End of training

README.md

@@ -1,65 +1,57 @@
 ---
-license: mit
 base_model: openai-community/gpt2
+library_name: transformers
+model_name: gpt_finetuned_piqa
 tags:
+- generated_from_trainer
 - trl
 - sft
-- generated_from_trainer
-datasets:
-- piqa
-model-index:
-- name: gpt_finetuned_piqa
-  results: []
+licence: license
 ---
 
-<!-- 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. -->
-
-# gpt_finetuned_piqa
-
-This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the piqa dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.9017
+# Model Card for gpt_finetuned_piqa
 
-## Model description
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-More information needed
+## Quick start
 
-## Intended uses & limitations
+```python
+from transformers import pipeline
 
-More information needed
+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="codefactory4791/gpt_finetuned_piqa", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## Training and evaluation data
+## Training procedure
 
-More information needed
 
-## Training procedure
 
-### Training hyperparameters
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 3
+### Framework versions
 
-### Training results
+- TRL: 0.12.0
+- Transformers: 4.46.1
+- Pytorch: 2.0.0
+- Datasets: 3.1.0
+- Tokenizers: 0.20.1
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 3.1691        | 0.9926 | 500  | 2.9619          |
-| 2.9055        | 1.9851 | 1000 | 2.9117          |
-| 2.7908        | 2.9777 | 1500 | 2.9017          |
+## Citations
 
 
-### Framework versions
 
-- Transformers 4.43.3
-- Pytorch 2.3.1+cu121
-- Datasets 2.20.0
-- Tokenizers 0.19.1
+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}}
+}
+```

config.json

@@ -34,7 +34,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.43.3",
+  "transformers_version": "4.46.1",
   "use_cache": true,
   "vocab_size": 50257
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.43.3"
+  "transformers_version": "4.46.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e15fc2bd2061bafdc7c9f6f6e143afee62face443a4b8704c1d5cc49fe9b404
+oid sha256:2971dd8005dcd9cb4963b180536afefdc299d7b27565d886d1683311148f0f0e
 size 497774208

runs/Nov02_21-24-00_algo-1/events.out.tfevents.1730582646.algo-1.64.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92b3c8101a7302b735c7cd5a23fe3b6d0e5041727539a3e6903d2502f105c96
+size 7386

tokenizer_config.json

@@ -11,7 +11,7 @@
     }
   },
   "bos_token": "<|endoftext|>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cabb7763feb6645e3072b469427e9703053a441cef0fa7184855fb1963256c57
-size 5432
+oid sha256:62255c3a4e20ba737fd383368c1f2f1ea363dec4a924592ba61db4ae82241a63
+size 5051