad_norm": 1.1171787456661884,
+      "learning_rate": 5.990666335220738e-06,
+      "loss": 0.0178,
+      "step": 2080
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 1.6452874612147976,
+      "learning_rate": 5.950072928590781e-06,
+      "loss": 0.018,
+      "step": 2090
+    },
+    {
+      "epoch": 1.4935988620199145,
+      "grad_norm": 0.9884439749765455,
+      "learning_rate": 5.909414448814971e-06,
+      "loss": 0.0209,
+      "step": 2100
+    },
+    {
+      "epoch": 1.5007112375533427,
+      "grad_norm": 1.554996157376441,
+      "learning_rate": 5.8686936807060335e-06,
+      "loss": 0.0192,
+      "step": 2110
+    },
+    {
+      "epoch": 1.5078236130867708,
+      "grad_norm": 1.0929475144672365,
+      "learning_rate": 5.827913413343003e-06,
+      "loss": 0.018,
+      "step": 2120
+    },
+    {
+      "epoch": 1.5149359886201992,
+      "grad_norm": 1.0492081159201816,
+      "learning_rate": 5.787076439880177e-06,
+      "loss": 0.0179,
+      "step": 2130
+    },
+    {
+      "epoch": 1.5220483641536273,
+      "grad_norm": 1.2333928332291602,
+      "learning_rate": 5.746185557355814e-06,
+      "loss": 0.0211,
+      "step": 2140
+    },
+    {
+      "epoch": 1.5291607396870555,
+      "grad_norm": 0.8940904857757537,
+      "learning_rate": 5.70524356650056e-06,
+      "loss": 0.0168,
+      "step": 2150
+    },
+    {
+      "epoch": 1.5362731152204836,
+      "grad_norm": 0.9594678027850269,
+      "learning_rate": 5.664253271545603e-06,
+      "loss": 0.0172,
+      "step": 2160
+    },
+    {
+      "epoch": 1.543385490753912,
+      "grad_norm": 1.133529225026687,
+      "learning_rate": 5.623217480030622e-06,
+      "loss": 0.0178,
+      "step": 2170
+    },
+    {
+      "epoch": 1.55049786628734,
+      "grad_norm": 1.0245366404113008,
+      "learning_rate": 5.58213900261148e-06,
+      "loss": 0.0135,
+      "step": 2180
+    },
+    {
+      "epoch": 1.5576102418207682,
+      "grad_norm": 0.7068889699880522,
+      "learning_rate": 5.541020652867713e-06,
+      "loss": 0.0153,
+      "step": 2190
+    },
+    {
+      "epoch": 1.5647226173541964,
+      "grad_norm": 1.2084727884034199,
+      "learning_rate": 5.49986524710983e-06,
+      "loss": 0.0143,
+      "step": 2200
+    },
+    {
+      "epoch": 1.5718349928876245,
+      "grad_norm": 1.5054621892964164,
+      "learning_rate": 5.4586756041864065e-06,
+      "loss": 0.016,
+      "step": 2210
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 1.4176580158063212,
+      "learning_rate": 5.417454545291017e-06,
+      "loss": 0.0168,
+      "step": 2220
+    },
+    {
+      "epoch": 1.5860597439544808,
+      "grad_norm": 1.1824924291702557,
+      "learning_rate": 5.376204893769e-06,
+      "loss": 0.0198,
+      "step": 2230
+    },
+    {
+      "epoch": 1.593172119487909,
+      "grad_norm": 1.7631808589665254,
+      "learning_rate": 5.334929474924093e-06,
+      "loss": 0.0155,
+      "step": 2240
+    },
+    {
+      "epoch": 1.600284495021337,
+      "grad_norm": 1.215149372258629,
+      "learning_rate": 5.293631115824897e-06,
+      "loss": 0.0138,
+      "step": 2250
+    },
+    {
+      "epoch": 1.6073968705547652,
+      "grad_norm": 1.718329335563461,
+      "learning_rate": 5.252312645111266e-06,
+      "loss": 0.0173,
+      "step": 2260
+    },
+    {
+      "epoch": 1.6145092460881934,
+      "grad_norm": 1.0751615799620988,
+      "learning_rate": 5.2109768928005454e-06,
+      "loss": 0.0142,
+      "step": 2270
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.8027120709435296,
+      "learning_rate": 5.169626690093751e-06,
+      "loss": 0.014,
+      "step": 2280
+    },
+    {
+      "epoch": 1.6287339971550496,
+      "grad_norm": 1.6699231722730825,
+      "learning_rate": 5.128264869181646e-06,
+      "loss": 0.0127,
+      "step": 2290
+    },
+    {
+      "epoch": 1.635846372688478,
+      "grad_norm": 1.2559995566307685,
+      "learning_rate": 5.086894263050755e-06,
+      "loss": 0.011,
+      "step": 2300
+    },
+    {
+      "epoch": 1.6429587482219061,
+      "grad_norm": 1.349960059022035,
+      "learning_rate": 5.045517705289328e-06,
+      "loss": 0.0111,
+      "step": 2310
+    },
+    {
+      "epoch": 1.6500711237553343,
+      "grad_norm": 0.8142603267011976,
+      "learning_rate": 5.004138029893257e-06,
+      "loss": 0.0138,
+      "step": 2320
+    },
+    {
+      "epoch": 1.6571834992887624,
+      "grad_norm": 1.0621437820203163,
+      "learning_rate": 4.9627580710719734e-06,
+      "loss": 0.0128,
+      "step": 2330
+    },
+    {
+      "epoch": 1.6642958748221908,
+      "grad_norm": 1.7262184368035551,
+      "learning_rate": 4.921380663054318e-06,
+      "loss": 0.0128,
+      "step": 2340
+    },
+    {
+      "epoch": 1.671408250355619,
+      "grad_norm": 1.2695847947859624,
