End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: bigcode-openrail-m
|
| 4 |
+
base_model: bigcode/starcoderbase-1b
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: starcoder-peft-airscript
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# starcoder-peft-airscript
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.7155
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0005
|
| 39 |
+
- train_batch_size: 10
|
| 40 |
+
- eval_batch_size: 10
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 2
|
| 43 |
+
- total_train_batch_size: 20
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 30
|
| 47 |
+
- training_steps: 1700
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 1.2691 | 0.0588 | 100 | 1.1636 |
|
| 54 |
+
| 0.9655 | 0.1176 | 200 | 0.9384 |
|
| 55 |
+
| 0.8138 | 0.1765 | 300 | 0.8387 |
|
| 56 |
+
| 0.719 | 0.2353 | 400 | 0.7847 |
|
| 57 |
+
| 0.6408 | 0.2941 | 500 | 0.7503 |
|
| 58 |
+
| 0.5788 | 0.3529 | 600 | 0.7314 |
|
| 59 |
+
| 0.5386 | 0.4118 | 700 | 0.7168 |
|
| 60 |
+
| 0.4894 | 0.4706 | 800 | 0.7156 |
|
| 61 |
+
| 0.4583 | 0.5294 | 900 | 0.7101 |
|
| 62 |
+
| 0.4271 | 0.5882 | 1000 | 0.7070 |
|
| 63 |
+
| 0.4053 | 0.6471 | 1100 | 0.7117 |
|
| 64 |
+
| 0.3934 | 0.7059 | 1200 | 0.7123 |
|
| 65 |
+
| 0.379 | 0.7647 | 1300 | 0.7143 |
|
| 66 |
+
| 0.3666 | 0.8235 | 1400 | 0.7171 |
|
| 67 |
+
| 0.363 | 0.8824 | 1500 | 0.7171 |
|
| 68 |
+
| 0.3588 | 0.9412 | 1600 | 0.7163 |
|
| 69 |
+
| 0.357 | 1.0 | 1700 | 0.7155 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- PEFT 0.13.2
|
| 75 |
+
- Transformers 4.45.2
|
| 76 |
+
- Pytorch 2.5.0
|
| 77 |
+
- Datasets 3.0.1
|
| 78 |
+
- Tokenizers 0.20.1
|