Upload table SFT checkpoint

README.md

@@ -0,0 +1,58 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: transformers
+model_name: table
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for table
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B).
+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
+
+[<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/aq1048576-princeton-university/huggingface/runs/xz32vbyx) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.23.0
+- Transformers: 4.57.1
+- Pytorch: 2.8.0
+- Datasets: 3.5.0
+- Tokenizers: 0.22.1
+
+## 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}}
+}
+```

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1098dbbb69a063c169d800166d3db23baf269fd4c4823dfeaf6e2aa44262bc44
+oid sha256:17390f599a09131d867f5082e79bbfd6bf9739f03fe5201302d31df5ba79c615
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a873d99e2675d4ae38b952373db4655873ffacb59d9f9f0a9734596035fb0b41
+oid sha256:868b92a6b2a57794cf7b21af4fc6733d6b2001cca65023dee0482029070f643f
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860dfed311f046f27da6ff4cd75b51251bb42bbab2f4da8b296a199be3bcf4ac
+oid sha256:cc7fdc9302d0a044f76d9eca53d469df7429d4f4e95dfa21c32f8705cabbe97e
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a92d43a37ba8fb61c60b1f045957357bacaf34c3e1436e50c34decbfdaaeaca3
+oid sha256:61f5926292a1202347dc6501f27f48facefcc6bb7e1efbdf47a924b8db713795
 size 1168138808

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
-size 17210019
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -2059,5 +2059,6 @@
   ],
   "model_max_length": 4096,
   "pad_token": "<|end_of_text|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'user' %}{{ '<|user|>\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>\n'  + message['content'] + eos_token + '\n' }}{% else %}{{ '<|assistant|>\n'  + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}{% endfor %}"
 }

trainer_state.json

@@ -4,30 +4,26 @@
   "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 52,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "entropy": 0.7864327458146121,
       "epoch": 1.0,
-      "grad_norm": 1.3046875,
-      "learning_rate": 3.4096741493194197e-07,
-      "loss": 1.1363,
-      "step": 20
-    },
-    {
-      "epoch": 1.0,
-      "step": 20,
-      "total_flos": 3.434522481451336e+17,
-      "train_loss": 1.136316967010498,
-      "train_runtime": 261.6908,
-      "train_samples_per_second": 18.915,
-      "train_steps_per_second": 0.076
+      "mean_token_accuracy": 0.8194242536877315,
+      "num_tokens": 2959320.0,
+      "step": 52,
+      "total_flos": 2.0714871222750413e+17,
+      "train_loss": 0.8364706039428711,
+      "train_runtime": 316.5604,
+      "train_samples_per_second": 15.637,
+      "train_steps_per_second": 0.164
     }
   ],
-  "logging_steps": 20,
-  "max_steps": 20,
+  "logging_steps": 500,
+  "max_steps": 52,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -43,7 +39,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.434522481451336e+17,
+  "total_flos": 2.0714871222750413e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88a9b23344ae5f92849fdcdce40ebff35bbe01c31a6da2f2d6b19bbeab64a25
-size 5841
+oid sha256:ffddec3fcb612943270afb048c817d5e689eabd08f240219e334957235badf64
+size 6289