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 sha256:8cf1fce4dec2e2552bb70aa69f6940f538ea4cccb0487187fffa5f734f48f74b
+size 4997184968

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae81ad5dce4dc0ff7a88dc29d371942541988a472ff5da564b4487c6367b090b
+size 4997741608

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9d24be056fd581d52af05ed12e2cfad8b00b2a9a53c412e52c93197413cb90
+size 4997742208

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5223887d5d91486511c8347bae138248ed4e7a5b3974ca81cf873fd408af9fea
+size 4997743184

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3fad36ba4ded3733f3a9b5fdbc5e94bd936bd607a816d396e8aef9cf15ff1f
+size 4997743184

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e94115f1abf873e698e2b8ee49c8aebb9d099fbe7e39a65d7030e7184645bf
+size 4997743184

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c2127f7f3893cc60138d8d13da9b4f5181294bfb4d3c26f004ab73d08c2d403
+size 4997743184

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eafb20497e9878da3a5b1424fa414a7e79293ad095c5c2f1debe5ca0559b723
+size 4997743184

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd31d7204d9436f4e818ea8455849c21e62659098241e29e4b1cdcd9044cf43
+size 4997743184

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99e3e06f5802c2dab4b3321d45c6d71f95f86403ca43602e799b982077a571c
+size 4997743184

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8340a042711ce0648da1a10f8cb4fe2054f26c74d95dc39d09e46e04f3db37
+size 4997743184

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b8ad980e8691526ab671e30394a121b947e8373c4598c44b42e6c945036366
+size 4997743184

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e917fe9f194382e5259ec9b112dfb86d2baee2d58dd7556314e9bc4cfeaa703
+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 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.36133694670280037,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0018066847335140017,
+      "grad_norm": 2.8394027200091747,
+      "learning_rate": 0.0,
+      "loss": 0.8251,
+      "step": 1
+    },
+    {
+      "epoch": 0.0036133694670280035,
+      "grad_norm": 2.8846288476633135,
+      "learning_rate": 1.0714285714285714e-06,
+      "loss": 0.8284,
+      "step": 2
+    },
+    {
+      "epoch": 0.005420054200542005,
+      "grad_norm": 2.9025021758600973,
+      "learning_rate": 2.1428571428571427e-06,
+      "loss": 0.8427,
+      "step": 3
+    },
+    {
+      "epoch": 0.007226738934056007,
+      "grad_norm": 2.8006966406467435,
+      "learning_rate": 3.2142857142857143e-06,
+      "loss": 0.8377,
+      "step": 4
+    },
+    {
+      "epoch": 0.009033423667570008,
+      "grad_norm": 2.5933707261583208,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.8227,
+      "step": 5
+    },
+    {
+      "epoch": 0.01084010840108401,
+      "grad_norm": 2.0871248987589857,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 0.8095,
+      "step": 6
+    },
+    {
+      "epoch": 0.012646793134598013,
+      "grad_norm": 1.5051624332871105,
+      "learning_rate": 6.428571428571429e-06,
+      "loss": 0.7739,
+      "step": 7
+    },
+    {
+      "epoch": 0.014453477868112014,
+      "grad_norm": 1.390065658542279,
+      "learning_rate": 7.5e-06,
+      "loss": 0.7734,
+      "step": 8
+    },
+    {
+      "epoch": 0.016260162601626018,
+      "grad_norm": 1.3346375437162221,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.7655,
+      "step": 9
+    },
+    {
+      "epoch": 0.018066847335140017,
+      "grad_norm": 2.368502454719072,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 0.7502,
+      "step": 10
+    },
+    {
+      "epoch": 0.01987353206865402,
+      "grad_norm": 2.355019739749437,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.7355,
+      "step": 11
+    },
+    {
+      "epoch": 0.02168021680216802,
+      "grad_norm": 2.235397645486187,
+      "learning_rate": 1.1785714285714286e-05,
+      "loss": 0.7489,
+      "step": 12
+    },
+    {
+      "epoch": 0.023486901535682024,
+      "grad_norm": 1.8443725862230025,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.7253,
+      "step": 13
+    },
+    {
+      "epoch": 0.025293586269196026,
+      "grad_norm": 3.9119844600464275,
+      "learning_rate": 1.3928571428571429e-05,
+      "loss": 0.7285,
+      "step": 14
+    },
+    {
+      "epoch": 0.02710027100271003,
+      "grad_norm": 1.6411422206825859,
+      "learning_rate": 1.5e-05,
+      "loss": 0.7284,
+      "step": 15
+    },
+    {
+      "epoch": 0.028906955736224028,
+      "grad_norm": 1.3411860085380753,
+      "learning_rate": 1.6071428571428572e-05,
+      "loss": 0.7105,
+      "step": 16
+    },
+    {
+      "epoch": 0.03071364046973803,
