Init commit

.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

README.md

@@ -1,3 +1,60 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: qwen2.5-7B-q4-pe-normalized-text
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen2.5-7B-q4-pe-normalized-text
+
+This model is a fine-tuned version of [unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit) on the pe dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2.5-7B-Instruct-unsloth-bnb-4bit",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a369235d495e71fe2d6e3cedc4634dfba9015c053af178979a217590e5ba2385
+size 80792096

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.894409937888199,
+    "total_flos": 5.058205338938573e+16,
+    "train_loss": 0.058221997842192647,
+    "train_runtime": 1234.8427,
+    "train_samples_per_second": 1.304,
+    "train_steps_per_second": 0.162
+}

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": "<|vision_pad|>",
+    "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 +1,209 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\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>\" }}\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) 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{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.894409937888199,
+    "total_flos": 5.058205338938573e+16,
+    "train_loss": 0.058221997842192647,
+    "train_runtime": 1234.8427,
+    "train_samples_per_second": 1.304,
+    "train_steps_per_second": 0.162
+}

trainer_log.jsonl

@@ -0,0 +1,21 @@
+{"current_steps": 10, "total_steps": 200, "loss": 0.2624, "lr": 2.5e-05, "epoch": 0.2484472049689441, "percentage": 5.0, "elapsed_time": "0:01:00", "remaining_time": "0:19:16"}
+{"current_steps": 20, "total_steps": 200, "loss": 0.1247, "lr": 5e-05, "epoch": 0.4968944099378882, "percentage": 10.0, "elapsed_time": "0:02:02", "remaining_time": "0:18:26"}
+{"current_steps": 30, "total_steps": 200, "loss": 0.1121, "lr": 4.962019382530521e-05, "epoch": 0.7453416149068323, "percentage": 15.0, "elapsed_time": "0:03:05", "remaining_time": "0:17:32"}
+{"current_steps": 40, "total_steps": 200, "loss": 0.107, "lr": 4.849231551964771e-05, "epoch": 0.9937888198757764, "percentage": 20.0, "elapsed_time": "0:04:08", "remaining_time": "0:16:33"}
+{"current_steps": 50, "total_steps": 200, "loss": 0.0748, "lr": 4.665063509461097e-05, "epoch": 1.2236024844720497, "percentage": 25.0, "elapsed_time": "0:05:07", "remaining_time": "0:15:23"}
+{"current_steps": 60, "total_steps": 200, "loss": 0.0644, "lr": 4.415111107797445e-05, "epoch": 1.4720496894409938, "percentage": 30.0, "elapsed_time": "0:06:10", "remaining_time": "0:14:25"}
+{"current_steps": 70, "total_steps": 200, "loss": 0.0714, "lr": 4.1069690242163484e-05, "epoch": 1.720496894409938, "percentage": 35.0, "elapsed_time": "0:07:12", "remaining_time": "0:13:22"}
+{"current_steps": 80, "total_steps": 200, "loss": 0.072, "lr": 3.7500000000000003e-05, "epoch": 1.968944099378882, "percentage": 40.0, "elapsed_time": "0:08:14", "remaining_time": "0:12:22"}
+{"current_steps": 90, "total_steps": 200, "loss": 0.0508, "lr": 3.355050358314172e-05, "epoch": 2.198757763975155, "percentage": 45.0, "elapsed_time": "0:09:14", "remaining_time": "0:11:17"}
+{"current_steps": 100, "total_steps": 200, "loss": 0.0354, "lr": 2.9341204441673266e-05, "epoch": 2.4472049689440993, "percentage": 50.0, "elapsed_time": "0:10:13", "remaining_time": "0:10:13"}
+{"current_steps": 110, "total_steps": 200, "loss": 0.0437, "lr": 2.5e-05, "epoch": 2.6956521739130435, "percentage": 55.0, "elapsed_time": "0:11:15", "remaining_time": "0:09:13"}
+{"current_steps": 120, "total_steps": 200, "loss": 0.0407, "lr": 2.0658795558326743e-05, "epoch": 2.9440993788819876, "percentage": 60.0, "elapsed_time": "0:12:18", "remaining_time": "0:08:12"}
+{"current_steps": 130, "total_steps": 200, "loss": 0.027, "lr": 1.6449496416858284e-05, "epoch": 3.1739130434782608, "percentage": 65.0, "elapsed_time": "0:13:18", "remaining_time": "0:07:09"}
+{"current_steps": 140, "total_steps": 200, "loss": 0.0154, "lr": 1.2500000000000006e-05, "epoch": 3.422360248447205, "percentage": 70.0, "elapsed_time": "0:14:22", "remaining_time": "0:06:09"}
+{"current_steps": 150, "total_steps": 200, "loss": 0.0166, "lr": 8.930309757836517e-06, "epoch": 3.670807453416149, "percentage": 75.0, "elapsed_time": "0:15:23", "remaining_time": "0:05:07"}
+{"current_steps": 160, "total_steps": 200, "loss": 0.0131, "lr": 5.848888922025553e-06, "epoch": 3.919254658385093, "percentage": 80.0, "elapsed_time": "0:16:24", "remaining_time": "0:04:06"}
+{"current_steps": 170, "total_steps": 200, "loss": 0.0139, "lr": 3.3493649053890326e-06, "epoch": 4.149068322981367, "percentage": 85.0, "elapsed_time": "0:17:24", "remaining_time": "0:03:04"}
