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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<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
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b3e66f0dd0aaabc11ff22ef21e400048964ce1ffa6c3379eeee8453d0a4f15
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e35ede4836d089fae971a3f78b2ff99d0fda174fb34011fad3642849d4d6b43
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63599b1aa452543a7f882658f0e29d1e5c494a2b66b988557237c87548616a23
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f497d02a2d925538b303fc95dbefb2c54f8da74030ae9ed7f531c7d905e71149
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfaa3ba98d4162760925c2dc17f8720a8b9883e731dfabc95a3bec24be37a510
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00ff1392772bdd53f0df1e9c42edd25581b51a225b3b6494db6407f84bffe8fb
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b77dca5822f89113c283e84edba4fde8bc93e6439f9a839dc56b96b044366c
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0235f65880a7d8d12996de16f711ef807fec7a2d7d2944e7967393f6ca06f63
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5866a2c2497008d1f90fe32ebe4a14d52dd88e7bb32731fbbad8db1cd70feb91
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eceaa8649a5146334e99926dcde69d6dcb574c8b1e13bb617a3cadabb189e49
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c02afeb380522b36998b762ae3826f183d5f6edd2363fce5244c7f182c452b
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:052a54d1b7c4ac0743a3d2324a4763f3a7eb642184c011eecdf1ce1ef1e0ca37
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d757c7990f471eba9f44bc246c316af31fc1a240e16ecabd794a8c377b917ca9
+size 1094220288

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,241 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "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
+}

trainer_state.json

@@ -0,0 +1,3534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9033423667570009,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018066847335140017,
+      "grad_norm": 2.833710603673153,
+      "learning_rate": 0.0,
+      "loss": 0.8251,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036133694670280035,
+      "grad_norm": 2.881526090787093,
+      "learning_rate": 1.7857142857142858e-07,
+      "loss": 0.8284,
+      "step": 2
+    },
+    {
+      "epoch": 0.005420054200542005,
+      "grad_norm": 2.892351545715412,
+      "learning_rate": 3.5714285714285716e-07,
+      "loss": 0.8432,
+      "step": 3
+    },
+    {
+      "epoch": 0.007226738934056007,
+      "grad_norm": 2.854997748052911,
+      "learning_rate": 5.357142857142857e-07,
+      "loss": 0.8398,
+      "step": 4
+    },
+    {
+      "epoch": 0.009033423667570008,
+      "grad_norm": 2.800194786509123,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.8302,
+      "step": 5
+    },
+    {
+      "epoch": 0.01084010840108401,
+      "grad_norm": 2.7703722030307465,
+      "learning_rate": 8.928571428571429e-07,
+      "loss": 0.8306,
+      "step": 6
+    },
+    {
+      "epoch": 0.012646793134598013,
+      "grad_norm": 2.7419868468578503,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.813,
+      "step": 7
+    },
+    {
+      "epoch": 0.014453477868112014,
+      "grad_norm": 2.782799904203301,
+      "learning_rate": 1.25e-06,
+      "loss": 0.8215,
+      "step": 8
+    },
+    {
+      "epoch": 0.016260162601626018,
+      "grad_norm": 2.657957788320578,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.8192,
+      "step": 9
+    },
+    {
+      "epoch": 0.018066847335140017,
+      "grad_norm": 2.599128638584182,
+      "learning_rate": 1.6071428571428574e-06,
+      "loss": 0.8146,
+      "step": 10
+    },
+    {
+      "epoch": 0.01987353206865402,
+      "grad_norm": 2.2653416227389065,
+      "learning_rate": 1.7857142857142859e-06,
+      "loss": 0.8023,
+      "step": 11
+    },
+    {
+      "epoch": 0.02168021680216802,
+      "grad_norm": 2.132529562690701,
+      "learning_rate": 1.9642857142857144e-06,
+      "loss": 0.813,
+      "step": 12
+    },
+    {
+      "epoch": 0.023486901535682024,
+      "grad_norm": 2.183869626490225,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.8047,
+      "step": 13
+    },
+    {
+      "epoch": 0.025293586269196026,
+      "grad_norm": 2.038470938805882,
+      "learning_rate": 2.321428571428572e-06,
+      "loss": 0.8006,
+      "step": 14
+    },
+    {
+      "epoch": 0.02710027100271003,
+      "grad_norm": 1.4549601698726884,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7864,
+      "step": 15
+    },
+    {
+      "epoch": 0.028906955736224028,
+      "grad_norm": 1.4204350596775097,
+      "learning_rate": 2.6785714285714285e-06,
+      "loss": 0.7795,
+      "step": 16
+    },
+    {
+      "epoch": 0.03071364046973803,
+      "grad_norm": 1.3806667810715707,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.7872,
+      "step": 17
+    },
+    {
+      "epoch": 0.032520325203252036,
+      "grad_norm": 1.274491626508539,
+      "learning_rate": 3.0357142857142856e-06,
+      "loss": 0.7795,
+      "step": 18
+    },
+    {
+      "epoch": 0.03432700993676603,
+      "grad_norm": 1.216777658487583,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 0.773,
+      "step": 19
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "grad_norm": 1.0495765967682895,
+      "learning_rate": 3.3928571428571435e-06,
+      "loss": 0.743,
+      "step": 20
+    },
+    {
+      "epoch": 0.037940379403794036,
+      "grad_norm": 1.1207660747477255,
+      "learning_rate": 3.5714285714285718e-06,
+      "loss": 0.7403,
+      "step": 21
+    },
+    {
+      "epoch": 0.03974706413730804,
+      "grad_norm": 1.2817143165080294,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.7296,
+      "step": 22
+    },
+    {
+      "epoch": 0.04155374887082204,
+      "grad_norm": 1.3509916465584577,
+      "learning_rate": 3.928571428571429e-06,
+      "loss": 0.7302,
+      "step": 23
+    },
+    {
+      "epoch": 0.04336043360433604,
+      "grad_norm": 1.2332702771542092,
+      "learning_rate": 4.107142857142857e-06,
+      "loss": 0.7359,
+      "step": 24
+    },
+    {
+      "epoch": 0.045167118337850046,
+      "grad_norm": 0.9471118008485697,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.7129,
+      "step": 25
+    },
+    {
+      "epoch": 0.04697380307136405,
+      "grad_norm": 0.7486583362489228,
+      "learning_rate": 4.464285714285715e-06,
+      "loss": 0.7275,
+      "step": 26
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 0.6717818173905871,
+      "learning_rate": 4.642857142857144e-06,
+      "loss": 0.7021,
+      "step": 27
+    },
+    {
+      "epoch": 0.05058717253839205,
+      "grad_norm": 0.7950859243166388,
+      "learning_rate": 4.821428571428572e-06,
+      "loss": 0.6997,
+      "step": 28
+    },
+    {
+      "epoch": 0.052393857271906055,
+      "grad_norm": 0.8884910173051872,
+      "learning_rate": 5e-06,
+      "loss": 0.7086,
+      "step": 29
+    },
+    {
+      "epoch": 0.05420054200542006,
+      "grad_norm": 0.9673224881715593,
+      "learning_rate": 4.999955240022903e-06,
+      "loss": 0.7067,
+      "step": 30
+    },
+    {
+      "epoch": 0.05600722673893405,
+      "grad_norm": 0.9034786964026056,
+      "learning_rate": 4.999820961694372e-06,
+      "loss": 0.6936,
+      "step": 31
+    },
+    {
+      "epoch": 0.057813911472448055,
+      "grad_norm": 0.662557988289521,
+      "learning_rate": 4.999597169822646e-06,
+      "loss": 0.6811,
+      "step": 32
+    },
+    {
+      "epoch": 0.05962059620596206,
+      "grad_norm": 0.5043328133424003,
+      "learning_rate": 4.999283872421259e-06,
+      "loss": 0.6911,
+      "step": 33
+    },
+    {
+      "epoch": 0.06142728093947606,
+      "grad_norm": 0.5806752340113361,
+      "learning_rate": 4.998881080708759e-06,
+      "loss": 0.6766,
+      "step": 34
+    },
+    {
+      "epoch": 0.06323396567299007,
+      "grad_norm": 0.572041040601822,
+      "learning_rate": 4.998388809108304e-06,
+      "loss": 0.6815,
+      "step": 35
+    },
+    {
+      "epoch": 0.06504065040650407,
+      "grad_norm": 0.49944539615671646,
+      "learning_rate": 4.997807075247147e-06,
+      "loss": 0.6752,
+      "step": 36
+    },
+    {
+      "epoch": 0.06684733514001806,
+      "grad_norm": 0.5564450644413174,
+      "learning_rate": 4.997135899956002e-06,
+      "loss": 0.6781,
+      "step": 37
+    },
+    {
+      "epoch": 0.06865401987353206,
+      "grad_norm": 0.4421624128151595,
+      "learning_rate": 4.996375307268303e-06,
+      "loss": 0.6708,
+      "step": 38
+    },
+    {
+      "epoch": 0.07046070460704607,
+      "grad_norm": 0.4865410430073666,
+      "learning_rate": 4.995525324419338e-06,
+      "loss": 0.6706,
+      "step": 39
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "grad_norm": 0.3765775514297677,
+      "learning_rate": 4.994585981845278e-06,
+      "loss": 0.659,
+      "step": 40
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.3548944502238461,
+      "learning_rate": 4.993557313182086e-06,
+      "loss": 0.6664,
+      "step": 41
+    },
+    {
+      "epoch": 0.07588075880758807,
+      "grad_norm": 0.36293566558445617,
+      "learning_rate": 4.992439355264308e-06,
+      "loss": 0.656,
+      "step": 42
+    },
+    {
+      "epoch": 0.07768744354110207,
+      "grad_norm": 0.3975630575488288,
+      "learning_rate": 4.9912321481237616e-06,
+      "loss": 0.6566,
+      "step": 43
+    },
+    {
+      "epoch": 0.07949412827461608,
+      "grad_norm": 0.37034479741196286,
+      "learning_rate": 4.989935734988098e-06,
+      "loss": 0.6492,
+      "step": 44
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "grad_norm": 0.35041438533218666,
+      "learning_rate": 4.988550162279255e-06,
+      "loss": 0.6557,
+      "step": 45
+    },
+    {
+      "epoch": 0.08310749774164408,
+      "grad_norm": 0.3929751461483523,
+      "learning_rate": 4.9870754796117956e-06,
+      "loss": 0.658,
+      "step": 46
+    },
+    {
+      "epoch": 0.08491418247515808,
+      "grad_norm": 0.3228131120122744,
+      "learning_rate": 4.985511739791129e-06,
+      "loss": 0.6595,
+      "step": 47
+    },
+    {
+      "epoch": 0.08672086720867209,
+      "grad_norm": 0.32669811901998275,
+      "learning_rate": 4.983858998811622e-06,
+      "loss": 0.6464,
+      "step": 48
+    },
+    {
+      "epoch": 0.08852755194218609,
+      "grad_norm": 0.2958192972688314,
+      "learning_rate": 4.982117315854594e-06,
+      "loss": 0.6508,
+      "step": 49
+    },
+    {
+      "epoch": 0.09033423667570009,
+      "grad_norm": 0.29517256658089447,
+      "learning_rate": 4.980286753286196e-06,
+      "loss": 0.6493,
+      "step": 50
+    },
+    {
+      "epoch": 0.0921409214092141,
+      "grad_norm": 0.28707888927411485,
+      "learning_rate": 4.978367376655177e-06,
+      "loss": 0.639,
+      "step": 51
+    },
+    {
+      "epoch": 0.0939476061427281,
+      "grad_norm": 0.2839510706729385,
+      "learning_rate": 4.976359254690543e-06,
+      "loss": 0.6577,
+      "step": 52
+    },
+    {
+      "epoch": 0.0957542908762421,
+      "grad_norm": 0.2652433955956874,
+      "learning_rate": 4.974262459299088e-06,
+      "loss": 0.6408,
+      "step": 53
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.26894761764637504,
+      "learning_rate": 4.9720770655628216e-06,
+      "loss": 0.6323,
