Model save

.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

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2-VL-2B-Instruct
+library_name: transformers
+model_name: Qwen2-VL-2B-Instruct-SFT_1600_epo20
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2-VL-2B-Instruct-SFT_1600_epo20
+
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="BleachNick/Qwen2-VL-2B-Instruct-SFT_1600_epo20", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/haozhezhao/huggingface/runs/nrhznie5) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1+cu124
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 8.00754383150121e+16,
+    "train_loss": 0.29854341844717663,
+    "train_runtime": 5255.3389,
+    "train_samples": 1600,
+    "train_samples_per_second": 3.045,
+    "train_steps_per_second": 0.057
+}

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "Qwen/Qwen2-VL-2B-Instruct",
+  "architectures": [
+    "Qwen2VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2_vl",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1536,
+    "in_chans": 3,
+    "model_type": "qwen2_vl",
+    "spatial_patch_size": 14,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "attn_implementation": null,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.01,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b049be79a68acd5cf558694f7916b319ac15dd51556f57684477ed86e497ad76
+size 4884798456

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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a3a6fcb80132f76da8aa40cdc3fccd7e5d8468ef15421f5b0c2715e85217d2
+size 11420538

tokenizer_config.json

@@ -0,0 +1,144 @@
+{
+  "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
+    }
+  },
+  "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": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 8.00754383150121e+16,
+    "train_loss": 0.29854341844717663,
+    "train_runtime": 5255.3389,
+    "train_samples": 1600,
+    "train_samples_per_second": 3.045,
+    "train_steps_per_second": 0.057
+}