+      "learning_rate": 4.880008639894421e-06,
+      "loss": 0.014,
+      "step": 2350
+    },
+    {
+      "epoch": 1.678520625889047,
+      "grad_norm": 0.9261536386806662,
+      "learning_rate": 4.838644835277585e-06,
+      "loss": 0.0144,
+      "step": 2360
+    },
+    {
+      "epoch": 1.6856330014224752,
+      "grad_norm": 0.6867762051400554,
+      "learning_rate": 4.79729208232621e-06,
+      "loss": 0.0109,
+      "step": 2370
+    },
+    {
+      "epoch": 1.6927453769559033,
+      "grad_norm": 0.6232870542134327,
+      "learning_rate": 4.75595321340573e-06,
+      "loss": 0.0122,
+      "step": 2380
+    },
+    {
+      "epoch": 1.6998577524893315,
+      "grad_norm": 0.970176828182309,
+      "learning_rate": 4.714631059930622e-06,
+      "loss": 0.012,
+      "step": 2390
+    },
+    {
+      "epoch": 1.7069701280227596,
+      "grad_norm": 1.6173382913062293,
+      "learning_rate": 4.6733284521704816e-06,
+      "loss": 0.0124,
+      "step": 2400
+    },
+    {
+      "epoch": 1.7140825035561877,
+      "grad_norm": 0.9844171855603,
+      "learning_rate": 4.632048219056159e-06,
+      "loss": 0.012,
+      "step": 2410
+    },
+    {
+      "epoch": 1.7211948790896159,
+      "grad_norm": 1.3183824382551952,
+      "learning_rate": 4.590793187986003e-06,
+      "loss": 0.0149,
+      "step": 2420
+    },
+    {
+      "epoch": 1.728307254623044,
+      "grad_norm": 0.5730734000902559,
+      "learning_rate": 4.549566184632206e-06,
+      "loss": 0.0117,
+      "step": 2430
+    },
+    {
+      "epoch": 1.7354196301564722,
+      "grad_norm": 0.9239894283732394,
+      "learning_rate": 4.508370032747261e-06,
+      "loss": 0.0092,
+      "step": 2440
+    },
+    {
+      "epoch": 1.7425320056899003,
+      "grad_norm": 0.9732516534559529,
+      "learning_rate": 4.467207553970564e-06,
+      "loss": 0.012,
+      "step": 2450
+    },
+    {
+      "epoch": 1.7496443812233284,
+      "grad_norm": 0.9139268416210883,
+      "learning_rate": 4.426081567635137e-06,
+      "loss": 0.0092,
+      "step": 2460
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 1.2921223854630304,
+      "learning_rate": 4.3849948905745385e-06,
+      "loss": 0.0137,
+      "step": 2470
+    },
+    {
+      "epoch": 1.763869132290185,
+      "grad_norm": 0.8703692417885042,
+      "learning_rate": 4.343950336929927e-06,
+      "loss": 0.0095,
+      "step": 2480
+    },
+    {
+      "epoch": 1.770981507823613,
+      "grad_norm": 0.9536442700427114,
+      "learning_rate": 4.302950717957304e-06,
+      "loss": 0.0098,
+      "step": 2490
+    },
+    {
+      "epoch": 1.7780938833570412,
+      "grad_norm": 0.852536162993322,
+      "learning_rate": 4.261998841834972e-06,
+      "loss": 0.0101,
+      "step": 2500
+    },
+    {
+      "epoch": 1.7852062588904696,
+      "grad_norm": 1.248725823462744,
+      "learning_rate": 4.221097513471199e-06,
+      "loss": 0.0094,
+      "step": 2510
+    },
+    {
+      "epoch": 1.7923186344238977,
+      "grad_norm": 0.487586863686056,
+      "learning_rate": 4.18024953431209e-06,
+      "loss": 0.009,
+      "step": 2520
+    },
+    {
+      "epoch": 1.7994310099573259,
+      "grad_norm": 0.6857485925261184,
+      "learning_rate": 4.13945770214971e-06,
+      "loss": 0.0098,
+      "step": 2530
+    },
+    {
+      "epoch": 1.806543385490754,
+      "grad_norm": 0.5224101041795471,
+      "learning_rate": 4.098724810930472e-06,
+      "loss": 0.0077,
+      "step": 2540
+    },
+    {
+      "epoch": 1.8136557610241821,
+      "grad_norm": 0.3255236838052598,
+      "learning_rate": 4.058053650563747e-06,
+      "loss": 0.0069,
+      "step": 2550
+    },
+    {
+      "epoch": 1.8207681365576103,
+      "grad_norm": 0.5535169044707119,
+      "learning_rate": 4.017447006730796e-06,
+      "loss": 0.0084,
+      "step": 2560
+    },
+    {
+      "epoch": 1.8278805120910384,
+      "grad_norm": 0.6587680546008802,
+      "learning_rate": 3.976907660693954e-06,
+      "loss": 0.0068,
+      "step": 2570
+    },
+    {
+      "epoch": 1.8349928876244666,
+      "grad_norm": 0.7451030339766666,
+      "learning_rate": 3.936438389106154e-06,
+      "loss": 0.0091,
+      "step": 2580
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.7854707802079127,
+      "learning_rate": 3.896041963820724e-06,
+      "loss": 0.0105,
+      "step": 2590
+    },
+    {
+      "epoch": 1.8492176386913228,
+      "grad_norm": 0.6990927586140553,
+      "learning_rate": 3.855721151701548e-06,
+      "loss": 0.0099,
+      "step": 2600
+    },
+    {
+      "epoch": 1.856330014224751,
+      "grad_norm": 1.318630670215527,
+      "learning_rate": 3.815478714433559e-06,
+      "loss": 0.0095,
+      "step": 2610
+    },
+    {
+      "epoch": 1.863442389758179,
+      "grad_norm": 0.8518153474787149,
+      "learning_rate": 3.775317408333571e-06,
