Upload 14 files

.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
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df198d95be73242f4af7d353dc49feeb013ca64276c9061dcb5b09ef8f71344d
+oid sha256:1382f27e5c0e65c8249d8b137d7e3f0626975364e8a0c989b9e0ba5a4fe34862
 size 2384234968

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b083c39fe6388e575235f5e9fc0de1f1f66b59a6209788eb53663fc005d70f1
+size 1064

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": "<|endoftext|>",
+    "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:c760c4e715b8fa39254607191eca619d9b0612d5b29d3002ac512a5b6cad7d55
+size 11422934

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,552 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3735,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013386880856760375,
+      "grad_norm": 10.444840431213379,
+      "learning_rate": 9.995753909720682e-06,
+      "loss": 0.6863,
+      "step": 50
+    },
+    {
+      "epoch": 0.02677376171352075,
+      "grad_norm": 6.0297532081604,
+      "learning_rate": 9.98267481169144e-06,
+      "loss": 0.5107,
+      "step": 100
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 10.061092376708984,
+      "learning_rate": 9.960784067018357e-06,
+      "loss": 0.461,
+      "step": 150
+    },
+    {
+      "epoch": 0.0535475234270415,
+      "grad_norm": 6.345846176147461,
+      "learning_rate": 9.930120388544258e-06,
+      "loss": 0.464,
+      "step": 200
+    },
+    {
+      "epoch": 0.06693440428380187,
+      "grad_norm": 11.498032569885254,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 0.4628,
+      "step": 250
+    },
+    {
+      "epoch": 0.08032128514056225,
+      "grad_norm": 7.820000648498535,
+      "learning_rate": 9.842706558450787e-06,
+      "loss": 0.4477,
+      "step": 300
+    },
+    {
+      "epoch": 0.09370816599732262,
+      "grad_norm": 11.710145950317383,
+      "learning_rate": 9.786110994439813e-06,
+      "loss": 0.4411,
+      "step": 350
+    },
+    {
+      "epoch": 0.107095046854083,
+      "grad_norm": 7.274962902069092,
+      "learning_rate": 9.721051398463065e-06,
+      "loss": 0.4735,
+      "step": 400
+    },
+    {
+      "epoch": 0.12048192771084337,
+      "grad_norm": 8.92360782623291,
+      "learning_rate": 9.647642825624925e-06,
+      "loss": 0.4501,
+      "step": 450
+    },
+    {
+      "epoch": 0.13386880856760375,
+      "grad_norm": 8.818862915039062,
+      "learning_rate": 9.56601509583717e-06,
+      "loss": 0.457,
+      "step": 500
+    },
+    {
+      "epoch": 0.14725568942436412,
+      "grad_norm": 12.081962585449219,
+      "learning_rate": 9.476312564238035e-06,
+      "loss": 0.4308,
+      "step": 550
+    },
+    {
+      "epoch": 0.1606425702811245,
+      "grad_norm": 10.395655632019043,
+      "learning_rate": 9.378693865906347e-06,
+      "loss": 0.4408,
+      "step": 600
+    },
+    {
+      "epoch": 0.17402945113788487,
+      "grad_norm": 8.816801071166992,
+      "learning_rate": 9.273331635322185e-06,
+      "loss": 0.4497,
+      "step": 650
+    },
+    {
+      "epoch": 0.18741633199464525,
+      "grad_norm": 5.368481636047363,
+      "learning_rate": 9.160412201070217e-06,
+      "loss": 0.4447,
+      "step": 700
+    },
+    {
+      "epoch": 0.20080321285140562,
+      "grad_norm": 6.392587184906006,
+      "learning_rate": 9.040135256325584e-06,
+      "loss": 0.4407,
+      "step": 750
+    },
+    {
+      "epoch": 0.214190093708166,
+      "grad_norm": 7.844484806060791,
+      "learning_rate": 8.912713505705093e-06,
+      "loss": 0.4528,
+      "step": 800
+    },
+    {
+      "epoch": 0.22757697456492637,
+      "grad_norm": 8.644186019897461,
+      "learning_rate": 8.778372289108224e-06,
+      "loss": 0.4218,
+      "step": 850
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 10.462806701660156,
+      "learning_rate": 8.637349183213186e-06,
+      "loss": 0.4194,
+      "step": 900
+    },
+    {
+      "epoch": 0.2543507362784471,
+      "grad_norm": 8.724151611328125,
+      "learning_rate": 8.489893581332753e-06,
+      "loss": 0.4529,
+      "step": 950
+    },
+    {
+      "epoch": 0.2677376171352075,
+      "grad_norm": 8.977086067199707,
+      "learning_rate": 8.33626625237289e-06,
+      "loss": 0.4354,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28112449799196787,
+      "grad_norm": 7.824547290802002,
+      "learning_rate": 8.176738879674129e-06,
+      "loss": 0.4314,
+      "step": 1050
+    },
+    {
+      "epoch": 0.29451137884872824,
+      "grad_norm": 5.790531635284424,
+      "learning_rate": 8.01159358055124e-06,
+      "loss": 0.4286,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3078982597054886,