+      "step": 54
+    },
+    {
+      "epoch": 0.0993676603432701,
+      "grad_norm": 0.3393488396315471,
+      "learning_rate": 4.969803151736285e-06,
+      "loss": 0.6443,
+      "step": 55
+    },
+    {
+      "epoch": 0.1011743450767841,
+      "grad_norm": 0.2936280995299213,
+      "learning_rate": 4.967440799243739e-06,
+      "loss": 0.6504,
+      "step": 56
+    },
+    {
+      "epoch": 0.10298102981029811,
+      "grad_norm": 0.5048572168975388,
+      "learning_rate": 4.964990092676263e-06,
+      "loss": 0.6358,
+      "step": 57
+    },
+    {
+      "epoch": 0.10478771454381211,
+      "grad_norm": 0.253534540909337,
+      "learning_rate": 4.962451119788709e-06,
+      "loss": 0.6434,
+      "step": 58
+    },
+    {
+      "epoch": 0.10659439927732611,
+      "grad_norm": 0.24450647410382542,
+      "learning_rate": 4.959823971496575e-06,
+      "loss": 0.6287,
+      "step": 59
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "grad_norm": 0.24318659934415682,
+      "learning_rate": 4.957108741872736e-06,
+      "loss": 0.6298,
+      "step": 60
+    },
+    {
+      "epoch": 0.1102077687443541,
+      "grad_norm": 0.26159880879938346,
+      "learning_rate": 4.954305528144085e-06,
+      "loss": 0.6338,
+      "step": 61
+    },
+    {
+      "epoch": 0.1120144534778681,
+      "grad_norm": 0.25390256208872614,
+      "learning_rate": 4.9514144306880506e-06,
+      "loss": 0.6392,
+      "step": 62
+    },
+    {
+      "epoch": 0.11382113821138211,
+      "grad_norm": 0.2557236984724456,
+      "learning_rate": 4.948435553028994e-06,
+      "loss": 0.6381,
+      "step": 63
+    },
+    {
+      "epoch": 0.11562782294489611,
+      "grad_norm": 0.24995746272587419,
+      "learning_rate": 4.9453690018345144e-06,
+      "loss": 0.6358,
+      "step": 64
+    },
+    {
+      "epoch": 0.11743450767841011,
+      "grad_norm": 0.24266667399842143,
+      "learning_rate": 4.942214886911619e-06,
+      "loss": 0.6309,
+      "step": 65
+    },
+    {
+      "epoch": 0.11924119241192412,
+      "grad_norm": 0.2614760212116958,
+      "learning_rate": 4.938973321202799e-06,
+      "loss": 0.6324,
+      "step": 66
+    },
+    {
+      "epoch": 0.12104787714543812,
+      "grad_norm": 0.23803026874912583,
+      "learning_rate": 4.935644420781978e-06,
+      "loss": 0.6228,
+      "step": 67
+    },
+    {
+      "epoch": 0.12285456187895212,
+      "grad_norm": 0.23755765861041625,
+      "learning_rate": 4.932228304850363e-06,
+      "loss": 0.6387,
+      "step": 68
+    },
+    {
+      "epoch": 0.12466124661246612,
+      "grad_norm": 0.23843258528052497,
+      "learning_rate": 4.9287250957321685e-06,
+      "loss": 0.6401,
+      "step": 69
+    },
+    {
+      "epoch": 0.12646793134598014,
+      "grad_norm": 0.26210939608771777,
+      "learning_rate": 4.925134918870245e-06,
+      "loss": 0.6458,
+      "step": 70
+    },
+    {
+      "epoch": 0.12827461607949414,
+      "grad_norm": 0.32756867637738996,
+      "learning_rate": 4.921457902821578e-06,
+      "loss": 0.6164,
+      "step": 71
+    },
+    {
+      "epoch": 0.13008130081300814,
+      "grad_norm": 0.23025066317701987,
+      "learning_rate": 4.917694179252692e-06,
+      "loss": 0.6343,
+      "step": 72
+    },
+    {
+      "epoch": 0.13188798554652212,
+      "grad_norm": 0.2342725143215051,
+      "learning_rate": 4.9138438829349296e-06,
+      "loss": 0.633,
+      "step": 73
+    },
+    {
+      "epoch": 0.13369467028003612,
+      "grad_norm": 0.25602275015410886,
+      "learning_rate": 4.909907151739634e-06,
+      "loss": 0.6247,
+      "step": 74
+    },
+    {
+      "epoch": 0.13550135501355012,
+      "grad_norm": 0.27962135134351895,
+      "learning_rate": 4.9058841266332005e-06,
+      "loss": 0.6226,
+      "step": 75
+    },
+    {
+      "epoch": 0.13730803974706413,
+      "grad_norm": 0.2577599322141621,
+      "learning_rate": 4.901774951672041e-06,
+      "loss": 0.618,
+      "step": 76
+    },
+    {
+      "epoch": 0.13911472448057813,
+      "grad_norm": 0.25384048802645065,
+      "learning_rate": 4.897579773997415e-06,
+      "loss": 0.6122,
+      "step": 77
+    },
+    {
+      "epoch": 0.14092140921409213,
+      "grad_norm": 0.25252662487176686,
+      "learning_rate": 4.893298743830168e-06,
+      "loss": 0.625,
+      "step": 78
+    },
+    {
+      "epoch": 0.14272809394760613,
+      "grad_norm": 0.2581525435101277,
+      "learning_rate": 4.8889320144653525e-06,
+      "loss": 0.6345,
+      "step": 79
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 0.2559916652692462,
+      "learning_rate": 4.884479742266731e-06,
+      "loss": 0.6432,
+      "step": 80
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.2633785753789179,
+      "learning_rate": 4.879942086661185e-06,
+      "loss": 0.625,
+      "step": 81
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.25653911708344745,
+      "learning_rate": 4.875319210133004e-06,
+      "loss": 0.6185,
+      "step": 82
+    },
+    {
+      "epoch": 0.14995483288166214,
+      "grad_norm": 0.2508750960975656,
+      "learning_rate": 4.870611278218066e-06,
+      "loss": 0.6301,
+      "step": 83
+    },
+    {
+      "epoch": 0.15176151761517614,
+      "grad_norm": 0.2561874287228457,
+      "learning_rate": 4.865818459497911e-06,
+      "loss": 0.6222,
+      "step": 84
+    },
+    {
+      "epoch": 0.15356820234869015,
+      "grad_norm": 0.2353115985430909,
+      "learning_rate": 4.860940925593703e-06,
+      "loss": 0.6238,
+      "step": 85
+    },
+    {
+      "epoch": 0.15537488708220415,
+      "grad_norm": 0.24543988420919832,
+      "learning_rate": 4.855978851160088e-06,
+      "loss": 0.6243,
+      "step": 86
+    },
+    {
+      "epoch": 0.15718157181571815,
+      "grad_norm": 0.23980236271661898,
+      "learning_rate": 4.850932413878934e-06,
+      "loss": 0.6264,
+      "step": 87
+    },
+    {
+      "epoch": 0.15898825654923215,
+      "grad_norm": 0.23746967391567278,
+      "learning_rate": 4.845801794452978e-06,
+      "loss": 0.6308,
+      "step": 88
+    },
+    {
+      "epoch": 0.16079494128274616,
+      "grad_norm": 0.2438060428432456,
+      "learning_rate": 4.8405871765993435e-06,
+      "loss": 0.6256,
+      "step": 89
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "grad_norm": 0.2504401843691212,
+      "learning_rate": 4.8352887470429726e-06,
+      "loss": 0.6193,
+      "step": 90
+    },
+    {
+      "epoch": 0.16440831074977416,
+      "grad_norm": 0.22268738858248663,
+      "learning_rate": 4.829906695509934e-06,
+      "loss": 0.6175,
+      "step": 91
+    },
+    {
+      "epoch": 0.16621499548328816,
+      "grad_norm": 0.2560623721447496,
+      "learning_rate": 4.824441214720629e-06,
+      "loss": 0.6207,
+      "step": 92
+    },
+    {
+      "epoch": 0.16802168021680217,
+      "grad_norm": 0.23139572900738714,
+      "learning_rate": 4.8188925003828945e-06,
+      "loss": 0.6276,
+      "step": 93
+    },
+    {
+      "epoch": 0.16982836495031617,
+      "grad_norm": 0.2394430562047215,
+      "learning_rate": 4.813260751184992e-06,
+      "loss": 0.6254,
+      "step": 94
+    },
+    {
+      "epoch": 0.17163504968383017,
+      "grad_norm": 0.23489365258879913,
+      "learning_rate": 4.8075461687884935e-06,
+      "loss": 0.6184,
+      "step": 95
+    },
+    {
+      "epoch": 0.17344173441734417,
+      "grad_norm": 0.2390908704544338,
+      "learning_rate": 4.801748957821061e-06,
+      "loss": 0.6164,
+      "step": 96
+    },
+    {
+      "epoch": 0.17524841915085818,
+      "grad_norm": 0.2250588188582116,
+      "learning_rate": 4.795869325869117e-06,
+      "loss": 0.623,
+      "step": 97
+    },
+    {
+      "epoch": 0.17705510388437218,
+      "grad_norm": 0.21860584575831038,
+      "learning_rate": 4.7899074834704165e-06,
+      "loss": 0.6173,
+      "step": 98
+    },
+    {
+      "epoch": 0.17886178861788618,
+      "grad_norm": 0.24617787352480855,
+      "learning_rate": 4.783863644106502e-06,
+      "loss": 0.6291,
+      "step": 99
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "grad_norm": 0.21802652765301336,
+      "learning_rate": 4.777738024195065e-06,
+      "loss": 0.603,
+      "step": 100
+    },
+    {
+      "epoch": 0.18247515808491419,
+      "grad_norm": 0.24612254991135574,
+      "learning_rate": 4.771530843082187e-06,
+      "loss": 0.6184,
+      "step": 101
+    },
+    {
+      "epoch": 0.1842818428184282,
+      "grad_norm": 0.2215674593325698,
+      "learning_rate": 4.765242323034498e-06,
+      "loss": 0.6373,
+      "step": 102
+    },
+    {
+      "epoch": 0.1860885275519422,
+      "grad_norm": 0.25404300985614986,
+      "learning_rate": 4.7588726892312085e-06,
+      "loss": 0.6163,
+      "step": 103
+    },
+    {
+      "epoch": 0.1878952122854562,
+      "grad_norm": 0.23783935115186008,
+      "learning_rate": 4.752422169756048e-06,
+      "loss": 0.6147,
+      "step": 104
+    },
+    {
+      "epoch": 0.1897018970189702,
+      "grad_norm": 0.24743986064760354,
+      "learning_rate": 4.7458909955891015e-06,
+      "loss": 0.6065,
+      "step": 105
+    },
+    {
+      "epoch": 0.1915085817524842,
+      "grad_norm": 0.23334887533510995,
+      "learning_rate": 4.7392794005985324e-06,
+      "loss": 0.6078,
+      "step": 106
+    },
+    {
+      "epoch": 0.1933152664859982,
+      "grad_norm": 0.23602009638229515,
+      "learning_rate": 4.732587621532214e-06,
+      "loss": 0.6138,
+      "step": 107
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.24805889543073664,
+      "learning_rate": 4.7258158980092475e-06,
+      "loss": 0.6125,
+      "step": 108
+    },
+    {
+      "epoch": 0.1969286359530262,
+      "grad_norm": 0.23498308809668583,
+      "learning_rate": 4.718964472511386e-06,
+      "loss": 0.6225,
+      "step": 109
+    },
+    {
+      "epoch": 0.1987353206865402,
+      "grad_norm": 0.23642037798176344,
+      "learning_rate": 4.712033590374346e-06,
+      "loss": 0.6039,
+      "step": 110
+    },
+    {
+      "epoch": 0.2005420054200542,
+      "grad_norm": 0.22293626788964602,
+      "learning_rate": 4.705023499779031e-06,
+      "loss": 0.6229,
+      "step": 111
+    },
+    {
+      "epoch": 0.2023486901535682,
+      "grad_norm": 0.2760226539747174,
+      "learning_rate": 4.6979344517426345e-06,
+      "loss": 0.6157,
+      "step": 112
+    },
+    {
+      "epoch": 0.2041553748870822,
+      "grad_norm": 0.21252834514519925,
+      "learning_rate": 4.690766700109659e-06,
+      "loss": 0.6192,
+      "step": 113
+    },
+    {
+      "epoch": 0.20596205962059622,
+      "grad_norm": 0.2445316744832756,
+      "learning_rate": 4.683520501542825e-06,
+      "loss": 0.6021,
+      "step": 114
+    },
+    {
+      "epoch": 0.20776874435411022,
+      "grad_norm": 0.24106223998119997,
+      "learning_rate": 4.676196115513876e-06,
+      "loss": 0.6184,
+      "step": 115
+    },
+    {
+      "epoch": 0.20957542908762422,
+      "grad_norm": 0.22622127875647777,
+      "learning_rate": 4.668793804294294e-06,
+      "loss": 0.6128,
+      "step": 116
+    },
+    {
+      "epoch": 0.21138211382113822,
+      "grad_norm": 0.2438334449683093,
+      "learning_rate": 4.661313832945904e-06,
+      "loss": 0.6226,
+      "step": 117
+    },
+    {
+      "epoch": 0.21318879855465223,
+      "grad_norm": 0.22677844575581005,
+      "learning_rate": 4.653756469311381e-06,
+      "loss": 0.6103,
