metadata
library_name: peft
tags:
- generated_from_trainer
base_model: ybelkada/falcon-7b-sharded-bf16
model-index:
- name: outputs
results: []
outputs
This model is a fine-tuned version of ybelkada/falcon-7b-sharded-bf16 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6616
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.1204 | 0.95 | 15 | 0.8785 |
| 0.7729 | 1.97 | 31 | 0.7206 |
| 0.6722 | 2.98 | 47 | 0.6840 |
| 0.6157 | 4.0 | 63 | 0.6678 |
| 0.619 | 4.95 | 78 | 0.6612 |
| 0.5354 | 5.71 | 90 | 0.6616 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.36.1
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0