|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ |
|
model-index: |
|
- name: coinplusfire_llm_2 |
|
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. --> |
|
|
|
# coinplusfire_llm_2 |
|
|
|
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3706 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2 |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.2985 | 0.99 | 51 | 1.8297 | |
|
| 1.6179 | 1.99 | 103 | 1.6461 | |
|
| 1.4812 | 3.0 | 155 | 1.5621 | |
|
| 1.3993 | 4.0 | 207 | 1.5078 | |
|
| 1.3646 | 4.99 | 258 | 1.4690 | |
|
| 1.2914 | 5.99 | 310 | 1.4270 | |
|
| 1.2542 | 7.0 | 362 | 1.4022 | |
|
| 1.2263 | 8.0 | 414 | 1.3832 | |
|
| 1.2279 | 8.99 | 465 | 1.3720 | |
|
| 1.1812 | 9.86 | 510 | 1.3706 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.0 |
|
- Transformers 4.38.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
