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_baseline_v5_full_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_baseline_v5_full_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: 3.8632
|
| 22 |
+
- Accuracy: 0.5660
|
| 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 | 2.0550 | 0.5952 |
|
| 60 |
+
| 2.3403 | 1.9966 | 149 | 2.0411 | 0.5933 |
|
| 61 |
+
| 2.0198 | 2.9883 | 223 | 2.0403 | 0.5932 |
|
| 62 |
+
| 2.0198 | 3.9933 | 298 | 2.0647 | 0.5922 |
|
| 63 |
+
| 1.9239 | 4.9983 | 373 | 2.0999 | 0.5921 |
|
| 64 |
+
| 1.7309 | 5.9899 | 447 | 2.1973 | 0.5879 |
|
| 65 |
+
| 1.5254 | 6.9950 | 522 | 2.2753 | 0.5861 |
|
| 66 |
+
| 1.5254 | 8.0 | 597 | 2.4079 | 0.5819 |
|
| 67 |
+
| 1.2937 | 8.9916 | 671 | 2.5096 | 0.5775 |
|
| 68 |
+
| 1.0409 | 9.9966 | 746 | 2.6079 | 0.5739 |
|
| 69 |
+
| 0.8766 | 10.9883 | 820 | 2.7579 | 0.5718 |
|
| 70 |
+
| 0.8766 | 11.9933 | 895 | 2.8722 | 0.5688 |
|
| 71 |
+
| 0.721 | 12.9983 | 970 | 2.9797 | 0.5672 |
|
| 72 |
+
| 0.6011 | 13.9899 | 1044 | 3.0708 | 0.5662 |
|
| 73 |
+
| 0.5455 | 14.9950 | 1119 | 3.1660 | 0.5648 |
|
| 74 |
+
| 0.5455 | 16.0 | 1194 | 3.2479 | 0.5650 |
|
| 75 |
+
| 0.5003 | 16.9916 | 1268 | 3.2445 | 0.5655 |
|
| 76 |
+
| 0.4683 | 17.9966 | 1343 | 3.2800 | 0.5638 |
|
| 77 |
+
| 0.457 | 18.9883 | 1417 | 3.4280 | 0.5640 |
|
| 78 |
+
| 0.457 | 19.9933 | 1492 | 3.4113 | 0.5662 |
|
| 79 |
+
| 0.4441 | 20.9983 | 1567 | 3.4731 | 0.5637 |
|
| 80 |
+
| 0.4327 | 21.9899 | 1641 | 3.5407 | 0.5639 |
|
| 81 |
+
| 0.4308 | 22.9950 | 1716 | 3.4811 | 0.5640 |
|
| 82 |
+
| 0.4308 | 24.0 | 1791 | 3.5854 | 0.5642 |
|
| 83 |
+
| 0.4245 | 24.9916 | 1865 | 3.5206 | 0.5640 |
|
| 84 |
+
| 0.416 | 25.9966 | 1940 | 3.6091 | 0.5638 |
|
| 85 |
+
| 0.4173 | 26.9883 | 2014 | 3.5707 | 0.5643 |
|
| 86 |
+
| 0.4173 | 27.9933 | 2089 | 3.6671 | 0.5648 |
|
| 87 |
+
| 0.4117 | 28.9983 | 2164 | 3.6267 | 0.5631 |
|
| 88 |
+
| 0.409 | 29.9899 | 2238 | 3.6658 | 0.5604 |
|
| 89 |
+
| 0.4085 | 30.9950 | 2313 | 3.6984 | 0.5621 |
|
| 90 |
+
| 0.4085 | 32.0 | 2388 | 3.6584 | 0.5660 |
|
| 91 |
+
| 0.403 | 32.9916 | 2462 | 3.5848 | 0.5626 |
|
| 92 |
+
| 0.404 | 33.9966 | 2537 | 3.6365 | 0.5631 |
|
| 93 |
+
| 0.4013 | 34.9883 | 2611 | 3.7047 | 0.5647 |
|
| 94 |
+
| 0.4013 | 35.9933 | 2686 | 3.7735 | 0.5643 |
|
| 95 |
+
| 0.3987 | 36.9983 | 2761 | 3.6867 | 0.5657 |
|
| 96 |
+
| 0.3951 | 37.9899 | 2835 | 3.7349 | 0.5662 |
|
| 97 |
+
| 0.3971 | 38.9950 | 2910 | 3.7173 | 0.5643 |
|
| 98 |
+
| 0.3971 | 40.0 | 2985 | 3.8004 | 0.5643 |
|
| 99 |
+
| 0.3939 | 40.9916 | 3059 | 3.8041 | 0.5636 |
|
| 100 |
+
| 0.3912 | 41.9966 | 3134 | 3.8263 | 0.5648 |
|
| 101 |
+
| 0.3941 | 42.9883 | 3208 | 3.7954 | 0.5646 |
|
| 102 |
+
| 0.3941 | 43.9933 | 3283 | 3.8001 | 0.5637 |
|
| 103 |
+
| 0.3878 | 44.9983 | 3358 | 3.8438 | 0.5634 |
|
| 104 |
+
| 0.3879 | 45.9899 | 3432 | 3.8626 | 0.5631 |
|
| 105 |
+
| 0.3907 | 46.9950 | 3507 | 3.7882 | 0.5645 |
|
| 106 |
+
| 0.3907 | 48.0 | 3582 | 3.8001 | 0.5622 |
|
| 107 |
+
| 0.3864 | 48.9916 | 3656 | 3.7201 | 0.5609 |
|
| 108 |
+
| 0.3871 | 49.5812 | 3700 | 3.8632 | 0.5660 |
|
| 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
|