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 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\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>" }}
+    {%- 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

config.json

@@ -0,0 +1,55 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.1",
+  "use_cache": true,
+  "use_mrope": 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": "4.53.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c5c349cb1481ea81ee05358111d622fc330db9edffaabfaf4064cb4de225cdd
+size 1976163472

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caff98e52a0fb7a67201751dff4db47c9f96f2f45f5c12f7f59d738a68612e9d
+size 3952505739

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae999e3bf3b913b0513ba4e2510cbbca43afe2c42c2d5e578e390dfa199860f
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37137fcce90cbae257becb508234162a0904803cee4f854ad6be5b47dfb6a127
+size 1465

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>",
+  "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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,354 @@
+{
+  "best_global_step": 3060,
+  "best_metric": 0.44437724351882935,
+  "best_model_checkpoint": "./sft_output_simpleQA\\checkpoint-3060",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 15300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16339869281045752,
+      "grad_norm": 1.7589987516403198,
+      "learning_rate": 1.9347712418300655e-05,
+      "loss": 0.6565,
+      "mean_token_accuracy": 0.8448051940202713,
+      "num_tokens": 260778.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.32679738562091504,
+      "grad_norm": 1.7202545404434204,
+      "learning_rate": 1.8694117647058824e-05,
+      "loss": 0.5658,
+      "mean_token_accuracy": 0.8607444787025451,
+      "num_tokens": 532143.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.5248209834098816,
+      "learning_rate": 1.8040522875816995e-05,
+      "loss": 0.4945,
+      "mean_token_accuracy": 0.8776222993135452,
+      "num_tokens": 794641.0,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6535947712418301,
+      "grad_norm": 1.153851866722107,
+      "learning_rate": 1.7386928104575163e-05,
+      "loss": 0.4709,
+      "mean_token_accuracy": 0.8819570996761322,
+      "num_tokens": 1067466.0,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8169934640522876,
+      "grad_norm": 2.172006607055664,
+      "learning_rate": 1.6733333333333335e-05,
+      "loss": 0.4283,
+      "mean_token_accuracy": 0.8932461794614792,
+      "num_tokens": 1332041.0,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 1.1672557592391968,
+      "learning_rate": 1.6079738562091506e-05,
+      "loss": 0.4424,
+      "mean_token_accuracy": 0.8902202717065811,
+      "num_tokens": 1591566.0,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.44437724351882935,
+      "eval_mean_token_accuracy": 0.8896721144309219,
+      "eval_num_tokens": 1620476.0,
+      "eval_runtime": 17.1879,
+      "eval_samples_per_second": 22.225,
+      "eval_steps_per_second": 22.225,
+      "step": 3060
+    },
+    {
+      "epoch": 1.1437908496732025,
+      "grad_norm": 1.5445764064788818,
+      "learning_rate": 1.5426143790849674e-05,
+      "loss": 0.2976,
+      "mean_token_accuracy": 0.9238177012205124,
+      "num_tokens": 1847540.0,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3071895424836601,
+      "grad_norm": 1.4802546501159668,
+      "learning_rate": 1.4772549019607844e-05,
+      "loss": 0.301,
+      "mean_token_accuracy": 0.9228217270374298,
+      "num_tokens": 2114882.0,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 1.7694408893585205,
+      "learning_rate": 1.4118954248366016e-05,
+      "loss": 0.275,
+      "mean_token_accuracy": 0.9289815596342087,
+      "num_tokens": 2383543.0,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 0.5041053295135498,
+      "learning_rate": 1.3465359477124185e-05,
+      "loss": 0.2656,
+      "mean_token_accuracy": 0.9312243936061859,
+      "num_tokens": 2655408.0,
+      "step": 5000
+    },
+    {
+      "epoch": 1.7973856209150327,
+      "grad_norm": 1.395111083984375,
+      "learning_rate": 1.2811764705882355e-05,
+      "loss": 0.277,
+      "mean_token_accuracy": 0.9283499264717102,
+      "num_tokens": 2909181.0,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.5925441980361938,
+      "learning_rate": 1.2158169934640525e-05,
+      "loss": 0.2716,
+      "mean_token_accuracy": 0.9297851510047913,
+      "num_tokens": 3175738.0,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.444907546043396,
+      "eval_mean_token_accuracy": 0.8944824228736119,
+      "eval_num_tokens": 3240952.0,
+      "eval_runtime": 16.6457,
+      "eval_samples_per_second": 22.949,
+      "eval_steps_per_second": 22.949,
+      "step": 6120
+    },
+    {
+      "epoch": 2.1241830065359477,
+      "grad_norm": 0.823498010635376,
+      "learning_rate": 1.1504575163398695e-05,
+      "loss": 0.178,
+      "mean_token_accuracy": 0.9529191081523896,
+      "num_tokens": 3438042.0,
+      "step": 6500
+    },
+    {
+      "epoch": 2.287581699346405,
+      "grad_norm": 2.165581703186035,
+      "learning_rate": 1.0850980392156865e-05,
+      "loss": 0.1592,
