<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
santacoder-finetuned-the-stack-rust
This model is a fine-tuned version of bigcode/santacoder on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7999
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 10000
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.2075 | 0.05 | 500 | 1.0610 |
1.79 | 0.1 | 1000 | 1.0754 |
1.2441 | 0.15 | 1500 | 1.0339 |
1.1709 | 0.2 | 2000 | 0.9829 |
0.7645 | 0.25 | 2500 | 0.9738 |
1.0381 | 0.3 | 3000 | 0.9536 |
1.0625 | 0.35 | 3500 | 0.9268 |
0.78 | 0.4 | 4000 | 0.9130 |
0.9294 | 0.45 | 4500 | 0.9001 |
0.9767 | 0.5 | 5000 | 0.8857 |
5.7027 | 0.55 | 5500 | 0.8728 |
0.9476 | 0.6 | 6000 | 0.8556 |
0.6185 | 0.65 | 6500 | 0.8404 |
0.5057 | 0.7 | 7000 | 0.8328 |
0.6451 | 0.75 | 7500 | 0.8199 |
0.8298 | 0.8 | 8000 | 0.8111 |
0.2447 | 0.85 | 8500 | 0.8069 |
0.8177 | 0.9 | 9000 | 0.8020 |
0.7184 | 0.95 | 9500 | 0.8003 |
0.9166 | 1.0 | 10000 | 0.7999 |
Framework versions
- Transformers 4.26.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2