metadata
license: apache-2.0
base_model: JackFram/llama-68m
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-sft-lima
results: []
gpt2-sft-lima
This model is a fine-tuned version of JackFram/llama-68m on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.4846
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.4931 | 1.0 | 24 | 5.5962 |
| 3.4278 | 2.0 | 48 | 5.4846 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.2
- Datasets 2.14.6
- Tokenizers 0.19.1