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

.ipynb_checkpoints/chat_template-checkpoint.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 %}

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 %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "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": "bfloat16",
+  "transformers_version": "4.52.3",
+  "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": "4.52.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ea2b0eddce7339b298bc8c58918397f123349245192d815d2af8b56d04fb8b
+size 1192135096

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065361b4201df8f00f40101c448ef39e3d78f155c70eb5820845e6c92d05e61c
+size 2384459962

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645b71843375baf4cc10bc75a2f0f04e91b8e3f8e8929f518a87022898b3bc20
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8a0a6f8495e51630367fb3fb55dd38143389a4578d11ad92e9a83577accd3c
+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 sha256:574de68a0f63f2004784a421c7d42c2b2786c05cb38542d2ed3525757a1f7fde
+size 11422932

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 +1,304 @@
+{
+  "best_global_step": 3000,
+  "best_metric": 1.5481228828430176,
+  "best_model_checkpoint": "./models/checkpoint-3000",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 9405,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1595150741745095,
+      "grad_norm": 6.21875,
+      "learning_rate": 4.73471557682084e-05,
+      "loss": 1.6533,
+      "step": 500
+    },
+    {
+      "epoch": 0.1595150741745095,
+      "eval_loss": 1.670200228691101,
+      "eval_runtime": 1.8707,
+      "eval_samples_per_second": 53.457,
+      "eval_steps_per_second": 13.364,
+      "step": 500
+    },
+    {
+      "epoch": 0.319030148349019,
+      "grad_norm": 6.5,
+      "learning_rate": 4.468899521531101e-05,
+      "loss": 1.5746,
+      "step": 1000
+    },
+    {
+      "epoch": 0.319030148349019,
+      "eval_loss": 1.6311461925506592,
+      "eval_runtime": 1.8699,
+      "eval_samples_per_second": 53.48,
+      "eval_steps_per_second": 13.37,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4785452225235285,
+      "grad_norm": 6.90625,
+      "learning_rate": 4.203083466241361e-05,
+      "loss": 1.5591,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4785452225235285,
+      "eval_loss": 1.6131033897399902,
+      "eval_runtime": 1.8703,
+      "eval_samples_per_second": 53.466,
+      "eval_steps_per_second": 13.367,
+      "step": 1500
+    },
+    {
+      "epoch": 0.638060296698038,
+      "grad_norm": 6.0,
+      "learning_rate": 3.9372674109516216e-05,
+      "loss": 1.5301,
+      "step": 2000
+    },
+    {
+      "epoch": 0.638060296698038,
+      "eval_loss": 1.582728624343872,
+      "eval_runtime": 1.8741,
+      "eval_samples_per_second": 53.358,
+      "eval_steps_per_second": 13.34,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7975753708725475,
+      "grad_norm": 6.09375,
+      "learning_rate": 3.671451355661882e-05,
+      "loss": 1.5222,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7975753708725475,
+      "eval_loss": 1.5706853866577148,
+      "eval_runtime": 1.8744,
+      "eval_samples_per_second": 53.351,
+      "eval_steps_per_second": 13.338,
+      "step": 2500
+    },
+    {
+      "epoch": 0.957090445047057,
+      "grad_norm": 6.1875,
+      "learning_rate": 3.405635300372142e-05,
+      "loss": 1.4987,
+      "step": 3000
+    },
+    {
+      "epoch": 0.957090445047057,
+      "eval_loss": 1.5481228828430176,
+      "eval_runtime": 1.875,
+      "eval_samples_per_second": 53.335,
+      "eval_steps_per_second": 13.334,
+      "step": 3000
+    },
+    {
+      "epoch": 1.116446004147392,
+      "grad_norm": 6.21875,
+      "learning_rate": 3.1398192450824035e-05,
+      "loss": 1.3145,
+      "step": 3500
+    },
+    {
+      "epoch": 1.116446004147392,
+      "eval_loss": 1.565281629562378,
+      "eval_runtime": 1.8772,
+      "eval_samples_per_second": 53.272,
+      "eval_steps_per_second": 13.318,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2759610783219015,
+      "grad_norm": 7.28125,
+      "learning_rate": 2.8740031897926635e-05,
+      "loss": 1.2554,
+      "step": 4000
+    },
+    {
+      "epoch": 1.2759610783219015,
