metadata
license: apache-2.0
base_model: tiiuae/falcon-7b
tags:
- generated_from_trainer
model-index:
- name: falcon-generate-560-smallset
results: []
falcon-generate-560-smallset
This model is a fine-tuned version of tiiuae/falcon-7b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2138
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: 0.0005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.5842 | 0.21 | 10 | 2.1612 |
2.1402 | 0.43 | 20 | 1.6726 |
1.2388 | 0.64 | 30 | 1.7379 |
1.593 | 0.85 | 40 | 1.6660 |
1.693 | 1.06 | 50 | 1.5479 |
1.1697 | 1.28 | 60 | 1.8677 |
1.7327 | 1.49 | 70 | 1.6845 |
1.5152 | 1.7 | 80 | 1.5870 |
2.0819 | 1.91 | 90 | 1.2138 |
0.9853 | 2.13 | 100 | 1.9800 |
1.0804 | 2.34 | 110 | 1.3695 |
1.8216 | 2.55 | 120 | 1.8492 |
1.0342 | 2.77 | 130 | 1.8183 |
0.9118 | 2.98 | 140 | 1.8248 |
0.7258 | 3.19 | 150 | 1.8724 |
0.7392 | 3.4 | 160 | 1.8986 |
0.9705 | 3.62 | 170 | 2.0972 |
1.81 | 3.83 | 180 | 2.1715 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3