|
--- |
|
base_model: eleutherai/pythia-14m |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: goal-encoder-exp |
|
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. --> |
|
|
|
# goal-encoder-exp |
|
|
|
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: 0.2389 |
|
- Accuracy: 0.9 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 10.7829 | 0.2 | 12 | 2.1746 | 0.26 | |
|
| 2.282 | 0.4 | 24 | 1.4918 | 0.44 | |
|
| 1.4675 | 0.6 | 36 | 1.2938 | 0.4 | |
|
| 1.1909 | 0.8 | 48 | 1.1243 | 0.52 | |
|
| 0.9884 | 1.0 | 60 | 0.9595 | 0.62 | |
|
| 0.8292 | 1.2 | 72 | 0.7748 | 0.68 | |
|
| 0.5574 | 1.4 | 84 | 0.4913 | 0.84 | |
|
| 0.3673 | 1.6 | 96 | 0.3591 | 0.88 | |
|
| 0.2768 | 1.8 | 108 | 0.2822 | 0.92 | |
|
| 0.1779 | 2.0 | 120 | 0.2389 | 0.9 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.1 |
|
- Pytorch 2.0.0+cu117 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
