metadata
base_model: google/gemma-2-2b-it
datasets:
- GaetanMichelet/chat-60_ft_task-2
- GaetanMichelet/chat-120_ft_task-2
- GaetanMichelet/chat-180_ft_task-2
library_name: peft
license: gemma
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: Gemma-2-2B_task-2_180-samples_config-2
results: []
Gemma-2-2B_task-2_180-samples_config-2
This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-2, the GaetanMichelet/chat-120_ft_task-2 and the GaetanMichelet/chat-180_ft_task-2 datasets. It achieves the following results on the evaluation set:
- Loss: 0.6501
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 |
|---|---|---|---|
| 1.0192 | 0.9412 | 8 | 1.0544 |
| 0.8716 | 2.0 | 17 | 0.8601 |
| 0.7904 | 2.9412 | 25 | 0.7689 |
| 0.6518 | 4.0 | 34 | 0.7122 |
| 0.6153 | 4.9412 | 42 | 0.6816 |
| 0.6309 | 6.0 | 51 | 0.6577 |
| 0.5496 | 6.9412 | 59 | 0.6501 |
| 0.5015 | 8.0 | 68 | 0.6549 |
| 0.3755 | 8.9412 | 76 | 0.7022 |
| 0.341 | 10.0 | 85 | 0.7520 |
| 0.2562 | 10.9412 | 93 | 0.8381 |
| 0.152 | 12.0 | 102 | 1.0347 |
| 0.1132 | 12.9412 | 110 | 1.1877 |
| 0.0618 | 14.0 | 119 | 1.3359 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1