| --- |
| library_name: peft |
| tags: |
| - trl |
| - sft |
| - generated_from_trainer |
| base_model: ybelkada/falcon-7b-sharded-bf16 |
| model-index: |
| - name: webcraft_falcon |
| results: [] |
| --- |
| |
| <!-- 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. --> |
|
|
| # webcraft_falcon |
| |
| This model is a fine-tuned version of [ybelkada/falcon-7b-sharded-bf16](https://huggingface.co/ybelkada/falcon-7b-sharded-bf16) on the None dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.7024 |
| |
| ## Model description |
| |
| More information needed |
| |
| ## Intended uses & limitations |
| |
| More information needed |
| |
| ## Training and evaluation data |
| |
| More information needed |
| |
| ## Training procedure |
| |
| ### Training hyperparameters |
| |
| The following hyperparameters were used during training: |
| - learning_rate: 0.0002 |
| - train_batch_size: 2 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 4 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: cosine |
| - lr_scheduler_warmup_ratio: 0.03 |
| - training_steps: 320 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 1.1409 | 0.19 | 20 | 1.1040 | |
| | 1.0692 | 0.38 | 40 | 0.9462 | |
| | 0.968 | 0.57 | 60 | 0.8406 | |
| | 0.6599 | 0.75 | 80 | 0.7712 | |
| | 0.7967 | 0.94 | 100 | 0.7678 | |
| | 0.5992 | 1.13 | 120 | 0.7373 | |
| | 0.5424 | 1.32 | 140 | 0.7241 | |
| | 0.5073 | 1.51 | 160 | 0.6995 | |
| | 0.5786 | 1.7 | 180 | 0.6978 | |
| | 0.6064 | 1.89 | 200 | 0.6954 | |
| | 0.4634 | 2.08 | 220 | 0.7070 | |
| | 0.4737 | 2.26 | 240 | 0.7020 | |
| | 0.4967 | 2.45 | 260 | 0.7024 | |
| |
| |
| ### Framework versions |
| |
| - PEFT 0.10.0 |
| - Transformers 4.39.3 |
| - Pytorch 2.2.2+cu121 |
| - Datasets 2.18.0 |
| - Tokenizers 0.15.2 |
