|
--- |
|
license: other |
|
base_model: TheBloke/Tess-M-v1.3-GPTQ |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Tess34-fans |
|
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. --> |
|
|
|
# Tess34-fans |
|
|
|
This model is a fine-tuned version of [TheBloke/Tess-M-v1.3-GPTQ](https://huggingface.co/TheBloke/Tess-M-v1.3-GPTQ) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7360 |
|
|
|
## 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: 0.0004 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2094 | 0.02 | 50 | 0.9702 | |
|
| 0.9633 | 0.04 | 100 | 0.9093 | |
|
| 0.91 | 0.06 | 150 | 0.8754 | |
|
| 0.8928 | 0.08 | 200 | 0.8588 | |
|
| 0.8768 | 0.1 | 250 | 0.8428 | |
|
| 0.8344 | 0.12 | 300 | 0.8235 | |
|
| 0.8345 | 0.14 | 350 | 0.8160 | |
|
| 0.812 | 0.16 | 400 | 0.8125 | |
|
| 0.8605 | 0.18 | 450 | 0.8079 | |
|
| 0.8263 | 0.21 | 500 | 0.7884 | |
|
| 0.7863 | 0.23 | 550 | 0.7849 | |
|
| 0.7751 | 0.25 | 600 | 0.7798 | |
|
| 0.7976 | 0.27 | 650 | 0.7695 | |
|
| 0.7584 | 0.29 | 700 | 0.7631 | |
|
| 0.8019 | 0.31 | 750 | 0.7552 | |
|
| 0.7626 | 0.33 | 800 | 0.7501 | |
|
| 0.7566 | 0.35 | 850 | 0.7472 | |
|
| 0.7261 | 0.37 | 900 | 0.7424 | |
|
| 0.7613 | 0.39 | 950 | 0.7379 | |
|
| 0.7274 | 0.41 | 1000 | 0.7360 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