trainer_state.json

@@ -0,0 +1,462 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 39.13534927368164,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 2.3532,
+      "step": 5
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 17.555816650390625,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.9868,
+      "step": 10
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 8.326282501220703,
+      "learning_rate": 5e-06,
+      "loss": 1.259,
+      "step": 15
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 5.493110179901123,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.8018,
+      "step": 20
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 8.113493919372559,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6479,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.912256956100464,
+      "learning_rate": 1e-05,
+      "loss": 0.5196,
+      "step": 30
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 4.460363388061523,
+      "learning_rate": 9.991540791356342e-06,
+      "loss": 0.4227,
+      "step": 35
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 5.932071685791016,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.3738,
+      "step": 40
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 5.956723690032959,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 0.3456,
+      "step": 45
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 3.7256667613983154,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.3267,
+      "step": 50
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 5.209020137786865,
+      "learning_rate": 9.789947561577445e-06,
+      "loss": 0.3079,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 10.075045585632324,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.2969,
+      "step": 60
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 4.17183256149292,
+      "learning_rate": 9.591080534401371e-06,
+      "loss": 0.2805,
+      "step": 65
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 4.0775065422058105,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 0.257,
+      "step": 70
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 6.453698635101318,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.2403,
+      "step": 75
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 5.133937835693359,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.2375,
+      "step": 80
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 5.349823474884033,
+      "learning_rate": 9.01061596377522e-06,
+      "loss": 0.2512,
+      "step": 85
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.886929512023926,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.2365,
+      "step": 90
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 5.774188995361328,
+      "learning_rate": 8.636868207865244e-06,
+      "loss": 0.2252,
+      "step": 95
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 6.560914993286133,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.2158,
+      "step": 100
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 12.387423515319824,
+      "learning_rate": 8.213938048432697e-06,
+      "loss": 0.2081,
+      "step": 105
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 9.847865104675293,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.2164,
+      "step": 110
+    },
+    {
+      "epoch": 3.8333333333333335,
+      "grad_norm": 7.43393087387085,
+      "learning_rate": 7.747544890354031e-06,
+      "loss": 0.2104,
+      "step": 115
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.650928020477295,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2011,
+      "step": 120
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 5.313305854797363,
+      "learning_rate": 7.243995901002312e-06,
+      "loss": 0.1839,
+      "step": 125
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 9.173078536987305,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.1853,
+      "step": 130
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 5.460617542266846,
+      "learning_rate": 6.710100716628345e-06,
+      "loss": 0.1922,
+      "step": 135
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 9.463379859924316,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.2092,
+      "step": 140
+    },
+    {
+      "epoch": 4.833333333333333,
+      "grad_norm": 7.925484657287598,
+      "learning_rate": 6.153079353712201e-06,
+      "loss": 0.197,
+      "step": 145
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 8.87891674041748,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.1899,
+      "step": 150
+    },
+    {
+      "epoch": 5.166666666666667,
+      "grad_norm": 6.015185356140137,
+      "learning_rate": 5.5804645706261515e-06,
+      "loss": 0.1744,
+      "step": 155
+    },
+    {
+      "epoch": 5.333333333333333,
+      "grad_norm": 6.5013227462768555,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.1733,
+      "step": 160
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 3.8927905559539795,
+      "learning_rate": 5e-06,
+      "loss": 0.1665,
+      "step": 165
+    },
+    {
+      "epoch": 5.666666666666667,
+      "grad_norm": 7.750868797302246,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.1695,
+      "step": 170
+    },
+    {
+      "epoch": 5.833333333333333,
+      "grad_norm": 8.282203674316406,
+      "learning_rate": 4.4195354293738484e-06,
+      "loss": 0.1729,
+      "step": 175
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.089918613433838,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.1677,
+      "step": 180
+    },
+    {
+      "epoch": 6.166666666666667,
+      "grad_norm": 5.203615188598633,
+      "learning_rate": 3.8469206462878e-06,
+      "loss": 0.1616,
+      "step": 185
+    },
+    {
+      "epoch": 6.333333333333333,
+      "grad_norm": 10.215794563293457,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.1631,
+      "step": 190
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 7.743990898132324,
+      "learning_rate": 3.289899283371657e-06,
+      "loss": 0.1627,
+      "step": 195
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 5.7741546630859375,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.16,
+      "step": 200
+    },
+    {
+      "epoch": 6.833333333333333,
+      "grad_norm": 7.476262092590332,
+      "learning_rate": 2.7560040989976894e-06,
+      "loss": 0.1543,
+      "step": 205
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 6.046145915985107,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.1547,
+      "step": 210
+    },
+    {
+      "epoch": 7.166666666666667,
+      "grad_norm": 12.649035453796387,
+      "learning_rate": 2.2524551096459703e-06,
+      "loss": 0.1432,
+      "step": 215
+    },
+    {
+      "epoch": 7.333333333333333,
+      "grad_norm": 10.913522720336914,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.1427,
+      "step": 220
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 5.837172985076904,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.1426,
+      "step": 225
+    },
+    {
+      "epoch": 7.666666666666667,
+      "grad_norm": 13.21788215637207,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.1431,
+      "step": 230
+    },
+    {
+      "epoch": 7.833333333333333,
+      "grad_norm": 4.8505120277404785,
+      "learning_rate": 1.3631317921347564e-06,
+      "loss": 0.1411,
+      "step": 235
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 4.8936448097229,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.1379,
+      "step": 240
+    },
+    {
+      "epoch": 8.166666666666666,
+      "grad_norm": 6.43206787109375,
+      "learning_rate": 9.893840362247809e-07,
+      "loss": 0.133,
+      "step": 245
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 7.297297477722168,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.1303,
+      "step": 250
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 3.71684193611145,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.1266,
+      "step": 255
+    },
+    {
+      "epoch": 8.666666666666666,
+      "grad_norm": 5.448196887969971,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.1294,
+      "step": 260
+    },
+    {
+      "epoch": 8.833333333333334,
+      "grad_norm": 4.3221964836120605,
+      "learning_rate": 4.089194655986306e-07,
+      "loss": 0.1276,
+      "step": 265
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 9.115724563598633,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.1269,
+      "step": 270
+    },
+    {
+      "epoch": 9.166666666666666,
+      "grad_norm": 6.583105564117432,
+      "learning_rate": 2.1005243842255552e-07,
+      "loss": 0.1212,
+      "step": 275
+    },
+    {
+      "epoch": 9.333333333333334,
+      "grad_norm": 7.882899761199951,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.1216,
+      "step": 280
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 5.73756217956543,
+      "learning_rate": 7.59612349389599e-08,
+      "loss": 0.1206,
+      "step": 285
+    },
+    {
+      "epoch": 9.666666666666666,
+      "grad_norm": 4.246568202972412,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.1221,
+      "step": 290
+    },
+    {
+      "epoch": 9.833333333333334,
+      "grad_norm": 5.009049415588379,
+      "learning_rate": 8.459208643659122e-09,
+      "loss": 0.1201,
+      "step": 295
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 5.221693515777588,
+      "learning_rate": 0.0,
+      "loss": 0.1227,
+      "step": 300
+    },
+    {
+      "epoch": 10.0,
+      "step": 300,
+      "total_flos": 8.00754383150121e+16,
+      "train_loss": 0.29854341844717663,
+      "train_runtime": 5255.3389,
+      "train_samples_per_second": 3.045,
+      "train_steps_per_second": 0.057
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.00754383150121e+16,
+  "train_batch_size": 18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfa0af299a07a0c2516a41cbe30d1bdac43b650378a7cc37cd9f482feb819a5
+size 7224