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
results: []
Gemma-2-2B_task-3_180-samples_config-1
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: 0.4579
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 |
|---|---|---|---|
| 2.5602 | 1.0 | 17 | 2.2181 |
| 0.7021 | 2.0 | 34 | 0.6752 |
| 0.3994 | 3.0 | 51 | 0.5230 |
| 0.291 | 4.0 | 68 | 0.4654 |
| 0.2886 | 5.0 | 85 | 0.4579 |
| 0.3088 | 6.0 | 102 | 0.4717 |
| 0.2315 | 7.0 | 119 | 0.5575 |
| 0.0902 | 8.0 | 136 | 0.6359 |
| 0.05 | 9.0 | 153 | 0.8562 |
| 0.0274 | 10.0 | 170 | 0.8861 |
| 0.0116 | 11.0 | 187 | 1.0696 |
| 0.0158 | 12.0 | 204 | 0.9895 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1