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: find_marker_both_sent_train_400_eval_40_first_permute_Qwen_Qwen1.5-4B_3e-4_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 |
+
# find_marker_both_sent_train_400_eval_40_first_permute_Qwen_Qwen1.5-4B_3e-4_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: 0.3150
|
| 22 |
+
- Accuracy: 0.7659
|
| 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: 0.0003
|
| 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 |
+
| 1.5824 | 0.9933 | 130 | 1.1797 | 0.6851 |
|
| 60 |
+
| 0.7977 | 1.9943 | 261 | 0.5359 | 0.7429 |
|
| 61 |
+
| 0.3387 | 2.9952 | 392 | 0.3361 | 0.7614 |
|
| 62 |
+
| 0.1537 | 3.9962 | 523 | 0.2855 | 0.7653 |
|
| 63 |
+
| 0.1389 | 4.9971 | 654 | 0.2712 | 0.7666 |
|
| 64 |
+
| 0.1383 | 5.9981 | 785 | 0.2502 | 0.7676 |
|
| 65 |
+
| 0.1252 | 6.9990 | 916 | 0.2457 | 0.7684 |
|
| 66 |
+
| 0.122 | 8.0 | 1047 | 0.2310 | 0.7694 |
|
| 67 |
+
| 0.1169 | 8.9933 | 1177 | 0.2316 | 0.7689 |
|
| 68 |
+
| 0.1167 | 9.9943 | 1308 | 0.2311 | 0.7699 |
|
| 69 |
+
| 0.1161 | 10.9952 | 1439 | 0.2159 | 0.7708 |
|
| 70 |
+
| 0.1126 | 11.9962 | 1570 | 0.2188 | 0.7694 |
|
| 71 |
+
| 0.1088 | 12.9971 | 1701 | 0.2270 | 0.7661 |
|
| 72 |
+
| 0.1104 | 13.9981 | 1832 | 0.2181 | 0.7677 |
|
| 73 |
+
| 0.1076 | 14.9990 | 1963 | 0.2135 | 0.7680 |
|
| 74 |
+
| 0.1069 | 16.0 | 2094 | 0.2219 | 0.7670 |
|
| 75 |
+
| 0.1048 | 16.9933 | 2224 | 0.2298 | 0.7668 |
|
| 76 |
+
| 0.1044 | 17.9943 | 2355 | 0.2341 | 0.7666 |
|
| 77 |
+
| 0.1061 | 18.9952 | 2486 | 0.2628 | 0.7660 |
|
| 78 |
+
| 0.1104 | 19.9962 | 2617 | 0.2712 | 0.7651 |
|
| 79 |
+
| 0.1111 | 20.9971 | 2748 | 0.2921 | 0.7652 |
|
| 80 |
+
| 0.1102 | 21.9981 | 2879 | 0.2700 | 0.7660 |
|
| 81 |
+
| 0.1049 | 22.9990 | 3010 | 0.2905 | 0.7662 |
|
| 82 |
+
| 0.1024 | 24.0 | 3141 | 0.2852 | 0.7664 |
|
| 83 |
+
| 0.1079 | 24.9933 | 3271 | 0.2418 | 0.7653 |
|
| 84 |
+
| 0.1066 | 25.9943 | 3402 | 0.2759 | 0.7662 |
|
| 85 |
+
| 0.1054 | 26.9952 | 3533 | 0.2958 | 0.7656 |
|
| 86 |
+
| 0.105 | 27.9962 | 3664 | 0.3109 | 0.7663 |
|
| 87 |
+
| 0.1066 | 28.9971 | 3795 | 0.3062 | 0.7660 |
|
| 88 |
+
| 0.1048 | 29.9981 | 3926 | 0.2714 | 0.7660 |
|
| 89 |
+
| 0.1043 | 30.9990 | 4057 | 0.2821 | 0.7662 |
|
| 90 |
+
| 0.1039 | 32.0 | 4188 | 0.2961 | 0.7661 |
|
| 91 |
+
| 0.1055 | 32.9933 | 4318 | 0.2942 | 0.7662 |
|
| 92 |
+
| 0.1045 | 33.9943 | 4449 | 0.3152 | 0.7659 |
|
| 93 |
+
| 0.1045 | 34.9952 | 4580 | 0.2828 | 0.7666 |
|
| 94 |
+
| 0.1038 | 35.9962 | 4711 | 0.2355 | 0.7662 |
|
| 95 |
+
| 0.102 | 36.9971 | 4842 | 0.2926 | 0.7664 |
|
| 96 |
+
| 0.103 | 37.9981 | 4973 | 0.2825 | 0.7660 |
|
| 97 |
+
| 0.1061 | 38.9990 | 5104 | 0.2899 | 0.7663 |
|
| 98 |
+
| 0.1064 | 40.0 | 5235 | 0.2930 | 0.7660 |
|
| 99 |
+
| 0.105 | 40.9933 | 5365 | 0.2806 | 0.7657 |
|
| 100 |
+
| 0.1038 | 41.9943 | 5496 | 0.2973 | 0.7664 |
|
| 101 |
+
| 0.1016 | 42.9952 | 5627 | 0.3379 | 0.7662 |
|
| 102 |
+
| 0.1046 | 43.9962 | 5758 | 0.3200 | 0.7655 |
|
| 103 |
+
| 0.1039 | 44.9971 | 5889 | 0.3151 | 0.7652 |
|
| 104 |
+
| 0.107 | 45.9981 | 6020 | 0.2969 | 0.7658 |
|
| 105 |
+
| 0.1059 | 46.9990 | 6151 | 0.3146 | 0.7659 |
|
| 106 |
+
| 0.1058 | 48.0 | 6282 | 0.3070 | 0.7656 |
|
| 107 |
+
| 0.103 | 48.9933 | 6412 | 0.3060 | 0.7660 |
|
| 108 |
+
| 0.1012 | 49.6657 | 6500 | 0.3150 | 0.7659 |
|
| 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
|