metadata
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: data/Tukan-1.1B-Chat-reasoning-sft_merged
model-index:
- name: Tukan-1.1B-Chat-reasoning-sft
results: []
Tukan-1.1B-Chat-reasoning-sft
This model was trained from scratch on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.0960
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: 6
- eval_batch_size: 3
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 20
- total_train_batch_size: 120
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1426 | 0.24 | 10 | 1.1188 |
| 1.1231 | 0.47 | 20 | 1.1059 |
| 1.1179 | 0.71 | 30 | 1.0980 |
| 1.0996 | 0.94 | 40 | 1.0960 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.2.0a0+gitd925d94
- Datasets 2.14.6
- Tokenizers 0.15.0
Training procedure
Framework versions
- PEFT 0.6.1