NanQiangHF/llama3_8b_instruct_BWRM

.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

@@ -1,74 +1,57 @@
 ---
-license: llama3
-library_name: peft
+library_name: transformers
 tags:
+- generated_from_trainer
 - trl
 - reward-trainer
-- generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
-metrics:
-- accuracy
-model-index:
-- name: llama3_8b_instruct_BWRM
-  results: []
+model_name: llama3_8b_instruct_BWRM
+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. -->
-
-# llama3_8b_instruct_BWRM
-
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0578
-- Accuracy: 0.9945
+# Model Card for llama3_8b_instruct_BWRM
 
-## Model description
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
+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="NanQiangHF/llama3_8b_instruct_BWRM", 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 Reward.
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0005
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 1
+### Framework versions
 
-### Training results
+- TRL: 0.12.0.dev0
+- Transformers: 4.46.0.dev0
+- Pytorch: 2.3.0
+- Datasets: 3.0.0
+- Tokenizers: 0.20.1
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 0.1912        | 0.0863 | 300  | 0.1233          | 0.9877   |
-| 0.1126        | 0.1725 | 600  | 0.0812          | 0.9896   |
-| 0.0884        | 0.2588 | 900  | 0.0742          | 0.9896   |
-| 0.0886        | 0.3450 | 1200 | 0.0834          | 0.9887   |
-| 0.0779        | 0.4313 | 1500 | 0.0732          | 0.9945   |
-| 0.0788        | 0.5175 | 1800 | 0.0941          | 0.9922   |
-| 0.0716        | 0.6038 | 2100 | 0.0657          | 0.9935   |
-| 0.0693        | 0.6901 | 2400 | 0.0656          | 0.9961   |
-| 0.0656        | 0.7763 | 2700 | 0.0635          | 0.9938   |
-| 0.0664        | 0.8626 | 3000 | 0.0587          | 0.9958   |
-| 0.0594        | 0.9488 | 3300 | 0.0578          | 0.9945   |
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.13.1
-- Transformers 4.44.0
-- Pytorch 2.3.0+cu121
-- Datasets 3.0.0
-- 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}}
+}
+```

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0604ffcef2943a79b80b8b68b3d089459c129261e61c10a12b0d8926a040db14
-size 13656728
+oid sha256:60747d7c9b087a5d0241c60bba9002e0c6c11bcb2df2dcef082b43db6422655e
+size 13664920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe1e49d5fe1b09d2f498020e77772149df32d9f1b69d5b97281373e7a7a735a
-size 5368
+oid sha256:91b2964536ae0ad56a6912de4f73cb1cf904210236738ee76641e78da53abc2c
+size 5432