metadata
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-1
- GaetanMichelet/chat-120_ft_task-1
- GaetanMichelet/chat-180_ft_task-1
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-1_180-samples_config-2
results: []
Gemma-2-2B_task-1_180-samples_config-2
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-1, the GaetanMichelet/chat-120_ft_task-1 and the GaetanMichelet/chat-180_ft_task-1 datasets. It achieves the following results on the evaluation set:
- Loss: 1.2884
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 |
|---|---|---|---|
| 2.3482 | 0.9412 | 8 | 2.2693 |
| 1.7809 | 2.0 | 17 | 1.6932 |
| 1.553 | 2.9412 | 25 | 1.5041 |
| 1.2823 | 4.0 | 34 | 1.3678 |
| 1.1298 | 4.9412 | 42 | 1.3193 |
| 1.027 | 6.0 | 51 | 1.2884 |
| 0.8219 | 6.9412 | 59 | 1.3590 |
| 0.6244 | 8.0 | 68 | 1.5296 |
| 0.398 | 8.9412 | 76 | 1.7941 |
| 0.2704 | 10.0 | 85 | 2.2475 |
| 0.1592 | 10.9412 | 93 | 2.5631 |
| 0.0797 | 12.0 | 102 | 2.7847 |
| 0.0459 | 12.9412 | 110 | 2.9444 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1