metadata
license: gemma
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-2b
datasets:
- generator
model-index:
- name: gemma2b-summarize-gemini1_5flash-1k
results: []
gemma2b-summarize-gemini1_5flash-1k
This model is a fine-tuned version of google/gemma-2b on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.7426
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.9957 | 1.0 | 2 | 3.1984 |
| 2.9957 | 2.0 | 4 | 3.0673 |
| 2.8525 | 3.0 | 6 | 2.9478 |
| 2.8525 | 4.0 | 8 | 2.8806 |
| 2.3323 | 5.0 | 10 | 2.8382 |
| 2.3323 | 6.0 | 12 | 2.8050 |
| 2.3323 | 7.0 | 14 | 2.7636 |
| 2.0887 | 8.0 | 16 | 2.7495 |
| 2.0887 | 9.0 | 18 | 2.7433 |
| 1.9997 | 10.0 | 20 | 2.7426 |
Framework versions
- PEFT 0.11.1
- Transformers 4.40.1
- Pytorch 2.2.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1