|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_pct_reverse_r16 |
|
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_reverse_r16 |
|
|
|
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: 1.9143 |
|
|
|
## 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: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 32 |
|
- 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.0341 | 0.0206 | 8 | 1.9528 | |
|
| 2.0078 | 0.0412 | 16 | 1.9550 | |
|
| 2.0269 | 0.0618 | 24 | 1.9357 | |
|
| 1.9472 | 0.0824 | 32 | 1.9405 | |
|
| 1.993 | 0.1031 | 40 | 1.9381 | |
|
| 1.9936 | 0.1237 | 48 | 1.9402 | |
|
| 2.0043 | 0.1443 | 56 | 1.9410 | |
|
| 1.9356 | 0.1649 | 64 | 1.9369 | |
|
| 1.9953 | 0.1855 | 72 | 1.9396 | |
|
| 2.0184 | 0.2061 | 80 | 1.9405 | |
|
| 1.995 | 0.2267 | 88 | 1.9410 | |
|
| 1.9307 | 0.2473 | 96 | 1.9407 | |
|
| 2.0037 | 0.2680 | 104 | 1.9414 | |
|
| 1.889 | 0.2886 | 112 | 1.9397 | |
|
| 1.9455 | 0.3092 | 120 | 1.9401 | |
|
| 1.9789 | 0.3298 | 128 | 1.9438 | |
|
| 1.9642 | 0.3504 | 136 | 1.9408 | |
|
| 1.9387 | 0.3710 | 144 | 1.9405 | |
|
| 2.0036 | 0.3916 | 152 | 1.9394 | |
|
| 2.0407 | 0.4122 | 160 | 1.9393 | |
|
| 2.0519 | 0.4329 | 168 | 1.9385 | |
|
| 1.9361 | 0.4535 | 176 | 1.9396 | |
|
| 1.9812 | 0.4741 | 184 | 1.9404 | |
|
| 1.9947 | 0.4947 | 192 | 1.9382 | |
|
| 1.9343 | 0.5153 | 200 | 1.9353 | |
|
| 1.9707 | 0.5359 | 208 | 1.9357 | |
|
| 2.0131 | 0.5565 | 216 | 1.9351 | |
|
| 1.9416 | 0.5771 | 224 | 1.9310 | |
|
| 1.9652 | 0.5977 | 232 | 1.9351 | |
|
| 1.9156 | 0.6184 | 240 | 1.9266 | |
|
| 1.9405 | 0.6390 | 248 | 1.9260 | |
|
| 1.9909 | 0.6596 | 256 | 1.9250 | |
|
| 1.9179 | 0.6802 | 264 | 1.9232 | |
|
| 1.9877 | 0.7008 | 272 | 1.9217 | |
|
| 1.8745 | 0.7214 | 280 | 1.9207 | |
|
| 2.016 | 0.7420 | 288 | 1.9195 | |
|
| 1.9238 | 0.7626 | 296 | 1.9185 | |
|
| 1.9414 | 0.7833 | 304 | 1.9193 | |
|
| 1.9417 | 0.8039 | 312 | 1.9172 | |
|
| 1.9647 | 0.8245 | 320 | 1.9169 | |
|
| 1.9704 | 0.8451 | 328 | 1.9172 | |
|
| 1.9629 | 0.8657 | 336 | 1.9157 | |
|
| 1.9574 | 0.8863 | 344 | 1.9150 | |
|
| 1.9278 | 0.9069 | 352 | 1.9143 | |
|
| 2.0079 | 0.9275 | 360 | 1.9140 | |
|
| 1.9203 | 0.9481 | 368 | 1.9138 | |
|
| 1.9834 | 0.9688 | 376 | 1.9139 | |
|
| 1.8809 | 0.9894 | 384 | 1.9143 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
