metadata
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-1
- GaetanMichelet/chat-120_ft_task-1
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-1_120-samples_config-2
results: []
Gemma-2-2B_task-1_120-samples_config-2
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-1 and the GaetanMichelet/chat-120_ft_task-1 datasets. It achieves the following results on the evaluation set:
- Loss: 1.3268
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: 16
- total_train_batch_size: 16
- 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 |
|---|---|---|---|
| 2.4033 | 0.9091 | 5 | 2.3638 |
| 2.1644 | 2.0 | 11 | 1.9085 |
| 1.5867 | 2.9091 | 16 | 1.6096 |
| 1.3937 | 4.0 | 22 | 1.4499 |
| 1.2999 | 4.9091 | 27 | 1.3671 |
| 1.1454 | 6.0 | 33 | 1.3296 |
| 0.9351 | 6.9091 | 38 | 1.3268 |
| 0.8108 | 8.0 | 44 | 1.3552 |
| 0.6191 | 8.9091 | 49 | 1.4658 |
| 0.4271 | 10.0 | 55 | 1.7157 |
| 0.3163 | 10.9091 | 60 | 2.0603 |
| 0.1817 | 12.0 | 66 | 2.5517 |
| 0.104 | 12.9091 | 71 | 2.9069 |
| 0.0403 | 14.0 | 77 | 3.1679 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1