Training in progress, step 294, checkpoint

.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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/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
+}

last-checkpoint/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": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9045f8cc668eda88beacce9c1f33656a2ad38ae6d88fb9aab77d34127538c7ea
+size 2384234968

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af24d6146f8c90a308947e7101625cdfb8578e010d0f9faa9d61ca053907e0e
+size 4768662910

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d9a870ac912d1c886891701964c85501c156954f01974e25e3e56f75c8719e8
+size 1064

last-checkpoint/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
+  }
+}

last-checkpoint/tokenizer.json

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

last-checkpoint/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 not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,295 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.973384030418251,
+  "eval_steps": 100,
+  "global_step": 294,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10139416983523447,
+      "grad_norm": 7.341689586639404,
+      "learning_rate": 3e-06,
+      "loss": 1.9301,
+      "mean_token_accuracy": 0.7015900192782283,
+      "num_tokens": 40960.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.20278833967046894,
+      "grad_norm": 3.4939892292022705,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.3711,
+      "mean_token_accuracy": 0.9222113467752934,
+      "num_tokens": 81920.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.3041825095057034,
+      "grad_norm": 3.1293270587921143,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.3329,
+      "mean_token_accuracy": 0.9295499004423619,
+      "num_tokens": 122880.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.4055766793409379,
+      "grad_norm": 2.696124792098999,
+      "learning_rate": 9.65909090909091e-06,
+      "loss": 0.3534,
+      "mean_token_accuracy": 0.923385514318943,
+      "num_tokens": 163840.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.5069708491761724,
+      "grad_norm": 2.7373180389404297,
+      "learning_rate": 9.28030303030303e-06,
+      "loss": 0.323,
+      "mean_token_accuracy": 0.927984344214201,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6083650190114068,
+      "grad_norm": 2.713202953338623,
+      "learning_rate": 8.901515151515152e-06,
+      "loss": 0.325,
+      "mean_token_accuracy": 0.9285714246332646,
+      "num_tokens": 245760.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.7097591888466414,
+      "grad_norm": 1.9529573917388916,
+      "learning_rate": 8.522727272727273e-06,
+      "loss": 0.3085,
+      "mean_token_accuracy": 0.9311888426542282,
+      "num_tokens": 286720.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.8111533586818758,
+      "grad_norm": 2.214193344116211,
+      "learning_rate": 8.143939393939394e-06,
+      "loss": 0.3141,
+      "mean_token_accuracy": 0.9285958878695965,
+      "num_tokens": 327680.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.9125475285171103,
+      "grad_norm": 2.9874253273010254,
+      "learning_rate": 7.765151515151516e-06,
+      "loss": 0.2978,
+      "mean_token_accuracy": 0.9332191735506058,
+      "num_tokens": 368640.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.0101394169835234,
+      "grad_norm": 1.6859478950500488,
+      "learning_rate": 7.386363636363637e-06,
+      "loss": 0.2904,
+      "mean_token_accuracy": 0.9350141000438046,
+      "num_tokens": 408064.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.111533586818758,
+      "grad_norm": 2.440042734146118,
+      "learning_rate": 7.0075757575757585e-06,
+      "loss": 0.2429,
+      "mean_token_accuracy": 0.9437133051455021,
+      "num_tokens": 449024.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.2129277566539924,
+      "grad_norm": 2.3471450805664062,
+      "learning_rate": 6.628787878787879e-06,
+      "loss": 0.2284,
+      "mean_token_accuracy": 0.9461105674505234,
+      "num_tokens": 489984.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.3143219264892267,
+      "grad_norm": 2.114746332168579,
+      "learning_rate": 6.25e-06,
+      "loss": 0.2168,
+      "mean_token_accuracy": 0.9476271934807301,
+      "num_tokens": 530944.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.4157160963244613,
