metadata
license: apache-2.0
base_model: EleutherAI/pythia-1.4b
tags:
- generated_from_trainer
datasets:
- alpaca_farm
model-index:
- name: pythia-1.4b_alpaca_farm_instructions_sft_constant_pa
results: []
pythia-1.4b_alpaca_farm_instructions_sft_constant_pa
This model is a fine-tuned version of EleutherAI/pythia-1.4b on the alpaca_farm dataset. It achieves the following results on the evaluation set:
- Loss: 0.1513
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: 8e-06
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5967 | 1.0 | 2500 | 1.0668 |
| 1.0239 | 2.0 | 5000 | 0.5980 |
| 0.5893 | 3.0 | 7500 | 0.3444 |
| 0.3651 | 4.0 | 10000 | 0.2424 |
| 0.272 | 5.0 | 12500 | 0.2009 |
| 0.2294 | 6.0 | 15000 | 0.1792 |
| 0.2056 | 7.0 | 17500 | 0.1686 |
| 0.192 | 8.0 | 20000 | 0.1609 |
| 0.1841 | 9.0 | 22500 | 0.1551 |
| 0.1773 | 10.0 | 25000 | 0.1513 |
Framework versions
- Transformers 4.35.2
- Pytorch 1.13.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0