+      "grad_norm": 1.157320872714633,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.7068,
+      "step": 17
+    },
+    {
+      "epoch": 0.032520325203252036,
+      "grad_norm": 0.7462236915744604,
+      "learning_rate": 1.8214285714285712e-05,
+      "loss": 0.6926,
+      "step": 18
+    },
+    {
+      "epoch": 0.03432700993676603,
+      "grad_norm": 0.8473541980236234,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 0.6858,
+      "step": 19
+    },
+    {
+      "epoch": 0.036133694670280034,
+      "grad_norm": 0.7215438560743268,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 0.6605,
+      "step": 20
+    },
+    {
+      "epoch": 0.037940379403794036,
+      "grad_norm": 0.6345550993430565,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.6668,
+      "step": 21
+    },
+    {
+      "epoch": 0.03974706413730804,
+      "grad_norm": 0.6182590458724911,
+      "learning_rate": 2.25e-05,
+      "loss": 0.6559,
+      "step": 22
+    },
+    {
+      "epoch": 0.04155374887082204,
+      "grad_norm": 0.623617204927979,
+      "learning_rate": 2.357142857142857e-05,
+      "loss": 0.6561,
+      "step": 23
+    },
+    {
+      "epoch": 0.04336043360433604,
+      "grad_norm": 0.5049024834505677,
+      "learning_rate": 2.464285714285714e-05,
+      "loss": 0.6613,
+      "step": 24
+    },
+    {
+      "epoch": 0.045167118337850046,
+      "grad_norm": 0.5485283866894338,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 0.6429,
+      "step": 25
+    },
+    {
+      "epoch": 0.04697380307136405,
+      "grad_norm": 0.5146774550210349,
+      "learning_rate": 2.6785714285714288e-05,
+      "loss": 0.6572,
+      "step": 26
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 0.4849533483489942,
+      "learning_rate": 2.7857142857142858e-05,
+      "loss": 0.6352,
+      "step": 27
+    },
+    {
+      "epoch": 0.05058717253839205,
+      "grad_norm": 0.4679753904023602,
+      "learning_rate": 2.892857142857143e-05,
+      "loss": 0.6372,
+      "step": 28
+    },
+    {
+      "epoch": 0.052393857271906055,
+      "grad_norm": 0.49823982670847244,
+      "learning_rate": 3e-05,
+      "loss": 0.649,
+      "step": 29
+    },
+    {
+      "epoch": 0.05420054200542006,
+      "grad_norm": 0.3998487451158294,
+      "learning_rate": 2.9999731440137413e-05,
+      "loss": 0.6492,
+      "step": 30
+    },
+    {
+      "epoch": 0.05600722673893405,
+      "grad_norm": 0.4037683931810622,
+      "learning_rate": 2.9998925770166232e-05,
+      "loss": 0.6384,
+      "step": 31
+    },
+    {
+      "epoch": 0.057813911472448055,
+      "grad_norm": 0.3869283159888842,
+      "learning_rate": 2.9997583018935875e-05,
+      "loss": 0.6266,
+      "step": 32
+    },
+    {
+      "epoch": 0.05962059620596206,
+      "grad_norm": 0.4105676527710418,
+      "learning_rate": 2.9995703234527553e-05,
+      "loss": 0.6365,
+      "step": 33
+    },
+    {
+      "epoch": 0.06142728093947606,
+      "grad_norm": 0.3428905600355113,
+      "learning_rate": 2.999328648425255e-05,
+      "loss": 0.6236,
+      "step": 34
+    },
+    {
+      "epoch": 0.06323396567299007,
+      "grad_norm": 0.3666139696974658,
+      "learning_rate": 2.999033285464982e-05,
+      "loss": 0.6293,
+      "step": 35
+    },
+    {
+      "epoch": 0.06504065040650407,
+      "grad_norm": 0.369662441500822,
+      "learning_rate": 2.9986842451482876e-05,
+      "loss": 0.6251,
+      "step": 36
+    },
+    {
+      "epoch": 0.06684733514001806,
+      "grad_norm": 0.3677980333288224,
+      "learning_rate": 2.9982815399736008e-05,
+      "loss": 0.6297,
+      "step": 37
+    },
+    {
+      "epoch": 0.06865401987353206,
+      "grad_norm": 0.3223035029779702,
+      "learning_rate": 2.9978251843609816e-05,
+      "loss": 0.6219,
+      "step": 38
+    },
+    {
+      "epoch": 0.07046070460704607,
+      "grad_norm": 0.37293367784153375,
+      "learning_rate": 2.9973151946516027e-05,
+      "loss": 0.6242,
+      "step": 39
+    },
+    {
+      "epoch": 0.07226738934056007,
+      "grad_norm": 0.322511907065973,
+      "learning_rate": 2.996751589107167e-05,
+      "loss": 0.6122,
+      "step": 40
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 0.34111037181843756,
+      "learning_rate": 2.9961343879092512e-05,
+      "loss": 0.6186,
+      "step": 41
+    },
+    {
+      "epoch": 0.07588075880758807,
+      "grad_norm": 0.30130338237811194,
+      "learning_rate": 2.9954636131585845e-05,
+      "loss": 0.6113,
+      "step": 42
+    },
+    {
+      "epoch": 0.07768744354110207,
+      "grad_norm": 0.32753158641617225,
+      "learning_rate": 2.9947392888742566e-05,
+      "loss": 0.6112,
+      "step": 43
+    },
+    {
+      "epoch": 0.07949412827461608,
