|
|
--- |
|
|
library_name: transformers |
|
|
base_model: EleutherAI/pythia-14m |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: mini-chennus |
|
|
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. --> |
|
|
|
|
|
# mini-chennus |
|
|
|
|
|
This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.9861 |
|
|
- Accuracy: 0.0 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 8 |
|
|
- seed: 42 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- num_epochs: 3 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
|
| 1.4394 | 0.1616 | 200 | 1.4008 | 0.0 | |
|
|
| 1.2966 | 0.3231 | 400 | 1.2502 | 0.0 | |
|
|
| 1.2088 | 0.4847 | 600 | 1.1922 | 0.0 | |
|
|
| 1.1689 | 0.6462 | 800 | 1.1538 | 0.0001 | |
|
|
| 1.1303 | 0.8078 | 1000 | 1.1333 | 0.0 | |
|
|
| 1.1094 | 0.9693 | 1200 | 1.1012 | 0.0 | |
|
|
| 1.0967 | 1.1309 | 1400 | 1.0750 | 0.0 | |
|
|
| 1.0621 | 1.2924 | 1600 | 1.0659 | 0.0 | |
|
|
| 1.0647 | 1.4540 | 1800 | 1.0566 | 0.0 | |
|
|
| 1.0388 | 1.6155 | 2000 | 1.0452 | 0.0 | |
|
|
| 1.0465 | 1.7771 | 2200 | 1.0266 | 0.0 | |
|
|
| 1.0274 | 1.9386 | 2400 | 1.0119 | 0.0 | |
|
|
| 1.0125 | 2.1002 | 2600 | 1.0084 | 0.0 | |
|
|
| 1.0023 | 2.2617 | 2800 | 1.0002 | 0.0 | |
|
|
| 1.0001 | 2.4233 | 3000 | 0.9968 | 0.0 | |
|
|
| 0.9954 | 2.5848 | 3200 | 0.9912 | 0.0 | |
|
|
| 0.9865 | 2.7464 | 3400 | 0.9853 | 0.0 | |
|
|
| 0.9913 | 2.9079 | 3600 | 0.9861 | 0.0 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.57.2 |
|
|
- Pytorch 2.9.0+cu126 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.22.1 |
|
|
|
