ZiHDeng's picture
End of training
47689f2 verified
|
raw
history blame
2.49 kB
---
license: bigcode-openrail-m
library_name: peft
tags:
- generated_from_trainer
base_model: bigcode/starcoderbase-1b
model-index:
- name: peft-lora-starcoder1B-Instruction-ny8
results: []
---
<!-- 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. -->
# peft-lora-starcoder1B-Instruction-ny8
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1132
## 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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- 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
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.2847 | 0.05 | 100 | 0.3010 |
| 0.2397 | 0.1 | 200 | 0.3370 |
| 0.1288 | 0.15 | 300 | 0.5087 |
| 0.0894 | 0.2 | 400 | 0.6274 |
| 0.067 | 0.25 | 500 | 0.7248 |
| 0.0489 | 0.3 | 600 | 0.7530 |
| 0.03 | 0.35 | 700 | 0.8735 |
| 0.0192 | 0.4 | 800 | 0.9347 |
| 0.0143 | 0.45 | 900 | 0.9769 |
| 0.0127 | 0.5 | 1000 | 1.0044 |
| 0.0114 | 0.55 | 1100 | 1.0451 |
| 0.0108 | 0.6 | 1200 | 1.0593 |
| 0.0101 | 0.65 | 1300 | 1.0556 |
| 0.0092 | 0.7 | 1400 | 1.0834 |
| 0.0093 | 0.75 | 1500 | 1.1055 |
| 0.0092 | 0.8 | 1600 | 1.0918 |
| 0.0079 | 0.85 | 1700 | 1.1194 |
| 0.0089 | 0.9 | 1800 | 1.1114 |
| 0.0086 | 0.95 | 1900 | 1.1126 |
| 0.0079 | 1.0 | 2000 | 1.1132 |
### Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0