+      "loss": 0.0105,
+      "step": 2620
+    },
+    {
+      "epoch": 1.8705547652916072,
+      "grad_norm": 1.0023735620026466,
+      "learning_rate": 3.7352399841614996e-06,
+      "loss": 0.0082,
+      "step": 2630
+    },
+    {
+      "epoch": 1.8776671408250356,
+      "grad_norm": 0.9809887806472293,
+      "learning_rate": 3.695249186931954e-06,
+      "loss": 0.0087,
+      "step": 2640
+    },
+    {
+      "epoch": 1.8847795163584637,
+      "grad_norm": 0.9540456428445807,
+      "learning_rate": 3.655347755726224e-06,
+      "loss": 0.0076,
+      "step": 2650
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.7066159412282622,
+      "learning_rate": 3.6155384235046674e-06,
+      "loss": 0.0086,
+      "step": 2660
+    },
+    {
+      "epoch": 1.89900426742532,
+      "grad_norm": 0.5137592216850851,
+      "learning_rate": 3.5758239169195276e-06,
+      "loss": 0.005,
+      "step": 2670
+    },
+    {
+      "epoch": 1.9061166429587484,
+      "grad_norm": 0.3439517878091387,
+      "learning_rate": 3.5362069561281764e-06,
+      "loss": 0.0072,
+      "step": 2680
+    },
+    {
+      "epoch": 1.9132290184921765,
+      "grad_norm": 0.3970319267325305,
+      "learning_rate": 3.4966902546068016e-06,
+      "loss": 0.0072,
+      "step": 2690
+    },
+    {
+      "epoch": 1.9203413940256047,
+      "grad_norm": 0.9810798909167313,
+      "learning_rate": 3.4572765189645516e-06,
+      "loss": 0.0073,
+      "step": 2700
+    },
+    {
+      "epoch": 1.9274537695590328,
+      "grad_norm": 1.4872117479815739,
+      "learning_rate": 3.4179684487581555e-06,
+      "loss": 0.0067,
+      "step": 2710
+    },
+    {
+      "epoch": 1.934566145092461,
+      "grad_norm": 0.17941271447530188,
+      "learning_rate": 3.3787687363070256e-06,
+      "loss": 0.0075,
+      "step": 2720
+    },
+    {
+      "epoch": 1.941678520625889,
+      "grad_norm": 0.21377268278340267,
+      "learning_rate": 3.3396800665088435e-06,
+      "loss": 0.0069,
+      "step": 2730
+    },
+    {
+      "epoch": 1.9487908961593172,
+      "grad_norm": 0.8027020001474104,
+      "learning_rate": 3.300705116655672e-06,
+      "loss": 0.0058,
+      "step": 2740
+    },
+    {
+      "epoch": 1.9559032716927454,
+      "grad_norm": 0.607769605088779,
+      "learning_rate": 3.26184655625058e-06,
+      "loss": 0.0055,
+      "step": 2750
+    },
+    {
+      "epoch": 1.9630156472261735,
+      "grad_norm": 0.29396831979764293,
+      "learning_rate": 3.2231070468247954e-06,
+      "loss": 0.0062,
+      "step": 2760
+    },
+    {
+      "epoch": 1.9701280227596016,
+      "grad_norm": 0.49083863249583537,
+      "learning_rate": 3.1844892417554102e-06,
+      "loss": 0.0063,
+      "step": 2770
+    },
+    {
+      "epoch": 1.9772403982930298,
+      "grad_norm": 0.710753958854101,
+      "learning_rate": 3.1459957860836528e-06,
+      "loss": 0.0065,
+      "step": 2780
+    },
+    {
+      "epoch": 1.984352773826458,
+      "grad_norm": 0.27012727932102704,
+      "learning_rate": 3.1076293163337074e-06,
+      "loss": 0.0068,
+      "step": 2790
+    },
+    {
+      "epoch": 1.991465149359886,
+      "grad_norm": 0.34603765606499187,
+      "learning_rate": 3.069392460332141e-06,
+      "loss": 0.0057,
+      "step": 2800
+    },
+    {
+      "epoch": 1.9985775248933144,
+      "grad_norm": 0.3721250969176249,
+      "learning_rate": 3.031287837027911e-06,
+      "loss": 0.0066,
+      "step": 2810
+    },
+    {
+      "epoch": 2.0056899004267423,
+      "grad_norm": 0.781768421432185,
+      "learning_rate": 2.9933180563129936e-06,
+      "loss": 0.0041,
+      "step": 2820
+    },
+    {
+      "epoch": 2.012802275960171,
+      "grad_norm": 0.24350008390092337,
+      "learning_rate": 2.955485718843616e-06,
+      "loss": 0.0056,
+      "step": 2830
+    },
+    {
+      "epoch": 2.019914651493599,
+      "grad_norm": 0.4576741832894929,
+      "learning_rate": 2.917793415862129e-06,
+      "loss": 0.0048,
+      "step": 2840
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.9890835980780475,
+      "learning_rate": 2.880243729019546e-06,
+      "loss": 0.0038,
+      "step": 2850
+    },
+    {
+      "epoch": 2.0341394025604553,
+      "grad_norm": 0.3917033136267895,
+      "learning_rate": 2.842839230198685e-06,
+      "loss": 0.0052,
+      "step": 2860
+    },
+    {
+      "epoch": 2.0412517780938835,
+      "grad_norm": 0.12450209954114903,
+      "learning_rate": 2.805582481338044e-06,
+      "loss": 0.0047,
+      "step": 2870
+    },
+    {
+      "epoch": 2.0483641536273116,
+      "grad_norm": 0.5486661654701261,
+      "learning_rate": 2.7684760342563045e-06,
+      "loss": 0.0047,
+      "step": 2880
+    },
+    {
+      "epoch": 2.0554765291607398,
+      "grad_norm": 0.22758726780410876,
+      "learning_rate": 2.731522430477571e-06,