+      "step": 118
+    },
+    {
+      "epoch": 0.21499548328816623,
+      "grad_norm": 0.22925833245122096,
+      "learning_rate": 4.646121984004666e-06,
+      "loss": 0.6017,
+      "step": 119
+    },
+    {
+      "epoch": 0.21680216802168023,
+      "grad_norm": 0.23651197792785295,
+      "learning_rate": 4.638410650401267e-06,
+      "loss": 0.6192,
+      "step": 120
+    },
+    {
+      "epoch": 0.2186088527551942,
+      "grad_norm": 0.23284082311202126,
+      "learning_rate": 4.630622744628478e-06,
+      "loss": 0.6156,
+      "step": 121
+    },
+    {
+      "epoch": 0.2204155374887082,
+      "grad_norm": 0.22835537092235955,
+      "learning_rate": 4.622758545555485e-06,
+      "loss": 0.6202,
+      "step": 122
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.26232157389806815,
+      "learning_rate": 4.614818334783384e-06,
+      "loss": 0.6118,
+      "step": 123
+    },
+    {
+      "epoch": 0.2240289069557362,
+      "grad_norm": 1.0190897748265104,
+      "learning_rate": 4.606802396635098e-06,
+      "loss": 0.5974,
+      "step": 124
+    },
+    {
+      "epoch": 0.22583559168925021,
+      "grad_norm": 0.22367646253830858,
+      "learning_rate": 4.598711018145193e-06,
+      "loss": 0.6034,
+      "step": 125
+    },
+    {
+      "epoch": 0.22764227642276422,
+      "grad_norm": 0.30477162914891215,
+      "learning_rate": 4.590544489049602e-06,
+      "loss": 0.6166,
+      "step": 126
+    },
+    {
+      "epoch": 0.22944896115627822,
+      "grad_norm": 0.24111073356626345,
+      "learning_rate": 4.582303101775249e-06,
+      "loss": 0.608,
+      "step": 127
+    },
+    {
+      "epoch": 0.23125564588979222,
+      "grad_norm": 0.22993786809415329,
+      "learning_rate": 4.573987151429579e-06,
+      "loss": 0.6075,
+      "step": 128
+    },
+    {
+      "epoch": 0.23306233062330622,
+      "grad_norm": 0.24166169868220508,
+      "learning_rate": 4.565596935789987e-06,
+      "loss": 0.6032,
+      "step": 129
+    },
+    {
+      "epoch": 0.23486901535682023,
+      "grad_norm": 0.2817874670342333,
+      "learning_rate": 4.557132755293164e-06,
+      "loss": 0.622,
+      "step": 130
+    },
+    {
+      "epoch": 0.23667570009033423,
+      "grad_norm": 0.24069107260810058,
+      "learning_rate": 4.54859491302433e-06,
+      "loss": 0.6154,
+      "step": 131
+    },
+    {
+      "epoch": 0.23848238482384823,
+      "grad_norm": 0.22882671727182136,
+      "learning_rate": 4.539983714706383e-06,
+      "loss": 0.5943,
+      "step": 132
+    },
+    {
+      "epoch": 0.24028906955736223,
+      "grad_norm": 0.22659848940942331,
+      "learning_rate": 4.531299468688956e-06,
+      "loss": 0.61,
+      "step": 133
+    },
+    {
+      "epoch": 0.24209575429087624,
+      "grad_norm": 0.22507834440544988,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.6105,
+      "step": 134
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.2337177257871415,
+      "learning_rate": 4.5137130800215025e-06,
+      "loss": 0.6068,
+      "step": 135
+    },
+    {
+      "epoch": 0.24570912375790424,
+      "grad_norm": 0.22156146362385887,
+      "learning_rate": 4.50481156710456e-06,
+      "loss": 0.6115,
+      "step": 136
+    },
+    {
+      "epoch": 0.24751580849141824,
+      "grad_norm": 0.23698883199253348,
+      "learning_rate": 4.495838265931754e-06,
+      "loss": 0.5951,
+      "step": 137
+    },
+    {
+      "epoch": 0.24932249322493225,
+      "grad_norm": 0.2229333193124451,
+      "learning_rate": 4.486793497818889e-06,
+      "loss": 0.612,
+      "step": 138
+    },
+    {
+      "epoch": 0.25112917795844625,
+      "grad_norm": 0.22777084728583424,
+      "learning_rate": 4.477677586640854e-06,
+      "loss": 0.6156,
+      "step": 139
+    },
+    {
+      "epoch": 0.2529358626919603,
+      "grad_norm": 0.29038768857745073,
+      "learning_rate": 4.4684908588200305e-06,
+      "loss": 0.6157,
+      "step": 140
+    },
+    {
+      "epoch": 0.25474254742547425,
+      "grad_norm": 0.2473807343598257,
+      "learning_rate": 4.4592336433146e-06,
+      "loss": 0.5953,
+      "step": 141
+    },
+    {
+      "epoch": 0.2565492321589883,
+      "grad_norm": 0.21649386979218563,
+      "learning_rate": 4.449906271606766e-06,
+      "loss": 0.6159,
+      "step": 142
+    },
+    {
+      "epoch": 0.25835591689250226,
+      "grad_norm": 0.24042251758250033,
+      "learning_rate": 4.440509077690883e-06,
+      "loss": 0.6069,
+      "step": 143
+    },
+    {
+      "epoch": 0.2601626016260163,
+      "grad_norm": 0.36770971559928356,
+      "learning_rate": 4.431042398061499e-06,
+      "loss": 0.5967,
+      "step": 144
+    },
+    {
+      "epoch": 0.26196928635953026,
+      "grad_norm": 0.20875517006997382,
+      "learning_rate": 4.421506571701305e-06,
+      "loss": 0.6091,
+      "step": 145
+    },
+    {
+      "epoch": 0.26377597109304424,
+      "grad_norm": 0.34540212409106824,
+      "learning_rate": 4.411901940068997e-06,
+      "loss": 0.6111,
+      "step": 146
+    },
+    {
+      "epoch": 0.26558265582655827,
+      "grad_norm": 0.2313988977179789,
+      "learning_rate": 4.402228847087046e-06,
+      "loss": 0.6036,
+      "step": 147
+    },
+    {
+      "epoch": 0.26738934056007224,
+      "grad_norm": 0.2566389864906536,
+      "learning_rate": 4.3924876391293915e-06,
+      "loss": 0.6049,
+      "step": 148
+    },
+    {
+      "epoch": 0.26919602529358627,
+      "grad_norm": 0.22910952216670477,
+      "learning_rate": 4.382678665009028e-06,
+      "loss": 0.6016,
+      "step": 149
+    },
+    {
+      "epoch": 0.27100271002710025,
+      "grad_norm": 0.229201881251706,
+      "learning_rate": 4.372802275965521e-06,
+      "loss": 0.6102,
+      "step": 150
+    },
+    {
+      "epoch": 0.2728093947606143,
+      "grad_norm": 0.2689283377981859,
+      "learning_rate": 4.362858825652428e-06,
+      "loss": 0.595,
+      "step": 151
+    },
+    {
+      "epoch": 0.27461607949412825,
+      "grad_norm": 0.2348399745355362,
+      "learning_rate": 4.352848670124637e-06,
+      "loss": 0.5995,
+      "step": 152
+    },
+    {
+      "epoch": 0.2764227642276423,
+      "grad_norm": 0.23839869995063648,
+      "learning_rate": 4.342772167825613e-06,
+      "loss": 0.6009,
+      "step": 153
+    },
+    {
+      "epoch": 0.27822944896115626,
+      "grad_norm": 0.22612816420838172,
+      "learning_rate": 4.332629679574566e-06,
+      "loss": 0.6063,
+      "step": 154
+    },
+    {
+      "epoch": 0.2800361336946703,
+      "grad_norm": 0.2385731884325847,
+      "learning_rate": 4.322421568553529e-06,
+      "loss": 0.5963,
+      "step": 155
+    },
+    {
+      "epoch": 0.28184281842818426,
+      "grad_norm": 0.2069980149679815,
+      "learning_rate": 4.312148200294355e-06,
+      "loss": 0.598,
+      "step": 156
+    },
+    {
+      "epoch": 0.2836495031616983,
+      "grad_norm": 0.2443362265256338,
+      "learning_rate": 4.3018099426656255e-06,
+      "loss": 0.6106,
+      "step": 157
+    },
+    {
+      "epoch": 0.28545618789521227,
+      "grad_norm": 0.22125798424540696,
+      "learning_rate": 4.291407165859481e-06,
+      "loss": 0.6073,
+      "step": 158
+    },
+    {
+      "epoch": 0.2872628726287263,
+      "grad_norm": 0.23484255914212887,
+      "learning_rate": 4.280940242378363e-06,
+      "loss": 0.5893,
+      "step": 159
+    },
+    {
+      "epoch": 0.28906955736224027,
+      "grad_norm": 0.2378182470960287,
+      "learning_rate": 4.2704095470216745e-06,
+      "loss": 0.5983,
+      "step": 160
+    },
+    {
+      "epoch": 0.2908762420957543,
+      "grad_norm": 0.22837213595253308,
+      "learning_rate": 4.259815456872363e-06,
+      "loss": 0.604,
+      "step": 161
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.22929353301353925,
+      "learning_rate": 4.249158351283414e-06,
+      "loss": 0.5904,
+      "step": 162
+    },
+    {
+      "epoch": 0.2944896115627823,
+      "grad_norm": 0.23217030236809272,
+      "learning_rate": 4.2384386118642696e-06,
+      "loss": 0.6007,
+      "step": 163
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.23822375648362773,
+      "learning_rate": 4.227656622467162e-06,
+      "loss": 0.609,
+      "step": 164
+    },
+    {
+      "epoch": 0.2981029810298103,
+      "grad_norm": 0.24124088260796128,
+      "learning_rate": 4.216812769173371e-06,
+      "loss": 0.6008,
+      "step": 165
+    },
+    {
+      "epoch": 0.2999096657633243,
+      "grad_norm": 0.22153075465196947,
+      "learning_rate": 4.205907440279395e-06,
+      "loss": 0.607,
+      "step": 166
+    },
+    {
+      "epoch": 0.3017163504968383,
+      "grad_norm": 0.21711862309864874,
+      "learning_rate": 4.194941026283053e-06,
+      "loss": 0.6063,
+      "step": 167
+    },
+    {
+      "epoch": 0.3035230352303523,
+      "grad_norm": 0.22432330344213172,
+      "learning_rate": 4.183913919869495e-06,
+      "loss": 0.6039,
+      "step": 168
+    },
+    {
+      "epoch": 0.3053297199638663,
+      "grad_norm": 0.21572998238848462,
+      "learning_rate": 4.172826515897146e-06,
+      "loss": 0.5969,
+      "step": 169
+    },
+    {
+      "epoch": 0.3071364046973803,
+      "grad_norm": 0.22067551805641855,
+      "learning_rate": 4.161679211383565e-06,
+      "loss": 0.6116,
+      "step": 170
+    },
+    {
+      "epoch": 0.3089430894308943,
+      "grad_norm": 0.22703585317519762,
+      "learning_rate": 4.150472405491226e-06,
+      "loss": 0.5937,
+      "step": 171
+    },
+    {
+      "epoch": 0.3107497741644083,
+      "grad_norm": 0.22250449959205287,
+      "learning_rate": 4.139206499513231e-06,
+      "loss": 0.6001,
+      "step": 172
+    },
+    {
+      "epoch": 0.31255645889792233,
+      "grad_norm": 0.20802156234358865,
+      "learning_rate": 4.127881896858934e-06,
+      "loss": 0.6037,
+      "step": 173
+    },
+    {
+      "epoch": 0.3143631436314363,
+      "grad_norm": 0.22038948428329844,
+      "learning_rate": 4.116499003039499e-06,
+      "loss": 0.5948,
+      "step": 174
+    },
+    {
+      "epoch": 0.31616982836495033,
+      "grad_norm": 0.23649589313584202,
+      "learning_rate": 4.105058225653381e-06,
+      "loss": 0.5999,
+      "step": 175
+    },
+    {
+      "epoch": 0.3179765130984643,
+      "grad_norm": 0.2274306926862935,
+      "learning_rate": 4.093559974371725e-06,
+      "loss": 0.6134,
+      "step": 176
+    },
+    {
+      "epoch": 0.31978319783197834,
+      "grad_norm": 0.22419208649241737,
+      "learning_rate": 4.0820046609237026e-06,
+      "loss": 0.5881,
+      "step": 177
+    },
+    {
+      "epoch": 0.3215898825654923,
+      "grad_norm": 0.21680164152050496,
+      "learning_rate": 4.070392699081767e-06,
+      "loss": 0.5947,
+      "step": 178
+    },
+    {
+      "epoch": 0.32339656729900634,
+      "grad_norm": 0.2223339254360786,
+      "learning_rate": 4.058724504646834e-06,
+      "loss": 0.6055,
+      "step": 179
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 0.23331107157838193,
+      "learning_rate": 4.047000495433397e-06,
+      "loss": 0.6134,
+      "step": 180
+    },
+    {
+      "epoch": 0.32700993676603435,
+      "grad_norm": 0.21996861718872435,
+      "learning_rate": 4.035221091254563e-06,
+      "loss": 0.5902,
+      "step": 181
+    },
+    {
+      "epoch": 0.3288166214995483,
+      "grad_norm": 0.24428874512652157,
+      "learning_rate": 4.023386713907021e-06,
+      "loss": 0.6003,
