|
--- |
|
base_model: unsloth/Qwen2-7B |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- unsloth |
|
- generated_from_trainer |
|
model-index: |
|
- name: Qwen2-7B_pct_default_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_default_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: 1.9141 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 2.031 | 0.0206 | 8 | 1.9518 | |
|
| 2.0039 | 0.0412 | 16 | 1.9527 | |
|
| 2.0258 | 0.0618 | 24 | 1.9364 | |
|
| 1.9476 | 0.0824 | 32 | 1.9396 | |
|
| 1.993 | 0.1031 | 40 | 1.9391 | |
|
| 1.9924 | 0.1237 | 48 | 1.9413 | |
|
| 2.0036 | 0.1443 | 56 | 1.9407 | |
|
| 1.9358 | 0.1649 | 64 | 1.9378 | |
|
| 1.9956 | 0.1855 | 72 | 1.9401 | |
|
| 2.0183 | 0.2061 | 80 | 1.9399 | |
|
| 1.9952 | 0.2267 | 88 | 1.9411 | |
|
| 1.9309 | 0.2473 | 96 | 1.9413 | |
|
| 2.0042 | 0.2680 | 104 | 1.9426 | |
|
| 1.8885 | 0.2886 | 112 | 1.9405 | |
|
| 1.9462 | 0.3092 | 120 | 1.9409 | |
|
| 1.9787 | 0.3298 | 128 | 1.9441 | |
|
| 1.9647 | 0.3504 | 136 | 1.9408 | |
|
| 1.9391 | 0.3710 | 144 | 1.9398 | |
|
| 2.0038 | 0.3916 | 152 | 1.9389 | |
|
| 2.0412 | 0.4122 | 160 | 1.9402 | |
|
| 2.0523 | 0.4329 | 168 | 1.9371 | |
|
| 1.9364 | 0.4535 | 176 | 1.9394 | |
|
| 1.9805 | 0.4741 | 184 | 1.9395 | |
|
| 1.9935 | 0.4947 | 192 | 1.9380 | |
|
| 1.9342 | 0.5153 | 200 | 1.9346 | |
|
| 1.9708 | 0.5359 | 208 | 1.9361 | |
|
| 2.0128 | 0.5565 | 216 | 1.9355 | |
|
| 1.9416 | 0.5771 | 224 | 1.9304 | |
|
| 1.9658 | 0.5977 | 232 | 1.9349 | |
|
| 1.9161 | 0.6184 | 240 | 1.9258 | |
|
| 1.94 | 0.6390 | 248 | 1.9258 | |
|
| 1.9908 | 0.6596 | 256 | 1.9244 | |
|
| 1.9169 | 0.6802 | 264 | 1.9242 | |
|
| 1.9868 | 0.7008 | 272 | 1.9216 | |
|
| 1.8737 | 0.7214 | 280 | 1.9209 | |
|
| 2.0166 | 0.7420 | 288 | 1.9198 | |
|
| 1.9246 | 0.7626 | 296 | 1.9188 | |
|
| 1.9418 | 0.7833 | 304 | 1.9198 | |
|
| 1.9417 | 0.8039 | 312 | 1.9172 | |
|
| 1.9652 | 0.8245 | 320 | 1.9169 | |
|
| 1.9715 | 0.8451 | 328 | 1.9171 | |
|
| 1.9634 | 0.8657 | 336 | 1.9159 | |
|
| 1.9566 | 0.8863 | 344 | 1.9153 | |
|
| 1.9277 | 0.9069 | 352 | 1.9147 | |
|
| 2.0087 | 0.9275 | 360 | 1.9142 | |
|
| 1.921 | 0.9481 | 368 | 1.9143 | |
|
| 1.9842 | 0.9688 | 376 | 1.9140 | |
|
| 1.8825 | 0.9894 | 384 | 1.9141 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.12.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