+      "loss": 0.0056,
+      "step": 2890
+    },
+    {
+      "epoch": 2.062588904694168,
+      "grad_norm": 0.2218164583744802,
+      "learning_rate": 2.694724201057273e-06,
+      "loss": 0.0048,
+      "step": 2900
+    },
+    {
+      "epoch": 2.069701280227596,
+      "grad_norm": 0.45353402328041514,
+      "learning_rate": 2.6580838664088214e-06,
+      "loss": 0.0042,
+      "step": 2910
+    },
+    {
+      "epoch": 2.076813655761024,
+      "grad_norm": 0.29165554258590237,
+      "learning_rate": 2.6216039361309753e-06,
+      "loss": 0.0044,
+      "step": 2920
+    },
+    {
+      "epoch": 2.0839260312944523,
+      "grad_norm": 0.42787997336579114,
+      "learning_rate": 2.5852869088359495e-06,
+      "loss": 0.0041,
+      "step": 2930
+    },
+    {
+      "epoch": 2.0910384068278804,
+      "grad_norm": 0.44323215466285076,
+      "learning_rate": 2.549135271978275e-06,
+      "loss": 0.0032,
+      "step": 2940
+    },
+    {
+      "epoch": 2.0981507823613086,
+      "grad_norm": 0.1143123602309504,
+      "learning_rate": 2.5131515016844345e-06,
+      "loss": 0.0046,
+      "step": 2950
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.16583828479799412,
+      "learning_rate": 2.4773380625832603e-06,
+      "loss": 0.0047,
+      "step": 2960
+    },
+    {
+      "epoch": 2.112375533428165,
+      "grad_norm": 0.15755302830922696,
+      "learning_rate": 2.4416974076371304e-06,
+      "loss": 0.0039,
+      "step": 2970
+    },
+    {
+      "epoch": 2.119487908961593,
+      "grad_norm": 0.62834650400931,
+      "learning_rate": 2.406231977973942e-06,
+      "loss": 0.0037,
+      "step": 2980
+    },
+    {
+      "epoch": 2.126600284495021,
+      "grad_norm": 0.3425562134173693,
+      "learning_rate": 2.3709442027199387e-06,
+      "loss": 0.0049,
+      "step": 2990
+    },
+    {
+      "epoch": 2.1337126600284497,
+      "grad_norm": 0.1176241490475843,
+      "learning_rate": 2.3358364988333066e-06,
+      "loss": 0.0045,
+      "step": 3000
+    },
+    {
+      "epoch": 2.140825035561878,
+      "grad_norm": 0.21718467446163836,
+      "learning_rate": 2.3009112709386454e-06,
+      "loss": 0.0052,
+      "step": 3010
+    },
+    {
+      "epoch": 2.147937411095306,
+      "grad_norm": 0.1447042548468856,
+      "learning_rate": 2.2661709111622666e-06,
+      "loss": 0.0047,
+      "step": 3020
+    },
+    {
+      "epoch": 2.155049786628734,
+      "grad_norm": 0.2850367854449551,
+      "learning_rate": 2.2316177989683458e-06,
+      "loss": 0.004,
+      "step": 3030
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.33564220562935804,
+      "learning_rate": 2.197254300995953e-06,
+      "loss": 0.0052,
+      "step": 3040
+    },
+    {
+      "epoch": 2.1692745376955904,
+      "grad_norm": 0.1545067926251289,
+      "learning_rate": 2.163082770896943e-06,
+      "loss": 0.0043,
+      "step": 3050
+    },
+    {
+      "epoch": 2.1763869132290186,
+      "grad_norm": 0.08868335935281069,
+      "learning_rate": 2.1291055491747643e-06,
+      "loss": 0.0034,
+      "step": 3060
+    },
+    {
+      "epoch": 2.1834992887624467,
+      "grad_norm": 0.0678499455537346,
+      "learning_rate": 2.095324963024137e-06,
+      "loss": 0.0039,
+      "step": 3070
+    },
+    {
+      "epoch": 2.190611664295875,
+      "grad_norm": 0.1962461433328382,
+      "learning_rate": 2.061743326171668e-06,
+      "loss": 0.0038,
+      "step": 3080
+    },
+    {
+      "epoch": 2.197724039829303,
+      "grad_norm": 0.07801886707618137,
+      "learning_rate": 2.02836293871736e-06,
+      "loss": 0.0035,
+      "step": 3090
+    },
+    {
+      "epoch": 2.204836415362731,
+      "grad_norm": 0.3629078506453925,
+      "learning_rate": 1.9951860869771e-06,
+      "loss": 0.0038,
+      "step": 3100
+    },
+    {
+      "epoch": 2.2119487908961593,
+      "grad_norm": 0.8806588814039079,
+      "learning_rate": 1.962215043326029e-06,
+      "loss": 0.004,
+      "step": 3110
+    },
+    {
+      "epoch": 2.2190611664295874,
+      "grad_norm": 0.33169199243250613,
+      "learning_rate": 1.9294520660429284e-06,
+      "loss": 0.0036,
+      "step": 3120
+    },
+    {
+      "epoch": 2.2261735419630155,
+      "grad_norm": 0.12310821458251077,
+      "learning_rate": 1.8968993991555301e-06,
+      "loss": 0.0045,
+      "step": 3130
+    },
+    {
+      "epoch": 2.2332859174964437,
+      "grad_norm": 0.1564234234161847,
+      "learning_rate": 1.8645592722868223e-06,
+      "loss": 0.0041,
+      "step": 3140
+    },
+    {
+      "epoch": 2.240398293029872,
+      "grad_norm": 0.1908716606221835,
+      "learning_rate": 1.8324339005023273e-06,
+      "loss": 0.0042,
+      "step": 3150
+    },
+    {
+      "epoch": 2.2475106685633,
+      "grad_norm": 0.17491525199519603,
+      "learning_rate": 1.8005254841584035e-06,