+      "step": 182
+    },
+    {
+      "epoch": 0.33062330623306235,
+      "grad_norm": 0.2305392278811606,
+      "learning_rate": 4.011497787155938e-06,
+      "loss": 0.6123,
+      "step": 183
+    },
+    {
+      "epoch": 0.3324299909665763,
+      "grad_norm": 0.2561643139152072,
+      "learning_rate": 3.999554736719785e-06,
+      "loss": 0.6095,
+      "step": 184
+    },
+    {
+      "epoch": 0.33423667570009036,
+      "grad_norm": 0.2358012826148262,
+      "learning_rate": 3.987557990255093e-06,
+      "loss": 0.6053,
+      "step": 185
+    },
+    {
+      "epoch": 0.33604336043360433,
+      "grad_norm": 0.24287341826766704,
+      "learning_rate": 3.975507977341141e-06,
+      "loss": 0.601,
+      "step": 186
+    },
+    {
+      "epoch": 0.33785004516711836,
+      "grad_norm": 0.20879030526781392,
+      "learning_rate": 3.963405129464569e-06,
+      "loss": 0.5983,
+      "step": 187
+    },
+    {
+      "epoch": 0.33965672990063234,
+      "grad_norm": 0.28353592150903156,
+      "learning_rate": 3.951249880003934e-06,
+      "loss": 0.5974,
+      "step": 188
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.2214488122199161,
+      "learning_rate": 3.939042664214185e-06,
+      "loss": 0.6053,
+      "step": 189
+    },
+    {
+      "epoch": 0.34327009936766034,
+      "grad_norm": 0.23803809202081058,
+      "learning_rate": 3.92678391921108e-06,
+      "loss": 0.5937,
+      "step": 190
+    },
+    {
+      "epoch": 0.34507678410117437,
+      "grad_norm": 0.22684507950838628,
+      "learning_rate": 3.914474083955537e-06,
+      "loss": 0.592,
+      "step": 191
+    },
+    {
+      "epoch": 0.34688346883468835,
+      "grad_norm": 0.20681090678985584,
+      "learning_rate": 3.902113599237911e-06,
+      "loss": 0.5986,
+      "step": 192
+    },
+    {
+      "epoch": 0.3486901535682023,
+      "grad_norm": 0.19866617565983444,
+      "learning_rate": 3.889702907662212e-06,
+      "loss": 0.6008,
+      "step": 193
+    },
+    {
+      "epoch": 0.35049683830171635,
+      "grad_norm": 0.2302303968413167,
+      "learning_rate": 3.8772424536302565e-06,
+      "loss": 0.602,
+      "step": 194
+    },
+    {
+      "epoch": 0.3523035230352303,
+      "grad_norm": 0.2363831434168681,
+      "learning_rate": 3.864732683325755e-06,
+      "loss": 0.5857,
+      "step": 195
+    },
+    {
+      "epoch": 0.35411020776874436,
+      "grad_norm": 0.23853047160053847,
+      "learning_rate": 3.852174044698333e-06,
+      "loss": 0.5988,
+      "step": 196
+    },
+    {
+      "epoch": 0.35591689250225833,
+      "grad_norm": 0.22998735263346828,
+      "learning_rate": 3.839566987447492e-06,
+      "loss": 0.598,
+      "step": 197
+    },
+    {
+      "epoch": 0.35772357723577236,
+      "grad_norm": 0.23941067077880493,
+      "learning_rate": 3.826911963006508e-06,
+      "loss": 0.5752,
+      "step": 198
+    },
+    {
+      "epoch": 0.35953026196928634,
+      "grad_norm": 0.2284898801622664,
+      "learning_rate": 3.8142094245262617e-06,
+      "loss": 0.5978,
+      "step": 199
+    },
+    {
+      "epoch": 0.36133694670280037,
+      "grad_norm": 0.2310316432666973,
+      "learning_rate": 3.801459826859022e-06,
+      "loss": 0.5876,
+      "step": 200
+    },
+    {
+      "epoch": 0.36314363143631434,
+      "grad_norm": 0.22874021440150738,
+      "learning_rate": 3.788663626542146e-06,
+      "loss": 0.5822,
+      "step": 201
+    },
+    {
+      "epoch": 0.36495031616982837,
+      "grad_norm": 0.23754593387894263,
+      "learning_rate": 3.7758212817817406e-06,
+      "loss": 0.6092,
+      "step": 202
+    },
+    {
+      "epoch": 0.36675700090334235,
+      "grad_norm": 0.23555267453276538,
+      "learning_rate": 3.7629332524362532e-06,
+      "loss": 0.5961,
+      "step": 203
+    },
+    {
+      "epoch": 0.3685636856368564,
+      "grad_norm": 0.263996613196296,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6088,
+      "step": 204
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 0.2220695749412859,
+      "learning_rate": 3.7370219875866497e-06,
+      "loss": 0.5985,
+      "step": 205
+    },
+    {
+      "epoch": 0.3721770551038844,
+      "grad_norm": 0.22266417943488925,
+      "learning_rate": 3.7239996799126315e-06,
+      "loss": 0.5863,
+      "step": 206
+    },
+    {
+      "epoch": 0.37398373983739835,
+      "grad_norm": 0.22936855717559157,
+      "learning_rate": 3.7109335432805006e-06,
+      "loss": 0.5944,
+      "step": 207
+    },
+    {
+      "epoch": 0.3757904245709124,
+      "grad_norm": 0.22850775987856617,
+      "learning_rate": 3.697824045562238e-06,
+      "loss": 0.5806,
+      "step": 208
+    },
+    {
+      "epoch": 0.37759710930442636,
+      "grad_norm": 0.24701920957996232,
+      "learning_rate": 3.684671656182497e-06,
+      "loss": 0.6027,
+      "step": 209
+    },
+    {
+      "epoch": 0.3794037940379404,
+      "grad_norm": 0.21373080476647208,
+      "learning_rate": 3.671476846101797e-06,
+      "loss": 0.5974,
+      "step": 210
+    },
+    {
+      "epoch": 0.38121047877145436,
+      "grad_norm": 0.22435107184170758,
+      "learning_rate": 3.658240087799655e-06,
+      "loss": 0.5996,
+      "step": 211
+    },
+    {
+      "epoch": 0.3830171635049684,
+      "grad_norm": 0.22948717204733204,
+      "learning_rate": 3.644961855257669e-06,
+      "loss": 0.608,
+      "step": 212
+    },
+    {
+      "epoch": 0.38482384823848237,
+      "grad_norm": 0.24067858739835768,
+      "learning_rate": 3.6316426239425484e-06,
+      "loss": 0.6062,
+      "step": 213
+    },
+    {
+      "epoch": 0.3866305329719964,
+      "grad_norm": 0.24899724125737957,
+      "learning_rate": 3.6182828707890816e-06,
+      "loss": 0.5924,
+      "step": 214
+    },
+    {
+      "epoch": 0.3884372177055104,
+      "grad_norm": 0.2355151032011817,
+      "learning_rate": 3.6048830741830678e-06,
+      "loss": 0.6195,
+      "step": 215
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.23883341592646898,
+      "learning_rate": 3.5914437139441754e-06,
+      "loss": 0.6082,
+      "step": 216
+    },
+    {
+      "epoch": 0.3920505871725384,
+      "grad_norm": 0.23501581194194024,
+      "learning_rate": 3.5779652713087717e-06,
+      "loss": 0.6082,
+      "step": 217
+    },
+    {
+      "epoch": 0.3938572719060524,
+      "grad_norm": 0.2569106741294839,
+      "learning_rate": 3.564448228912682e-06,
+      "loss": 0.5999,
+      "step": 218
+    },
+    {
+      "epoch": 0.3956639566395664,
+      "grad_norm": 0.23451645141530233,
+      "learning_rate": 3.5508930707739143e-06,
+      "loss": 0.5942,
+      "step": 219
+    },
+    {
+      "epoch": 0.3974706413730804,
+      "grad_norm": 0.25332615378033807,
+      "learning_rate": 3.5373002822753217e-06,
+      "loss": 0.5984,
+      "step": 220
+    },
+    {
+      "epoch": 0.3992773261065944,
+      "grad_norm": 0.21573314905985583,
+      "learning_rate": 3.523670350147227e-06,
+      "loss": 0.586,
+      "step": 221
+    },
+    {
+      "epoch": 0.4010840108401084,
+      "grad_norm": 0.22402654512077783,
+      "learning_rate": 3.510003762449988e-06,
+      "loss": 0.6031,
+      "step": 222
+    },
+    {
+      "epoch": 0.4028906955736224,
+      "grad_norm": 0.23430699042260314,
+      "learning_rate": 3.496301008556529e-06,
+      "loss": 0.5861,
+      "step": 223
+    },
+    {
+      "epoch": 0.4046973803071364,
+      "grad_norm": 0.2112766887800661,
+      "learning_rate": 3.4825625791348093e-06,
+      "loss": 0.5917,
+      "step": 224
+    },
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 0.2594229676066792,
+      "learning_rate": 3.4687889661302577e-06,
+      "loss": 0.5951,
+      "step": 225
+    },
+    {
+      "epoch": 0.4083107497741644,
+      "grad_norm": 0.21977632231714242,
+      "learning_rate": 3.454980662748156e-06,
+      "loss": 0.6022,
+      "step": 226
+    },
+    {
+      "epoch": 0.4101174345076784,
+      "grad_norm": 0.24331427531174873,
+      "learning_rate": 3.44113816343598e-06,
+      "loss": 0.6074,
+      "step": 227
+    },
+    {
+      "epoch": 0.41192411924119243,
+      "grad_norm": 0.2420730990351626,
+      "learning_rate": 3.4272619638656914e-06,
+      "loss": 0.5938,
+      "step": 228
+    },
+    {
+      "epoch": 0.4137308039747064,
+      "grad_norm": 0.2113848379255305,
+      "learning_rate": 3.4133525609159883e-06,
+      "loss": 0.5953,
+      "step": 229
+    },
+    {
+      "epoch": 0.41553748870822044,
+      "grad_norm": 0.2278511980807453,
+      "learning_rate": 3.399410452654518e-06,
+      "loss": 0.5976,
+      "step": 230
+    },
+    {
+      "epoch": 0.4173441734417344,
+      "grad_norm": 0.22656717412493943,
+      "learning_rate": 3.3854361383200372e-06,
+      "loss": 0.5981,
+      "step": 231
+    },
+    {
+      "epoch": 0.41915085817524844,
+      "grad_norm": 0.21257157836910553,
+      "learning_rate": 3.3714301183045382e-06,
+      "loss": 0.6008,
+      "step": 232
+    },
+    {
+      "epoch": 0.4209575429087624,
+      "grad_norm": 0.225673129949644,
+      "learning_rate": 3.357392894135329e-06,
+      "loss": 0.5818,
+      "step": 233
+    },
+    {
+      "epoch": 0.42276422764227645,
+      "grad_norm": 0.4682554631351164,
+      "learning_rate": 3.3433249684570757e-06,
+      "loss": 0.5984,
+      "step": 234
+    },
+    {
+      "epoch": 0.4245709123757904,
+      "grad_norm": 0.21876994996840093,
+      "learning_rate": 3.329226845013802e-06,
+      "loss": 0.5929,
+      "step": 235
+    },
+    {
+      "epoch": 0.42637759710930445,
+      "grad_norm": 0.21396549715257288,
+      "learning_rate": 3.315099028630855e-06,
+      "loss": 0.605,
+      "step": 236
+    },
+    {
+      "epoch": 0.4281842818428184,
+      "grad_norm": 0.24546725294633087,
+      "learning_rate": 3.3009420251968245e-06,
+      "loss": 0.6027,
+      "step": 237
+    },
+    {
+      "epoch": 0.42999096657633246,
+      "grad_norm": 0.21189353474136885,
+      "learning_rate": 3.28675634164543e-06,
+      "loss": 0.6123,
+      "step": 238
+    },
+    {
+      "epoch": 0.43179765130984643,
+      "grad_norm": 0.23626902591793353,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.5943,
+      "step": 239
+    },
+    {
+      "epoch": 0.43360433604336046,
+      "grad_norm": 0.21589261558067036,
+      "learning_rate": 3.258300967042125e-06,
+      "loss": 0.5947,
+      "step": 240
+    },
+    {
+      "epoch": 0.43541102077687444,
+      "grad_norm": 0.24017253917658596,
+      "learning_rate": 3.2440322949197467e-06,
+      "loss": 0.5927,
+      "step": 241
+    },
+    {
+      "epoch": 0.4372177055103884,
+      "grad_norm": 0.21325298090224806,
+      "learning_rate": 3.229736980502584e-06,
+      "loss": 0.5935,
+      "step": 242
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.23117870895524098,
+      "learning_rate": 3.2154155356769922e-06,
+      "loss": 0.5974,
+      "step": 243
+    },
+    {
+      "epoch": 0.4408310749774164,
+      "grad_norm": 0.2206632860171201,
+      "learning_rate": 3.201068473265007e-06,
+      "loss": 0.6029,
+      "step": 244
+    },
+    {
+      "epoch": 0.44263775971093045,
+      "grad_norm": 0.22021715956332263,
+      "learning_rate": 3.186696307005976e-06,
+      "loss": 0.5962,
+      "step": 245
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.23476509271910456,
+      "learning_rate": 3.1722995515381644e-06,
+      "loss": 0.6027,