+      "grad_norm": 0.3060506987492754,
+      "learning_rate": 2.993961440992859e-05,
+      "loss": 0.6056,
+      "step": 44
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "grad_norm": 0.5813127875924191,
+      "learning_rate": 2.993130097367553e-05,
+      "loss": 0.6131,
+      "step": 45
+    },
+    {
+      "epoch": 0.08310749774164408,
+      "grad_norm": 0.30546110146813144,
+      "learning_rate": 2.9922452877670775e-05,
+      "loss": 0.6144,
+      "step": 46
+    },
+    {
+      "epoch": 0.08491418247515808,
+      "grad_norm": 0.3009821627626054,
+      "learning_rate": 2.991307043874677e-05,
+      "loss": 0.617,
+      "step": 47
+    },
+    {
+      "epoch": 0.08672086720867209,
+      "grad_norm": 0.2835661481876977,
+      "learning_rate": 2.9903153992869734e-05,
+      "loss": 0.6031,
+      "step": 48
+    },
+    {
+      "epoch": 0.08852755194218609,
+      "grad_norm": 0.31548723118407335,
+      "learning_rate": 2.989270389512756e-05,
+      "loss": 0.6107,
+      "step": 49
+    },
+    {
+      "epoch": 0.09033423667570009,
+      "grad_norm": 0.2864309330552123,
+      "learning_rate": 2.988172051971717e-05,
+      "loss": 0.6097,
+      "step": 50
+    },
+    {
+      "epoch": 0.0921409214092141,
+      "grad_norm": 0.29953498642613263,
+      "learning_rate": 2.9870204259931062e-05,
+      "loss": 0.5998,
+      "step": 51
+    },
+    {
+      "epoch": 0.0939476061427281,
+      "grad_norm": 0.2782739210196595,
+      "learning_rate": 2.9858155528143256e-05,
+      "loss": 0.6169,
+      "step": 52
+    },
+    {
+      "epoch": 0.0957542908762421,
+      "grad_norm": 0.3431216549638938,
+      "learning_rate": 2.9845574755794522e-05,
+      "loss": 0.6024,
+      "step": 53
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 0.26425217740885376,
+      "learning_rate": 2.9832462393376926e-05,
+      "loss": 0.5921,
+      "step": 54
+    },
+    {
+      "epoch": 0.0993676603432701,
+      "grad_norm": 0.3422702392148149,
+      "learning_rate": 2.9818818910417706e-05,
+      "loss": 0.6079,
+      "step": 55
+    },
+    {
+      "epoch": 0.1011743450767841,
+      "grad_norm": 0.3197424015440345,
+      "learning_rate": 2.9804644795462437e-05,
+      "loss": 0.612,
+      "step": 56
+    },
+    {
+      "epoch": 0.10298102981029811,
+      "grad_norm": 0.3035603795716621,
+      "learning_rate": 2.9789940556057574e-05,
+      "loss": 0.5975,
+      "step": 57
+    },
+    {
+      "epoch": 0.10478771454381211,
+      "grad_norm": 0.3410992160925094,
+      "learning_rate": 2.9774706718732255e-05,
+      "loss": 0.6058,
+      "step": 58
+    },
+    {
+      "epoch": 0.10659439927732611,
+      "grad_norm": 0.27322743279862205,
+      "learning_rate": 2.9758943828979444e-05,
+      "loss": 0.592,
+      "step": 59
+    },
+    {
+      "epoch": 0.10840108401084012,
+      "grad_norm": 0.3639122458989281,
+      "learning_rate": 2.9742652451236414e-05,
+      "loss": 0.5932,
+      "step": 60
+    },
+    {
+      "epoch": 0.1102077687443541,
+      "grad_norm": 0.3014533566173352,
+      "learning_rate": 2.972583316886451e-05,
+      "loss": 0.597,
+      "step": 61
+    },
+    {
+      "epoch": 0.1120144534778681,
+      "grad_norm": 0.34457895149113055,
+      "learning_rate": 2.9708486584128303e-05,
+      "loss": 0.6017,
+      "step": 62
+    },
+    {
+      "epoch": 0.11382113821138211,
+      "grad_norm": 0.30295456441359353,
+      "learning_rate": 2.9690613318173966e-05,
+      "loss": 0.6015,
+      "step": 63
+    },
+    {
+      "epoch": 0.11562782294489611,
+      "grad_norm": 0.2899317610304254,
+      "learning_rate": 2.9672214011007087e-05,
+      "loss": 0.5999,
+      "step": 64
+    },
+    {
+      "epoch": 0.11743450767841011,
+      "grad_norm": 0.29733861402573497,
+      "learning_rate": 2.9653289321469715e-05,
+      "loss": 0.5939,
+      "step": 65
+    },
+    {
+      "epoch": 0.11924119241192412,
+      "grad_norm": 0.27257724173917824,
+      "learning_rate": 2.9633839927216793e-05,
+      "loss": 0.5969,
+      "step": 66
+    },
+    {
+      "epoch": 0.12104787714543812,
+      "grad_norm": 0.2898338043822156,
+      "learning_rate": 2.9613866524691867e-05,
+      "loss": 0.5873,
+      "step": 67
+    },
+    {
+      "epoch": 0.12285456187895212,
+      "grad_norm": 0.2884348823630205,
+      "learning_rate": 2.9593369829102173e-05,
+      "loss": 0.6026,
+      "step": 68
+    },
+    {
+      "epoch": 0.12466124661246612,
+      "grad_norm": 0.28168278457326457,
+      "learning_rate": 2.957235057439301e-05,
+      "loss": 0.6042,
+      "step": 69
+    },
+    {
+      "epoch": 0.12646793134598014,
+      "grad_norm": 0.2869178339893195,
+      "learning_rate": 2.955080951322147e-05,
