metadata
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: google/gemma-7b-it
model-index:
- name: gemma-7b-it-dolly-15k-english-brainstorming
results: []
gemma-7b-it-dolly-15k-english-brainstorming
This model is a fine-tuned version of google/gemma-7b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3974
- Rouge Scores: {'rouge1': 0.8672818649395687, 'rouge2': 0.6454332350275582, 'rougeL': 0.6351345254871303, 'rougeLsum': 0.8672626398857906}
- Bleu Scores: [0.8956480474494563, 0.8706364987273697, 0.8304269359390679, 0.785372823061285]
- Gen Len: 170.6158
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge Scores | Bleu Scores | Gen Len |
|---|---|---|---|---|---|---|
| 2.3012 | 1.0 | 398 | 2.0026 | {'rouge1': 0.8605967894222545, 'rouge2': 0.636131431928223, 'rougeL': 0.6291428969983008, 'rougeLsum': 0.860624331598749} | [0.8793248327807496, 0.8543278363738773, 0.8139923136639805, 0.7687265678282116] | 170.5932 |
| 1.2054 | 2.0 | 796 | 2.0260 | {'rouge1': 0.8587397434055452, 'rouge2': 0.6353005312218787, 'rougeL': 0.6345388735413529, 'rougeLsum': 0.8588818459220777} | [0.874882697664012, 0.8507131493229504, 0.8111205664503656, 0.7665706439816697] | 170.6271 |
| 0.519 | 3.0 | 1194 | 2.3974 | {'rouge1': 0.8672818649395687, 'rouge2': 0.6454332350275582, 'rougeL': 0.6351345254871303, 'rougeLsum': 0.8672626398857906} | [0.8956480474494563, 0.8706364987273697, 0.8304269359390679, 0.785372823061285] | 170.6158 |
Framework versions
- PEFT 0.9.1.dev0
- Transformers 4.39.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.18.1.dev0
- Tokenizers 0.15.2