|
--- |
|
license: llama2 |
|
base_model: TheBloke/vigogne-2-70B-chat-GPTQ |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Vigogne70b-last_fan |
|
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. --> |
|
|
|
# Vigogne70b-last_fan |
|
|
|
This model is a fine-tuned version of [TheBloke/vigogne-2-70B-chat-GPTQ](https://huggingface.co/TheBloke/vigogne-2-70B-chat-GPTQ) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7698 |
|
|
|
## 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: 1 |
|
- eval_batch_size: 1 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 0.01 | 50 | 1.0362 | |
|
| No log | 0.02 | 100 | 0.9411 | |
|
| No log | 0.03 | 150 | 0.9255 | |
|
| No log | 0.04 | 200 | 0.8966 | |
|
| No log | 0.05 | 250 | 0.8685 | |
|
| No log | 0.06 | 300 | 0.8707 | |
|
| No log | 0.08 | 350 | 0.8515 | |
|
| No log | 0.09 | 400 | 0.8420 | |
|
| No log | 0.1 | 450 | 0.8399 | |
|
| 0.9406 | 0.11 | 500 | 0.8246 | |
|
| 0.9406 | 0.12 | 550 | 0.8070 | |
|
| 0.9406 | 0.13 | 600 | 0.8089 | |
|
| 0.9406 | 0.14 | 650 | 0.8018 | |
|
| 0.9406 | 0.15 | 700 | 0.7947 | |
|
| 0.9406 | 0.16 | 750 | 0.7910 | |
|
| 0.9406 | 0.17 | 800 | 0.7828 | |
|
| 0.9406 | 0.18 | 850 | 0.7774 | |
|
| 0.9406 | 0.19 | 900 | 0.7747 | |
|
| 0.9406 | 0.21 | 950 | 0.7712 | |
|
| 0.7812 | 0.22 | 1000 | 0.7698 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
