metadata
license: apache-2.0
base_model: tiiuae/falcon-7b
tags:
- generated_from_trainer
model-index:
- name: falcon-rewrite-581-smallset
results: []
falcon-rewrite-581-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: 1.8029
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: 4
- eval_batch_size: 4
- 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 |
---|---|---|---|
2.4551 | 0.04 | 10 | 2.4085 |
1.4203 | 0.08 | 20 | 2.3957 |
1.6967 | 0.13 | 30 | 2.1396 |
1.5897 | 0.17 | 40 | 2.2547 |
1.4068 | 0.21 | 50 | 2.2484 |
2.4724 | 0.25 | 60 | 2.1803 |
1.6358 | 0.3 | 70 | 2.0363 |
1.7565 | 0.34 | 80 | 2.3048 |
1.9326 | 0.38 | 90 | 2.2237 |
1.4726 | 0.42 | 100 | 1.9666 |
2.6885 | 0.47 | 110 | 2.0889 |
1.7221 | 0.51 | 120 | 2.0868 |
2.7958 | 0.55 | 130 | 2.0033 |
1.6916 | 0.59 | 140 | 2.0824 |
0.9544 | 0.64 | 150 | 2.1048 |
1.8363 | 0.68 | 160 | 1.9306 |
2.2805 | 0.72 | 170 | 2.0956 |
2.2398 | 0.76 | 180 | 2.1049 |
1.0369 | 0.81 | 190 | 2.0348 |
0.9023 | 0.85 | 200 | 1.9050 |
1.1511 | 0.89 | 210 | 2.0645 |
1.1805 | 0.93 | 220 | 1.9241 |
1.0402 | 0.97 | 230 | 2.0542 |
1.1116 | 1.02 | 240 | 1.9184 |
2.2786 | 1.06 | 250 | 2.0039 |
1.5313 | 1.1 | 260 | 1.9232 |
1.0101 | 1.14 | 270 | 1.8365 |
1.3444 | 1.19 | 280 | 1.9812 |
1.9973 | 1.23 | 290 | 2.0105 |
1.001 | 1.27 | 300 | 1.8029 |
1.5717 | 1.31 | 310 | 1.8190 |
1.7842 | 1.36 | 320 | 2.0034 |
0.841 | 1.4 | 330 | 2.0345 |
0.9212 | 1.44 | 340 | 1.9301 |
1.6442 | 1.48 | 350 | 2.0139 |
2.0697 | 1.53 | 360 | 2.1341 |
1.0772 | 1.57 | 370 | 2.0179 |
1.4152 | 1.61 | 380 | 1.8754 |
0.912 | 1.65 | 390 | 1.9178 |
1.7032 | 1.69 | 400 | 1.9235 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3