|
|
--- |
|
|
base_model: NousResearch/Llama-2-7b-hf |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: classifier-7b-v9 |
|
|
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. --> |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
|
|
# classifier-7b-v9 |
|
|
|
|
|
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 1.8197 |
|
|
|
|
|
## 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: 0.0002 |
|
|
- train_batch_size: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 8 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 10 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 2.171 | 0.02 | 20 | 2.1160 | |
|
|
| 1.881 | 0.04 | 40 | 1.9814 | |
|
|
| 2.0141 | 0.06 | 60 | 1.9357 | |
|
|
| 1.9386 | 0.08 | 80 | 1.9156 | |
|
|
| 1.9899 | 0.1 | 100 | 1.9032 | |
|
|
| 1.9022 | 0.11 | 120 | 1.8964 | |
|
|
| 1.9176 | 0.13 | 140 | 1.8880 | |
|
|
| 1.9431 | 0.15 | 160 | 1.8827 | |
|
|
| 1.8847 | 0.17 | 180 | 1.8772 | |
|
|
| 1.8158 | 0.19 | 200 | 1.8740 | |
|
|
| 1.851 | 0.21 | 220 | 1.8711 | |
|
|
| 1.8173 | 0.23 | 240 | 1.8678 | |
|
|
| 1.7902 | 0.25 | 260 | 1.8639 | |
|
|
| 1.8507 | 0.27 | 280 | 1.8600 | |
|
|
| 1.8749 | 0.29 | 300 | 1.8582 | |
|
|
| 1.9203 | 0.3 | 320 | 1.8543 | |
|
|
| 1.8876 | 0.32 | 340 | 1.8518 | |
|
|
| 1.8918 | 0.34 | 360 | 1.8510 | |
|
|
| 1.9568 | 0.36 | 380 | 1.8482 | |
|
|
| 1.7887 | 0.38 | 400 | 1.8489 | |
|
|
| 1.9188 | 0.4 | 420 | 1.8451 | |
|
|
| 1.855 | 0.42 | 440 | 1.8434 | |
|
|
| 1.94 | 0.44 | 460 | 1.8421 | |
|
|
| 1.7969 | 0.46 | 480 | 1.8399 | |
|
|
| 1.875 | 0.48 | 500 | 1.8384 | |
|
|
| 1.8493 | 0.5 | 520 | 1.8383 | |
|
|
| 1.8048 | 0.51 | 540 | 1.8370 | |
|
|
| 1.9077 | 0.53 | 560 | 1.8352 | |
|
|
| 1.804 | 0.55 | 580 | 1.8327 | |
|
|
| 1.8623 | 0.57 | 600 | 1.8315 | |
|
|
| 1.8156 | 0.59 | 620 | 1.8312 | |
|
|
| 1.8639 | 0.61 | 640 | 1.8306 | |
|
|
| 1.909 | 0.63 | 660 | 1.8292 | |
|
|
| 1.8636 | 0.65 | 680 | 1.8290 | |
|
|
| 1.7888 | 0.67 | 700 | 1.8270 | |
|
|
| 1.7797 | 0.69 | 720 | 1.8259 | |
|
|
| 1.8014 | 0.7 | 740 | 1.8248 | |
|
|
| 1.7313 | 0.72 | 760 | 1.8240 | |
|
|
| 1.8429 | 0.74 | 780 | 1.8235 | |
|
|
| 1.814 | 0.76 | 800 | 1.8235 | |
|
|
| 1.7861 | 0.78 | 820 | 1.8221 | |
|
|
| 1.8515 | 0.8 | 840 | 1.8212 | |
|
|
| 1.8432 | 0.82 | 860 | 1.8209 | |
|
|
| 1.8018 | 0.84 | 880 | 1.8204 | |
|
|
| 1.864 | 0.86 | 900 | 1.8203 | |
|
|
| 1.7234 | 0.88 | 920 | 1.8201 | |
|
|
| 1.84 | 0.89 | 940 | 1.8198 | |
|
|
| 1.8721 | 0.91 | 960 | 1.8199 | |
|
|
| 1.7822 | 0.93 | 980 | 1.8198 | |
|
|
| 1.8464 | 0.95 | 1000 | 1.8197 | |
|
|
| 1.7454 | 0.97 | 1020 | 1.8197 | |
|
|
| 1.7434 | 0.99 | 1040 | 1.8197 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.34.1 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.14.5 |
|
|
- Tokenizers 0.14.1 |
|
|
|
