metadata
base_model: bigcode/starcoderbase-1b
library_name: peft
license: bigcode-openrail-m
tags:
- generated_from_trainer
model-index:
- name: peft-starcoder-finetuned
results: []
peft-starcoder-finetuned
This model is a fine-tuned version of bigcode/starcoderbase-1b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2297
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-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use 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: 50
- training_steps: 1000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.234 | 0.0996 | 50 | 1.2381 |
| 1.0882 | 0.1992 | 100 | 1.2581 |
| 0.9431 | 0.2988 | 150 | 1.2722 |
| 0.8286 | 0.3984 | 200 | 1.2415 |
| 0.7855 | 0.4980 | 250 | 1.2368 |
| 0.7417 | 0.5976 | 300 | 1.2313 |
| 0.7189 | 0.6972 | 350 | 1.2391 |
| 0.6781 | 0.7968 | 400 | 1.2231 |
| 0.6902 | 0.8964 | 450 | 1.2234 |
| 0.653 | 0.9960 | 500 | 1.2330 |
| 0.6556 | 1.0956 | 550 | 1.2255 |
| 0.6343 | 1.1952 | 600 | 1.2197 |
| 0.606 | 1.2948 | 650 | 1.2366 |
| 0.6223 | 1.3944 | 700 | 1.2300 |
| 0.6313 | 1.4940 | 750 | 1.2340 |
| 0.6068 | 1.5936 | 800 | 1.2327 |
| 0.6012 | 1.6932 | 850 | 1.2280 |
| 0.6299 | 1.7928 | 900 | 1.2296 |
| 0.5962 | 1.8924 | 950 | 1.2293 |
| 0.6041 | 1.9920 | 1000 | 1.2297 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.3