|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_pct_ortho |
|
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. --> |
|
|
|
# Qwen2-7B_pct_ortho |
|
|
|
This model is a fine-tuned version of [unsloth/Qwen2-7B](https://huggingface.co/unsloth/Qwen2-7B) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0710 |
|
|
|
## 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: 0.0003 |
|
- 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: cosine |
|
- lr_scheduler_warmup_ratio: 0.02 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.0836 | 0.0206 | 8 | 1.9997 | |
|
| 2.0451 | 0.0412 | 16 | 1.9894 | |
|
| 2.0868 | 0.0618 | 24 | 2.0094 | |
|
| 2.0404 | 0.0824 | 32 | 2.0230 | |
|
| 2.0951 | 0.1031 | 40 | 2.0406 | |
|
| 2.1037 | 0.1237 | 48 | 2.0564 | |
|
| 2.1105 | 0.1443 | 56 | 2.0572 | |
|
| 2.098 | 0.1649 | 64 | 2.0666 | |
|
| 2.1234 | 0.1855 | 72 | 2.0810 | |
|
| 2.1848 | 0.2061 | 80 | 2.0770 | |
|
| 2.1566 | 0.2267 | 88 | 2.0833 | |
|
| 2.1434 | 0.2473 | 96 | 2.0774 | |
|
| 2.1722 | 0.2680 | 104 | 2.0898 | |
|
| 2.0835 | 0.2886 | 112 | 2.1009 | |
|
| 2.1355 | 0.3092 | 120 | 2.1047 | |
|
| 2.1492 | 0.3298 | 128 | 2.0960 | |
|
| 2.1524 | 0.3504 | 136 | 2.1070 | |
|
| 2.1429 | 0.3710 | 144 | 2.1120 | |
|
| 2.1611 | 0.3916 | 152 | 2.1227 | |
|
| 2.1943 | 0.4122 | 160 | 2.1149 | |
|
| 2.2268 | 0.4329 | 168 | 2.1105 | |
|
| 2.135 | 0.4535 | 176 | 2.1087 | |
|
| 2.1443 | 0.4741 | 184 | 2.1076 | |
|
| 2.1925 | 0.4947 | 192 | 2.1068 | |
|
| 2.1225 | 0.5153 | 200 | 2.1034 | |
|
| 2.1679 | 0.5359 | 208 | 2.1078 | |
|
| 2.2091 | 0.5565 | 216 | 2.1100 | |
|
| 2.1175 | 0.5771 | 224 | 2.0976 | |
|
| 2.1288 | 0.5977 | 232 | 2.1060 | |
|
| 2.1234 | 0.6184 | 240 | 2.0916 | |
|
| 2.1084 | 0.6390 | 248 | 2.0916 | |
|
| 2.1631 | 0.6596 | 256 | 2.0923 | |
|
| 2.1299 | 0.6802 | 264 | 2.0842 | |
|
| 2.1939 | 0.7008 | 272 | 2.0919 | |
|
| 2.071 | 0.7214 | 280 | 2.0830 | |
|
| 2.181 | 0.7420 | 288 | 2.0801 | |
|
| 2.1076 | 0.7626 | 296 | 2.0804 | |
|
| 2.1185 | 0.7833 | 304 | 2.0761 | |
|
| 2.1079 | 0.8039 | 312 | 2.0749 | |
|
| 2.1499 | 0.8245 | 320 | 2.0783 | |
|
| 2.1551 | 0.8451 | 328 | 2.0784 | |
|
| 2.1117 | 0.8657 | 336 | 2.0784 | |
|
| 2.1463 | 0.8863 | 344 | 2.0750 | |
|
| 2.1167 | 0.9069 | 352 | 2.0696 | |
|
| 2.1882 | 0.9275 | 360 | 2.0714 | |
|
| 2.1131 | 0.9481 | 368 | 2.0716 | |
|
| 2.1626 | 0.9688 | 376 | 2.0714 | |
|
| 2.1141 | 0.9894 | 384 | 2.0710 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
