EMS_all_75_code-starcoder-lora-batch_10_steps_2000
This model is a fine-tuned version of bigcode/starcoderbase-1b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0309
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: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 2000
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.3667 | 0.05 | 100 | 0.4484 |
0.428 | 0.1 | 200 | 0.3095 |
0.3 | 0.15 | 300 | 0.2275 |
0.2296 | 0.2 | 400 | 0.1711 |
0.1062 | 0.25 | 500 | 0.1522 |
0.1347 | 0.3 | 600 | 0.1305 |
0.1624 | 0.35 | 700 | 0.0949 |
0.1207 | 0.4 | 800 | 0.0766 |
0.1052 | 0.45 | 900 | 0.0614 |
0.0777 | 0.5 | 1000 | 0.0548 |
0.0773 | 0.55 | 1100 | 0.0476 |
0.0653 | 0.6 | 1200 | 0.0423 |
0.0664 | 0.65 | 1300 | 0.0384 |
0.06 | 0.7 | 1400 | 0.0357 |
0.0514 | 0.75 | 1500 | 0.0336 |
0.0395 | 0.8 | 1600 | 0.0326 |
0.0594 | 0.85 | 1700 | 0.0318 |
0.049 | 0.9 | 1800 | 0.0312 |
0.0403 | 0.95 | 1900 | 0.0309 |
0.0445 | 1.0 | 2000 | 0.0309 |
Framework versions
- PEFT 0.14.0
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.20.3
- Downloads last month
- 34
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for rahkrish1/EMS_all_75_code-starcoder-lora-batch_10_steps_2000
Base model
bigcode/starcoderbase-1b