Upload model

.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 +1,59 @@
+---
+base_model: Qwen/Qwen3-0.6B-Base
+datasets: arynkiewicz/biomedical-evidence-support-gpt-oss-sft
+library_name: transformers
+tags:
+- generated_from_trainer
+- trl
+- sft
+- alignment-handbook
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B-Base](https://huggingface.co/Qwen/Qwen3-0.6B-Base) on the [arynkiewicz/biomedical-evidence-support-gpt-oss-sft](https://huggingface.co/datasets/arynkiewicz/biomedical-evidence-support-gpt-oss-sft) dataset.
+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="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.23.0
+- Transformers: 4.56.1
+- Pytorch: 2.6.0
+- Datasets: 4.0.0
+- Tokenizers: 0.22.0
+
+## 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 Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

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
+}

all_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "num_tokens": 117474320.0,
+    "total_flos": 56147696418816.0,
+    "train_loss": 1.8167425843630973,
+    "train_runtime": 1364.5021,
+    "train_samples": 70000,
+    "train_samples_per_second": 153.902,
+    "train_steps_per_second": 0.301
+}

chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.56.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842282645698b8ee37625324157a0f7db71421c77805c73afee7e4a27bf48abd
+size 1192135096

runs/Sep11_21-20-58_gpu16/events.out.tfevents.1757618497.gpu16.3798062.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf65bd021acab5c70baba158f6153036f02663153e73bc0adb63df59b6e837a
+size 17909

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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,
+  "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
+}

train_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "num_tokens": 117474320.0,
+    "total_flos": 56147696418816.0,
+    "train_loss": 1.8167425843630973,
+    "train_runtime": 1364.5021,
+    "train_samples": 70000,
+    "train_samples_per_second": 153.902,
+    "train_steps_per_second": 0.301
+}

