metadata
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-2
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-2_60-samples_config-1_full
results: []
Gemma-2-2B_task-2_60-samples_config-1_full
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8953
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 |
|---|---|---|---|
| 1.2928 | 0.8696 | 5 | 1.3069 |
| 1.2992 | 1.9130 | 11 | 1.2225 |
| 1.1839 | 2.9565 | 17 | 1.1170 |
| 1.0415 | 4.0 | 23 | 1.0408 |
| 0.9451 | 4.8696 | 28 | 0.9726 |
| 0.8679 | 5.9130 | 34 | 0.9312 |
| 0.8006 | 6.9565 | 40 | 0.9111 |
| 0.7924 | 8.0 | 46 | 0.9005 |
| 0.7768 | 8.8696 | 51 | 0.8965 |
| 0.7665 | 9.9130 | 57 | 0.8953 |
| 0.6893 | 10.9565 | 63 | 0.9024 |
| 0.6515 | 12.0 | 69 | 0.9145 |
| 0.6535 | 12.8696 | 74 | 0.9321 |
| 0.5737 | 13.9130 | 80 | 0.9723 |
| 0.5352 | 14.9565 | 86 | 0.9994 |
| 0.5419 | 16.0 | 92 | 1.0520 |
| 0.3587 | 16.8696 | 97 | 1.1345 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1