metadata
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
model-index:
- name: starcoderbase1b-personal-copilot-A100-40GB-colab
results: []
starcoderbase1b-personal-copilot-A100-40GB-colab
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: 0.3625
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 30
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8203 | 0.05 | 100 | 0.8005 |
| 0.762 | 0.1 | 200 | 0.6704 |
| 0.7456 | 0.15 | 300 | 0.5798 |
| 0.6643 | 0.2 | 400 | 0.5415 |
| 0.6 | 0.25 | 500 | 0.5266 |
| 0.5847 | 0.3 | 600 | 0.4981 |
| 0.5323 | 0.35 | 700 | 0.4616 |
| 0.608 | 0.4 | 800 | 0.4527 |
| 0.4632 | 0.45 | 900 | 0.4480 |
| 0.5385 | 0.5 | 1000 | 0.4285 |
| 0.4835 | 0.55 | 1100 | 0.4098 |
| 0.5149 | 0.6 | 1200 | 0.3829 |
| 0.4233 | 0.65 | 1300 | 0.3768 |
| 0.5448 | 0.7 | 1400 | 0.3696 |
| 0.3498 | 0.75 | 1500 | 0.3663 |
| 0.7823 | 0.8 | 1600 | 0.3637 |
| 0.3285 | 0.85 | 1700 | 0.3618 |
| 0.3635 | 0.9 | 1800 | 0.3636 |
| 0.3066 | 0.95 | 1900 | 0.3630 |
| 0.4495 | 1.0 | 2000 | 0.3625 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3