+      "loss": 0.6085,
+      "step": 70
+    },
+    {
+      "epoch": 0.12827461607949414,
+      "grad_norm": 0.3037977880321082,
+      "learning_rate": 2.9528747416929467e-05,
+      "loss": 0.5817,
+      "step": 71
+    },
+    {
+      "epoch": 0.13008130081300814,
+      "grad_norm": 0.28914281369381906,
+      "learning_rate": 2.9506165075516148e-05,
+      "loss": 0.5985,
+      "step": 72
+    },
+    {
+      "epoch": 0.13188798554652212,
+      "grad_norm": 0.3680574307953626,
+      "learning_rate": 2.9483063297609577e-05,
+      "loss": 0.5975,
+      "step": 73
+    },
+    {
+      "epoch": 0.13369467028003612,
+      "grad_norm": 0.3174888148098996,
+      "learning_rate": 2.9459442910437798e-05,
+      "loss": 0.5891,
+      "step": 74
+    },
+    {
+      "epoch": 0.13550135501355012,
+      "grad_norm": 0.31913893930146975,
+      "learning_rate": 2.94353047597992e-05,
+      "loss": 0.5888,
+      "step": 75
+    },
+    {
+      "epoch": 0.13730803974706413,
+      "grad_norm": 0.28949770075545406,
+      "learning_rate": 2.941064971003224e-05,
+      "loss": 0.5841,
+      "step": 76
+    },
+    {
+      "epoch": 0.13911472448057813,
+      "grad_norm": 0.3247755531851961,
+      "learning_rate": 2.9385478643984484e-05,
+      "loss": 0.5795,
+      "step": 77
+    },
+    {
+      "epoch": 0.14092140921409213,
+      "grad_norm": 0.3511957059688905,
+      "learning_rate": 2.9359792462981007e-05,
+      "loss": 0.5905,
+      "step": 78
+    },
+    {
+      "epoch": 0.14272809394760613,
+      "grad_norm": 0.302521463157134,
+      "learning_rate": 2.9333592086792113e-05,
+      "loss": 0.5985,
+      "step": 79
+    },
+    {
+      "epoch": 0.14453477868112014,
+      "grad_norm": 0.3549679822021618,
+      "learning_rate": 2.9306878453600382e-05,
+      "loss": 0.6074,
+      "step": 80
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 0.3198459509652125,
+      "learning_rate": 2.9279652519967105e-05,
+      "loss": 0.5922,
+      "step": 81
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.3576854570877617,
+      "learning_rate": 2.9251915260798024e-05,
+      "loss": 0.5846,
+      "step": 82
+    },
+    {
+      "epoch": 0.14995483288166214,
+      "grad_norm": 0.3452717739532111,
+      "learning_rate": 2.9223667669308395e-05,
+      "loss": 0.5949,
+      "step": 83
+    },
+    {
+      "epoch": 0.15176151761517614,
+      "grad_norm": 0.35130798066442276,
+      "learning_rate": 2.9194910756987464e-05,
+      "loss": 0.5882,
+      "step": 84
+    },
+    {
+      "epoch": 0.15356820234869015,
+      "grad_norm": 0.2979218241802279,
+      "learning_rate": 2.9165645553562215e-05,
+      "loss": 0.5911,
+      "step": 85
+    },
+    {
+      "epoch": 0.15537488708220415,
+      "grad_norm": 0.30352540649162485,
+      "learning_rate": 2.9135873106960525e-05,
+      "loss": 0.5902,
+      "step": 86
+    },
+    {
+      "epoch": 0.15718157181571815,
+      "grad_norm": 0.3047300397649292,
+      "learning_rate": 2.9105594483273603e-05,
+      "loss": 0.5927,
+      "step": 87
+    },
+    {
+      "epoch": 0.15898825654923215,
+      "grad_norm": 0.3034444492388091,
+      "learning_rate": 2.9074810766717865e-05,
+      "loss": 0.5969,
+      "step": 88
+    },
+    {
+      "epoch": 0.16079494128274616,
+      "grad_norm": 0.31726687931722786,
+      "learning_rate": 2.904352305959606e-05,
+      "loss": 0.5938,
+      "step": 89
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "grad_norm": 0.2844238571820103,
+      "learning_rate": 2.9011732482257835e-05,
+      "loss": 0.5856,
+      "step": 90
+    },
+    {
+      "epoch": 0.16440831074977416,
+      "grad_norm": 0.33861384709236475,
+      "learning_rate": 2.89794401730596e-05,
+      "loss": 0.5835,
+      "step": 91
+    },
+    {
+      "epoch": 0.16621499548328816,
+      "grad_norm": 0.31986755243990583,
+      "learning_rate": 2.894664728832377e-05,
+      "loss": 0.5875,
+      "step": 92
+    },
+    {
+      "epoch": 0.16802168021680217,
+      "grad_norm": 0.31772953202959486,
+      "learning_rate": 2.8913355002297367e-05,
+      "loss": 0.5937,
+      "step": 93
+    },
+    {
+      "epoch": 0.16982836495031617,
+      "grad_norm": 0.3404713775893871,
+      "learning_rate": 2.887956450710995e-05,
+      "loss": 0.5933,
+      "step": 94
+    },
+    {
+      "epoch": 0.17163504968383017,
+      "grad_norm": 0.3270438057428047,
+      "learning_rate": 2.8845277012730963e-05,
+      "loss": 0.5854,
+      "step": 95
+    },
+    {
+      "epoch": 0.17344173441734417,
+      "grad_norm": 0.2813265419298624,
+      "learning_rate": 2.8810493746926364e-05,
+      "loss": 0.5849,
+      "step": 96
+    },
+    {