+      "loss": 0.0032,
+      "step": 3160
+    },
+    {
+      "epoch": 2.2546230440967285,
+      "grad_norm": 0.15681019357467124,
+      "learning_rate": 1.768836208751516e-06,
+      "loss": 0.0039,
+      "step": 3170
+    },
+    {
+      "epoch": 2.2617354196301562,
+      "grad_norm": 0.16172138112249296,
+      "learning_rate": 1.7373682447685624e-06,
+      "loss": 0.004,
+      "step": 3180
+    },
+    {
+      "epoch": 2.268847795163585,
+      "grad_norm": 0.10575834882863448,
+      "learning_rate": 1.706123747538196e-06,
+      "loss": 0.0035,
+      "step": 3190
+    },
+    {
+      "epoch": 2.275960170697013,
+      "grad_norm": 0.18222310954574267,
+      "learning_rate": 1.6751048570832184e-06,
+      "loss": 0.0041,
+      "step": 3200
+    },
+    {
+      "epoch": 2.283072546230441,
+      "grad_norm": 0.14875677905536833,
+      "learning_rate": 1.6443136979739855e-06,
+      "loss": 0.003,
+      "step": 3210
+    },
+    {
+      "epoch": 2.2901849217638692,
+      "grad_norm": 0.10898246145730768,
+      "learning_rate": 1.6137523791829007e-06,
+      "loss": 0.0034,
+      "step": 3220
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.1309461753215428,
+      "learning_rate": 1.5834229939399637e-06,
+      "loss": 0.0034,
+      "step": 3230
+    },
+    {
+      "epoch": 2.3044096728307255,
+      "grad_norm": 0.07200423508178247,
+      "learning_rate": 1.5533276195893987e-06,
+      "loss": 0.0037,
+      "step": 3240
+    },
+    {
+      "epoch": 2.3115220483641536,
+      "grad_norm": 0.28943328560772674,
+      "learning_rate": 1.5234683174473669e-06,
+      "loss": 0.0039,
+      "step": 3250
+    },
+    {
+      "epoch": 2.318634423897582,
+      "grad_norm": 0.5192612699526135,
+      "learning_rate": 1.493847132660789e-06,
+      "loss": 0.0034,
+      "step": 3260
+    },
+    {
+      "epoch": 2.32574679943101,
+      "grad_norm": 0.1606295965015448,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.0044,
+      "step": 3270
+    },
+    {
+      "epoch": 2.332859174964438,
+      "grad_norm": 0.37034704670980706,
+      "learning_rate": 1.435327214056103e-06,
+      "loss": 0.0036,
+      "step": 3280
+    },
+    {
+      "epoch": 2.339971550497866,
+      "grad_norm": 0.1985714241377405,
+      "learning_rate": 1.406432488430508e-06,
+      "loss": 0.0041,
+      "step": 3290
+    },
+    {
+      "epoch": 2.3470839260312943,
+      "grad_norm": 0.13803180507649276,
+      "learning_rate": 1.3777838962708602e-06,
+      "loss": 0.0035,
+      "step": 3300
+    },
+    {
+      "epoch": 2.3541963015647225,
+      "grad_norm": 0.16321860803207505,
+      "learning_rate": 1.3493833997991745e-06,
+      "loss": 0.0033,
+      "step": 3310
+    },
+    {
+      "epoch": 2.3613086770981506,
+      "grad_norm": 0.2001811539323451,
+      "learning_rate": 1.3212329442446985e-06,
+      "loss": 0.0042,
+      "step": 3320
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.1453173744872287,
+      "learning_rate": 1.2933344577106822e-06,
+      "loss": 0.0032,
+      "step": 3330
+    },
+    {
+      "epoch": 2.3755334281650073,
+      "grad_norm": 0.10401910511567347,
+      "learning_rate": 1.2656898510423122e-06,
+      "loss": 0.0031,
+      "step": 3340
+    },
+    {
+      "epoch": 2.382645803698435,
+      "grad_norm": 0.10582948879092595,
+      "learning_rate": 1.2383010176958372e-06,
+      "loss": 0.0033,
+      "step": 3350
+    },
+    {
+      "epoch": 2.3897581792318636,
+      "grad_norm": 0.16511981732406306,
+      "learning_rate": 1.2111698336088717e-06,
+      "loss": 0.0039,
+      "step": 3360
+    },
+    {
+      "epoch": 2.3968705547652918,
+      "grad_norm": 0.14041169290258051,
+      "learning_rate": 1.1842981570719237e-06,
+      "loss": 0.0034,
+      "step": 3370
+    },
+    {
+      "epoch": 2.40398293029872,
+      "grad_norm": 0.216807318559693,
+      "learning_rate": 1.157687828601094e-06,
+      "loss": 0.0039,
+      "step": 3380
+    },
+    {
+      "epoch": 2.411095305832148,
+      "grad_norm": 0.1487410996270859,
+      "learning_rate": 1.1313406708120327e-06,
+      "loss": 0.0033,
+      "step": 3390
+    },
+    {
+      "epoch": 2.418207681365576,
+      "grad_norm": 0.17410715559913836,
+      "learning_rate": 1.1052584882950896e-06,
+      "loss": 0.0032,
+      "step": 3400
+    },
+    {
+      "epoch": 2.4253200568990043,
+      "grad_norm": 0.14679067077660998,
+      "learning_rate": 1.0794430674917262e-06,
+      "loss": 0.0029,
+      "step": 3410
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.11730320262217042,
+      "learning_rate": 1.0538961765721429e-06,
+      "loss": 0.0034,
+      "step": 3420
+    },
+    {
+      "epoch": 2.4395448079658606,
+      "grad_norm": 0.15601345944604691,
+      "learning_rate": 1.0286195653141822e-06,
+      "loss": 0.0033,