+      "step": 246
+    },
+    {
+      "epoch": 0.44625112917795845,
+      "grad_norm": 0.22784064428785847,
+      "learning_rate": 3.1578787223803296e-06,
+      "loss": 0.5855,
+      "step": 247
+    },
+    {
+      "epoch": 0.4480578139114724,
+      "grad_norm": 0.2235087678808535,
+      "learning_rate": 3.1434343359132565e-06,
+      "loss": 0.6036,
+      "step": 248
+    },
+    {
+      "epoch": 0.44986449864498645,
+      "grad_norm": 0.207464881051444,
+      "learning_rate": 3.128966909361272e-06,
+      "loss": 0.5866,
+      "step": 249
+    },
+    {
+      "epoch": 0.45167118337850043,
+      "grad_norm": 0.2174732745725859,
+      "learning_rate": 3.1144769607737204e-06,
+      "loss": 0.6011,
+      "step": 250
+    },
+    {
+      "epoch": 0.45347786811201446,
+      "grad_norm": 0.21953836324624784,
+      "learning_rate": 3.099965009006415e-06,
+      "loss": 0.5894,
+      "step": 251
+    },
+    {
+      "epoch": 0.45528455284552843,
+      "grad_norm": 0.21126348106595308,
+      "learning_rate": 3.08543157370306e-06,
+      "loss": 0.5707,
+      "step": 252
+    },
+    {
+      "epoch": 0.45709123757904246,
+      "grad_norm": 0.24650243361345475,
+      "learning_rate": 3.0708771752766397e-06,
+      "loss": 0.5935,
+      "step": 253
+    },
+    {
+      "epoch": 0.45889792231255644,
+      "grad_norm": 0.2249746208569381,
+      "learning_rate": 3.056302334890786e-06,
+      "loss": 0.5921,
+      "step": 254
+    },
+    {
+      "epoch": 0.46070460704607047,
+      "grad_norm": 0.21497114185767313,
+      "learning_rate": 3.041707574441118e-06,
+      "loss": 0.5862,
+      "step": 255
+    },
+    {
+      "epoch": 0.46251129177958444,
+      "grad_norm": 0.22138733157917687,
+      "learning_rate": 3.027093416536548e-06,
+      "loss": 0.5867,
+      "step": 256
+    },
+    {
+      "epoch": 0.4643179765130985,
+      "grad_norm": 0.22437622502926427,
+      "learning_rate": 3.0124603844805767e-06,
+      "loss": 0.5962,
+      "step": 257
+    },
+    {
+      "epoch": 0.46612466124661245,
+      "grad_norm": 0.2135165286596709,
+      "learning_rate": 2.9978090022525456e-06,
+      "loss": 0.5914,
+      "step": 258
+    },
+    {
+      "epoch": 0.4679313459801265,
+      "grad_norm": 0.2182517656574138,
+      "learning_rate": 2.9831397944888833e-06,
+      "loss": 0.5955,
+      "step": 259
+    },
+    {
+      "epoch": 0.46973803071364045,
+      "grad_norm": 0.24251723379092627,
+      "learning_rate": 2.9684532864643123e-06,
+      "loss": 0.6096,
+      "step": 260
+    },
+    {
+      "epoch": 0.4715447154471545,
+      "grad_norm": 0.30798107619678294,
+      "learning_rate": 2.953750004073041e-06,
+      "loss": 0.6009,
+      "step": 261
+    },
+    {
+      "epoch": 0.47335140018066846,
+      "grad_norm": 0.2036561256279162,
+      "learning_rate": 2.9390304738099385e-06,
+      "loss": 0.5895,
+      "step": 262
+    },
+    {
+      "epoch": 0.4751580849141825,
+      "grad_norm": 0.20262069143669137,
+      "learning_rate": 2.9242952227516726e-06,
+      "loss": 0.5931,
+      "step": 263
+    },
+    {
+      "epoch": 0.47696476964769646,
+      "grad_norm": 0.22115029057191055,
+      "learning_rate": 2.9095447785378446e-06,
+      "loss": 0.6007,
+      "step": 264
+    },
+    {
+      "epoch": 0.4787714543812105,
+      "grad_norm": 0.20864586645540997,
+      "learning_rate": 2.89477966935209e-06,
+      "loss": 0.581,
+      "step": 265
+    },
+    {
+      "epoch": 0.48057813911472447,
+      "grad_norm": 0.21448437622422867,
+      "learning_rate": 2.8800004239031687e-06,
+      "loss": 0.6053,
+      "step": 266
+    },
+    {
+      "epoch": 0.4823848238482385,
+      "grad_norm": 0.22058650439308047,
+      "learning_rate": 2.8652075714060296e-06,
+      "loss": 0.5895,
+      "step": 267
+    },
+    {
+      "epoch": 0.48419150858175247,
+      "grad_norm": 0.22504440683675958,
+      "learning_rate": 2.850401641562865e-06,
+      "loss": 0.5901,
+      "step": 268
+    },
+    {
+      "epoch": 0.4859981933152665,
+      "grad_norm": 0.2143472148561155,
+      "learning_rate": 2.835583164544139e-06,
+      "loss": 0.5957,
+      "step": 269
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.21751502930550626,
+      "learning_rate": 2.820752670969606e-06,
+      "loss": 0.5786,
+      "step": 270
+    },
+    {
+      "epoch": 0.4896115627822945,
+      "grad_norm": 0.21691622039430525,
+      "learning_rate": 2.805910691889307e-06,
+      "loss": 0.5997,
+      "step": 271
+    },
+    {
+      "epoch": 0.4914182475158085,
+      "grad_norm": 0.2219827422506738,
+      "learning_rate": 2.791057758764557e-06,
+      "loss": 0.5942,
+      "step": 272
+    },
+    {
+      "epoch": 0.4932249322493225,
+      "grad_norm": 0.22182577176913804,
+      "learning_rate": 2.776194403448915e-06,
+      "loss": 0.6024,
+      "step": 273
+    },
+    {
+      "epoch": 0.4950316169828365,
+      "grad_norm": 0.23456424438625753,
+      "learning_rate": 2.761321158169134e-06,
+      "loss": 0.5891,
+      "step": 274
+    },
+    {
+      "epoch": 0.4968383017163505,
+      "grad_norm": 0.20662902731079838,
+      "learning_rate": 2.7464385555061092e-06,
+      "loss": 0.5843,
+      "step": 275
+    },
+    {
+      "epoch": 0.4986449864498645,
+      "grad_norm": 0.2042688233772306,
+      "learning_rate": 2.731547128375804e-06,
+      "loss": 0.5765,
+      "step": 276
+    },
+    {
+      "epoch": 0.5004516711833785,
+      "grad_norm": 0.2010718475151129,
+      "learning_rate": 2.7166474100101676e-06,
+      "loss": 0.5889,
+      "step": 277
+    },
+    {
+      "epoch": 0.5022583559168925,
+      "grad_norm": 0.21780066674743287,
+      "learning_rate": 2.7017399339380435e-06,
+      "loss": 0.5753,
+      "step": 278
+    },
+    {
+      "epoch": 0.5040650406504065,
+      "grad_norm": 0.23094036536640075,
+      "learning_rate": 2.686825233966061e-06,
+      "loss": 0.5901,
+      "step": 279
+    },
+    {
+      "epoch": 0.5058717253839206,
+      "grad_norm": 0.22149977838891852,
+      "learning_rate": 2.6719038441595236e-06,
+      "loss": 0.5863,
+      "step": 280
+    },
+    {
+      "epoch": 0.5076784101174345,
+      "grad_norm": 0.23588829860771496,
+      "learning_rate": 2.6569762988232838e-06,
+      "loss": 0.5874,
+      "step": 281
+    },
+    {
+      "epoch": 0.5094850948509485,
+      "grad_norm": 0.20928084741622358,
+      "learning_rate": 2.642043132482612e-06,
+      "loss": 0.5806,
+      "step": 282
+    },
+    {
+      "epoch": 0.5112917795844625,
+      "grad_norm": 0.21032848792961903,
+      "learning_rate": 2.6271048798640547e-06,
+      "loss": 0.598,
+      "step": 283
+    },
+    {
+      "epoch": 0.5130984643179766,
+      "grad_norm": 0.21154254189290178,
+      "learning_rate": 2.6121620758762877e-06,
+      "loss": 0.5855,
+      "step": 284
+    },
+    {
+      "epoch": 0.5149051490514905,
+      "grad_norm": 0.19044363575025977,
+      "learning_rate": 2.5972152555909625e-06,
+      "loss": 0.578,
+      "step": 285
+    },
+    {
+      "epoch": 0.5167118337850045,
+      "grad_norm": 0.2164720308872652,
+      "learning_rate": 2.5822649542235468e-06,
+      "loss": 0.5785,
+      "step": 286
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 0.2267479938328202,
+      "learning_rate": 2.5673117071141574e-06,
+      "loss": 0.6006,
+      "step": 287
+    },
+    {
+      "epoch": 0.5203252032520326,
+      "grad_norm": 0.2264960086832089,
+      "learning_rate": 2.5523560497083927e-06,
+      "loss": 0.5964,
+      "step": 288
+    },
+    {
+      "epoch": 0.5221318879855466,
+      "grad_norm": 0.1985933300834711,
+      "learning_rate": 2.5373985175381595e-06,
+      "loss": 0.5806,
+      "step": 289
+    },
+    {
+      "epoch": 0.5239385727190605,
+      "grad_norm": 0.21800556164349963,
+      "learning_rate": 2.522439646202495e-06,
+      "loss": 0.5927,
+      "step": 290
+    },
+    {
+      "epoch": 0.5257452574525745,
+      "grad_norm": 0.2307111155167328,
+      "learning_rate": 2.507479971348391e-06,
+      "loss": 0.5973,
+      "step": 291
+    },
+    {
+      "epoch": 0.5275519421860885,
+      "grad_norm": 0.19676562110774456,
+      "learning_rate": 2.49252002865161e-06,
+      "loss": 0.5999,
+      "step": 292
+    },
+    {
+      "epoch": 0.5293586269196026,
+      "grad_norm": 0.20847492332742104,
+      "learning_rate": 2.4775603537975055e-06,
+      "loss": 0.5943,
+      "step": 293
+    },
+    {
+      "epoch": 0.5311653116531165,
+      "grad_norm": 0.21153503973865617,
+      "learning_rate": 2.4626014824618418e-06,
+      "loss": 0.5853,
+      "step": 294
+    },
+    {
+      "epoch": 0.5329719963866305,
+      "grad_norm": 0.2031008224582669,
+      "learning_rate": 2.447643950291608e-06,
+      "loss": 0.5842,
+      "step": 295
+    },
+    {
+      "epoch": 0.5347786811201445,
+      "grad_norm": 0.21983351954706135,
+      "learning_rate": 2.4326882928858435e-06,
+      "loss": 0.5869,
+      "step": 296
+    },
+    {
+      "epoch": 0.5365853658536586,
+      "grad_norm": 0.20906785660797234,
+      "learning_rate": 2.417735045776453e-06,
+      "loss": 0.5937,
+      "step": 297
+    },
+    {
+      "epoch": 0.5383920505871725,
+      "grad_norm": 0.20179687852224082,
+      "learning_rate": 2.4027847444090384e-06,
+      "loss": 0.5873,
+      "step": 298
+    },
+    {
+      "epoch": 0.5401987353206865,
+      "grad_norm": 0.21814673778220395,
+      "learning_rate": 2.3878379241237136e-06,
+      "loss": 0.604,
+      "step": 299
+    },
+    {
+      "epoch": 0.5420054200542005,
+      "grad_norm": 0.20643292380076875,
+      "learning_rate": 2.372895120135946e-06,
+      "loss": 0.5917,
+      "step": 300
+    },
+    {
+      "epoch": 0.5438121047877146,
+      "grad_norm": 0.2046393946281201,
+      "learning_rate": 2.3579568675173894e-06,
+      "loss": 0.5918,
+      "step": 301
+    },
+    {
+      "epoch": 0.5456187895212286,
+      "grad_norm": 0.19615967291155278,
+      "learning_rate": 2.3430237011767166e-06,
+      "loss": 0.6048,
+      "step": 302
+    },
+    {
+      "epoch": 0.5474254742547425,
+      "grad_norm": 0.2000764963063287,
+      "learning_rate": 2.3280961558404773e-06,
+      "loss": 0.5862,
+      "step": 303
+    },
+    {
+      "epoch": 0.5492321589882565,
+      "grad_norm": 0.20741775151038053,
+      "learning_rate": 2.3131747660339396e-06,
+      "loss": 0.5808,
+      "step": 304
+    },
+    {
+      "epoch": 0.5510388437217706,
+      "grad_norm": 0.22297483996840473,
+      "learning_rate": 2.2982600660619574e-06,
+      "loss": 0.5871,
+      "step": 305
+    },
+    {
+      "epoch": 0.5528455284552846,
+      "grad_norm": 0.22522123218884285,
+      "learning_rate": 2.2833525899898324e-06,
+      "loss": 0.5851,
+      "step": 306
+    },
+    {
+      "epoch": 0.5546522131887985,
+      "grad_norm": 0.21268387741990938,
+      "learning_rate": 2.268452871624197e-06,
+      "loss": 0.6034,
+      "step": 307
+    },
+    {
+      "epoch": 0.5564588979223125,
+      "grad_norm": 0.20654302956803075,
+      "learning_rate": 2.253561444493891e-06,
+      "loss": 0.5824,
+      "step": 308
+    },
+    {
+      "epoch": 0.5582655826558266,
+      "grad_norm": 0.21409459284336346,
+      "learning_rate": 2.238678841830867e-06,
+      "loss": 0.5917,
+      "step": 309
+    },
+    {
+      "epoch": 0.5600722673893406,
+      "grad_norm": 0.23678847045512513,