+      "epoch": 0.17524841915085818,
+      "grad_norm": 0.30908563683812523,
+      "learning_rate": 2.87752159552147e-05,
+      "loss": 0.5906,
+      "step": 97
+    },
+    {
+      "epoch": 0.17705510388437218,
+      "grad_norm": 0.28172567784588337,
+      "learning_rate": 2.87394449008225e-05,
+      "loss": 0.5836,
+      "step": 98
+    },
+    {
+      "epoch": 0.17886178861788618,
+      "grad_norm": 0.32776100679221937,
+      "learning_rate": 2.8703181864639013e-05,
+      "loss": 0.5968,
+      "step": 99
+    },
+    {
+      "epoch": 0.18066847335140018,
+      "grad_norm": 0.2829820594340673,
+      "learning_rate": 2.8666428145170385e-05,
+      "loss": 0.5698,
+      "step": 100
+    },
+    {
+      "epoch": 0.18247515808491419,
+      "grad_norm": 0.2634972832550828,
+      "learning_rate": 2.8629185058493116e-05,
+      "loss": 0.5858,
+      "step": 101
+    },
+    {
+      "epoch": 0.1842818428184282,
+      "grad_norm": 0.33074374876902657,
+      "learning_rate": 2.8591453938206985e-05,
+      "loss": 0.6042,
+      "step": 102
+    },
+    {
+      "epoch": 0.1860885275519422,
+      "grad_norm": 0.2755244711155326,
+      "learning_rate": 2.8553236135387247e-05,
+      "loss": 0.5827,
+      "step": 103
+    },
+    {
+      "epoch": 0.1878952122854562,
+      "grad_norm": 0.3306960703512347,
+      "learning_rate": 2.8514533018536286e-05,
+      "loss": 0.5805,
+      "step": 104
+    },
+    {
+      "epoch": 0.1897018970189702,
+      "grad_norm": 0.27767659256895755,
+      "learning_rate": 2.8475345973534605e-05,
+      "loss": 0.5731,
+      "step": 105
+    },
+    {
+      "epoch": 0.1915085817524842,
+      "grad_norm": 0.43715096447176,
+      "learning_rate": 2.8435676403591193e-05,
+      "loss": 0.5759,
+      "step": 106
+    },
+    {
+      "epoch": 0.1933152664859982,
+      "grad_norm": 0.28202224774674794,
+      "learning_rate": 2.8395525729193284e-05,
+      "loss": 0.5821,
+      "step": 107
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.2549341033504584,
+      "learning_rate": 2.835489538805548e-05,
+      "loss": 0.5801,
+      "step": 108
+    },
+    {
+      "epoch": 0.1969286359530262,
+      "grad_norm": 0.2885151330973423,
+      "learning_rate": 2.8313786835068314e-05,
+      "loss": 0.5891,
+      "step": 109
+    },
+    {
+      "epoch": 0.1987353206865402,
+      "grad_norm": 0.2795891601436777,
+      "learning_rate": 2.8272201542246077e-05,
+      "loss": 0.5707,
+      "step": 110
+    },
+    {
+      "epoch": 0.2005420054200542,
+      "grad_norm": 0.2955873960209813,
+      "learning_rate": 2.8230140998674185e-05,
+      "loss": 0.5903,
+      "step": 111
+    },
+    {
+      "epoch": 0.2023486901535682,
+      "grad_norm": 0.2686848479774233,
+      "learning_rate": 2.8187606710455807e-05,
+      "loss": 0.5836,
+      "step": 112
+    },
+    {
+      "epoch": 0.2041553748870822,
+      "grad_norm": 0.30130327978633054,
+      "learning_rate": 2.8144600200657953e-05,
+      "loss": 0.5882,
+      "step": 113
+    },
+    {
+      "epoch": 0.20596205962059622,
+      "grad_norm": 0.3094839897177016,
+      "learning_rate": 2.8101123009256946e-05,
+      "loss": 0.5712,
+      "step": 114
+    },
+    {
+      "epoch": 0.20776874435411022,
+      "grad_norm": 0.26683135581406914,
+      "learning_rate": 2.8057176693083253e-05,
+      "loss": 0.5873,
+      "step": 115
+    },
+    {
+      "epoch": 0.20957542908762422,
+      "grad_norm": 0.2990360414829194,
+      "learning_rate": 2.8012762825765763e-05,
+      "loss": 0.5804,
+      "step": 116
+    },
+    {
+      "epoch": 0.21138211382113822,
+      "grad_norm": 0.3133148730057432,
+      "learning_rate": 2.7967882997675424e-05,
+      "loss": 0.5919,
+      "step": 117
+    },
+    {
+      "epoch": 0.21318879855465223,
+      "grad_norm": 0.3038806250211378,
+      "learning_rate": 2.7922538815868287e-05,
+      "loss": 0.5792,
+      "step": 118
+    },
+    {
+      "epoch": 0.21499548328816623,
+      "grad_norm": 0.26808000519659025,
+      "learning_rate": 2.7876731904027994e-05,
+      "loss": 0.5694,
+      "step": 119
+    },
+    {
+      "epoch": 0.21680216802168023,
+      "grad_norm": 0.3124504773400534,
+      "learning_rate": 2.78304639024076e-05,
+      "loss": 0.5885,
+      "step": 120
+    },
+    {
+      "epoch": 0.2186088527551942,
+      "grad_norm": 0.2537155548055984,
+      "learning_rate": 2.7783736467770863e-05,
+      "loss": 0.5837,
+      "step": 121
+    },
+    {
+      "epoch": 0.2204155374887082,
+      "grad_norm": 0.2976068165908906,
+      "learning_rate": 2.7736551273332908e-05,
+      "loss": 0.5888,
+      "step": 122
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.28922047785965427,
