metadata
base_model: eleutherai/pythia-14m
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: goal-encoder-exp
results: []
goal-encoder-exp
This model is a fine-tuned version of eleutherai/pythia-14m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1952
- Accuracy: 0.96
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 |
|---|---|---|---|---|
| 8.0333 | 0.2 | 12 | 1.4882 | 0.42 |
| 1.5582 | 0.4 | 24 | 1.6071 | 0.36 |
| 1.4462 | 0.6 | 36 | 1.1355 | 0.54 |
| 1.2173 | 0.8 | 48 | 0.9234 | 0.62 |
| 0.9213 | 1.0 | 60 | 0.9122 | 0.54 |
| 0.7752 | 1.2 | 72 | 0.5608 | 0.88 |
| 0.5467 | 1.4 | 84 | 0.4030 | 0.92 |
| 0.3867 | 1.6 | 96 | 0.2786 | 0.94 |
| 0.27 | 1.8 | 108 | 0.2165 | 0.96 |
| 0.1646 | 2.0 | 120 | 0.1952 | 0.96 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.0.0+cu117
- Datasets 2.19.1
- Tokenizers 0.19.1