Upload 15 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 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c597bace32b85af5d63496591ab5214b73c4fcc6f638d3c11682f26cec56c246
+size 2384234968

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e1b2a0762fc906c0024942cd197380bf346c6d387e643a0bd86eb91b856ef7e
+size 4768667262

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b11a10749bfb1630d95eef94125f4590e8610c579d217d1f158e71ce518d72b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52efef1fe9ae010d0ec42f2156fe6897559bd28f2dc97fb71ebd6d797663a92a
+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": "<|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:c17662a7cccd0fe145cca6899f330fb623dd1636091c7050e9f61778a17faa12
+size 11422932

tokenizer_config.json

@@ -0,0 +1,246 @@
+{
+  "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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "max_length": 2048,
+  "model_max_length": 131072,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,343 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 100,
+  "global_step": 890,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05629838142153413,
+      "grad_norm": 73.79827880859375,
+      "learning_rate": 6.741573033707865e-07,
+      "loss": 1.1142,
+      "step": 25
+    },
+    {
+      "epoch": 0.11259676284306826,
+      "grad_norm": 42.81636047363281,
+      "learning_rate": 1.3764044943820225e-06,
+      "loss": 0.9691,
+      "step": 50
+    },
+    {
+      "epoch": 0.1688951442646024,
+      "grad_norm": 47.96848678588867,
+      "learning_rate": 2.078651685393259e-06,
+      "loss": 0.8995,
+      "step": 75
+    },
+    {
+      "epoch": 0.22519352568613651,
+      "grad_norm": 31.566650390625,
+      "learning_rate": 2.7808988764044947e-06,
+      "loss": 0.8544,
+      "step": 100
+    },
+    {
+      "epoch": 0.22519352568613651,
+      "eval_loss": 0.8106070160865784,
+      "eval_runtime": 144.058,
+      "eval_samples_per_second": 17.639,
+      "eval_steps_per_second": 4.415,
+      "step": 100
+    },
+    {
+      "epoch": 0.28149190710767064,
+      "grad_norm": 38.754512786865234,
+      "learning_rate": 3.4831460674157306e-06,
+      "loss": 0.8218,
+      "step": 125
+    },
+    {
+      "epoch": 0.3377902885292048,
+      "grad_norm": 31.520471572875977,
+      "learning_rate": 4.185393258426967e-06,
+      "loss": 0.8258,
+      "step": 150
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 56.859840393066406,
+      "learning_rate": 4.8876404494382024e-06,
+      "loss": 0.7988,
+      "step": 175
+    },
+    {
+      "epoch": 0.45038705137227303,
+      "grad_norm": 30.1495361328125,
+      "learning_rate": 4.989275486268417e-06,
+      "loss": 0.8601,
+      "step": 200
+    },
+    {
+      "epoch": 0.45038705137227303,
+      "eval_loss": 0.7438946962356567,
+      "eval_runtime": 143.9368,
+      "eval_samples_per_second": 17.654,
+      "eval_steps_per_second": 4.419,
+      "step": 200
+    },
+    {
+      "epoch": 0.5066854327938072,
+      "grad_norm": 31.79728889465332,
+      "learning_rate": 4.948681495949055e-06,
+      "loss": 0.8459,
+      "step": 225
+    },
+    {
+      "epoch": 0.5629838142153413,
+      "grad_norm": 49.886512756347656,
+      "learning_rate": 4.878322110300771e-06,
+      "loss": 0.7708,
+      "step": 250
+    },
+    {
+      "epoch": 0.6192821956368755,
+      "grad_norm": 43.86843490600586,
+      "learning_rate": 4.779052595691355e-06,
+      "loss": 0.8003,
+      "step": 275
+    },
+    {
+      "epoch": 0.6755805770584096,
+      "grad_norm": 40.10922622680664,
+      "learning_rate": 4.652079640843434e-06,
+      "loss": 0.7687,
+      "step": 300
+    },
+    {
+      "epoch": 0.6755805770584096,
+      "eval_loss": 0.7006282806396484,
+      "eval_runtime": 144.0594,
+      "eval_samples_per_second": 17.639,
+      "eval_steps_per_second": 4.415,
+      "step": 300
+    },
+    {
+      "epoch": 0.7318789584799437,
+      "grad_norm": 44.42373275756836,
+      "learning_rate": 4.498946688709216e-06,
+      "loss": 0.7929,
+      "step": 325
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 28.532670974731445,
+      "learning_rate": 4.321515174867686e-06,
+      "loss": 0.7436,
+      "step": 350
+    },
+    {
+      "epoch": 0.844475721323012,
+      "grad_norm": 31.210020065307617,
+      "learning_rate": 4.121941900504316e-06,
+      "loss": 0.7638,
+      "step": 375
+    },
+    {
+      "epoch": 0.9007741027445461,
+      "grad_norm": 22.040390014648438,
+      "learning_rate": 3.902652815020175e-06,
+      "loss": 0.7845,
+      "step": 400
+    },
+    {
+      "epoch": 0.9007741027445461,