+      "learning_rate": 2.7688910008700305e-05,
+      "loss": 0.5789,
+      "step": 123
+    },
+    {
+      "epoch": 0.2240289069557362,
+      "grad_norm": 0.24080562112321108,
+      "learning_rate": 2.764081437981059e-05,
+      "loss": 0.5647,
+      "step": 124
+    },
+    {
+      "epoch": 0.22583559168925021,
+      "grad_norm": 0.27448072752877173,
+      "learning_rate": 2.7592266108871158e-05,
+      "loss": 0.572,
+      "step": 125
+    },
+    {
+      "epoch": 0.22764227642276422,
+      "grad_norm": 0.2926601943246854,
+      "learning_rate": 2.754326693429761e-05,
+      "loss": 0.5845,
+      "step": 126
+    },
+    {
+      "epoch": 0.22944896115627822,
+      "grad_norm": 0.2556901465713744,
+      "learning_rate": 2.7493818610651493e-05,
+      "loss": 0.5772,
+      "step": 127
+    },
+    {
+      "epoch": 0.23125564588979222,
+      "grad_norm": 0.2561501825860112,
+      "learning_rate": 2.744392290857747e-05,
+      "loss": 0.5765,
+      "step": 128
+    },
+    {
+      "epoch": 0.23306233062330622,
+      "grad_norm": 0.27007071971247465,
+      "learning_rate": 2.7393581614739924e-05,
+      "loss": 0.5715,
+      "step": 129
+    },
+    {
+      "epoch": 0.23486901535682023,
+      "grad_norm": 0.2720070067806271,
+      "learning_rate": 2.7342796531758984e-05,
+      "loss": 0.5899,
+      "step": 130
+    },
+    {
+      "epoch": 0.23667570009033423,
+      "grad_norm": 0.27867638614924434,
+      "learning_rate": 2.729156947814598e-05,
+      "loss": 0.5847,
+      "step": 131
+    },
+    {
+      "epoch": 0.23848238482384823,
+      "grad_norm": 0.26134114963816046,
+      "learning_rate": 2.7239902288238297e-05,
+      "loss": 0.5632,
+      "step": 132
+    },
+    {
+      "epoch": 0.24028906955736223,
+      "grad_norm": 0.26639406666272125,
+      "learning_rate": 2.7187796812133733e-05,
+      "loss": 0.579,
+      "step": 133
+    },
+    {
+      "epoch": 0.24209575429087624,
+      "grad_norm": 0.2876739206328272,
+      "learning_rate": 2.7135254915624213e-05,
+      "loss": 0.5795,
+      "step": 134
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 0.27235240180814757,
+      "learning_rate": 2.708227848012901e-05,
+      "loss": 0.5771,
+      "step": 135
+    },
+    {
+      "epoch": 0.24570912375790424,
+      "grad_norm": 0.2720723951174645,
+      "learning_rate": 2.7028869402627357e-05,
+      "loss": 0.5801,
+      "step": 136
+    },
+    {
+      "epoch": 0.24751580849141824,
+      "grad_norm": 0.26926686974517616,
+      "learning_rate": 2.6975029595590523e-05,
+      "loss": 0.5639,
+      "step": 137
+    },
+    {
+      "epoch": 0.24932249322493225,
+      "grad_norm": 0.29325483042034345,
+      "learning_rate": 2.6920760986913332e-05,
+      "loss": 0.5808,
+      "step": 138
+    },
+    {
+      "epoch": 0.25112917795844625,
+      "grad_norm": 0.2698556596124732,
+      "learning_rate": 2.6866065519845124e-05,
+      "loss": 0.584,
+      "step": 139
+    },
+    {
+      "epoch": 0.2529358626919603,
+      "grad_norm": 0.2786316780374937,
+      "learning_rate": 2.681094515292018e-05,
+      "loss": 0.583,
+      "step": 140
+    },
+    {
+      "epoch": 0.25474254742547425,
+      "grad_norm": 0.24933279116696466,
+      "learning_rate": 2.6755401859887598e-05,
+      "loss": 0.5641,
+      "step": 141
+    },
+    {
+      "epoch": 0.2565492321589883,
+      "grad_norm": 0.3122326056143099,
+      "learning_rate": 2.6699437629640595e-05,
+      "loss": 0.5841,
+      "step": 142
+    },
+    {
+      "epoch": 0.25835591689250226,
+      "grad_norm": 0.28090053633091877,
+      "learning_rate": 2.6643054466145297e-05,
+      "loss": 0.5758,
+      "step": 143
+    },
+    {
+      "epoch": 0.2601626016260163,
+      "grad_norm": 0.27419051211590195,
+      "learning_rate": 2.6586254388368995e-05,
+      "loss": 0.5642,
+      "step": 144
+    },
+    {
+      "epoch": 0.26196928635953026,
+      "grad_norm": 0.25632244502638984,
+      "learning_rate": 2.652903943020783e-05,
+      "loss": 0.5769,
+      "step": 145
+    },
+    {
+      "epoch": 0.26377597109304424,
+      "grad_norm": 0.27493807993448327,
+      "learning_rate": 2.647141164041398e-05,
+      "loss": 0.5814,
+      "step": 146
+    },
+    {
+      "epoch": 0.26558265582655827,
+      "grad_norm": 0.2683678706046532,
+      "learning_rate": 2.641337308252228e-05,
+      "loss": 0.571,
+      "step": 147
+    },
+    {
+      "epoch": 0.26738934056007224,
+      "grad_norm": 0.29628453279860983,
+      "learning_rate": 2.6354925834776346e-05,
+      "loss": 0.5726,
+      "step": 148
+    },
+    {
+      "epoch": 0.26919602529358627,
+      "grad_norm": 0.28402654957400403,
+      "learning_rate": 2.6296071990054167e-05,