+      "learning_rate": 2.2238055965510853e-06,
+      "loss": 0.5753,
+      "step": 310
+    },
+    {
+      "epoch": 0.5618789521228545,
+      "grad_norm": 0.20888881522894184,
+      "learning_rate": 2.2089422412354434e-06,
+      "loss": 0.5927,
+      "step": 311
+    },
+    {
+      "epoch": 0.5636856368563685,
+      "grad_norm": 0.35491005892326005,
+      "learning_rate": 2.1940893081106946e-06,
+      "loss": 0.5922,
+      "step": 312
+    },
+    {
+      "epoch": 0.5654923215898826,
+      "grad_norm": 0.2359074382604886,
+      "learning_rate": 2.179247329030395e-06,
+      "loss": 0.5946,
+      "step": 313
+    },
+    {
+      "epoch": 0.5672990063233966,
+      "grad_norm": 0.2006465173455305,
+      "learning_rate": 2.1644168354558623e-06,
+      "loss": 0.5858,
+      "step": 314
+    },
+    {
+      "epoch": 0.5691056910569106,
+      "grad_norm": 0.1964655166756819,
+      "learning_rate": 2.1495983584371354e-06,
+      "loss": 0.5855,
+      "step": 315
+    },
+    {
+      "epoch": 0.5709123757904245,
+      "grad_norm": 0.25935669261529887,
+      "learning_rate": 2.134792428593971e-06,
+      "loss": 0.5832,
+      "step": 316
+    },
+    {
+      "epoch": 0.5727190605239386,
+      "grad_norm": 0.21166676225314787,
+      "learning_rate": 2.119999576096832e-06,
+      "loss": 0.5774,
+      "step": 317
+    },
+    {
+      "epoch": 0.5745257452574526,
+      "grad_norm": 0.21034466035167568,
+      "learning_rate": 2.1052203306479108e-06,
+      "loss": 0.5894,
+      "step": 318
+    },
+    {
+      "epoch": 0.5763324299909666,
+      "grad_norm": 0.21477089270590338,
+      "learning_rate": 2.090455221462156e-06,
+      "loss": 0.5995,
+      "step": 319
+    },
+    {
+      "epoch": 0.5781391147244805,
+      "grad_norm": 0.22654999181566404,
+      "learning_rate": 2.0757047772483278e-06,
+      "loss": 0.583,
+      "step": 320
+    },
+    {
+      "epoch": 0.5799457994579946,
+      "grad_norm": 0.210213799395079,
+      "learning_rate": 2.0609695261900624e-06,
+      "loss": 0.5786,
+      "step": 321
+    },
+    {
+      "epoch": 0.5817524841915086,
+      "grad_norm": 0.22316241515409585,
+      "learning_rate": 2.0462499959269596e-06,
+      "loss": 0.6005,
+      "step": 322
+    },
+    {
+      "epoch": 0.5835591689250226,
+      "grad_norm": 0.21470128847812983,
+      "learning_rate": 2.031546713535688e-06,
+      "loss": 0.5856,
+      "step": 323
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.19586563209961527,
+      "learning_rate": 2.0168602055111175e-06,
+      "loss": 0.5659,
+      "step": 324
+    },
+    {
+      "epoch": 0.5871725383920506,
+      "grad_norm": 0.20972410141424652,
+      "learning_rate": 2.0021909977474553e-06,
+      "loss": 0.5844,
+      "step": 325
+    },
+    {
+      "epoch": 0.5889792231255646,
+      "grad_norm": 0.20568687520267012,
+      "learning_rate": 1.987539615519424e-06,
+      "loss": 0.5928,
+      "step": 326
+    },
+    {
+      "epoch": 0.5907859078590786,
+      "grad_norm": 0.22858746561989765,
+      "learning_rate": 1.9729065834634533e-06,
+      "loss": 0.5809,
+      "step": 327
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 0.219066035309145,
+      "learning_rate": 1.958292425558883e-06,
+      "loss": 0.5864,
+      "step": 328
+    },
+    {
+      "epoch": 0.5943992773261066,
+      "grad_norm": 0.2226824752237514,
+      "learning_rate": 1.9436976651092143e-06,
+      "loss": 0.5777,
+      "step": 329
+    },
+    {
+      "epoch": 0.5962059620596206,
+      "grad_norm": 0.2034245216202459,
+      "learning_rate": 1.9291228247233607e-06,
+      "loss": 0.585,
+      "step": 330
+    },
+    {
+      "epoch": 0.5980126467931346,
+      "grad_norm": 0.21339109772232404,
+      "learning_rate": 1.9145684262969404e-06,
+      "loss": 0.5903,
+      "step": 331
+    },
+    {
+      "epoch": 0.5998193315266486,
+      "grad_norm": 0.1991853712111239,
+      "learning_rate": 1.9000349909935852e-06,
+      "loss": 0.5723,
+      "step": 332
+    },
+    {
+      "epoch": 0.6016260162601627,
+      "grad_norm": 0.2002553566062744,
+      "learning_rate": 1.8855230392262809e-06,
+      "loss": 0.5929,
+      "step": 333
+    },
+    {
+      "epoch": 0.6034327009936766,
+      "grad_norm": 0.20662439079944833,
+      "learning_rate": 1.8710330906387288e-06,
+      "loss": 0.6059,
+      "step": 334
+    },
+    {
+      "epoch": 0.6052393857271906,
+      "grad_norm": 0.21347474567951025,
+      "learning_rate": 1.8565656640867448e-06,
+      "loss": 0.5879,
+      "step": 335
+    },
+    {
+      "epoch": 0.6070460704607046,
+      "grad_norm": 0.2052816900866658,
+      "learning_rate": 1.8421212776196712e-06,
+      "loss": 0.5856,
+      "step": 336
+    },
+    {
+      "epoch": 0.6088527551942186,
+      "grad_norm": 0.20270795074379191,
+      "learning_rate": 1.827700448461836e-06,
+      "loss": 0.5864,
+      "step": 337
+    },
+    {
+      "epoch": 0.6106594399277326,
+      "grad_norm": 0.20702481129474415,
+      "learning_rate": 1.813303692994025e-06,
+      "loss": 0.5822,
+      "step": 338
+    },
+    {
+      "epoch": 0.6124661246612466,
+      "grad_norm": 0.20555781447822888,
+      "learning_rate": 1.7989315267349936e-06,
+      "loss": 0.591,
+      "step": 339
+    },
+    {
+      "epoch": 0.6142728093947606,
+      "grad_norm": 0.19378812967196427,
+      "learning_rate": 1.7845844643230086e-06,
+      "loss": 0.5866,
+      "step": 340
+    },
+    {
+      "epoch": 0.6160794941282746,
+      "grad_norm": 0.2018027260189549,
+      "learning_rate": 1.770263019497417e-06,
+      "loss": 0.5846,
+      "step": 341
+    },
+    {
+      "epoch": 0.6178861788617886,
+      "grad_norm": 0.2034365649959298,
+      "learning_rate": 1.7559677050802543e-06,
+      "loss": 0.5883,
+      "step": 342
+    },
+    {
+      "epoch": 0.6196928635953026,
+      "grad_norm": 0.2121729903043798,
+      "learning_rate": 1.7416990329578753e-06,
+      "loss": 0.5827,
+      "step": 343
+    },
+    {
+      "epoch": 0.6214995483288166,
+      "grad_norm": 0.1996950776064429,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.5719,
+      "step": 344
+    },
+    {
+      "epoch": 0.6233062330623306,
+      "grad_norm": 0.21273393853952527,
+      "learning_rate": 1.7132436583545703e-06,
+      "loss": 0.5867,
+      "step": 345
+    },
+    {
+      "epoch": 0.6251129177958447,
+      "grad_norm": 0.21807600293104162,
+      "learning_rate": 1.699057974803176e-06,
+      "loss": 0.5883,
+      "step": 346
+    },
+    {
+      "epoch": 0.6269196025293586,
+      "grad_norm": 0.2645660891129371,
+      "learning_rate": 1.6849009713691456e-06,
+      "loss": 0.5732,
+      "step": 347
+    },
+    {
+      "epoch": 0.6287262872628726,
+      "grad_norm": 0.22205298104140844,
+      "learning_rate": 1.670773154986199e-06,
+      "loss": 0.5741,
+      "step": 348
+    },
+    {
+      "epoch": 0.6305329719963866,
+      "grad_norm": 0.20314162053665355,
+      "learning_rate": 1.6566750315429254e-06,
+      "loss": 0.5766,
+      "step": 349
+    },
+    {
+      "epoch": 0.6323396567299007,
+      "grad_norm": 0.23300059534576428,
+      "learning_rate": 1.6426071058646718e-06,
+      "loss": 0.5893,
+      "step": 350
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 0.22463617554746781,
+      "learning_rate": 1.6285698816954626e-06,
+      "loss": 0.5795,
+      "step": 351
+    },
+    {
+      "epoch": 0.6359530261969286,
+      "grad_norm": 0.21871006268327386,
+      "learning_rate": 1.6145638616799636e-06,
+      "loss": 0.5932,
+      "step": 352
+    },
+    {
+      "epoch": 0.6377597109304426,
+      "grad_norm": 0.20172551655088927,
+      "learning_rate": 1.6005895473454836e-06,
+      "loss": 0.5932,
+      "step": 353
+    },
+    {
+      "epoch": 0.6395663956639567,
+      "grad_norm": 0.20333883984236462,
+      "learning_rate": 1.5866474390840126e-06,
+      "loss": 0.5885,
+      "step": 354
+    },
+    {
+      "epoch": 0.6413730803974707,
+      "grad_norm": 0.19927897295532812,
+      "learning_rate": 1.5727380361343103e-06,
+      "loss": 0.5778,
+      "step": 355
+    },
+    {
+      "epoch": 0.6431797651309846,
+      "grad_norm": 0.19972091036693457,
+      "learning_rate": 1.55886183656402e-06,
+      "loss": 0.5933,
+      "step": 356
+    },
+    {
+      "epoch": 0.6449864498644986,
+      "grad_norm": 0.21662963302788196,
+      "learning_rate": 1.545019337251844e-06,
+      "loss": 0.5936,
+      "step": 357
+    },
+    {
+      "epoch": 0.6467931345980127,
+      "grad_norm": 0.1881586687054326,
+      "learning_rate": 1.5312110338697427e-06,
+      "loss": 0.5988,
+      "step": 358
+    },
+    {
+      "epoch": 0.6485998193315267,
+      "grad_norm": 0.20352510057073783,
+      "learning_rate": 1.5174374208651913e-06,
+      "loss": 0.5715,
+      "step": 359
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 0.22480023651434194,
+      "learning_rate": 1.503698991443471e-06,
+      "loss": 0.5799,
+      "step": 360
+    },
+    {
+      "epoch": 0.6522131887985546,
+      "grad_norm": 0.2190975956485496,
+      "learning_rate": 1.489996237550012e-06,
+      "loss": 0.5866,
+      "step": 361
+    },
+    {
+      "epoch": 0.6540198735320687,
+      "grad_norm": 0.2022143060520903,
+      "learning_rate": 1.4763296498527744e-06,
+      "loss": 0.5974,
+      "step": 362
+    },
+    {
+      "epoch": 0.6558265582655827,
+      "grad_norm": 0.21608348435965957,
+      "learning_rate": 1.4626997177246787e-06,
+      "loss": 0.5879,
+      "step": 363
+    },
+    {
+      "epoch": 0.6576332429990966,
+      "grad_norm": 0.19739502471170703,
+      "learning_rate": 1.4491069292260867e-06,
+      "loss": 0.5861,
+      "step": 364
+    },
+    {
+      "epoch": 0.6594399277326106,
+      "grad_norm": 0.19474952415745872,
+      "learning_rate": 1.4355517710873184e-06,
+      "loss": 0.5787,
+      "step": 365
+    },
+    {
+      "epoch": 0.6612466124661247,
+      "grad_norm": 0.21091567910860665,
+      "learning_rate": 1.4220347286912296e-06,
+      "loss": 0.6009,
+      "step": 366
+    },
+    {
+      "epoch": 0.6630532971996387,
+      "grad_norm": 0.20662747423112274,
+      "learning_rate": 1.4085562860558256e-06,
+      "loss": 0.5819,
+      "step": 367
+    },
+    {
+      "epoch": 0.6648599819331527,
+      "grad_norm": 0.2728937498350651,
+      "learning_rate": 1.395116925816934e-06,
+      "loss": 0.5939,
+      "step": 368
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.20917713778131836,
+      "learning_rate": 1.3817171292109182e-06,
+      "loss": 0.5947,
+      "step": 369
+    },
+    {
+      "epoch": 0.6684733514001807,
+      "grad_norm": 0.20216752147153688,
+      "learning_rate": 1.3683573760574526e-06,
+      "loss": 0.5932,
+      "step": 370
+    },
+    {
+      "epoch": 0.6702800361336947,
+      "grad_norm": 0.24086639188361567,
+      "learning_rate": 1.3550381447423317e-06,
+      "loss": 0.5813,
+      "step": 371
+    },
+    {
+      "epoch": 0.6720867208672087,
+      "grad_norm": 0.2091604026851147,
+      "learning_rate": 1.3417599122003464e-06,
+      "loss": 0.5992,
+      "step": 372
+    },
+    {
+      "epoch": 0.6738934056007226,
+      "grad_norm": 0.20808064999420775,
+      "learning_rate": 1.3285231538982036e-06,
+      "loss": 0.5848,
+      "step": 373
+    },
+    {
+      "epoch": 0.6757000903342367,
