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-1
results: []
Gemma-2-2B_task-1_120-samples_config-1
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: 1.3272
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 |
|---|---|---|---|
| 2.311 | 1.0 | 11 | 2.2375 |
| 1.6775 | 2.0 | 22 | 1.6417 |
| 1.4086 | 3.0 | 33 | 1.4308 |
| 1.1316 | 4.0 | 44 | 1.3372 |
| 0.9745 | 5.0 | 55 | 1.3272 |
| 0.7135 | 6.0 | 66 | 1.3981 |
| 0.4228 | 7.0 | 77 | 1.7708 |
| 0.3143 | 8.0 | 88 | 2.1521 |
| 0.1454 | 9.0 | 99 | 2.6897 |
| 0.0857 | 10.0 | 110 | 2.6892 |
| 0.06 | 11.0 | 121 | 2.8942 |
| 0.0671 | 12.0 | 132 | 2.8843 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1