+      "grad_norm": 9.854269027709961,
+      "learning_rate": 7.84112240738086e-06,
+      "loss": 0.4201,
+      "step": 1150
+    },
+    {
+      "epoch": 0.321285140562249,
+      "grad_norm": 10.543339729309082,
+      "learning_rate": 7.665626831119396e-06,
+      "loss": 0.4405,
+      "step": 1200
+    },
+    {
+      "epoch": 0.33467202141900937,
+      "grad_norm": 4.100381851196289,
+      "learning_rate": 7.485417208164567e-06,
+      "loss": 0.4256,
+      "step": 1250
+    },
+    {
+      "epoch": 0.34805890227576974,
+      "grad_norm": 6.328100681304932,
+      "learning_rate": 7.300812231503435e-06,
+      "loss": 0.4333,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 5.430217742919922,
+      "learning_rate": 7.112138367117529e-06,
+      "loss": 0.3958,
+      "step": 1350
+    },
+    {
+      "epoch": 0.3748326639892905,
+      "grad_norm": 10.457396507263184,
+      "learning_rate": 6.91972927664176e-06,
+      "loss": 0.3899,
+      "step": 1400
+    },
+    {
+      "epoch": 0.38821954484605087,
+      "grad_norm": 6.345710754394531,
+      "learning_rate": 6.723925227298133e-06,
+      "loss": 0.3759,
+      "step": 1450
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "grad_norm": 9.008039474487305,
+      "learning_rate": 6.525072490147766e-06,
+      "loss": 0.3912,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4149933065595716,
+      "grad_norm": 7.655404090881348,
+      "learning_rate": 6.323522727725371e-06,
+      "loss": 0.3992,
+      "step": 1550
+    },
+    {
+      "epoch": 0.428380187416332,
+      "grad_norm": 7.3834967613220215,
+      "learning_rate": 6.119632372139152e-06,
+      "loss": 0.3655,
+      "step": 1600
+    },
+    {
+      "epoch": 0.44176706827309237,
+      "grad_norm": 8.772950172424316,
+      "learning_rate": 5.913761994735908e-06,
+      "loss": 0.4217,
+      "step": 1650
+    },
+    {
+      "epoch": 0.45515394912985274,
+      "grad_norm": 5.111259937286377,
+      "learning_rate": 5.706275668446074e-06,
+      "loss": 0.4281,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4685408299866131,
+      "grad_norm": 5.894604682922363,
+      "learning_rate": 5.497540323936371e-06,
+      "loss": 0.4276,
+      "step": 1750
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 9.776211738586426,
+      "learning_rate": 5.2879251007086555e-06,
+      "loss": 0.4073,
+      "step": 1800
+    },
+    {
+      "epoch": 0.49531459170013387,
+      "grad_norm": 8.807998657226562,
+      "learning_rate": 5.077800694292546e-06,
+      "loss": 0.4339,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5087014725568942,
+      "grad_norm": 8.668907165527344,
+      "learning_rate": 4.867538700686292e-06,
+      "loss": 0.432,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5220883534136547,
+      "grad_norm": 7.573647499084473,
+      "learning_rate": 4.657510959205182e-06,
+      "loss": 0.402,
+      "step": 1950
+    },
+    {
+      "epoch": 0.535475234270415,
+      "grad_norm": 7.700588703155518,
+      "learning_rate": 4.448088894899669e-06,
+      "loss": 0.3972,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5488621151271754,
+      "grad_norm": 7.340878009796143,
+      "learning_rate": 4.23964286170611e-06,
+      "loss": 0.3288,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5622489959839357,
+      "grad_norm": 7.881528377532959,
+      "learning_rate": 4.032541487491709e-06,
+      "loss": 0.4066,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5756358768406962,
+      "grad_norm": 7.409366607666016,
+      "learning_rate": 3.827151022151955e-06,
+      "loss": 0.3516,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5890227576974565,
+      "grad_norm": 7.922168731689453,
+      "learning_rate": 3.623834689913387e-06,
+      "loss": 0.3729,
+      "step": 2200
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 8.52475643157959,
+      "learning_rate": 3.4229520469871445e-06,
+      "loss": 0.4058,
+      "step": 2250
+    },
+    {
+      "epoch": 0.6157965194109772,
+      "grad_norm": 8.120729446411133,
+      "learning_rate": 3.2248583457092163e-06,
+      "loss": 0.3451,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6291834002677377,
+      "grad_norm": 8.336807250976562,
+      "learning_rate": 3.0299039062919417e-06,
+      "loss": 0.3691,
+      "step": 2350
+    },
+    {
+      "epoch": 0.642570281124498,
+      "grad_norm": 8.232279777526855,
+      "learning_rate": 2.8384334972977275e-06,
+      "loss": 0.412,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6559571619812584,
+      "grad_norm": 5.542270183563232,
+      "learning_rate": 2.650785725930657e-06,
