metadata
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-1_auto
- GaetanMichelet/chat-120_ft_task-1_auto
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-1_120-samples_config-1_auto
results: []
Gemma-2-2B_task-1_120-samples_config-1_auto
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-1_auto and the GaetanMichelet/chat-120_ft_task-1_auto datasets. It achieves the following results on the evaluation set:
- Loss: 0.9736
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 |
|---|---|---|---|
| 1.7508 | 1.0 | 11 | 1.5552 |
| 1.066 | 2.0 | 22 | 1.1328 |
| 0.9348 | 3.0 | 33 | 1.0277 |
| 0.8176 | 4.0 | 44 | 0.9744 |
| 0.6379 | 5.0 | 55 | 0.9736 |
| 0.497 | 6.0 | 66 | 1.0945 |
| 0.3367 | 7.0 | 77 | 1.3432 |
| 0.2147 | 8.0 | 88 | 1.6289 |
| 0.1552 | 9.0 | 99 | 1.8935 |
| 0.0668 | 10.0 | 110 | 2.0182 |
| 0.0425 | 11.0 | 121 | 2.3609 |
| 0.0507 | 12.0 | 132 | 2.3115 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1