Upload 13 files

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 +1,30 @@
+{
+  "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": "bfloat16",
+  "transformers_version": "4.51.3",
+  "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": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26959522b94299347f77730624a319c28109d0340d48c89f1dbb4989e648a66f
+size 1192135096

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a15c0dcd92ea2ff4a008bcaf9b5653cf5fef53e7cf4aa7cb8dad9bd87fb97a7
+size 2384457646

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698d5b4cf77c9ebc19b060194e14eae494d30aba44b34f24c150bbbf3aaaac25
+size 14168

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df01ea4051b9e399c9eb1eba2d0b9833905aec11ae0dcc812e899641ef69ba3f
+size 1056

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_config.json

@@ -0,0 +1,240 @@
+{
+  "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 message.content is string 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.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.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        {{- 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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,480 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9872122762148337,
+  "eval_steps": 100,
+  "global_step": 585,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05115089514066496,
+      "grad_norm": 12.8125,
+      "learning_rate": 9.846153846153848e-05,
+      "loss": 0.9959,
+      "step": 10
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "grad_norm": 4.6875,
+      "learning_rate": 9.675213675213675e-05,
+      "loss": 0.5833,
+      "step": 20
+    },
+    {
+      "epoch": 0.1534526854219949,
+      "grad_norm": 3.9375,
+      "learning_rate": 9.504273504273504e-05,
+      "loss": 0.4739,
+      "step": 30
+    },
+    {
+      "epoch": 0.20460358056265984,
+      "grad_norm": 3.734375,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.4993,
+      "step": 40
+    },
+    {
+      "epoch": 0.2557544757033248,
+      "grad_norm": 3.65625,
+      "learning_rate": 9.162393162393162e-05,
+      "loss": 0.4797,
+      "step": 50
+    },
+    {
+      "epoch": 0.3069053708439898,
+      "grad_norm": 2.875,
+      "learning_rate": 8.991452991452992e-05,
+      "loss": 0.389,
+      "step": 60
+    },
+    {
+      "epoch": 0.35805626598465473,
+      "grad_norm": 2.8125,
+      "learning_rate": 8.820512820512821e-05,
+      "loss": 0.4691,
+      "step": 70
+    },
+    {
+      "epoch": 0.4092071611253197,
+      "grad_norm": 2.46875,
+      "learning_rate": 8.64957264957265e-05,
+      "loss": 0.3734,
+      "step": 80
+    },
+    {
+      "epoch": 0.46035805626598464,
+      "grad_norm": 2.28125,
+      "learning_rate": 8.478632478632479e-05,
+      "loss": 0.4401,
+      "step": 90
+    },
+    {
+      "epoch": 0.5115089514066496,
+      "grad_norm": 2.734375,
+      "learning_rate": 8.307692307692309e-05,
+      "loss": 0.4304,
+      "step": 100
+    },
+    {
+      "epoch": 0.5115089514066496,
+      "eval_loss": 0.8407434821128845,
+      "eval_runtime": 35.229,
+      "eval_samples_per_second": 11.099,
+      "eval_steps_per_second": 5.564,
+      "step": 100
+    },
+    {
+      "epoch": 0.5626598465473146,
+      "grad_norm": 2.03125,
+      "learning_rate": 8.136752136752138e-05,
+      "loss": 0.4492,
+      "step": 110
+    },
+    {
+      "epoch": 0.6138107416879796,
+      "grad_norm": 3.53125,
+      "learning_rate": 7.965811965811965e-05,
+      "loss": 0.3949,
+      "step": 120
+    },
+    {
+      "epoch": 0.6649616368286445,
+      "grad_norm": 2.03125,
+      "learning_rate": 7.794871794871795e-05,
+      "loss": 0.3737,
+      "step": 130
+    },
+    {
+      "epoch": 0.7161125319693095,
+      "grad_norm": 2.375,
+      "learning_rate": 7.623931623931624e-05,
+      "loss": 0.4031,
+      "step": 140
+    },
+    {
+      "epoch": 0.7672634271099744,
+      "grad_norm": 2.375,
+      "learning_rate": 7.452991452991453e-05,
+      "loss": 0.3672,
+      "step": 150
+    },
+    {
