|
--- |
|
library_name: transformers |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: llama_1b_step2_batch_v4 |
|
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_1b_step2_batch_v4 |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3240 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 6 |
|
- eval_batch_size: 40 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 24 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.0775 | 0.1022 | 50 | 0.9867 | |
|
| 0.773 | 0.2045 | 100 | 0.7635 | |
|
| 0.6877 | 0.3067 | 150 | 0.6190 | |
|
| 0.5539 | 0.4090 | 200 | 0.5455 | |
|
| 0.5489 | 0.5112 | 250 | 0.4832 | |
|
| 0.5126 | 0.6135 | 300 | 0.4512 | |
|
| 0.3873 | 0.7157 | 350 | 0.4194 | |
|
| 0.4313 | 0.8180 | 400 | 0.3849 | |
|
| 0.4021 | 0.9202 | 450 | 0.3643 | |
|
| 0.2229 | 1.0225 | 500 | 0.3647 | |
|
| 0.2363 | 1.1247 | 550 | 0.3558 | |
|
| 0.2136 | 1.2270 | 600 | 0.3453 | |
|
| 0.1827 | 1.3292 | 650 | 0.3391 | |
|
| 0.2226 | 1.4315 | 700 | 0.3336 | |
|
| 0.1935 | 1.5337 | 750 | 0.3292 | |
|
| 0.2207 | 1.6360 | 800 | 0.3266 | |
|
| 0.2445 | 1.7382 | 850 | 0.3254 | |
|
| 0.1998 | 1.8405 | 900 | 0.3245 | |
|
| 0.2059 | 1.9427 | 950 | 0.3240 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 3.0.2 |
|
- Tokenizers 0.20.1 |
|
|