+      "loss": 0.5696,
+      "step": 149
+    },
+    {
+      "epoch": 0.27100271002710025,
+      "grad_norm": 0.2607317023496585,
+      "learning_rate": 2.6236813655793123e-05,
+      "loss": 0.5798,
+      "step": 150
+    },
+    {
+      "epoch": 0.2728093947606143,
+      "grad_norm": 0.273647796185402,
+      "learning_rate": 2.617715295391457e-05,
+      "loss": 0.5614,
+      "step": 151
+    },
+    {
+      "epoch": 0.27461607949412825,
+      "grad_norm": 0.2545529593791399,
+      "learning_rate": 2.6117092020747824e-05,
+      "loss": 0.5692,
+      "step": 152
+    },
+    {
+      "epoch": 0.2764227642276423,
+      "grad_norm": 0.274532875914137,
+      "learning_rate": 2.6056633006953677e-05,
+      "loss": 0.5694,
+      "step": 153
+    },
+    {
+      "epoch": 0.27822944896115626,
+      "grad_norm": 0.26288128426350693,
+      "learning_rate": 2.5995778077447393e-05,
+      "loss": 0.5731,
+      "step": 154
+    },
+    {
+      "epoch": 0.2800361336946703,
+      "grad_norm": 0.30284194692462474,
+      "learning_rate": 2.5934529411321174e-05,
+      "loss": 0.5658,
+      "step": 155
+    },
+    {
+      "epoch": 0.28184281842818426,
+      "grad_norm": 0.24452133079312888,
+      "learning_rate": 2.587288920176613e-05,
+      "loss": 0.5657,
+      "step": 156
+    },
+    {
+      "epoch": 0.2836495031616983,
+      "grad_norm": 0.28048503748226455,
+      "learning_rate": 2.581085965599375e-05,
+      "loss": 0.5787,
+      "step": 157
+    },
+    {
+      "epoch": 0.28545618789521227,
+      "grad_norm": 0.26599106457147237,
+      "learning_rate": 2.5748442995156882e-05,
+      "loss": 0.5763,
+      "step": 158
+    },
+    {
+      "epoch": 0.2872628726287263,
+      "grad_norm": 0.2839977556276154,
+      "learning_rate": 2.5685641454270172e-05,
+      "loss": 0.557,
+      "step": 159
+    },
+    {
+      "epoch": 0.28906955736224027,
+      "grad_norm": 0.3026219403510213,
+      "learning_rate": 2.5622457282130046e-05,
+      "loss": 0.5662,
+      "step": 160
+    },
+    {
+      "epoch": 0.2908762420957543,
+      "grad_norm": 0.25173949399581536,
+      "learning_rate": 2.5558892741234173e-05,
+      "loss": 0.5742,
+      "step": 161
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.3113881337024894,
+      "learning_rate": 2.5494950107700482e-05,
+      "loss": 0.5602,
+      "step": 162
+    },
+    {
+      "epoch": 0.2944896115627823,
+      "grad_norm": 0.26454819092843895,
+      "learning_rate": 2.5430631671185616e-05,
+      "loss": 0.5682,
+      "step": 163
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 0.27612792011239423,
+      "learning_rate": 2.5365939734802973e-05,
+      "loss": 0.5777,
+      "step": 164
+    },
+    {
+      "epoch": 0.2981029810298103,
+      "grad_norm": 0.2546081323722588,
+      "learning_rate": 2.5300876615040223e-05,
+      "loss": 0.5686,
+      "step": 165
+    },
+    {
+      "epoch": 0.2999096657633243,
+      "grad_norm": 0.2963445091229743,
+      "learning_rate": 2.523544464167637e-05,
+      "loss": 0.5752,
+      "step": 166
+    },
+    {
+      "epoch": 0.3017163504968383,
+      "grad_norm": 0.256196797189933,
+      "learning_rate": 2.5169646157698313e-05,
+      "loss": 0.5738,
+      "step": 167
+    },
+    {
+      "epoch": 0.3035230352303523,
+      "grad_norm": 0.27645696746126036,
+      "learning_rate": 2.5103483519216964e-05,
+      "loss": 0.5724,
+      "step": 168
+    },
+    {
+      "epoch": 0.3053297199638663,
+      "grad_norm": 0.26064430234348385,
+      "learning_rate": 2.5036959095382875e-05,
+      "loss": 0.5644,
+      "step": 169
+    },
+    {
+      "epoch": 0.3071364046973803,
+      "grad_norm": 0.2883428318862628,
+      "learning_rate": 2.4970075268301388e-05,
+      "loss": 0.5781,
+      "step": 170
+    },
+    {
+      "epoch": 0.3089430894308943,
+      "grad_norm": 0.2632924938897706,
+      "learning_rate": 2.4902834432947353e-05,
+      "loss": 0.5612,
+      "step": 171
+    },
+    {
+      "epoch": 0.3107497741644083,
+      "grad_norm": 0.27223503577264474,
+      "learning_rate": 2.4835238997079382e-05,
+      "loss": 0.5681,
+      "step": 172
+    },
+    {
+      "epoch": 0.31255645889792233,
+      "grad_norm": 0.2777996613880595,
+      "learning_rate": 2.4767291381153603e-05,
+      "loss": 0.5713,
+      "step": 173
+    },
+    {
+      "epoch": 0.3143631436314363,
+      "grad_norm": 0.23698042977211534,
+      "learning_rate": 2.4698994018236994e-05,
+      "loss": 0.5624,
+      "step": 174
+    },
+    {
+      "epoch": 0.31616982836495033,
+      "grad_norm": 0.2942107184208593,
+      "learning_rate": 2.4630349353920284e-05,
+      "loss": 0.567,
+      "step": 175