+      "epoch": 0.8184143222506394,
+      "grad_norm": 2.6875,
+      "learning_rate": 7.282051282051282e-05,
+      "loss": 0.3944,
+      "step": 160
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 2.625,
+      "learning_rate": 7.111111111111112e-05,
+      "loss": 0.4473,
+      "step": 170
+    },
+    {
+      "epoch": 0.9207161125319693,
+      "grad_norm": 2.21875,
+      "learning_rate": 6.940170940170941e-05,
+      "loss": 0.3476,
+      "step": 180
+    },
+    {
+      "epoch": 0.9718670076726342,
+      "grad_norm": 3.578125,
+      "learning_rate": 6.76923076923077e-05,
+      "loss": 0.3961,
+      "step": 190
+    },
+    {
+      "epoch": 1.020460358056266,
+      "grad_norm": 3.34375,
+      "learning_rate": 6.598290598290599e-05,
+      "loss": 0.3859,
+      "step": 200
+    },
+    {
+      "epoch": 1.020460358056266,
+      "eval_loss": 0.7718821167945862,
+      "eval_runtime": 33.9574,
+      "eval_samples_per_second": 11.514,
+      "eval_steps_per_second": 5.772,
+      "step": 200
+    },
+    {
+      "epoch": 1.0716112531969308,
+      "grad_norm": 2.578125,
+      "learning_rate": 6.427350427350429e-05,
+      "loss": 0.3484,
+      "step": 210
+    },
+    {
+      "epoch": 1.1227621483375958,
+      "grad_norm": 3.296875,
+      "learning_rate": 6.256410256410256e-05,
+      "loss": 0.3425,
+      "step": 220
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 2.09375,
+      "learning_rate": 6.085470085470085e-05,
+      "loss": 0.3622,
+      "step": 230
+    },
+    {
+      "epoch": 1.2250639386189257,
+      "grad_norm": 2.796875,
+      "learning_rate": 5.9145299145299146e-05,
+      "loss": 0.3369,
+      "step": 240
+    },
+    {
+      "epoch": 1.2762148337595907,
+      "grad_norm": 4.59375,
+      "learning_rate": 5.7435897435897434e-05,
+      "loss": 0.3215,
+      "step": 250
+    },
+    {
+      "epoch": 1.3273657289002558,
+      "grad_norm": 3.734375,
+      "learning_rate": 5.572649572649573e-05,
+      "loss": 0.328,
+      "step": 260
+    },
+    {
+      "epoch": 1.3785166240409208,
+      "grad_norm": 2.71875,
+      "learning_rate": 5.401709401709402e-05,
+      "loss": 0.3117,
+      "step": 270
+    },
+    {
+      "epoch": 1.4296675191815857,
+      "grad_norm": 2.328125,
+      "learning_rate": 5.230769230769231e-05,
+      "loss": 0.2767,
+      "step": 280
+    },
+    {
+      "epoch": 1.4808184143222507,
+      "grad_norm": 2.125,
+      "learning_rate": 5.05982905982906e-05,
+      "loss": 0.2631,
+      "step": 290
+    },
+    {
+      "epoch": 1.5319693094629157,
+      "grad_norm": 2.375,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 0.3234,
+      "step": 300
+    },
+    {
+      "epoch": 1.5319693094629157,
+      "eval_loss": 0.7180720567703247,
+      "eval_runtime": 34.1345,
+      "eval_samples_per_second": 11.455,
+      "eval_steps_per_second": 5.742,
+      "step": 300
+    },
+    {
+      "epoch": 1.5831202046035806,
+      "grad_norm": 2.328125,
+      "learning_rate": 4.717948717948718e-05,
+      "loss": 0.2915,
+      "step": 310
+    },
+    {
+      "epoch": 1.6342710997442456,
+      "grad_norm": 2.640625,
+      "learning_rate": 4.5470085470085474e-05,
+      "loss": 0.3123,
+      "step": 320
+    },
+    {
+      "epoch": 1.6854219948849105,
+      "grad_norm": 2.09375,
+      "learning_rate": 4.376068376068376e-05,
+      "loss": 0.3252,
+      "step": 330
+    },
+    {
+      "epoch": 1.7365728900255755,
+      "grad_norm": 1.7734375,
+      "learning_rate": 4.205128205128206e-05,
+      "loss": 0.3095,
+      "step": 340
+    },
+    {
+      "epoch": 1.7877237851662404,
+      "grad_norm": 2.28125,
+      "learning_rate": 4.0341880341880346e-05,
+      "loss": 0.2539,
+      "step": 350
+    },
+    {
+      "epoch": 1.8388746803069054,
+      "grad_norm": 2.5625,
+      "learning_rate": 3.8632478632478634e-05,
+      "loss": 0.2742,
+      "step": 360
+    },
+    {
+      "epoch": 1.8900255754475703,
+      "grad_norm": 3.078125,
+      "learning_rate": 3.692307692307693e-05,
+      "loss": 0.3169,
+      "step": 370
