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_qaonly_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_qaonly_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: 3.3449
|
| 22 |
+
- Accuracy: 0.5876
|
| 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 |
+
| No log | 0.9916 | 74 | 1.6290 | 0.6255 |
|
| 60 |
+
| 1.924 | 1.9966 | 149 | 1.6617 | 0.6233 |
|
| 61 |
+
| 1.4922 | 2.9883 | 223 | 1.6980 | 0.6205 |
|
| 62 |
+
| 1.4922 | 3.9933 | 298 | 1.7298 | 0.6192 |
|
| 63 |
+
| 1.4068 | 4.9983 | 373 | 1.7481 | 0.6196 |
|
| 64 |
+
| 1.2983 | 5.9899 | 447 | 1.8004 | 0.6162 |
|
| 65 |
+
| 1.185 | 6.9950 | 522 | 1.8513 | 0.6133 |
|
| 66 |
+
| 1.185 | 8.0 | 597 | 1.9491 | 0.6078 |
|
| 67 |
+
| 1.0272 | 8.9916 | 671 | 2.0439 | 0.6047 |
|
| 68 |
+
| 0.837 | 9.9966 | 746 | 2.0819 | 0.6030 |
|
| 69 |
+
| 0.6959 | 10.9883 | 820 | 2.2470 | 0.5975 |
|
| 70 |
+
| 0.6959 | 11.9933 | 895 | 2.3402 | 0.5950 |
|
| 71 |
+
| 0.5675 | 12.9983 | 970 | 2.4646 | 0.5927 |
|
| 72 |
+
| 0.4565 | 13.9899 | 1044 | 2.5360 | 0.5919 |
|
| 73 |
+
| 0.4075 | 14.9950 | 1119 | 2.6063 | 0.5919 |
|
| 74 |
+
| 0.4075 | 16.0 | 1194 | 2.6696 | 0.5902 |
|
| 75 |
+
| 0.371 | 16.9916 | 1268 | 2.7577 | 0.5906 |
|
| 76 |
+
| 0.3443 | 17.9966 | 1343 | 2.8044 | 0.5889 |
|
| 77 |
+
| 0.3357 | 18.9883 | 1417 | 2.7873 | 0.5904 |
|
| 78 |
+
| 0.3357 | 19.9933 | 1492 | 2.7809 | 0.5918 |
|
| 79 |
+
| 0.3235 | 20.9983 | 1567 | 2.8768 | 0.5891 |
|
| 80 |
+
| 0.3152 | 21.9899 | 1641 | 2.8592 | 0.5899 |
|
| 81 |
+
| 0.3142 | 22.9950 | 1716 | 2.8668 | 0.5921 |
|
| 82 |
+
| 0.3142 | 24.0 | 1791 | 2.9501 | 0.5910 |
|
| 83 |
+
| 0.3092 | 24.9916 | 1865 | 2.9203 | 0.5912 |
|
| 84 |
+
| 0.3032 | 25.9966 | 1940 | 2.9752 | 0.5924 |
|
| 85 |
+
| 0.3044 | 26.9883 | 2014 | 2.9303 | 0.5905 |
|
| 86 |
+
| 0.3044 | 27.9933 | 2089 | 2.9913 | 0.5915 |
|
| 87 |
+
| 0.2998 | 28.9983 | 2164 | 2.9710 | 0.5901 |
|
| 88 |
+
| 0.2958 | 29.9899 | 2238 | 3.0960 | 0.5935 |
|
| 89 |
+
| 0.2977 | 30.9950 | 2313 | 2.9996 | 0.592 |
|
| 90 |
+
| 0.2977 | 32.0 | 2388 | 3.0486 | 0.5914 |
|
| 91 |
+
| 0.2935 | 32.9916 | 2462 | 3.0225 | 0.5911 |
|
| 92 |
+
| 0.2931 | 33.9966 | 2537 | 2.9860 | 0.5912 |
|
| 93 |
+
| 0.293 | 34.9883 | 2611 | 3.0856 | 0.5903 |
|
| 94 |
+
| 0.293 | 35.9933 | 2686 | 3.0234 | 0.5893 |
|
| 95 |
+
| 0.2909 | 36.9983 | 2761 | 3.0614 | 0.5922 |
|
| 96 |
+
| 0.2879 | 37.9899 | 2835 | 3.0555 | 0.5918 |
|
| 97 |
+
| 0.2906 | 38.9950 | 2910 | 3.1130 | 0.5921 |
|
| 98 |
+
| 0.2906 | 40.0 | 2985 | 3.1067 | 0.5913 |
|
| 99 |
+
| 0.2865 | 40.9916 | 3059 | 3.1949 | 0.5905 |
|
| 100 |
+
| 0.2857 | 41.9966 | 3134 | 3.1127 | 0.5913 |
|
| 101 |
+
| 0.2879 | 42.9883 | 3208 | 3.1623 | 0.5907 |
|
| 102 |
+
| 0.2879 | 43.9933 | 3283 | 3.1368 | 0.5901 |
|
| 103 |
+
| 0.2844 | 44.9983 | 3358 | 3.1650 | 0.5898 |
|
| 104 |
+
| 0.2838 | 45.9899 | 3432 | 3.2152 | 0.5893 |
|
| 105 |
+
| 0.2851 | 46.9950 | 3507 | 3.1605 | 0.5906 |
|
| 106 |
+
| 0.2851 | 48.0 | 3582 | 3.1204 | 0.5917 |
|
| 107 |
+
| 0.282 | 48.9916 | 3656 | 3.1551 | 0.5883 |
|
| 108 |
+
| 0.2812 | 49.5812 | 3700 | 3.3449 | 0.5876 |
|
| 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
|