+      "grad_norm": 0.18817236588164815,
+      "learning_rate": 1.3153283438175036e-06,
+      "loss": 0.5735,
+      "step": 374
+    },
+    {
+      "epoch": 0.6775067750677507,
+      "grad_norm": 0.19128344320769594,
+      "learning_rate": 1.3021759544377632e-06,
+      "loss": 0.5889,
+      "step": 375
+    },
+    {
+      "epoch": 0.6793134598012647,
+      "grad_norm": 0.19834550984118285,
+      "learning_rate": 1.2890664567195e-06,
+      "loss": 0.5736,
+      "step": 376
+    },
+    {
+      "epoch": 0.6811201445347786,
+      "grad_norm": 0.2077959887040641,
+      "learning_rate": 1.27600032008737e-06,
+      "loss": 0.5892,
+      "step": 377
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.20162867649815305,
+      "learning_rate": 1.2629780124133511e-06,
+      "loss": 0.5903,
+      "step": 378
+    },
+    {
+      "epoch": 0.6847335140018067,
+      "grad_norm": 0.21683500604581735,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.592,
+      "step": 379
+    },
+    {
+      "epoch": 0.6865401987353207,
+      "grad_norm": 0.18845292977716074,
+      "learning_rate": 1.2370667475637474e-06,
+      "loss": 0.5737,
+      "step": 380
+    },
+    {
+      "epoch": 0.6883468834688347,
+      "grad_norm": 0.19858214832528265,
+      "learning_rate": 1.2241787182182596e-06,
+      "loss": 0.5894,
+      "step": 381
+    },
+    {
+      "epoch": 0.6901535682023487,
+      "grad_norm": 0.20192306854242342,
+      "learning_rate": 1.2113363734578548e-06,
+      "loss": 0.5773,
+      "step": 382
+    },
+    {
+      "epoch": 0.6919602529358627,
+      "grad_norm": 0.1957085698823615,
+      "learning_rate": 1.1985401731409793e-06,
+      "loss": 0.5968,
+      "step": 383
+    },
+    {
+      "epoch": 0.6937669376693767,
+      "grad_norm": 0.2125180828512492,
+      "learning_rate": 1.185790575473738e-06,
+      "loss": 0.5952,
+      "step": 384
+    },
+    {
+      "epoch": 0.6955736224028907,
+      "grad_norm": 0.19996798857466866,
+      "learning_rate": 1.1730880369934933e-06,
+      "loss": 0.5768,
+      "step": 385
+    },
+    {
+      "epoch": 0.6973803071364046,
+      "grad_norm": 0.19109311362278736,
+      "learning_rate": 1.160433012552508e-06,
+      "loss": 0.588,
+      "step": 386
+    },
+    {
+      "epoch": 0.6991869918699187,
+      "grad_norm": 0.2069488322575602,
+      "learning_rate": 1.1478259553016683e-06,
+      "loss": 0.5884,
+      "step": 387
+    },
+    {
+      "epoch": 0.7009936766034327,
+      "grad_norm": 0.2063220949153012,
+      "learning_rate": 1.1352673166742463e-06,
+      "loss": 0.5879,
+      "step": 388
+    },
+    {
+      "epoch": 0.7028003613369467,
+      "grad_norm": 0.19867402281700364,
+      "learning_rate": 1.122757546369744e-06,
+      "loss": 0.5915,
+      "step": 389
+    },
+    {
+      "epoch": 0.7046070460704607,
+      "grad_norm": 0.1954873804514819,
+      "learning_rate": 1.1102970923377893e-06,
+      "loss": 0.5836,
+      "step": 390
+    },
+    {
+      "epoch": 0.7064137308039747,
+      "grad_norm": 0.2010207307649061,
+      "learning_rate": 1.0978864007620896e-06,
+      "loss": 0.5852,
+      "step": 391
+    },
+    {
+      "epoch": 0.7082204155374887,
+      "grad_norm": 0.2211151863933889,
+      "learning_rate": 1.085525916044464e-06,
+      "loss": 0.5911,
+      "step": 392
+    },
+    {
+      "epoch": 0.7100271002710027,
+      "grad_norm": 0.22126252458153034,
+      "learning_rate": 1.073216080788921e-06,
+      "loss": 0.5954,
+      "step": 393
+    },
+    {
+      "epoch": 0.7118337850045167,
+      "grad_norm": 0.19413607526264012,
+      "learning_rate": 1.0609573357858166e-06,
+      "loss": 0.597,
+      "step": 394
+    },
+    {
+      "epoch": 0.7136404697380307,
+      "grad_norm": 0.20696275357198107,
+      "learning_rate": 1.048750119996066e-06,
+      "loss": 0.5937,
+      "step": 395
+    },
+    {
+      "epoch": 0.7154471544715447,
+      "grad_norm": 0.20262348611385844,
+      "learning_rate": 1.0365948705354309e-06,
+      "loss": 0.5864,
+      "step": 396
+    },
+    {
+      "epoch": 0.7172538392050587,
+      "grad_norm": 0.20538614507552014,
+      "learning_rate": 1.0244920226588599e-06,
+      "loss": 0.5853,
+      "step": 397
+    },
+    {
+      "epoch": 0.7190605239385727,
+      "grad_norm": 0.1905482173846242,
+      "learning_rate": 1.0124420097449077e-06,
+      "loss": 0.5873,
+      "step": 398
+    },
+    {
+      "epoch": 0.7208672086720868,
+      "grad_norm": 0.18443281595390557,
+      "learning_rate": 1.0004452632802158e-06,
+      "loss": 0.5917,
+      "step": 399
+    },
+    {
+      "epoch": 0.7226738934056007,
+      "grad_norm": 0.20129888302461288,
+      "learning_rate": 9.88502212844063e-07,
+      "loss": 0.5874,
+      "step": 400
+    },
+    {
+      "epoch": 0.7244805781391147,
+      "grad_norm": 0.21452153041002034,
+      "learning_rate": 9.7661328609298e-07,
+      "loss": 0.59,
+      "step": 401
+    },
+    {
+      "epoch": 0.7262872628726287,
+      "grad_norm": 0.21422138477452932,
+      "learning_rate": 9.64778908745437e-07,
+      "loss": 0.5977,
+      "step": 402
+    },
+    {
+      "epoch": 0.7280939476061428,
+      "grad_norm": 0.20274956421616797,
+      "learning_rate": 9.529995045666041e-07,
+      "loss": 0.5788,
+      "step": 403
+    },
+    {
+      "epoch": 0.7299006323396567,
+      "grad_norm": 0.2013431410310367,
+      "learning_rate": 9.412754953531664e-07,
+      "loss": 0.5828,
+      "step": 404
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.1919758247929078,
+      "learning_rate": 9.296073009182341e-07,
+      "loss": 0.5823,
+      "step": 405
+    },
+    {
+      "epoch": 0.7335140018066847,
+      "grad_norm": 0.20154872882177322,
+      "learning_rate": 9.179953390762977e-07,
+      "loss": 0.5888,
+      "step": 406
+    },
+    {
+      "epoch": 0.7353206865401988,
+      "grad_norm": 0.20958430246936258,
+      "learning_rate": 9.064400256282757e-07,
+      "loss": 0.5806,
+      "step": 407
+    },
+    {
+      "epoch": 0.7371273712737128,
+      "grad_norm": 0.346779642044963,
+      "learning_rate": 8.949417743466199e-07,
+      "loss": 0.5754,
+      "step": 408
+    },
+    {
+      "epoch": 0.7389340560072267,
+      "grad_norm": 0.26408423210453413,
+      "learning_rate": 8.835009969605013e-07,
+      "loss": 0.5928,
+      "step": 409
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.1961937889808973,
+      "learning_rate": 8.721181031410661e-07,
+      "loss": 0.595,
+      "step": 410
+    },
+    {
+      "epoch": 0.7425474254742548,
+      "grad_norm": 0.19801858217452842,
+      "learning_rate": 8.607935004867693e-07,
+      "loss": 0.5963,
+      "step": 411
+    },
+    {
+      "epoch": 0.7443541102077688,
+      "grad_norm": 0.20021513556312917,
+      "learning_rate": 8.495275945087744e-07,
+      "loss": 0.5694,
+      "step": 412
+    },
+    {
+      "epoch": 0.7461607949412827,
+      "grad_norm": 0.19661429119710955,
+      "learning_rate": 8.383207886164366e-07,
+      "loss": 0.5861,
+      "step": 413
+    },
+    {
+      "epoch": 0.7479674796747967,
+      "grad_norm": 0.1928677620579264,
+      "learning_rate": 8.271734841028553e-07,
+      "loss": 0.5733,
+      "step": 414
+    },
+    {
+      "epoch": 0.7497741644083108,
+      "grad_norm": 0.1979045441126446,
+      "learning_rate": 8.16086080130506e-07,
+      "loss": 0.5951,
+      "step": 415
+    },
+    {
+      "epoch": 0.7515808491418248,
+      "grad_norm": 0.20218794601192208,
+      "learning_rate": 8.050589737169485e-07,
+      "loss": 0.5811,
+      "step": 416
+    },
+    {
+      "epoch": 0.7533875338753387,
+      "grad_norm": 0.20344794195772742,
+      "learning_rate": 7.940925597206053e-07,
+      "loss": 0.6035,
+      "step": 417
+    },
+    {
+      "epoch": 0.7551942186088527,
+      "grad_norm": 0.21268269017167418,
+      "learning_rate": 7.831872308266306e-07,
+      "loss": 0.5857,
+      "step": 418
+    },
+    {
+      "epoch": 0.7570009033423668,
+      "grad_norm": 0.1857432797738388,
+      "learning_rate": 7.723433775328385e-07,
+      "loss": 0.5858,
+      "step": 419
+    },
+    {
+      "epoch": 0.7588075880758808,
+      "grad_norm": 0.1968892912670059,
+      "learning_rate": 7.615613881357315e-07,
+      "loss": 0.6002,
+      "step": 420
+    },
+    {
+      "epoch": 0.7606142728093948,
+      "grad_norm": 0.19458011717852447,
+      "learning_rate": 7.508416487165862e-07,
+      "loss": 0.5805,
+      "step": 421
+    },
+    {
+      "epoch": 0.7624209575429087,
+      "grad_norm": 0.18851481977247553,
+      "learning_rate": 7.401845431276378e-07,
+      "loss": 0.5843,
+      "step": 422
+    },
+    {
+      "epoch": 0.7642276422764228,
+      "grad_norm": 0.20293782749771516,
+      "learning_rate": 7.295904529783265e-07,
+      "loss": 0.5939,
+      "step": 423
+    },
+    {
+      "epoch": 0.7660343270099368,
+      "grad_norm": 0.1929807120562277,
+      "learning_rate": 7.190597576216385e-07,
+      "loss": 0.5974,
+      "step": 424
+    },
+    {
+      "epoch": 0.7678410117434508,
+      "grad_norm": 0.19854186586265798,
+      "learning_rate": 7.085928341405193e-07,
+      "loss": 0.5761,
+      "step": 425
+    },
+    {
+      "epoch": 0.7696476964769647,
+      "grad_norm": 0.1914772718420052,
+      "learning_rate": 6.98190057334375e-07,
+      "loss": 0.5964,
+      "step": 426
+    },
+    {
+      "epoch": 0.7714543812104788,
+      "grad_norm": 0.19547394087507244,
+      "learning_rate": 6.878517997056458e-07,
+      "loss": 0.568,
+      "step": 427
+    },
+    {
+      "epoch": 0.7732610659439928,
+      "grad_norm": 0.19890854360676258,
+      "learning_rate": 6.775784314464717e-07,
+      "loss": 0.5885,
+      "step": 428
+    },
+    {
+      "epoch": 0.7750677506775068,
+      "grad_norm": 0.19723288328989222,
+      "learning_rate": 6.673703204254348e-07,
+      "loss": 0.5826,
+      "step": 429
+    },
+    {
+      "epoch": 0.7768744354110207,
+      "grad_norm": 0.1917732111792597,
+      "learning_rate": 6.572278321743871e-07,
+      "loss": 0.5851,
+      "step": 430
+    },
+    {
+      "epoch": 0.7786811201445348,
+      "grad_norm": 0.2144258319855419,
+      "learning_rate": 6.471513298753634e-07,
+      "loss": 0.5938,
+      "step": 431
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.1914954286444934,
+      "learning_rate": 6.371411743475717e-07,
+      "loss": 0.5886,
+      "step": 432
+    },
+    {
+      "epoch": 0.7822944896115628,
+      "grad_norm": 0.1915436424852639,
+      "learning_rate": 6.271977240344795e-07,
+      "loss": 0.5973,
+      "step": 433
+    },
+    {
+      "epoch": 0.7841011743450768,
+      "grad_norm": 0.1962061264070641,
+      "learning_rate": 6.17321334990973e-07,
+      "loss": 0.5964,
+      "step": 434
+    },
+    {
+      "epoch": 0.7859078590785907,
+      "grad_norm": 0.19084926119503218,
+      "learning_rate": 6.075123608706093e-07,
+      "loss": 0.5728,
+      "step": 435
+    },
+    {
+      "epoch": 0.7877145438121048,
+      "grad_norm": 0.19050326256104155,
+      "learning_rate": 5.97771152912954e-07,
+      "loss": 0.587,
+      "step": 436
+    },
+    {
+      "epoch": 0.7895212285456188,
+      "grad_norm": 0.18836498258283543,
+      "learning_rate": 5.880980599310041e-07,
+      "loss": 0.585,
+      "step": 437
+    },
+    {
+      "epoch": 0.7913279132791328,