trainer_state.json

@@ -0,0 +1,372 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 411,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.072992700729927,
+      "grad_norm": 7.62998519999138,
+      "learning_rate": 3.4615384615384617e-06,
+      "loss": 2.1931,
+      "num_tokens": 2861698.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 2.0378838645741393,
+      "learning_rate": 4.997196729961109e-06,
+      "loss": 2.0271,
+      "num_tokens": 5725093.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.21897810218978103,
+      "grad_norm": 1.1687767688324222,
+      "learning_rate": 4.980088396483145e-06,
+      "loss": 1.9229,
+      "num_tokens": 8584884.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.291970802919708,
+      "grad_norm": 1.5019234268738317,
+      "learning_rate": 4.947535513144287e-06,
+      "loss": 1.899,
+      "num_tokens": 11447171.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.36496350364963503,
+      "grad_norm": 1.3274194647163335,
+      "learning_rate": 4.899740800392143e-06,
+      "loss": 1.8861,
+      "num_tokens": 14305298.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.43795620437956206,
+      "grad_norm": 1.3351216353908748,
+      "learning_rate": 4.837001895933996e-06,
+      "loss": 1.8724,
+      "num_tokens": 17165371.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.5109489051094891,
+      "grad_norm": 1.3694945668597924,
+      "learning_rate": 4.75970950122206e-06,
+      "loss": 1.864,
+      "num_tokens": 20024286.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.583941605839416,
+      "grad_norm": 1.3674205399654282,
+      "learning_rate": 4.668344948391787e-06,
+      "loss": 1.8498,
+      "num_tokens": 22880217.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.656934306569343,
+      "grad_norm": 1.377613524812094,
+      "learning_rate": 4.563477202804941e-06,
+      "loss": 1.8502,
+      "num_tokens": 25733499.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.7299270072992701,
+      "grad_norm": 1.4034954365891135,
+      "learning_rate": 4.445759319863825e-06,
+      "loss": 1.848,
+      "num_tokens": 28583434.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.8029197080291971,
+      "grad_norm": 1.412142777635451,
+      "learning_rate": 4.315924378161599e-06,
+      "loss": 1.8352,
+      "num_tokens": 31446481.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.8759124087591241,
+      "grad_norm": 1.3940616426918506,
+      "learning_rate": 4.174780914294638e-06,
+      "loss": 1.8398,
+      "num_tokens": 34303388.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.948905109489051,
+      "grad_norm": 1.3677454956298989,
+      "learning_rate": 4.023207887766292e-06,
+      "loss": 1.8312,
+      "num_tokens": 37155157.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.0218978102189782,
+      "grad_norm": 1.370013187149163,
+      "learning_rate": 3.862149207337677e-06,
+      "loss": 1.8195,
+      "num_tokens": 40016949.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.094890510948905,
+      "grad_norm": 1.3453807513004084,
+      "learning_rate": 3.6926078529122245e-06,
+      "loss": 1.8123,
+      "num_tokens": 42870291.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.167883211678832,
+      "grad_norm": 1.3275053674064692,
+      "learning_rate": 3.5156396295594732e-06,
+      "loss": 1.7984,
+      "num_tokens": 45727372.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.2408759124087592,
+      "grad_norm": 1.2934233224716136,
+      "learning_rate": 3.332346592574404e-06,
+      "loss": 1.7999,
+      "num_tokens": 48577368.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.313868613138686,
+      "grad_norm": 1.2551658629308613,
+      "learning_rate": 3.1438701845172427e-06,
+      "loss": 1.7963,
+      "num_tokens": 51434586.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.3868613138686132,
+      "grad_norm": 1.213032797696571,
+      "learning_rate": 2.9513841269722554e-06,
+      "loss": 1.7881,
+      "num_tokens": 54297424.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.4598540145985401,
+      "grad_norm": 1.156968122738453,
+      "learning_rate": 2.756087111291533e-06,
+      "loss": 1.7897,
+      "num_tokens": 57162459.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.5328467153284673,
+      "grad_norm": 1.1249392481057738,
+      "learning_rate": 2.5591953338415597e-06,
+      "loss": 1.7849,
+      "num_tokens": 60018675.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.6058394160583942,
+      "grad_norm": 1.0994749587493056,
+      "learning_rate": 2.36193492223873e-06,
+      "loss": 1.7775,
+      "num_tokens": 62878668.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.6788321167883211,
+      "grad_norm": 1.0637208182057718,
+      "learning_rate": 2.1655342997388027e-06,
+      "loss": 1.7909,
+      "num_tokens": 65740651.0,
+      "step": 230
+    },
+    {
+      "epoch": 1.7518248175182483,
+      "grad_norm": 1.044107008859833,
+      "learning_rate": 1.9712165353304528e-06,
+      "loss": 1.7756,
+      "num_tokens": 68601510.0,
+      "step": 240
+    },
+    {
+      "epoch": 1.8248175182481752,
+      "grad_norm": 0.9925194390180851,
+      "learning_rate": 1.7801917271720841e-06,
+      "loss": 1.7832,
+      "num_tokens": 71458963.0,
+      "step": 250
+    },
+    {
+      "epoch": 1.897810218978102,
+      "grad_norm": 0.955995300227254,
+      "learning_rate": 1.593649466803439e-06,
+      "loss": 1.7844,
+      "num_tokens": 74316993.0,
+      "step": 260
+    },
+    {
+      "epoch": 1.9708029197080292,
+      "grad_norm": 0.917851333269758,
+      "learning_rate": 1.412751431060518e-06,
+      "loss": 1.7762,
+      "num_tokens": 77175911.0,
+      "step": 270
+    },
+    {
+      "epoch": 2.0437956204379564,
+      "grad_norm": 0.8904733879800006,
+      "learning_rate": 1.2386241478270566e-06,
+      "loss": 1.7703,
+      "num_tokens": 80032620.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.116788321167883,
+      "grad_norm": 0.8877855846920832,
+      "learning_rate": 1.0723519806732633e-06,
+      "loss": 1.7644,
+      "num_tokens": 82889866.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.18978102189781,
+      "grad_norm": 0.8648908773622401,
+      "learning_rate": 9.149703760694034e-07,
+      "loss": 1.7676,
+      "num_tokens": 85743417.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.2627737226277373,
+      "grad_norm": 0.8480142852639106,
+      "learning_rate": 7.674594152266707e-07,
+      "loss": 1.7678,
+      "num_tokens": 88603527.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.335766423357664,
+      "grad_norm": 0.8220641591692829,
+      "learning_rate": 6.307377107207275e-07,
+      "loss": 1.7687,
+      "num_tokens": 91459160.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.408759124087591,
+      "grad_norm": 0.8343743852690421,
+      "learning_rate": 5.056566859062018e-07,
+      "loss": 1.7634,
+      "num_tokens": 94315375.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.4817518248175183,
+      "grad_norm": 0.8234329687161832,
+      "learning_rate": 3.9299527274662353e-07,
+      "loss": 1.7634,
+      "num_tokens": 97180408.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.554744525547445,
+      "grad_norm": 0.8056748923441135,
+      "learning_rate": 2.934550610786327e-07,
+      "loss": 1.7609,
+      "num_tokens": 100041451.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.627737226277372,
+      "grad_norm": 0.8157145557692418,
+      "learning_rate": 2.0765592951802804e-07,
+      "loss": 1.7654,
+      "num_tokens": 102901398.0,
+      "step": 360
+    },
+    {
+      "epoch": 2.7007299270072993,
+      "grad_norm": 0.8132927418871645,
+      "learning_rate": 1.361321852158326e-07,
+      "loss": 1.7625,
+      "num_tokens": 105764937.0,
+      "step": 370
+    },
+    {
+      "epoch": 2.7737226277372264,
+      "grad_norm": 0.7925420271726725,
+      "learning_rate": 7.932923650373209e-08,
+      "loss": 1.7645,
+      "num_tokens": 108617497.0,
+      "step": 380
+    },
+    {
+      "epoch": 2.846715328467153,
+      "grad_norm": 0.8078926286548843,
+      "learning_rate": 3.7600819149724024e-08,
+      "loss": 1.7616,
+      "num_tokens": 111469621.0,
+      "step": 390
+    },
+    {
+      "epoch": 2.9197080291970803,
+      "grad_norm": 0.8084587727297771,
+      "learning_rate": 1.1206793497235413e-08,
+      "loss": 1.7543,
+      "num_tokens": 114331353.0,
+      "step": 400
+    },
+    {
+      "epoch": 2.9927007299270074,
+      "grad_norm": 0.8140377250304603,
+      "learning_rate": 3.11526205856727e-10,
+      "loss": 1.7653,
+      "num_tokens": 117187018.0,
+      "step": 410
+    },
+    {
+      "epoch": 3.0,
+      "num_tokens": 117474320.0,
+      "step": 411,
+      "total_flos": 56147696418816.0,
+      "train_loss": 1.8167425843630973,
+      "train_runtime": 1364.5021,
+      "train_samples_per_second": 153.902,
+      "train_steps_per_second": 0.301
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 411,
+  "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": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 56147696418816.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e536d647b8d9681a00688f415189831239bbba78f0532a5e8fe04be71d59d91
+size 7544