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.521367521367522e-05,
+      "loss": 0.2767,
+      "step": 380
+    },
+    {
+      "epoch": 1.9923273657289002,
+      "grad_norm": 1.859375,
+      "learning_rate": 3.3504273504273506e-05,
+      "loss": 0.3239,
+      "step": 390
+    },
+    {
+      "epoch": 2.040920716112532,
+      "grad_norm": 1.8203125,
+      "learning_rate": 3.1794871794871795e-05,
+      "loss": 0.269,
+      "step": 400
+    },
+    {
+      "epoch": 2.040920716112532,
+      "eval_loss": 0.6828166842460632,
+      "eval_runtime": 33.8312,
+      "eval_samples_per_second": 11.557,
+      "eval_steps_per_second": 5.793,
+      "step": 400
+    },
+    {
+      "epoch": 2.0920716112531967,
+      "grad_norm": 1.578125,
+      "learning_rate": 3.0085470085470086e-05,
+      "loss": 0.2818,
+      "step": 410
+    },
+    {
+      "epoch": 2.1432225063938617,
+      "grad_norm": 2.125,
+      "learning_rate": 2.8376068376068378e-05,
+      "loss": 0.2597,
+      "step": 420
+    },
+    {
+      "epoch": 2.1943734015345266,
+      "grad_norm": 2.21875,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.2343,
+      "step": 430
+    },
+    {
+      "epoch": 2.2455242966751916,
+      "grad_norm": 3.203125,
+      "learning_rate": 2.495726495726496e-05,
+      "loss": 0.2483,
+      "step": 440
+    },
+    {
+      "epoch": 2.296675191815857,
+      "grad_norm": 2.015625,
+      "learning_rate": 2.324786324786325e-05,
+      "loss": 0.2751,
+      "step": 450
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 1.546875,
+      "learning_rate": 2.1538461538461542e-05,
+      "loss": 0.2468,
+      "step": 460
+    },
+    {
+      "epoch": 2.398976982097187,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.982905982905983e-05,
+      "loss": 0.2586,
+      "step": 470
+    },
+    {
+      "epoch": 2.4501278772378514,
+      "grad_norm": 2.546875,
+      "learning_rate": 1.811965811965812e-05,
+      "loss": 0.249,
+      "step": 480
+    },
+    {
+      "epoch": 2.501278772378517,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.641025641025641e-05,
+      "loss": 0.2664,
+      "step": 490
+    },
+    {
+      "epoch": 2.5524296675191813,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.4700854700854703e-05,
+      "loss": 0.2642,
+      "step": 500
+    },
+    {
+      "epoch": 2.5524296675191813,
+      "eval_loss": 0.6801092028617859,
+      "eval_runtime": 33.1113,
+      "eval_samples_per_second": 11.809,
+      "eval_steps_per_second": 5.919,
+      "step": 500
+    },
+    {
+      "epoch": 2.6035805626598467,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.2991452991452993e-05,
+      "loss": 0.2889,
+      "step": 510
+    },
+    {
+      "epoch": 2.6547314578005117,
+      "grad_norm": 2.171875,
+      "learning_rate": 1.1282051282051283e-05,
+      "loss": 0.2604,
+      "step": 520
+    },
+    {
+      "epoch": 2.7058823529411766,
+      "grad_norm": 2.5625,
+      "learning_rate": 9.572649572649575e-06,
+      "loss": 0.2438,
+      "step": 530
+    },
+    {
+      "epoch": 2.7570332480818416,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.863247863247863e-06,
+      "loss": 0.2579,
+      "step": 540
+    },
+    {
+      "epoch": 2.8081841432225065,
+      "grad_norm": 5.09375,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 0.2926,
+      "step": 550
+    },
+    {
+      "epoch": 2.8593350383631715,
+      "grad_norm": 1.84375,
+      "learning_rate": 4.444444444444445e-06,
+      "loss": 0.2576,
+      "step": 560
+    },
+    {
+      "epoch": 2.9104859335038364,
+      "grad_norm": 1.8046875,
+      "learning_rate": 2.735042735042735e-06,
+      "loss": 0.2082,
+      "step": 570
+    },
+    {
+      "epoch": 2.9616368286445014,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.0256410256410257e-06,
+      "loss": 0.2314,
+      "step": 580
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 585,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1654075985362944.0,
+  "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:f4a2f02eee953f33957c1e7971b561ba4d9f45cd8633032a2da9c11e3d822787
+size 5280