metadata
license: bigcode-openrail-m
base_model: bigcode/starcoderbase-1b
tags:
- generated_from_trainer
library_name: peft
model-index:
- name: Test_Training_v3
results: []
Test_Training_v3
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: 1.5622
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: 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: 30
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4169 | 0.05 | 100 | 0.9127 |
| 0.2774 | 0.1 | 200 | 0.9903 |
| 0.1967 | 0.15 | 300 | 1.1247 |
| 0.1572 | 0.2 | 400 | 1.1690 |
| 0.1649 | 0.25 | 500 | 1.2579 |
| 0.123 | 0.3 | 600 | 1.2884 |
| 0.1023 | 0.35 | 700 | 1.3079 |
| 0.0777 | 0.4 | 800 | 1.3562 |
| 0.0674 | 0.45 | 900 | 1.4247 |
| 0.0704 | 0.5 | 1000 | 1.4536 |
| 0.0715 | 0.55 | 1100 | 1.4713 |
| 0.0502 | 0.6 | 1200 | 1.4968 |
| 0.0553 | 0.65 | 1300 | 1.5002 |
| 0.0505 | 0.7 | 1400 | 1.5015 |
| 0.043 | 0.75 | 1500 | 1.5359 |
| 0.0458 | 0.8 | 1600 | 1.5474 |
| 0.0355 | 0.85 | 1700 | 1.5581 |
| 0.0438 | 0.9 | 1800 | 1.5616 |
| 0.0507 | 0.95 | 1900 | 1.5633 |
| 0.0378 | 1.0 | 2000 | 1.5622 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.3.1+cu121
- Datasets 3.6.0
- Tokenizers 0.19.1