|
|
--- |
|
|
library_name: transformers |
|
|
tags: |
|
|
- trl |
|
|
- sft |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: llama_1b_step2_batch_v2 |
|
|
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_v2 |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3338 |
|
|
|
|
|
## 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: 2 |
|
|
- eval_batch_size: 40 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 8 |
|
|
- 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 | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.9373 | 0.0341 | 50 | 0.8757 | |
|
|
| 0.6838 | 0.0682 | 100 | 0.7815 | |
|
|
| 0.7189 | 0.1023 | 150 | 0.7197 | |
|
|
| 0.5827 | 0.1364 | 200 | 0.6686 | |
|
|
| 0.5084 | 0.1704 | 250 | 0.6180 | |
|
|
| 0.5357 | 0.2045 | 300 | 0.5858 | |
|
|
| 0.4738 | 0.2386 | 350 | 0.5618 | |
|
|
| 0.5091 | 0.2727 | 400 | 0.5337 | |
|
|
| 0.3793 | 0.3068 | 450 | 0.5149 | |
|
|
| 0.5388 | 0.3409 | 500 | 0.4985 | |
|
|
| 0.4726 | 0.3750 | 550 | 0.4801 | |
|
|
| 0.5348 | 0.4091 | 600 | 0.4632 | |
|
|
| 0.4644 | 0.4432 | 650 | 0.4477 | |
|
|
| 0.4033 | 0.4772 | 700 | 0.4367 | |
|
|
| 0.4283 | 0.5113 | 750 | 0.4309 | |
|
|
| 0.5275 | 0.5454 | 800 | 0.4201 | |
|
|
| 0.4633 | 0.5795 | 850 | 0.4115 | |
|
|
| 0.3312 | 0.6136 | 900 | 0.4038 | |
|
|
| 0.4768 | 0.6477 | 950 | 0.3969 | |
|
|
| 0.4401 | 0.6818 | 1000 | 0.3924 | |
|
|
| 0.3125 | 0.7159 | 1050 | 0.3882 | |
|
|
| 0.3651 | 0.7500 | 1100 | 0.3820 | |
|
|
| 0.354 | 0.7840 | 1150 | 0.3770 | |
|
|
| 0.3525 | 0.8181 | 1200 | 0.3701 | |
|
|
| 0.4069 | 0.8522 | 1250 | 0.3659 | |
|
|
| 0.2806 | 0.8863 | 1300 | 0.3613 | |
|
|
| 0.3593 | 0.9204 | 1350 | 0.3584 | |
|
|
| 0.3393 | 0.9545 | 1400 | 0.3540 | |
|
|
| 0.3114 | 0.9886 | 1450 | 0.3504 | |
|
|
| 0.2571 | 1.0228 | 1500 | 0.3556 | |
|
|
| 0.2991 | 1.0569 | 1550 | 0.3531 | |
|
|
| 0.2445 | 1.0910 | 1600 | 0.3512 | |
|
|
| 0.2865 | 1.1251 | 1650 | 0.3520 | |
|
|
| 0.2146 | 1.1592 | 1700 | 0.3492 | |
|
|
| 0.2469 | 1.1933 | 1750 | 0.3481 | |
|
|
| 0.2927 | 1.2274 | 1800 | 0.3474 | |
|
|
| 0.2797 | 1.2615 | 1850 | 0.3454 | |
|
|
| 0.247 | 1.2956 | 1900 | 0.3455 | |
|
|
| 0.2208 | 1.3296 | 1950 | 0.3433 | |
|
|
| 0.2396 | 1.3637 | 2000 | 0.3420 | |
|
|
| 0.252 | 1.3978 | 2050 | 0.3407 | |
|
|
| 0.2296 | 1.4319 | 2100 | 0.3387 | |
|
|
| 0.2349 | 1.4660 | 2150 | 0.3391 | |
|
|
| 0.2408 | 1.5001 | 2200 | 0.3374 | |
|
|
| 0.236 | 1.5342 | 2250 | 0.3376 | |
|
|
| 0.1969 | 1.5683 | 2300 | 0.3375 | |
|
|
| 0.2513 | 1.6024 | 2350 | 0.3368 | |
|
|
| 0.2619 | 1.6364 | 2400 | 0.3360 | |
|
|
| 0.3016 | 1.6705 | 2450 | 0.3351 | |
|
|
| 0.2345 | 1.7046 | 2500 | 0.3352 | |
|
|
| 0.2474 | 1.7387 | 2550 | 0.3347 | |
|
|
| 0.2475 | 1.7728 | 2600 | 0.3343 | |
|
|
| 0.2627 | 1.8069 | 2650 | 0.3342 | |
|
|
| 0.2381 | 1.8410 | 2700 | 0.3340 | |
|
|
| 0.2984 | 1.8751 | 2750 | 0.3338 | |
|
|
| 0.2434 | 1.9092 | 2800 | 0.3338 | |
|
|
| 0.2608 | 1.9432 | 2850 | 0.3338 | |
|
|
| 0.2526 | 1.9773 | 2900 | 0.3338 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.46.0 |
|
|
- Pytorch 2.1.0+cu118 |
|
|
- Datasets 3.0.2 |
|
|
- Tokenizers 0.20.1 |
|
|
|