+      "grad_norm": 0.20435071863480905,
+      "learning_rate": 5.784934282986956e-07,
+      "loss": 0.5772,
+      "step": 438
+    },
+    {
+      "epoch": 0.7931345980126467,
+      "grad_norm": 0.2023157209439081,
+      "learning_rate": 5.689576019385015e-07,
+      "loss": 0.5941,
+      "step": 439
+    },
+    {
+      "epoch": 0.7949412827461608,
+      "grad_norm": 0.20024639862122715,
+      "learning_rate": 5.59490922309118e-07,
+      "loss": 0.5861,
+      "step": 440
+    },
+    {
+      "epoch": 0.7967479674796748,
+      "grad_norm": 0.19423594398341354,
+      "learning_rate": 5.500937283932348e-07,
+      "loss": 0.57,
+      "step": 441
+    },
+    {
+      "epoch": 0.7985546522131888,
+      "grad_norm": 0.19433916433983744,
+      "learning_rate": 5.407663566854008e-07,
+      "loss": 0.5801,
+      "step": 442
+    },
+    {
+      "epoch": 0.8003613369467028,
+      "grad_norm": 0.20578340689151056,
+      "learning_rate": 5.3150914117997e-07,
+      "loss": 0.5879,
+      "step": 443
+    },
+    {
+      "epoch": 0.8021680216802168,
+      "grad_norm": 0.19675195680591387,
+      "learning_rate": 5.223224133591475e-07,
+      "loss": 0.5938,
+      "step": 444
+    },
+    {
+      "epoch": 0.8039747064137308,
+      "grad_norm": 0.20725412186119369,
+      "learning_rate": 5.132065021811123e-07,
+      "loss": 0.5817,
+      "step": 445
+    },
+    {
+      "epoch": 0.8057813911472448,
+      "grad_norm": 0.20053119388587262,
+      "learning_rate": 5.041617340682467e-07,
+      "loss": 0.5786,
+      "step": 446
+    },
+    {
+      "epoch": 0.8075880758807588,
+      "grad_norm": 0.19063636355734778,
+      "learning_rate": 4.951884328954401e-07,
+      "loss": 0.584,
+      "step": 447
+    },
+    {
+      "epoch": 0.8093947606142728,
+      "grad_norm": 0.17948151730955053,
+      "learning_rate": 4.862869199784984e-07,
+      "loss": 0.5863,
+      "step": 448
+    },
+    {
+      "epoch": 0.8112014453477868,
+      "grad_norm": 0.19768757570053508,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.5822,
+      "step": 449
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 0.1942777228720005,
+      "learning_rate": 4.687005313110454e-07,
+      "loss": 0.5921,
+      "step": 450
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 0.21425291439601463,
+      "learning_rate": 4.600162852936171e-07,
+      "loss": 0.5946,
+      "step": 451
+    },
+    {
+      "epoch": 0.8166214995483289,
+      "grad_norm": 0.19819708538024772,
+      "learning_rate": 4.514050869756703e-07,
+      "loss": 0.5899,
+      "step": 452
+    },
+    {
+      "epoch": 0.8184281842818428,
+      "grad_norm": 0.19195362842264865,
+      "learning_rate": 4.4286724470683576e-07,
+      "loss": 0.5819,
+      "step": 453
+    },
+    {
+      "epoch": 0.8202348690153568,
+      "grad_norm": 0.20338057359461525,
+      "learning_rate": 4.344030642100133e-07,
+      "loss": 0.5666,
+      "step": 454
+    },
+    {
+      "epoch": 0.8220415537488708,
+      "grad_norm": 0.20327817658583644,
+      "learning_rate": 4.2601284857042263e-07,
+      "loss": 0.5906,
+      "step": 455
+    },
+    {
+      "epoch": 0.8238482384823849,
+      "grad_norm": 0.20744598329087444,
+      "learning_rate": 4.1769689822475147e-07,
+      "loss": 0.5819,
+      "step": 456
+    },
+    {
+      "epoch": 0.8256549232158988,
+      "grad_norm": 0.2029409286632038,
+      "learning_rate": 4.0945551095039837e-07,
+      "loss": 0.5967,
+      "step": 457
+    },
+    {
+      "epoch": 0.8274616079494128,
+      "grad_norm": 0.19729156914796803,
+      "learning_rate": 4.012889818548069e-07,
+      "loss": 0.589,
+      "step": 458
+    },
+    {
+      "epoch": 0.8292682926829268,
+      "grad_norm": 0.1872570351127295,
+      "learning_rate": 3.931976033649021e-07,
+      "loss": 0.5783,
+      "step": 459
+    },
+    {
+      "epoch": 0.8310749774164409,
+      "grad_norm": 0.1943816366413793,
+      "learning_rate": 3.851816652166165e-07,
+      "loss": 0.5881,
+      "step": 460
+    },
+    {
+      "epoch": 0.8328816621499548,
+      "grad_norm": 0.18999841178320626,
+      "learning_rate": 3.772414544445163e-07,
+      "loss": 0.5757,
+      "step": 461
+    },
+    {
+      "epoch": 0.8346883468834688,
+      "grad_norm": 0.23829838305045872,
+      "learning_rate": 3.6937725537152277e-07,
+      "loss": 0.583,
+      "step": 462
+    },
+    {
+      "epoch": 0.8364950316169828,
+      "grad_norm": 0.1885927060959385,
+      "learning_rate": 3.615893495987335e-07,
+      "loss": 0.5879,
+      "step": 463
+    },
+    {
+      "epoch": 0.8383017163504969,
+      "grad_norm": 0.2015764989007377,
+      "learning_rate": 3.538780159953348e-07,
+      "loss": 0.5902,
+      "step": 464
+    },
+    {
+      "epoch": 0.8401084010840109,
+      "grad_norm": 0.2015900600206813,
+      "learning_rate": 3.462435306886194e-07,
+      "loss": 0.6,
+      "step": 465
+    },
+    {
+      "epoch": 0.8419150858175248,
+      "grad_norm": 0.2043727279833967,
+      "learning_rate": 3.3868616705409723e-07,
+      "loss": 0.5836,
+      "step": 466
+    },
+    {
+      "epoch": 0.8437217705510388,
+      "grad_norm": 0.19666307771397085,
+      "learning_rate": 3.312061957057061e-07,
+      "loss": 0.5797,
+      "step": 467
+    },
+    {
+      "epoch": 0.8455284552845529,
+      "grad_norm": 0.19069167880376858,
+      "learning_rate": 3.2380388448612437e-07,
+      "loss": 0.5906,
+      "step": 468
+    },
+    {
+      "epoch": 0.8473351400180669,
+      "grad_norm": 0.23586769464721072,
+      "learning_rate": 3.164794984571759e-07,
+      "loss": 0.5794,
+      "step": 469
+    },
+    {
+      "epoch": 0.8491418247515808,
+      "grad_norm": 0.2024878857222796,
+      "learning_rate": 3.092332998903416e-07,
+      "loss": 0.5748,
+      "step": 470
+    },
+    {
+      "epoch": 0.8509485094850948,
+      "grad_norm": 0.2067579361021575,
+      "learning_rate": 3.020655482573659e-07,
+      "loss": 0.6049,
+      "step": 471
+    },
+    {
+      "epoch": 0.8527551942186089,
+      "grad_norm": 0.21935627947112848,
+      "learning_rate": 2.949765002209698e-07,
+      "loss": 0.5763,
+      "step": 472
+    },
+    {
+      "epoch": 0.8545618789521229,
+      "grad_norm": 0.1906611720754469,
+      "learning_rate": 2.8796640962565374e-07,
+      "loss": 0.5955,
+      "step": 473
+    },
+    {
+      "epoch": 0.8563685636856369,
+      "grad_norm": 0.18330400428801807,
+      "learning_rate": 2.810355274886148e-07,
+      "loss": 0.5907,
+      "step": 474
+    },
+    {
+      "epoch": 0.8581752484191508,
+      "grad_norm": 0.2067435257059269,
+      "learning_rate": 2.7418410199075293e-07,
+      "loss": 0.5805,
+      "step": 475
+    },
+    {
+      "epoch": 0.8599819331526649,
+      "grad_norm": 0.19000373388890107,
+      "learning_rate": 2.674123784677868e-07,
+      "loss": 0.5874,
+      "step": 476
+    },
+    {
+      "epoch": 0.8617886178861789,
+      "grad_norm": 0.18526442128158882,
+      "learning_rate": 2.6072059940146775e-07,
+      "loss": 0.5836,
+      "step": 477
+    },
+    {
+      "epoch": 0.8635953026196929,
+      "grad_norm": 0.21478407044446765,
+      "learning_rate": 2.5410900441089905e-07,
+      "loss": 0.5954,
+      "step": 478
+    },
+    {
+      "epoch": 0.8654019873532068,
+      "grad_norm": 0.22386509278719685,
+      "learning_rate": 2.4757783024395244e-07,
+      "loss": 0.5818,
+      "step": 479
+    },
+    {
+      "epoch": 0.8672086720867209,
+      "grad_norm": 0.18372007023252018,
+      "learning_rate": 2.4112731076879254e-07,
+      "loss": 0.5798,
+      "step": 480
+    },
+    {
+      "epoch": 0.8690153568202349,
+      "grad_norm": 0.19040176908950068,
+      "learning_rate": 2.3475767696550327e-07,
+      "loss": 0.5894,
+      "step": 481
+    },
+    {
+      "epoch": 0.8708220415537489,
+      "grad_norm": 0.2004862041545315,
+      "learning_rate": 2.284691569178138e-07,
+      "loss": 0.5933,
+      "step": 482
+    },
+    {
+      "epoch": 0.8726287262872628,
+      "grad_norm": 0.19654881181561126,
+      "learning_rate": 2.2226197580493657e-07,
+      "loss": 0.5781,
+      "step": 483
+    },
+    {
+      "epoch": 0.8744354110207768,
+      "grad_norm": 0.1977337131166601,
+      "learning_rate": 2.1613635589349756e-07,
+      "loss": 0.5756,
+      "step": 484
+    },
+    {
+      "epoch": 0.8762420957542909,
+      "grad_norm": 0.19903230308008285,
+      "learning_rate": 2.100925165295839e-07,
+      "loss": 0.5849,
+      "step": 485
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.19613496635724054,
+      "learning_rate": 2.041306741308832e-07,
+      "loss": 0.5913,
+      "step": 486
+    },
+    {
+      "epoch": 0.8798554652213189,
+      "grad_norm": 0.19251722934409113,
+      "learning_rate": 1.982510421789402e-07,
+      "loss": 0.5789,
+      "step": 487
+    },
+    {
+      "epoch": 0.8816621499548328,
+      "grad_norm": 0.1883072319364769,
+      "learning_rate": 1.9245383121150678e-07,
+      "loss": 0.5783,
+      "step": 488
+    },
+    {
+      "epoch": 0.8834688346883469,
+      "grad_norm": 0.18855885019091942,
+      "learning_rate": 1.8673924881500826e-07,
+      "loss": 0.5877,
+      "step": 489
+    },
+    {
+      "epoch": 0.8852755194218609,
+      "grad_norm": 0.2181375847970685,
+      "learning_rate": 1.8110749961710582e-07,
+      "loss": 0.5843,
+      "step": 490
+    },
+    {
+      "epoch": 0.8870822041553749,
+      "grad_norm": 0.1925063200042687,
+      "learning_rate": 1.7555878527937164e-07,
+      "loss": 0.5763,
+      "step": 491
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.2021368170109263,
+      "learning_rate": 1.7009330449006712e-07,
+      "loss": 0.5781,
+      "step": 492
+    },
+    {
+      "epoch": 0.8906955736224029,
+      "grad_norm": 0.19509047381234865,
+      "learning_rate": 1.6471125295702773e-07,
+      "loss": 0.5719,
+      "step": 493
+    },
+    {
+      "epoch": 0.8925022583559169,
+      "grad_norm": 0.1921901997278579,
+      "learning_rate": 1.59412823400657e-07,
+      "loss": 0.5895,
+      "step": 494
+    },
+    {
+      "epoch": 0.8943089430894309,
+      "grad_norm": 0.1923785346679999,
+      "learning_rate": 1.5419820554702313e-07,
+      "loss": 0.5861,
+      "step": 495
+    },
+    {
+      "epoch": 0.8961156278229448,
+      "grad_norm": 0.19764959276565705,
+      "learning_rate": 1.4906758612106637e-07,
+      "loss": 0.599,
+      "step": 496
+    },
+    {
+      "epoch": 0.8979223125564589,
+      "grad_norm": 0.19700462380217873,
+      "learning_rate": 1.4402114883991318e-07,
+      "loss": 0.5858,
+      "step": 497
+    },
+    {
+      "epoch": 0.8997289972899729,
+      "grad_norm": 0.20609368769470798,
+      "learning_rate": 1.3905907440629752e-07,
+      "loss": 0.5848,
+      "step": 498
+    },
+    {
+      "epoch": 0.9015356820234869,
+      "grad_norm": 0.20327434936015687,
+      "learning_rate": 1.3418154050208937e-07,
+      "loss": 0.5946,
+      "step": 499
+    },
+    {
+      "epoch": 0.9033423667570009,
+      "grad_norm": 0.19818277901642153,
+      "learning_rate": 1.2938872178193395e-07,
+      "loss": 0.5924,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 553,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 579500543967232.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862cf87b1e05c0e1fb9e771f81ab56a7c4bd43704732a82920faf23e31b14aea
+size 8017