+    },
+    {
+      "epoch": 0.3179765130984643,
+      "grad_norm": 0.25517257945021476,
+      "learning_rate": 2.4561359846230346e-05,
+      "loss": 0.5809,
+      "step": 176
+    },
+    {
+      "epoch": 0.31978319783197834,
+      "grad_norm": 0.24673263637056791,
+      "learning_rate": 2.4492027965542217e-05,
+      "loss": 0.5566,
+      "step": 177
+    },
+    {
+      "epoch": 0.3215898825654923,
+      "grad_norm": 0.2654696054555115,
+      "learning_rate": 2.44223561944906e-05,
+      "loss": 0.5636,
+      "step": 178
+    },
+    {
+      "epoch": 0.32339656729900634,
+      "grad_norm": 0.2509205757784683,
+      "learning_rate": 2.4352347027881003e-05,
+      "loss": 0.573,
+      "step": 179
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 0.2782257679089532,
+      "learning_rate": 2.4282002972600382e-05,
+      "loss": 0.5811,
+      "step": 180
+    },
+    {
+      "epoch": 0.32700993676603435,
+      "grad_norm": 0.261975491450884,
+      "learning_rate": 2.4211326547527377e-05,
+      "loss": 0.5595,
+      "step": 181
+    },
+    {
+      "epoch": 0.3288166214995483,
+      "grad_norm": 0.2732747607543431,
+      "learning_rate": 2.4140320283442125e-05,
+      "loss": 0.5698,
+      "step": 182
+    },
+    {
+      "epoch": 0.33062330623306235,
+      "grad_norm": 0.2654409094285421,
+      "learning_rate": 2.4068986722935625e-05,
+      "loss": 0.5802,
+      "step": 183
+    },
+    {
+      "epoch": 0.3324299909665763,
+      "grad_norm": 0.27364065775420887,
+      "learning_rate": 2.3997328420318705e-05,
+      "loss": 0.5763,
+      "step": 184
+    },
+    {
+      "epoch": 0.33423667570009036,
+      "grad_norm": 0.26988406932399184,
+      "learning_rate": 2.3925347941530556e-05,
+      "loss": 0.573,
+      "step": 185
+    },
+    {
+      "epoch": 0.33604336043360433,
+      "grad_norm": 0.24913498548586777,
+      "learning_rate": 2.3853047864046843e-05,
+      "loss": 0.5678,
+      "step": 186
+    },
+    {
+      "epoch": 0.33785004516711836,
+      "grad_norm": 0.26662821751854754,
+      "learning_rate": 2.3780430776787413e-05,
+      "loss": 0.5652,
+      "step": 187
+    },
+    {
+      "epoch": 0.33965672990063234,
+      "grad_norm": 0.24027260391804556,
+      "learning_rate": 2.3707499280023604e-05,
+      "loss": 0.5654,
+      "step": 188
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.26313325975109614,
+      "learning_rate": 2.3634255985285104e-05,
+      "loss": 0.5726,
+      "step": 189
+    },
+    {
+      "epoch": 0.34327009936766034,
+      "grad_norm": 0.28321211914229444,
+      "learning_rate": 2.356070351526648e-05,
+      "loss": 0.5615,
+      "step": 190
+    },
+    {
+      "epoch": 0.34507678410117437,
+      "grad_norm": 0.2472498045788604,
+      "learning_rate": 2.348684450373322e-05,
+      "loss": 0.5593,
+      "step": 191
+    },
+    {
+      "epoch": 0.34688346883468835,
+      "grad_norm": 0.240143859643124,
+      "learning_rate": 2.3412681595427467e-05,
+      "loss": 0.5667,
+      "step": 192
+    },
+    {
+      "epoch": 0.3486901535682023,
+      "grad_norm": 0.27894029380988317,
+      "learning_rate": 2.3338217445973268e-05,
+      "loss": 0.5683,
+      "step": 193
+    },
+    {
+      "epoch": 0.35049683830171635,
+      "grad_norm": 0.2514644044619394,
+      "learning_rate": 2.3263454721781537e-05,
+      "loss": 0.5699,
+      "step": 194
+    },
+    {
+      "epoch": 0.3523035230352303,
+      "grad_norm": 0.2802978993269217,
+      "learning_rate": 2.318839609995453e-05,
+      "loss": 0.5534,
+      "step": 195
+    },
+    {
+      "epoch": 0.35411020776874436,
+      "grad_norm": 0.25311337469847905,
+      "learning_rate": 2.3113044268189995e-05,
+      "loss": 0.5664,
+      "step": 196
+    },
+    {
+      "epoch": 0.35591689250225833,
+      "grad_norm": 0.24577349249807215,
+      "learning_rate": 2.303740192468495e-05,
+      "loss": 0.5661,
+      "step": 197
+    },
+    {
+      "epoch": 0.35772357723577236,
+      "grad_norm": 0.26381231166122326,
+      "learning_rate": 2.2961471778039045e-05,
+      "loss": 0.5434,
+      "step": 198
+    },
+    {
+      "epoch": 0.35953026196928634,
+      "grad_norm": 0.2605543346247411,
+      "learning_rate": 2.288525654715757e-05,
+      "loss": 0.5666,
+      "step": 199
+    },
+    {
+      "epoch": 0.36133694670280037,
+      "grad_norm": 0.27062115319955804,
+      "learning_rate": 2.280875896115413e-05,
+      "loss": 0.5554,
+      "step": 200
+    }
+  ],
+  "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": 231524290789376.0,
+  "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 sha256:3d1d9633dcd6813d7de42edcae0b51cc3e5bb933de5e38e218eee4ae8ccdb74c
+size 8081