|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: llama-2-7b-chat-hf-ft-compact |
|
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. --> |
|
|
|
# llama-2-7b-chat-hf-ft-compact |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8585 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 4.1287 | 0.36 | 25 | 2.8154 | |
|
| 1.5 | 0.73 | 50 | 1.3773 | |
|
| 1.1092 | 1.09 | 75 | 0.9817 | |
|
| 0.9247 | 1.45 | 100 | 0.9045 | |
|
| 0.8907 | 1.82 | 125 | 0.8791 | |
|
| 0.8572 | 2.18 | 150 | 0.8663 | |
|
| 0.8359 | 2.55 | 175 | 0.8608 | |
|
| 0.8156 | 2.91 | 200 | 0.8585 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
