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-1
results: []
Gemma-2-2B_task-1_180-samples_config-1
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: 1.2944
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 |
|---|---|---|---|
| 2.2103 | 1.0 | 17 | 2.0467 |
| 1.4945 | 2.0 | 34 | 1.5311 |
| 1.2419 | 3.0 | 51 | 1.3481 |
| 1.055 | 4.0 | 68 | 1.2944 |
| 0.9312 | 5.0 | 85 | 1.3499 |
| 0.6594 | 6.0 | 102 | 1.4708 |
| 0.3964 | 7.0 | 119 | 1.7099 |
| 0.2489 | 8.0 | 136 | 2.3134 |
| 0.1183 | 9.0 | 153 | 2.5791 |
| 0.0799 | 10.0 | 170 | 2.6094 |
| 0.0689 | 11.0 | 187 | 2.9233 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1