|
|
--- |
|
|
library_name: peft |
|
|
license: mit |
|
|
base_model: klyang/MentaLLaMA-chat-7B-hf |
|
|
tags: |
|
|
- llama-factory |
|
|
- lora |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: MentaLLaMA-chat-7B-PsyCourse-fold3 |
|
|
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. --> |
|
|
|
|
|
# MentaLLaMA-chat-7B-PsyCourse-fold3 |
|
|
|
|
|
This model is a fine-tuned version of [klyang/MentaLLaMA-chat-7B-hf](https://huggingface.co/klyang/MentaLLaMA-chat-7B-hf) on the course-train-fold3 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0302 |
|
|
|
|
|
## 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: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 16 |
|
|
- total_train_batch_size: 16 |
|
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 5.0 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.8176 | 0.0753 | 50 | 0.6253 | |
|
|
| 0.149 | 0.1505 | 100 | 0.1208 | |
|
|
| 0.0858 | 0.2258 | 150 | 0.0719 | |
|
|
| 0.0728 | 0.3011 | 200 | 0.0563 | |
|
|
| 0.0574 | 0.3763 | 250 | 0.0496 | |
|
|
| 0.0603 | 0.4516 | 300 | 0.0534 | |
|
|
| 0.0432 | 0.5269 | 350 | 0.0435 | |
|
|
| 0.0506 | 0.6021 | 400 | 0.0447 | |
|
|
| 0.0418 | 0.6774 | 450 | 0.0427 | |
|
|
| 0.0319 | 0.7527 | 500 | 0.0380 | |
|
|
| 0.0409 | 0.8279 | 550 | 0.0393 | |
|
|
| 0.0289 | 0.9032 | 600 | 0.0373 | |
|
|
| 0.0301 | 0.9785 | 650 | 0.0378 | |
|
|
| 0.0289 | 1.0537 | 700 | 0.0367 | |
|
|
| 0.0283 | 1.1290 | 750 | 0.0354 | |
|
|
| 0.0338 | 1.2043 | 800 | 0.0352 | |
|
|
| 0.0286 | 1.2795 | 850 | 0.0351 | |
|
|
| 0.0396 | 1.3548 | 900 | 0.0357 | |
|
|
| 0.0286 | 1.4300 | 950 | 0.0344 | |
|
|
| 0.0276 | 1.5053 | 1000 | 0.0339 | |
|
|
| 0.0269 | 1.5806 | 1050 | 0.0337 | |
|
|
| 0.0202 | 1.6558 | 1100 | 0.0336 | |
|
|
| 0.0364 | 1.7311 | 1150 | 0.0316 | |
|
|
| 0.0265 | 1.8064 | 1200 | 0.0330 | |
|
|
| 0.0291 | 1.8816 | 1250 | 0.0307 | |
|
|
| 0.0244 | 1.9569 | 1300 | 0.0311 | |
|
|
| 0.0197 | 2.0322 | 1350 | 0.0313 | |
|
|
| 0.0223 | 2.1074 | 1400 | 0.0304 | |
|
|
| 0.0197 | 2.1827 | 1450 | 0.0311 | |
|
|
| 0.0204 | 2.2580 | 1500 | 0.0324 | |
|
|
| 0.0276 | 2.3332 | 1550 | 0.0311 | |
|
|
| 0.0146 | 2.4085 | 1600 | 0.0316 | |
|
|
| 0.0165 | 2.4838 | 1650 | 0.0329 | |
|
|
| 0.0242 | 2.5590 | 1700 | 0.0314 | |
|
|
| 0.0273 | 2.6343 | 1750 | 0.0321 | |
|
|
| 0.0204 | 2.7096 | 1800 | 0.0323 | |
|
|
| 0.021 | 2.7848 | 1850 | 0.0307 | |
|
|
| 0.0195 | 2.8601 | 1900 | 0.0335 | |
|
|
| 0.0221 | 2.9354 | 1950 | 0.0302 | |
|
|
| 0.0129 | 3.0106 | 2000 | 0.0305 | |
|
|
| 0.0127 | 3.0859 | 2050 | 0.0330 | |
|
|
| 0.0122 | 3.1612 | 2100 | 0.0331 | |
|
|
| 0.0129 | 3.2364 | 2150 | 0.0332 | |
|
|
| 0.0125 | 3.3117 | 2200 | 0.0333 | |
|
|
| 0.0132 | 3.3870 | 2250 | 0.0343 | |
|
|
| 0.0084 | 3.4622 | 2300 | 0.0352 | |
|
|
| 0.0086 | 3.5375 | 2350 | 0.0347 | |
|
|
| 0.0112 | 3.6128 | 2400 | 0.0351 | |
|
|
| 0.012 | 3.6880 | 2450 | 0.0365 | |
|
|
| 0.011 | 3.7633 | 2500 | 0.0361 | |
|
|
| 0.0079 | 3.8386 | 2550 | 0.0389 | |
|
|
| 0.0089 | 3.9138 | 2600 | 0.0368 | |
|
|
| 0.009 | 3.9891 | 2650 | 0.0364 | |
|
|
| 0.0086 | 4.0644 | 2700 | 0.0379 | |
|
|
| 0.005 | 4.1396 | 2750 | 0.0388 | |
|
|
| 0.0051 | 4.2149 | 2800 | 0.0397 | |
|
|
| 0.0055 | 4.2901 | 2850 | 0.0404 | |
|
|
| 0.0083 | 4.3654 | 2900 | 0.0409 | |
|
|
| 0.0055 | 4.4407 | 2950 | 0.0412 | |
|
|
| 0.0056 | 4.5159 | 3000 | 0.0414 | |
|
|
| 0.01 | 4.5912 | 3050 | 0.0417 | |
|
|
| 0.0041 | 4.6665 | 3100 | 0.0416 | |
|
|
| 0.0046 | 4.7417 | 3150 | 0.0416 | |
|
|
| 0.0029 | 4.8170 | 3200 | 0.0416 | |
|
|
| 0.0071 | 4.8923 | 3250 | 0.0417 | |
|
|
| 0.0039 | 4.9675 | 3300 | 0.0416 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.12.0 |
|
|
- Transformers 4.46.1 |
|
|
- Pytorch 2.5.1+cu124 |
|
|
- Datasets 3.1.0 |
|
|
- Tokenizers 0.20.3 |