+      "grad_norm": 2.633122205734253,
+      "learning_rate": 5.871212121212122e-06,
+      "loss": 0.2142,
+      "mean_token_accuracy": 0.9478473529219628,
+      "num_tokens": 571904.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.5171102661596958,
+      "grad_norm": 2.1850287914276123,
+      "learning_rate": 5.492424242424242e-06,
+      "loss": 0.1976,
+      "mean_token_accuracy": 0.9522015653550625,
+      "num_tokens": 612864.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6185044359949303,
+      "grad_norm": 2.434112071990967,
+      "learning_rate": 5.113636363636364e-06,
+      "loss": 0.206,
+      "mean_token_accuracy": 0.9499266095459461,
+      "num_tokens": 653824.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.7198986058301649,
+      "grad_norm": 3.3653509616851807,
+      "learning_rate": 4.734848484848486e-06,
+      "loss": 0.2281,
+      "mean_token_accuracy": 0.946281798928976,
+      "num_tokens": 694784.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.8212927756653992,
+      "grad_norm": 2.184190511703491,
+      "learning_rate": 4.356060606060606e-06,
+      "loss": 0.2303,
+      "mean_token_accuracy": 0.9448385506868362,
+      "num_tokens": 735744.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.9226869455006337,
+      "grad_norm": 2.4431374073028564,
+      "learning_rate": 3.9772727272727275e-06,
+      "loss": 0.2039,
+      "mean_token_accuracy": 0.9513698562979698,
+      "num_tokens": 776704.0,
+      "step": 190
+    },
+    {
+      "epoch": 2.0202788339670468,
+      "grad_norm": 2.5739476680755615,
+      "learning_rate": 3.598484848484849e-06,
+      "loss": 0.2243,
+      "mean_token_accuracy": 0.9448496668369739,
+      "num_tokens": 816128.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.1216730038022815,
+      "grad_norm": 2.1968252658843994,
+      "learning_rate": 3.21969696969697e-06,
+      "loss": 0.1475,
+      "mean_token_accuracy": 0.9632583141326905,
+      "num_tokens": 857088.0,
+      "step": 210
+    },
+    {
+      "epoch": 2.223067173637516,
+      "grad_norm": 3.157244920730591,
+      "learning_rate": 2.8409090909090916e-06,
+      "loss": 0.1592,
+      "mean_token_accuracy": 0.9609344378113747,
+      "num_tokens": 898048.0,
+      "step": 220
+    },
+    {
+      "epoch": 2.32446134347275,
+      "grad_norm": 2.608046770095825,
+      "learning_rate": 2.4621212121212125e-06,
+      "loss": 0.1602,
+      "mean_token_accuracy": 0.9605675131082535,
+      "num_tokens": 939008.0,
+      "step": 230
+    },
+    {
+      "epoch": 2.425855513307985,
+      "grad_norm": 2.5809144973754883,
+      "learning_rate": 2.0833333333333334e-06,
+      "loss": 0.1619,
+      "mean_token_accuracy": 0.9582925610244274,
+      "num_tokens": 979968.0,
+      "step": 240
+    },
+    {
+      "epoch": 2.527249683143219,
+      "grad_norm": 2.3788442611694336,
+      "learning_rate": 1.7045454545454546e-06,
+      "loss": 0.1608,
+      "mean_token_accuracy": 0.9608365908265114,
+      "num_tokens": 1020928.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.6286438529784535,
+      "grad_norm": 2.6588313579559326,
+      "learning_rate": 1.3257575757575757e-06,
+      "loss": 0.1386,
+      "mean_token_accuracy": 0.9653864972293377,
+      "num_tokens": 1061888.0,
+      "step": 260
+    },
+    {
+      "epoch": 2.7300380228136882,
+      "grad_norm": 3.2152559757232666,
+      "learning_rate": 9.469696969696971e-07,
+      "loss": 0.1568,
+      "mean_token_accuracy": 0.9612769052386284,
+      "num_tokens": 1102848.0,
+      "step": 270
+    },
+    {
+      "epoch": 2.8314321926489225,
+      "grad_norm": 2.439126968383789,
+      "learning_rate": 5.681818181818182e-07,
+      "loss": 0.1654,
+      "mean_token_accuracy": 0.9592221111059189,
+      "num_tokens": 1143808.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.9328263624841573,
+      "grad_norm": 2.8873305320739746,
+      "learning_rate": 1.893939393939394e-07,
+      "loss": 0.143,
+      "mean_token_accuracy": 0.9642123229801655,
+      "num_tokens": 1184768.0,
+      "step": 290
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 294,
+  "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": 3174410194255872.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4361e0bcfea42042f2345d8c36671f75fe29fdad081a849f4abbf632d7a96db0
+size 5688