+      "mean_token_accuracy": 0.9576994030475616,
+      "num_tokens": 3704561.0,
+      "step": 7000
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.9315876960754395,
+      "learning_rate": 1.0197385620915034e-05,
+      "loss": 0.1613,
+      "mean_token_accuracy": 0.9569584859609603,
+      "num_tokens": 3962939.0,
+      "step": 7500
+    },
+    {
+      "epoch": 2.6143790849673203,
+      "grad_norm": 0.6542718410491943,
+      "learning_rate": 9.543790849673204e-06,
+      "loss": 0.1498,
+      "mean_token_accuracy": 0.9596330618858337,
+      "num_tokens": 4227835.0,
+      "step": 8000
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 2.1195223331451416,
+      "learning_rate": 8.890196078431374e-06,
+      "loss": 0.1571,
+      "mean_token_accuracy": 0.9582107998132706,
+      "num_tokens": 4490222.0,
+      "step": 8500
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.9135161638259888,
+      "learning_rate": 8.236601307189544e-06,
+      "loss": 0.1617,
+      "mean_token_accuracy": 0.9568131999969482,
+      "num_tokens": 4768317.0,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.48607146739959717,
+      "eval_mean_token_accuracy": 0.8936509206032878,
+      "eval_num_tokens": 4861428.0,
+      "eval_runtime": 18.0359,
+      "eval_samples_per_second": 21.18,
+      "eval_steps_per_second": 21.18,
+      "step": 9180
+    },
+    {
+      "epoch": 3.104575163398693,
+      "grad_norm": 0.5220202803611755,
+      "learning_rate": 7.5830065359477136e-06,
+      "loss": 0.1193,
+      "mean_token_accuracy": 0.9686885585784912,
+      "num_tokens": 5033546.0,
+      "step": 9500
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 1.7922545671463013,
+      "learning_rate": 6.929411764705883e-06,
+      "loss": 0.0853,
+      "mean_token_accuracy": 0.9778412123918533,
+      "num_tokens": 5299950.0,
+      "step": 10000
+    },
+    {
+      "epoch": 3.431372549019608,
+      "grad_norm": 0.9012777209281921,
+      "learning_rate": 6.275816993464052e-06,
+      "loss": 0.0882,
+      "mean_token_accuracy": 0.9765507321357727,
+      "num_tokens": 5562491.0,
+      "step": 10500
+    },
+    {
+      "epoch": 3.5947712418300655,
+      "grad_norm": 0.7348634600639343,
+      "learning_rate": 5.622222222222222e-06,
+      "loss": 0.083,
+      "mean_token_accuracy": 0.9779657925367355,
+      "num_tokens": 5831882.0,
+      "step": 11000
+    },
+    {
+      "epoch": 3.758169934640523,
+      "grad_norm": 1.3759405612945557,
+      "learning_rate": 4.968627450980393e-06,
+      "loss": 0.0859,
+      "mean_token_accuracy": 0.9769166078567505,
+      "num_tokens": 6089238.0,
+      "step": 11500
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 1.0385228395462036,
+      "learning_rate": 4.315032679738563e-06,
+      "loss": 0.0905,
+      "mean_token_accuracy": 0.9758910204172134,
+      "num_tokens": 6358110.0,
+      "step": 12000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5520662665367126,
+      "eval_mean_token_accuracy": 0.8913699647518977,
+      "eval_num_tokens": 6481904.0,
+      "eval_runtime": 18.076,
+      "eval_samples_per_second": 21.133,
+      "eval_steps_per_second": 21.133,
+      "step": 12240
+    },
+    {
+      "epoch": 4.084967320261438,
+      "grad_norm": 1.1012531518936157,
+      "learning_rate": 3.6614379084967324e-06,
+      "loss": 0.0645,
+      "mean_token_accuracy": 0.9829886084794999,
+      "num_tokens": 6621827.0,
+      "step": 12500
+    },
+    {
+      "epoch": 4.248366013071895,
+      "grad_norm": 1.51634681224823,
+      "learning_rate": 3.007843137254902e-06,
+      "loss": 0.0492,
+      "mean_token_accuracy": 0.987127070903778,
+      "num_tokens": 6878025.0,
+      "step": 13000
+    },
+    {
+      "epoch": 4.411764705882353,
+      "grad_norm": 0.771700382232666,
+      "learning_rate": 2.354248366013072e-06,
+      "loss": 0.0565,
+      "mean_token_accuracy": 0.9855971633195877,
+      "num_tokens": 7144101.0,
+      "step": 13500
+    },
+    {
+      "epoch": 4.57516339869281,
+      "grad_norm": 1.2798362970352173,
+      "learning_rate": 1.7006535947712418e-06,
+      "loss": 0.051,
+      "mean_token_accuracy": 0.9865847392082214,
+      "num_tokens": 7416906.0,
+      "step": 14000
+    },
+    {
+      "epoch": 4.738562091503268,
+      "grad_norm": 0.4460426867008209,
+      "learning_rate": 1.0470588235294118e-06,
+      "loss": 0.0511,
+      "mean_token_accuracy": 0.9866908140182495,
+      "num_tokens": 7684903.0,
+      "step": 14500
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 0.559505045413971,
+      "learning_rate": 3.934640522875818e-07,
+      "loss": 0.051,
+      "mean_token_accuracy": 0.9866579355001449,
+      "num_tokens": 7945394.0,
+      "step": 15000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.6016601324081421,
+      "eval_mean_token_accuracy": 0.8893632412112821,
+      "eval_num_tokens": 8102380.0,
+      "eval_runtime": 18.1768,
+      "eval_samples_per_second": 21.016,
+      "eval_steps_per_second": 21.016,
+      "step": 15300
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 1.739895902823936e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7e3c225d81034256954fd32a3016c23609f6a0f0205ee13d321f749a45bdd0
+size 6161