+      "step": 3430
+    },
+    {
+      "epoch": 2.4466571834992887,
+      "grad_norm": 0.15596374680032918,
+      "learning_rate": 1.0036149649834786e-06,
+      "loss": 0.0033,
+      "step": 3440
+    },
+    {
+      "epoch": 2.453769559032717,
+      "grad_norm": 0.15341222073346109,
+      "learning_rate": 9.788840882148803e-07,
+      "loss": 0.0032,
+      "step": 3450
+    },
+    {
+      "epoch": 2.460881934566145,
+      "grad_norm": 0.18113221503751906,
+      "learning_rate": 9.544286288951393e-07,
+      "loss": 0.0028,
+      "step": 3460
+    },
+    {
+      "epoch": 2.467994310099573,
+      "grad_norm": 0.23824252331061962,
+      "learning_rate": 9.302502620469073e-07,
+      "loss": 0.003,
+      "step": 3470
+    },
+    {
+      "epoch": 2.4751066856330013,
+      "grad_norm": 0.1804454838531882,
+      "learning_rate": 9.063506437139901e-07,
+      "loss": 0.0033,
+      "step": 3480
+    },
+    {
+      "epoch": 2.4822190611664294,
+      "grad_norm": 0.12129461355182411,
+      "learning_rate": 8.827314108479357e-07,
+      "loss": 0.0035,
+      "step": 3490
+    },
+    {
+      "epoch": 2.4893314366998576,
+      "grad_norm": 0.2496105490338266,
+      "learning_rate": 8.593941811959078e-07,
+      "loss": 0.0037,
+      "step": 3500
+    },
+    {
+      "epoch": 2.496443812233286,
+      "grad_norm": 0.12260976552880777,
+      "learning_rate": 8.363405531898833e-07,
+      "loss": 0.0035,
+      "step": 3510
+    },
+    {
+      "epoch": 2.503556187766714,
+      "grad_norm": 0.17068909040005176,
+      "learning_rate": 8.135721058371681e-07,
+      "loss": 0.0038,
+      "step": 3520
+    },
+    {
+      "epoch": 2.5106685633001424,
+      "grad_norm": 0.14486041747836928,
+      "learning_rate": 7.910903986122537e-07,
+      "loss": 0.0023,
+      "step": 3530
+    },
+    {
+      "epoch": 2.5177809388335706,
+      "grad_norm": 0.16537212820522457,
+      "learning_rate": 7.688969713499983e-07,
+      "loss": 0.0033,
+      "step": 3540
+    },
+    {
+      "epoch": 2.5248933143669987,
+      "grad_norm": 0.06547618532234573,
+      "learning_rate": 7.469933441401606e-07,
+      "loss": 0.0036,
+      "step": 3550
+    },
+    {
+      "epoch": 2.532005689900427,
+      "grad_norm": 0.09486129847604534,
+      "learning_rate": 7.253810172232867e-07,
+      "loss": 0.0029,
+      "step": 3560
+    },
+    {
+      "epoch": 2.539118065433855,
+      "grad_norm": 0.15420596551214288,
+      "learning_rate": 7.040614708879489e-07,
+      "loss": 0.0031,
+      "step": 3570
+    },
+    {
+      "epoch": 2.546230440967283,
+      "grad_norm": 0.18795827544823362,
+      "learning_rate": 6.830361653693673e-07,
+      "loss": 0.0031,
+      "step": 3580
+    },
+    {
+      "epoch": 2.5533428165007113,
+      "grad_norm": 0.20144541991501458,
+      "learning_rate": 6.623065407493801e-07,
+      "loss": 0.0031,
+      "step": 3590
+    },
+    {
+      "epoch": 2.5604551920341394,
+      "grad_norm": 0.11898776472079374,
+      "learning_rate": 6.418740168578208e-07,
+      "loss": 0.0029,
+      "step": 3600
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.11704775629045612,
+      "learning_rate": 6.217399931752627e-07,
+      "loss": 0.0031,
+      "step": 3610
+    },
+    {
+      "epoch": 2.5746799431009957,
+      "grad_norm": 0.13757018665386925,
+      "learning_rate": 6.019058487371687e-07,
+      "loss": 0.0028,
+      "step": 3620
+    },
+    {
+      "epoch": 2.581792318634424,
+      "grad_norm": 0.07705433560973203,
+      "learning_rate": 5.82372942039432e-07,
+      "loss": 0.0037,
+      "step": 3630
+    },
+    {
+      "epoch": 2.588904694167852,
+      "grad_norm": 0.12004181043862794,
+      "learning_rate": 5.631426109453364e-07,
+      "loss": 0.003,
+      "step": 3640
+    },
+    {
+      "epoch": 2.59601706970128,
+      "grad_norm": 0.11547199526456815,
+      "learning_rate": 5.44216172593916e-07,
+      "loss": 0.0032,
+      "step": 3650
+    },
+    {
+      "epoch": 2.6031294452347082,
+      "grad_norm": 0.20275686253937805,
+      "learning_rate": 5.255949233097451e-07,
+      "loss": 0.0035,
+      "step": 3660
+    },
+    {
+      "epoch": 2.6102418207681364,
+      "grad_norm": 0.1327960409529542,
+      "learning_rate": 5.072801385141429e-07,
+      "loss": 0.0032,
+      "step": 3670
+    },
+    {
+      "epoch": 2.617354196301565,
+      "grad_norm": 0.13522734646826431,
+      "learning_rate": 4.89273072637827e-07,
+      "loss": 0.0027,
+      "step": 3680
+    },
+    {
+      "epoch": 2.6244665718349927,
+      "grad_norm": 0.0921535098896707,
+      "learning_rate": 4.7157495903498105e-07,
+      "loss": 0.0029,
+      "step": 3690
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.1305724860300583,
+      "learning_rate": 4.541870098987911e-07,
+      "loss": 0.0035,
