End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starcoderbase-1b
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: bigcode-openrail-m
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: peft-starcoder-finetuned-cpp
|
| 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 |
+
# peft-starcoder-finetuned-cpp
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bigcode/starcoderbase-1b](https://huggingface.co/bigcode/starcoderbase-1b) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.6176
|
| 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: 5e-06
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 2
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 20
|
| 47 |
+
- training_steps: 1000
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 0.9707 | 0.1273 | 20 | 0.9157 |
|
| 54 |
+
| 0.9027 | 0.2546 | 40 | 0.8960 |
|
| 55 |
+
| 0.7973 | 0.3819 | 60 | 0.8843 |
|
| 56 |
+
| 0.7716 | 0.5091 | 80 | 0.8618 |
|
| 57 |
+
| 0.6858 | 0.6364 | 100 | 0.8392 |
|
| 58 |
+
| 0.6603 | 0.7637 | 120 | 0.8126 |
|
| 59 |
+
| 0.6288 | 0.8910 | 140 | 0.7950 |
|
| 60 |
+
| 0.5693 | 1.0183 | 160 | 0.7798 |
|
| 61 |
+
| 0.5035 | 1.1456 | 180 | 0.7706 |
|
| 62 |
+
| 0.5376 | 1.2729 | 200 | 0.7583 |
|
| 63 |
+
| 0.4893 | 1.4002 | 220 | 0.7469 |
|
| 64 |
+
| 0.5256 | 1.5274 | 240 | 0.7366 |
|
| 65 |
+
| 0.4646 | 1.6547 | 260 | 0.7262 |
|
| 66 |
+
| 0.5039 | 1.7820 | 280 | 0.7156 |
|
| 67 |
+
| 0.4376 | 1.9093 | 300 | 0.7062 |
|
| 68 |
+
| 0.4262 | 2.0366 | 320 | 0.7000 |
|
| 69 |
+
| 0.445 | 2.1639 | 340 | 0.6917 |
|
| 70 |
+
| 0.4307 | 2.2912 | 360 | 0.6847 |
|
| 71 |
+
| 0.4531 | 2.4185 | 380 | 0.6822 |
|
| 72 |
+
| 0.4018 | 2.5457 | 400 | 0.6758 |
|
| 73 |
+
| 0.4466 | 2.6730 | 420 | 0.6695 |
|
| 74 |
+
| 0.3934 | 2.8003 | 440 | 0.6649 |
|
| 75 |
+
| 0.3815 | 2.9276 | 460 | 0.6607 |
|
| 76 |
+
| 0.3834 | 3.0549 | 480 | 0.6575 |
|
| 77 |
+
| 0.4001 | 3.1822 | 500 | 0.6523 |
|
| 78 |
+
| 0.398 | 3.3095 | 520 | 0.6481 |
|
| 79 |
+
| 0.3824 | 3.4368 | 540 | 0.6453 |
|
| 80 |
+
| 0.3756 | 3.5640 | 560 | 0.6409 |
|
| 81 |
+
| 0.3843 | 3.6913 | 580 | 0.6382 |
|
| 82 |
+
| 0.3829 | 3.8186 | 600 | 0.6357 |
|
| 83 |
+
| 0.3534 | 3.9459 | 620 | 0.6345 |
|
| 84 |
+
| 0.4136 | 4.0732 | 640 | 0.6343 |
|
| 85 |
+
| 0.3409 | 4.2005 | 660 | 0.6321 |
|
| 86 |
+
| 0.357 | 4.3278 | 680 | 0.6288 |
|
| 87 |
+
| 0.397 | 4.4551 | 700 | 0.6263 |
|
| 88 |
+
| 0.3713 | 4.5823 | 720 | 0.6255 |
|
| 89 |
+
| 0.3914 | 4.7096 | 740 | 0.6242 |
|
| 90 |
+
| 0.3657 | 4.8369 | 760 | 0.6230 |
|
| 91 |
+
| 0.3711 | 4.9642 | 780 | 0.6216 |
|
| 92 |
+
| 0.3538 | 5.0915 | 800 | 0.6205 |
|
| 93 |
+
| 0.377 | 5.2188 | 820 | 0.6199 |
|
| 94 |
+
| 0.3426 | 5.3461 | 840 | 0.6194 |
|
| 95 |
+
| 0.3583 | 5.4733 | 860 | 0.6188 |
|
| 96 |
+
| 0.3643 | 5.6006 | 880 | 0.6180 |
|
| 97 |
+
| 0.362 | 5.7279 | 900 | 0.6178 |
|
| 98 |
+
| 0.388 | 5.8552 | 920 | 0.6177 |
|
| 99 |
+
| 0.3424 | 5.9825 | 940 | 0.6177 |
|
| 100 |
+
| 0.3614 | 6.1098 | 960 | 0.6176 |
|
| 101 |
+
| 0.3652 | 6.2371 | 980 | 0.6176 |
|
| 102 |
+
| 0.3691 | 6.3644 | 1000 | 0.6176 |
|
| 103 |
+
|
| 104 |
+
|
| 105 |
+
### Framework versions
|
| 106 |
+
|
| 107 |
+
- PEFT 0.13.2
|
| 108 |
+
- Transformers 4.46.2
|
| 109 |
+
- Pytorch 2.4.1+cu121
|
| 110 |
+
- Datasets 3.0.1
|
| 111 |
+
- Tokenizers 0.20.3
|