metadata
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-3
- GaetanMichelet/chat-120_ft_task-3
- GaetanMichelet/chat-180_ft_task-3
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-3_180-samples_config-1_full
results: []
Gemma-2-2B_task-3_180-samples_config-1_full
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-3, the GaetanMichelet/chat-120_ft_task-3 and the GaetanMichelet/chat-180_ft_task-3 datasets. It achieves the following results on the evaluation set:
- Loss: 0.9429
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3583 | 1.0 | 17 | 1.3383 |
| 1.1931 | 2.0 | 34 | 1.1611 |
| 0.9969 | 3.0 | 51 | 1.0146 |
| 0.8959 | 4.0 | 68 | 0.9699 |
| 0.8646 | 5.0 | 85 | 0.9506 |
| 0.8205 | 6.0 | 102 | 0.9429 |
| 0.7947 | 7.0 | 119 | 0.9492 |
| 0.7099 | 8.0 | 136 | 0.9749 |
| 0.6368 | 9.0 | 153 | 1.0093 |
| 0.6039 | 10.0 | 170 | 1.0973 |
| 0.5767 | 11.0 | 187 | 1.1243 |
| 0.4197 | 12.0 | 204 | 1.3017 |
| 0.4419 | 13.0 | 221 | 1.2848 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1