+      "step": 3700
+    },
+    {
+      "epoch": 2.6386913229018494,
+      "grad_norm": 0.1366897855739292,
+      "learning_rate": 4.371104161784073e-07,
+      "loss": 0.0039,
+      "step": 3710
+    },
+    {
+      "epoch": 2.6458036984352775,
+      "grad_norm": 0.16675061725996185,
+      "learning_rate": 4.2034634749738623e-07,
+      "loss": 0.003,
+      "step": 3720
+    },
+    {
+      "epoch": 2.6529160739687057,
+      "grad_norm": 0.12062320450080749,
+      "learning_rate": 4.038959520735658e-07,
+      "loss": 0.0032,
+      "step": 3730
+    },
+    {
+      "epoch": 2.660028449502134,
+      "grad_norm": 0.07277873243358957,
+      "learning_rate": 3.8776035664043033e-07,
+      "loss": 0.0033,
+      "step": 3740
+    },
+    {
+      "epoch": 2.667140825035562,
+      "grad_norm": 0.09995970754512991,
+      "learning_rate": 3.719406663699349e-07,
+      "loss": 0.0036,
+      "step": 3750
+    },
+    {
+      "epoch": 2.67425320056899,
+      "grad_norm": 0.14356536332083528,
+      "learning_rate": 3.564379647968064e-07,
+      "loss": 0.0034,
+      "step": 3760
+    },
+    {
+      "epoch": 2.681365576102418,
+      "grad_norm": 0.1289519043233803,
+      "learning_rate": 3.4125331374433414e-07,
+      "loss": 0.0029,
+      "step": 3770
+    },
+    {
+      "epoch": 2.6884779516358464,
+      "grad_norm": 0.10645779562131363,
+      "learning_rate": 3.2638775325163517e-07,
+      "loss": 0.0027,
+      "step": 3780
+    },
+    {
+      "epoch": 2.6955903271692745,
+      "grad_norm": 0.10980156190201901,
+      "learning_rate": 3.1184230150243025e-07,
+      "loss": 0.0026,
+      "step": 3790
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.1212601092847071,
+      "learning_rate": 2.9761795475529375e-07,
+      "loss": 0.0027,
+      "step": 3800
+    },
+    {
+      "epoch": 2.7098150782361308,
+      "grad_norm": 0.10465054324216685,
+      "learning_rate": 2.8371568727542486e-07,
+      "loss": 0.0032,
+      "step": 3810
+    },
+    {
+      "epoch": 2.716927453769559,
+      "grad_norm": 0.14087107927522052,
+      "learning_rate": 2.7013645126791446e-07,
+      "loss": 0.0027,
+      "step": 3820
+    },
+    {
+      "epoch": 2.724039829302987,
+      "grad_norm": 0.11777162015019617,
+      "learning_rate": 2.5688117681252677e-07,
+      "loss": 0.0031,
+      "step": 3830
+    },
+    {
+      "epoch": 2.731152204836415,
+      "grad_norm": 0.12580839073471906,
+      "learning_rate": 2.439507717999945e-07,
+      "loss": 0.0027,
+      "step": 3840
+    },
+    {
+      "epoch": 2.7382645803698438,
+      "grad_norm": 0.11019351778666993,
+      "learning_rate": 2.3134612186983817e-07,
+      "loss": 0.0032,
+      "step": 3850
+    },
+    {
+      "epoch": 2.7453769559032715,
+      "grad_norm": 0.2540811705778796,
+      "learning_rate": 2.1906809034970057e-07,
+      "loss": 0.0032,
+      "step": 3860
+    },
+    {
+      "epoch": 2.7524893314367,
+      "grad_norm": 0.14533749828341638,
+      "learning_rate": 2.0711751819622038e-07,
+      "loss": 0.0028,
+      "step": 3870
+    },
+    {
+      "epoch": 2.759601706970128,
+      "grad_norm": 0.17723003777910762,
+      "learning_rate": 1.954952239374286e-07,
+      "loss": 0.0033,
+      "step": 3880
+    },
+    {
+      "epoch": 2.7667140825035563,
+      "grad_norm": 0.1714781247080342,
+      "learning_rate": 1.8420200361669137e-07,
+      "loss": 0.0028,
+      "step": 3890
+    },
+    {
+      "epoch": 2.7738264580369845,
+      "grad_norm": 0.1442879683659834,
+      "learning_rate": 1.732386307381767e-07,
+      "loss": 0.0028,
+      "step": 3900
+    },
+    {
+      "epoch": 2.7809388335704126,
+      "grad_norm": 0.11658671113478708,
+      "learning_rate": 1.6260585621388604e-07,
+      "loss": 0.0032,
+      "step": 3910
+    },
+    {
+      "epoch": 2.7880512091038407,
+      "grad_norm": 0.13555304661960596,
+      "learning_rate": 1.523044083122138e-07,
+      "loss": 0.0033,
+      "step": 3920
+    },
+    {
+      "epoch": 2.795163584637269,
+      "grad_norm": 0.16068613052421124,
+      "learning_rate": 1.4233499260807194e-07,
+      "loss": 0.0034,
+      "step": 3930
+    },
+    {
+      "epoch": 2.802275960170697,
+      "grad_norm": 0.1397672323891182,
+      "learning_rate": 1.326982919345582e-07,
+      "loss": 0.003,
+      "step": 3940
+    },
+    {
+      "epoch": 2.809388335704125,
+      "grad_norm": 0.1228326098193467,
+      "learning_rate": 1.2339496633619218e-07,
+      "loss": 0.0026,
+      "step": 3950
+    },
+    {
+      "epoch": 2.8165007112375533,
+      "grad_norm": 0.09294084238773208,
+      "learning_rate": 1.1442565302370146e-07,
+      "loss": 0.0026,
+      "step": 3960
+    },
+    {
+      "epoch": 2.8236130867709814,
+      "grad_norm": 0.10538827214385106,
+      "learning_rate": 1.0579096633038411e-07,