+      "loss": 0.3768,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6693440428380187,
+      "grad_norm": 5.975722312927246,
+      "learning_rate": 2.4672924392241493e-06,
+      "loss": 0.3842,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6827309236947792,
+      "grad_norm": 6.6057868003845215,
+      "learning_rate": 2.288278137183748e-06,
+      "loss": 0.3278,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6961178045515395,
+      "grad_norm": 7.060661792755127,
+      "learning_rate": 2.11405939892275e-06,
+      "loss": 0.3673,
+      "step": 2600
+    },
+    {
+      "epoch": 0.7095046854082999,
+      "grad_norm": 5.489977836608887,
+      "learning_rate": 1.9449443228056565e-06,
+      "loss": 0.3522,
+      "step": 2650
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 7.412909507751465,
+      "learning_rate": 1.7812319815894096e-06,
+      "loss": 0.366,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7362784471218207,
+      "grad_norm": 5.627942085266113,
+      "learning_rate": 1.6232118935260628e-06,
+      "loss": 0.3906,
+      "step": 2750
+    },
+    {
+      "epoch": 0.749665327978581,
+      "grad_norm": 6.9760212898254395,
+      "learning_rate": 1.4711635103621718e-06,
+      "loss": 0.3912,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7630522088353414,
+      "grad_norm": 7.291072368621826,
+      "learning_rate": 1.325355723140367e-06,
+      "loss": 0.3753,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7764390896921017,
+      "grad_norm": 6.7273478507995605,
+      "learning_rate": 1.1860463866770826e-06,
+      "loss": 0.3694,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7898259705488622,
+      "grad_norm": 7.016156196594238,
+      "learning_rate": 1.0534818635573751e-06,
+      "loss": 0.3636,
+      "step": 2950
+    },
+    {
+      "epoch": 0.8032128514056225,
+      "grad_norm": 7.053563117980957,
+      "learning_rate": 9.278965884532598e-07,
+      "loss": 0.4107,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8165997322623829,
+      "grad_norm": 6.060437202453613,
+      "learning_rate": 8.09512653536052e-07,
+      "loss": 0.3908,
+      "step": 3050
+    },
+    {
+      "epoch": 0.8299866131191432,
+      "grad_norm": 7.361605644226074,
+      "learning_rate": 6.985394157158893e-07,
+      "loss": 0.3662,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8433734939759037,
+      "grad_norm": 5.547077655792236,
+      "learning_rate": 5.951731264030202e-07,
+      "loss": 0.3513,
+      "step": 3150
+    },
+    {
+      "epoch": 0.856760374832664,
+      "grad_norm": 9.102234840393066,
+      "learning_rate": 4.995965844455969e-07,
+      "loss": 0.409,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8701472556894244,
+      "grad_norm": 6.737813472747803,
+      "learning_rate": 4.1197881285776675e-07,
+      "loss": 0.3838,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8835341365461847,
+      "grad_norm": 6.354872226715088,
+      "learning_rate": 3.324747599097078e-07,
+      "loss": 0.4013,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8969210174029452,
+      "grad_norm": 7.315886497497559,
+      "learning_rate": 2.61225025108276e-07,
+      "loss": 0.4003,
+      "step": 3350
+    },
+    {
+      "epoch": 0.9103078982597055,
+      "grad_norm": 7.8258562088012695,
+      "learning_rate": 1.9835561055279728e-07,
+      "loss": 0.3364,
+      "step": 3400
+    },
+    {
+      "epoch": 0.9236947791164659,
+      "grad_norm": 3.8167738914489746,
+      "learning_rate": 1.4397769810576668e-07,
+      "loss": 0.3611,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9370816599732262,
+      "grad_norm": 9.796895980834961,
+      "learning_rate": 9.818745277249076e-08,
+      "loss": 0.363,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9504685408299867,
+      "grad_norm": 9.241850852966309,
+      "learning_rate": 6.106585263740528e-08,
+      "loss": 0.4065,
+      "step": 3550
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 6.8581624031066895,
+      "learning_rate": 3.267854565780326e-08,
+      "loss": 0.361,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9772423025435074,
+      "grad_norm": 6.801017761230469,
+      "learning_rate": 1.3075733568240212e-08,
+      "loss": 0.3531,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9906291834002677,
+      "grad_norm": 7.733842372894287,
+      "learning_rate": 2.2920831009209944e-09,
+      "loss": 0.4049,
+      "step": 3700
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3735,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.010777670549504e+16,
+  "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:cd3bc88ff5b25f40cd4e4bf31742ef38e7a91fb605a571a3ce68503effacfe00
+size 5304