+{"current_steps": 180, "total_steps": 200, "loss": 0.0054, "lr": 1.5076844803522922e-06, "epoch": 4.39751552795031, "percentage": 90.0, "elapsed_time": "0:18:25", "remaining_time": "0:02:02"}
+{"current_steps": 190, "total_steps": 200, "loss": 0.0061, "lr": 3.7980617469479953e-07, "epoch": 4.645962732919255, "percentage": 95.0, "elapsed_time": "0:19:28", "remaining_time": "0:01:01"}
+{"current_steps": 200, "total_steps": 200, "loss": 0.0074, "lr": 0.0, "epoch": 4.894409937888199, "percentage": 100.0, "elapsed_time": "0:20:31", "remaining_time": "0:00:00"}
+{"current_steps": 200, "total_steps": 200, "epoch": 4.894409937888199, "percentage": 100.0, "elapsed_time": "0:20:33", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.894409937888199,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2484472049689441,
+      "grad_norm": 0.39474916458129883,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2624,
+      "step": 10
+    },
+    {
+      "epoch": 0.4968944099378882,
+      "grad_norm": 0.41419529914855957,
+      "learning_rate": 5e-05,
+      "loss": 0.1247,
+      "step": 20
+    },
+    {
+      "epoch": 0.7453416149068323,
+      "grad_norm": 0.9791710376739502,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 0.1121,
+      "step": 30
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 0.8597949743270874,
+      "learning_rate": 4.849231551964771e-05,
+      "loss": 0.107,
+      "step": 40
+    },
+    {
+      "epoch": 1.2236024844720497,
+      "grad_norm": 0.323322057723999,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.0748,
+      "step": 50
+    },
+    {
+      "epoch": 1.4720496894409938,
+      "grad_norm": 0.2703801691532135,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.0644,
+      "step": 60
+    },
+    {
+      "epoch": 1.720496894409938,
+      "grad_norm": 0.7586608529090881,
+      "learning_rate": 4.1069690242163484e-05,
+      "loss": 0.0714,
+      "step": 70
+    },
+    {
+      "epoch": 1.968944099378882,
+      "grad_norm": 0.7822660803794861,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 0.072,
+      "step": 80
+    },
+    {
+      "epoch": 2.198757763975155,
+      "grad_norm": 0.6878750920295715,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 0.0508,
+      "step": 90
+    },
+    {
+      "epoch": 2.4472049689440993,
+      "grad_norm": 0.6550189256668091,
+      "learning_rate": 2.9341204441673266e-05,
+      "loss": 0.0354,
+      "step": 100
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 0.43342578411102295,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0437,
+      "step": 110
+    },
+    {
+      "epoch": 2.9440993788819876,
+      "grad_norm": 0.36653441190719604,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.0407,
+      "step": 120
+    },
+    {
+      "epoch": 3.1739130434782608,
+      "grad_norm": 0.26225632429122925,
+      "learning_rate": 1.6449496416858284e-05,
+      "loss": 0.027,
+      "step": 130
+    },
+    {
+      "epoch": 3.422360248447205,
+      "grad_norm": 0.26739493012428284,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 0.0154,
+      "step": 140
+    },
+    {
+      "epoch": 3.670807453416149,
+      "grad_norm": 0.2866971790790558,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 0.0166,
+      "step": 150
+    },
+    {
+      "epoch": 3.919254658385093,
+      "grad_norm": 0.2178378403186798,
+      "learning_rate": 5.848888922025553e-06,
+      "loss": 0.0131,
+      "step": 160
+    },
+    {
+      "epoch": 4.149068322981367,
+      "grad_norm": 0.1943936049938202,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.0139,
+      "step": 170
+    },
+    {
+      "epoch": 4.39751552795031,
+      "grad_norm": 0.20081469416618347,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 0.0054,
+      "step": 180
+    },
+    {
+      "epoch": 4.645962732919255,
+      "grad_norm": 0.06184164062142372,
+      "learning_rate": 3.7980617469479953e-07,
+      "loss": 0.0061,
+      "step": 190
+    },
+    {
+      "epoch": 4.894409937888199,
+      "grad_norm": 0.3146420121192932,
+      "learning_rate": 0.0,
+      "loss": 0.0074,
+      "step": 200
+    },
+    {
+      "epoch": 4.894409937888199,
+      "step": 200,
+      "total_flos": 5.058205338938573e+16,
+      "train_loss": 0.058221997842192647,
+      "train_runtime": 1234.8427,
+      "train_samples_per_second": 1.304,
+      "train_steps_per_second": 0.162
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "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": 5.058205338938573e+16,
+  "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:ae05ab4eef3700981b9f82958e169ce348cb813ed953972925d07ef097ace204
+size 5752