Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: Qwen/Qwen1.5-4B
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: squad_qa_title_v5_full_add3_Qwen_Qwen1.5-4B_3e-5_lora
|
| 10 |
+
results: []
|
| 11 |
+
library_name: peft
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# squad_qa_title_v5_full_add3_Qwen_Qwen1.5-4B_3e-5_lora
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen1.5-4B](https://huggingface.co/Qwen/Qwen1.5-4B) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.7159
|
| 22 |
+
- Accuracy: 0.6085
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 1
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- gradient_accumulation_steps: 8
|
| 48 |
+
- total_train_batch_size: 32
|
| 49 |
+
- total_eval_batch_size: 8
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: constant
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 53 |
+
- num_epochs: 50.0
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 58 |
+
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
| 59 |
+
| 1.9008 | 0.9961 | 158 | 1.6150 | 0.6265 |
|
| 60 |
+
| 1.5665 | 1.9984 | 317 | 1.5618 | 0.6295 |
|
| 61 |
+
| 1.4367 | 2.9945 | 475 | 1.5173 | 0.6373 |
|
| 62 |
+
| 1.1524 | 3.9968 | 634 | 1.5250 | 0.6402 |
|
| 63 |
+
| 0.9982 | 4.9992 | 793 | 1.5331 | 0.6382 |
|
| 64 |
+
| 0.7607 | 5.9953 | 951 | 1.5775 | 0.6358 |
|
| 65 |
+
| 0.6105 | 6.9976 | 1110 | 1.6635 | 0.6353 |
|
| 66 |
+
| 0.5197 | 8.0 | 1269 | 1.7484 | 0.6306 |
|
| 67 |
+
| 0.4234 | 8.9961 | 1427 | 1.8600 | 0.6287 |
|
| 68 |
+
| 0.3673 | 9.9984 | 1586 | 1.9489 | 0.6274 |
|
| 69 |
+
| 0.3119 | 10.9945 | 1744 | 2.0436 | 0.6243 |
|
| 70 |
+
| 0.2809 | 11.9968 | 1903 | 2.1217 | 0.6204 |
|
| 71 |
+
| 0.2503 | 12.9992 | 2062 | 2.1670 | 0.6231 |
|
| 72 |
+
| 0.2409 | 13.9953 | 2220 | 2.2734 | 0.6229 |
|
| 73 |
+
| 0.2194 | 14.9976 | 2379 | 2.3544 | 0.6239 |
|
| 74 |
+
| 0.2165 | 16.0 | 2538 | 2.3639 | 0.6241 |
|
| 75 |
+
| 0.2085 | 16.9961 | 2696 | 2.3747 | 0.62 |
|
| 76 |
+
| 0.198 | 17.9984 | 2855 | 2.3743 | 0.6196 |
|
| 77 |
+
| 0.1982 | 18.9945 | 3013 | 2.3724 | 0.6224 |
|
| 78 |
+
| 0.1934 | 19.9968 | 3172 | 2.4015 | 0.6210 |
|
| 79 |
+
| 0.1926 | 20.9992 | 3331 | 2.3930 | 0.6197 |
|
| 80 |
+
| 0.1854 | 21.9953 | 3489 | 2.4737 | 0.6192 |
|
| 81 |
+
| 0.1829 | 22.9976 | 3648 | 2.4893 | 0.6216 |
|
| 82 |
+
| 0.1899 | 24.0 | 3807 | 2.5129 | 0.6218 |
|
| 83 |
+
| 0.1808 | 24.9961 | 3965 | 2.5751 | 0.6193 |
|
| 84 |
+
| 0.1825 | 25.9984 | 4124 | 2.5248 | 0.6165 |
|
| 85 |
+
| 0.1772 | 26.9945 | 4282 | 2.5468 | 0.6190 |
|
| 86 |
+
| 0.1776 | 27.9968 | 4441 | 2.6350 | 0.6192 |
|
| 87 |
+
| 0.1817 | 28.9992 | 4600 | 2.6314 | 0.6167 |
|
| 88 |
+
| 0.1734 | 29.9953 | 4758 | 2.5681 | 0.6113 |
|
| 89 |
+
| 0.1751 | 30.9976 | 4917 | 2.6428 | 0.6062 |
|
| 90 |
+
| 0.1733 | 32.0 | 5076 | 2.6567 | 0.6084 |
|
| 91 |
+
| 0.1721 | 32.9961 | 5234 | 2.6730 | 0.6079 |
|
| 92 |
+
| 0.1716 | 33.9984 | 5393 | 2.6146 | 0.6084 |
|
| 93 |
+
| 0.1695 | 34.9945 | 5551 | 2.6706 | 0.6142 |
|
| 94 |
+
| 0.1746 | 35.9968 | 5710 | 2.6580 | 0.6088 |
|
| 95 |
+
| 0.1696 | 36.9992 | 5869 | 2.6314 | 0.6050 |
|
| 96 |
+
| 0.1723 | 37.9953 | 6027 | 2.7503 | 0.6105 |
|
| 97 |
+
| 0.1712 | 38.9976 | 6186 | 2.7145 | 0.6045 |
|
| 98 |
+
| 0.1707 | 40.0 | 6345 | 2.6641 | 0.6115 |
|
| 99 |
+
| 0.171 | 40.9961 | 6503 | 2.7048 | 0.6091 |
|
| 100 |
+
| 0.1682 | 41.9984 | 6662 | 2.7567 | 0.6098 |
|
| 101 |
+
| 0.1681 | 42.9945 | 6820 | 2.7031 | 0.6077 |
|
| 102 |
+
| 0.1701 | 43.9968 | 6979 | 2.6729 | 0.6117 |
|
| 103 |
+
| 0.1666 | 44.9992 | 7138 | 2.7432 | 0.6066 |
|
| 104 |
+
| 0.1678 | 45.9953 | 7296 | 2.7227 | 0.6152 |
|
| 105 |
+
| 0.1649 | 46.9976 | 7455 | 2.7663 | 0.6090 |
|
| 106 |
+
| 0.1684 | 48.0 | 7614 | 2.6653 | 0.6155 |
|
| 107 |
+
| 0.1625 | 48.9961 | 7772 | 2.7707 | 0.6050 |
|
| 108 |
+
| 0.1654 | 49.8030 | 7900 | 2.7159 | 0.6085 |
|
| 109 |
+
|
| 110 |
+
|
| 111 |
+
### Framework versions
|
| 112 |
+
|
| 113 |
+
- PEFT 0.5.0
|
| 114 |
+
- Transformers 4.40.2
|
| 115 |
+
- Pytorch 2.3.0
|
| 116 |
+
- Datasets 2.19.1
|
| 117 |
+
- Tokenizers 0.19.1
|