+      "loss": 0.0033,
+      "step": 3970
+    },
+    {
+      "epoch": 2.8307254623044096,
+      "grad_norm": 0.09895208971100541,
+      "learning_rate": 9.749149767002197e-08,
+      "loss": 0.0029,
+      "step": 3980
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.17612347880517987,
+      "learning_rate": 8.952781549638412e-08,
+      "loss": 0.0038,
+      "step": 3990
+    },
+    {
+      "epoch": 2.844950213371266,
+      "grad_norm": 0.13285843764249902,
+      "learning_rate": 8.190046526428241e-08,
+      "loss": 0.0028,
+      "step": 4000
+    },
+    {
+      "epoch": 2.852062588904694,
+      "grad_norm": 0.15853886614347157,
+      "learning_rate": 7.460996939221643e-08,
+      "loss": 0.0032,
+      "step": 4010
+    },
+    {
+      "epoch": 2.8591749644381226,
+      "grad_norm": 0.10115826454451997,
+      "learning_rate": 6.765682722659151e-08,
+      "loss": 0.0034,
+      "step": 4020
+    },
+    {
+      "epoch": 2.8662873399715503,
+      "grad_norm": 0.16050424912282388,
+      "learning_rate": 6.104151500751609e-08,
+      "loss": 0.0026,
+      "step": 4030
+    },
+    {
+      "epoch": 2.873399715504979,
+      "grad_norm": 0.10822054946183253,
+      "learning_rate": 5.476448583618288e-08,
+      "loss": 0.0035,
+      "step": 4040
+    },
+    {
+      "epoch": 2.8805120910384066,
+      "grad_norm": 0.1113521110254991,
+      "learning_rate": 4.8826169643832464e-08,
+      "loss": 0.0026,
+      "step": 4050
+    },
+    {
+      "epoch": 2.887624466571835,
+      "grad_norm": 0.14081228392187445,
+      "learning_rate": 4.322697316231361e-08,
+      "loss": 0.0032,
+      "step": 4060
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.11756191197474342,
+      "learning_rate": 3.796727989621385e-08,
+      "loss": 0.0024,
+      "step": 4070
+    },
+    {
+      "epoch": 2.9018492176386914,
+      "grad_norm": 0.14346626654053973,
+      "learning_rate": 3.304745009660326e-08,
+      "loss": 0.003,
+      "step": 4080
+    },
+    {
+      "epoch": 2.9089615931721196,
+      "grad_norm": 0.13833583160259022,
+      "learning_rate": 2.8467820736350903e-08,
+      "loss": 0.0028,
+      "step": 4090
+    },
+    {
+      "epoch": 2.9160739687055477,
+      "grad_norm": 0.08441703695039304,
+      "learning_rate": 2.422870548705103e-08,
+      "loss": 0.003,
+      "step": 4100
+    },
+    {
+      "epoch": 2.923186344238976,
+      "grad_norm": 0.15199272572784162,
+      "learning_rate": 2.0330394697534726e-08,
+      "loss": 0.0032,
+      "step": 4110
+    },
+    {
+      "epoch": 2.930298719772404,
+      "grad_norm": 0.09905970954206261,
+      "learning_rate": 1.677315537398583e-08,
+      "loss": 0.0033,
+      "step": 4120
+    },
+    {
+      "epoch": 2.937411095305832,
+      "grad_norm": 0.12746964816800027,
+      "learning_rate": 1.355723116165164e-08,
+      "loss": 0.003,
+      "step": 4130
+    },
+    {
+      "epoch": 2.9445234708392602,
+      "grad_norm": 0.1730883953102828,
+      "learning_rate": 1.0682842328154086e-08,
+      "loss": 0.003,
+      "step": 4140
+    },
+    {
+      "epoch": 2.9516358463726884,
+      "grad_norm": 0.14592570068315344,
+      "learning_rate": 8.150185748405092e-09,
+      "loss": 0.0034,
+      "step": 4150
+    },
+    {
+      "epoch": 2.9587482219061165,
+      "grad_norm": 0.16218729377273186,
+      "learning_rate": 5.959434891121274e-09,
+      "loss": 0.0031,
+      "step": 4160
+    },
+    {
+      "epoch": 2.9658605974395447,
+      "grad_norm": 0.1534720207270455,
+      "learning_rate": 4.110739806940656e-09,
+      "loss": 0.0028,
+      "step": 4170
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.1535652411238345,
+      "learning_rate": 2.604227118148117e-09,
+      "loss": 0.0025,
+      "step": 4180
+    },
+    {
+      "epoch": 2.9800853485064014,
+      "grad_norm": 0.21854345544372025,
+      "learning_rate": 1.4400000100017741e-09,
+      "loss": 0.0028,
+      "step": 4190
+    },
+    {
+      "epoch": 2.987197724039829,
+      "grad_norm": 0.11360018294244285,
+      "learning_rate": 6.181382236641887e-10,
+      "loss": 0.0027,
+      "step": 4200
+    },
+    {
+      "epoch": 2.9943100995732577,
+      "grad_norm": 0.13109703302719727,
+      "learning_rate": 1.3869805074284704e-10,
+      "loss": 0.003,
+      "step": 4210
+    },
+    {
+      "epoch": 3.0,
+      "step": 4218,
+      "total_flos": 247294279680000.0,
+      "train_loss": 0.26427117863254007,
+      "train_runtime": 27747.0354,
+      "train_samples_per_second": 9.727,
+      "train_steps_per_second": 0.152
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 4218,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 247294279680000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563bd929e6fd35927a880d21f2f35e526927af1ddb0723f0bc25cafcbba4fa73
+size 7889