+      "eval_loss": 0.68995600938797,
+      "eval_runtime": 143.9705,
+      "eval_samples_per_second": 17.649,
+      "eval_steps_per_second": 4.418,
+      "step": 400
+    },
+    {
+      "epoch": 0.9570724841660803,
+      "grad_norm": 38.43577194213867,
+      "learning_rate": 3.6663135269607413e-06,
+      "loss": 0.7506,
+      "step": 425
+    },
+    {
+      "epoch": 1.011259676284307,
+      "grad_norm": 16.64950180053711,
+      "learning_rate": 3.415796901724183e-06,
+      "loss": 0.7202,
+      "step": 450
+    },
+    {
+      "epoch": 1.067558057705841,
+      "grad_norm": 43.190391540527344,
+      "learning_rate": 3.154148139921102e-06,
+      "loss": 0.4167,
+      "step": 475
+    },
+    {
+      "epoch": 1.123856439127375,
+      "grad_norm": 54.2507209777832,
+      "learning_rate": 2.884547760882115e-06,
+      "loss": 0.4801,
+      "step": 500
+    },
+    {
+      "epoch": 1.123856439127375,
+      "eval_loss": 0.8393383622169495,
+      "eval_runtime": 143.8302,
+      "eval_samples_per_second": 17.667,
+      "eval_steps_per_second": 4.422,
+      "step": 500
+    },
+    {
+      "epoch": 1.1801548205489092,
+      "grad_norm": 29.468156814575195,
+      "learning_rate": 2.610272941274012e-06,
+      "loss": 0.468,
+      "step": 525
+    },
+    {
+      "epoch": 1.2364532019704433,
+      "grad_norm": 54.59718704223633,
+      "learning_rate": 2.3346576787799995e-06,
+      "loss": 0.4276,
+      "step": 550
+    },
+    {
+      "epoch": 1.2927515833919774,
+      "grad_norm": 24.585559844970703,
+      "learning_rate": 2.0610522650816985e-06,
+      "loss": 0.4573,
+      "step": 575
+    },
+    {
+      "epoch": 1.3490499648135117,
+      "grad_norm": 46.79640579223633,
+      "learning_rate": 1.7927825607764699e-06,
+      "loss": 0.4322,
+      "step": 600
+    },
+    {
+      "epoch": 1.3490499648135117,
+      "eval_loss": 0.8045698404312134,
+      "eval_runtime": 143.8316,
+      "eval_samples_per_second": 17.666,
+      "eval_steps_per_second": 4.422,
+      "step": 600
+    },
+    {
+      "epoch": 1.4053483462350458,
+      "grad_norm": 38.788055419921875,
+      "learning_rate": 1.5331095672712463e-06,
+      "loss": 0.4275,
+      "step": 625
+    },
+    {
+      "epoch": 1.4616467276565799,
+      "grad_norm": 44.83256530761719,
+      "learning_rate": 1.2851897870841026e-06,
+      "loss": 0.4328,
+      "step": 650
+    },
+    {
+      "epoch": 1.517945109078114,
+      "grad_norm": 42.977962493896484,
+      "learning_rate": 1.0520368544011661e-06,
+      "loss": 0.5033,
+      "step": 675
+    },
+    {
+      "epoch": 1.574243490499648,
+      "grad_norm": 29.950496673583984,
+      "learning_rate": 8.364849022956395e-07,
+      "loss": 0.4405,
+      "step": 700
+    },
+    {
+      "epoch": 1.574243490499648,
+      "eval_loss": 0.7927849292755127,
+      "eval_runtime": 143.8064,
+      "eval_samples_per_second": 17.67,
+      "eval_steps_per_second": 4.423,
+      "step": 700
+    },
+    {
+      "epoch": 1.6305418719211824,
+      "grad_norm": 24.71552085876465,
+      "learning_rate": 6.41154111905393e-07,
+      "loss": 0.4053,
+      "step": 725
+    },
+    {
+      "epoch": 1.6868402533427163,
+      "grad_norm": 25.670047760009766,
+      "learning_rate": 4.684188623424088e-07,
+      "loss": 0.4095,
+      "step": 750
+    },
+    {
+      "epoch": 1.7431386347642506,
+      "grad_norm": 32.34583282470703,
+      "learning_rate": 3.203788684936535e-07,
+      "loss": 0.49,
+      "step": 775
+    },
+    {
+      "epoch": 1.7994370161857847,
+      "grad_norm": 20.85134506225586,
+      "learning_rate": 1.9883365755312357e-07,
+      "loss": 0.4536,
+      "step": 800
+    },
+    {
+      "epoch": 1.7994370161857847,
+      "eval_loss": 0.7712846398353577,
+      "eval_runtime": 143.8777,
+      "eval_samples_per_second": 17.661,
+      "eval_steps_per_second": 4.42,
+      "step": 800
+    },
+    {
+      "epoch": 1.8557353976073188,
+      "grad_norm": 41.842350006103516,
+      "learning_rate": 1.0526069454024651e-07,
+      "loss": 0.4295,
+      "step": 825
+    },
+    {
+      "epoch": 1.912033779028853,
+      "grad_norm": 64.68550109863281,
+      "learning_rate": 4.079742270388321e-08,
+      "loss": 0.4199,
+      "step": 850
+    },
+    {
+      "epoch": 1.968332160450387,
+      "grad_norm": 29.4891414642334,
+      "learning_rate": 6.2274371230905405e-09,
+      "loss": 0.5146,
+      "step": 875
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5382222970290176e+17,
+  "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 sha256:20a0c4a97aa63af240f588e1b25d231501a734ece5c3b8f816bea7e73a8f543d
+size 5304