+      "eval_loss": 1.5643690824508667,
+      "eval_runtime": 1.8766,
+      "eval_samples_per_second": 53.287,
+      "eval_steps_per_second": 13.322,
+      "step": 4000
+    },
+    {
+      "epoch": 1.435476152496411,
+      "grad_norm": 7.0,
+      "learning_rate": 2.608187134502924e-05,
+      "loss": 1.2597,
+      "step": 4500
+    },
+    {
+      "epoch": 1.435476152496411,
+      "eval_loss": 1.562727451324463,
+      "eval_runtime": 1.8896,
+      "eval_samples_per_second": 52.92,
+      "eval_steps_per_second": 13.23,
+      "step": 4500
+    },
+    {
+      "epoch": 1.5949912266709205,
+      "grad_norm": 6.84375,
+      "learning_rate": 2.3423710792131844e-05,
+      "loss": 1.2496,
+      "step": 5000
+    },
+    {
+      "epoch": 1.5949912266709205,
+      "eval_loss": 1.560770869255066,
+      "eval_runtime": 1.8771,
+      "eval_samples_per_second": 53.273,
+      "eval_steps_per_second": 13.318,
+      "step": 5000
+    },
+    {
+      "epoch": 1.75450630084543,
+      "grad_norm": 6.90625,
+      "learning_rate": 2.076555023923445e-05,
+      "loss": 1.2422,
+      "step": 5500
+    },
+    {
+      "epoch": 1.75450630084543,
+      "eval_loss": 1.5582979917526245,
+      "eval_runtime": 1.8771,
+      "eval_samples_per_second": 53.274,
+      "eval_steps_per_second": 13.319,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9140213750199395,
+      "grad_norm": 7.4375,
+      "learning_rate": 1.8107389686337057e-05,
+      "loss": 1.2432,
+      "step": 6000
+    },
+    {
+      "epoch": 1.9140213750199395,
+      "eval_loss": 1.5532492399215698,
+      "eval_runtime": 1.8789,
+      "eval_samples_per_second": 53.222,
+      "eval_steps_per_second": 13.306,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0733769341202746,
+      "grad_norm": 7.5,
+      "learning_rate": 1.544922913343966e-05,
+      "loss": 1.1977,
+      "step": 6500
+    },
+    {
+      "epoch": 2.0733769341202746,
+      "eval_loss": 1.5878651142120361,
+      "eval_runtime": 1.8781,
+      "eval_samples_per_second": 53.244,
+      "eval_steps_per_second": 13.311,
+      "step": 6500
+    },
+    {
+      "epoch": 2.232892008294784,
+      "grad_norm": 7.53125,
+      "learning_rate": 1.2791068580542265e-05,
+      "loss": 1.15,
+      "step": 7000
+    },
+    {
+      "epoch": 2.232892008294784,
+      "eval_loss": 1.5915130376815796,
+      "eval_runtime": 1.8844,
+      "eval_samples_per_second": 53.068,
+      "eval_steps_per_second": 13.267,
+      "step": 7000
+    },
+    {
+      "epoch": 2.392407082469293,
+      "grad_norm": 7.6875,
+      "learning_rate": 1.0132908027644871e-05,
+      "loss": 1.1389,
+      "step": 7500
+    },
+    {
+      "epoch": 2.392407082469293,
+      "eval_loss": 1.5931323766708374,
+      "eval_runtime": 1.8778,
+      "eval_samples_per_second": 53.255,
+      "eval_steps_per_second": 13.314,
+      "step": 7500
+    },
+    {
+      "epoch": 2.551922156643803,
+      "grad_norm": 7.4375,
+      "learning_rate": 7.474747474747475e-06,
+      "loss": 1.1464,
+      "step": 8000
+    },
+    {
+      "epoch": 2.551922156643803,
+      "eval_loss": 1.5903747081756592,
+      "eval_runtime": 1.8791,
+      "eval_samples_per_second": 53.216,
+      "eval_steps_per_second": 13.304,
+      "step": 8000
+    },
+    {
+      "epoch": 2.711437230818312,
+      "grad_norm": 7.46875,
+      "learning_rate": 4.816586921850081e-06,
+      "loss": 1.1446,
+      "step": 8500
+    },
+    {
+      "epoch": 2.711437230818312,
+      "eval_loss": 1.590154767036438,
+      "eval_runtime": 1.8787,
+      "eval_samples_per_second": 53.23,
+      "eval_steps_per_second": 13.307,
+      "step": 8500
+    },
+    {
+      "epoch": 2.870952304992822,
+      "grad_norm": 8.125,
+      "learning_rate": 2.158426368952685e-06,
+      "loss": 1.1444,
+      "step": 9000
+    },
+    {
+      "epoch": 2.870952304992822,
+      "eval_loss": 1.5894922018051147,
+      "eval_runtime": 1.8789,
+      "eval_samples_per_second": 53.221,
+      "eval_steps_per_second": 13.305,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9405,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.035763059359744e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcee203cf6874c58a2c88b846e1a5675b153e78ab8c5fd75a9dbd12e344526fe
+size 5240