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_random_permute_rerun_4_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_random_permute_rerun_4_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: 0.3920
|
| 22 |
+
- Accuracy: 0.7643
|
| 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 |
+
| 1.6149 | 0.9968 | 117 | 1.2999 | 0.6755 |
|
| 60 |
+
| 0.862 | 1.9936 | 234 | 0.6614 | 0.7318 |
|
| 61 |
+
| 0.3519 | 2.9989 | 352 | 0.3529 | 0.7612 |
|
| 62 |
+
| 0.2097 | 3.9957 | 469 | 0.3055 | 0.7604 |
|
| 63 |
+
| 0.1746 | 4.9925 | 586 | 0.2799 | 0.7659 |
|
| 64 |
+
| 0.1507 | 5.9979 | 704 | 0.2721 | 0.7651 |
|
| 65 |
+
| 0.1431 | 6.9947 | 821 | 0.2592 | 0.7674 |
|
| 66 |
+
| 0.1381 | 8.0 | 939 | 0.2589 | 0.7667 |
|
| 67 |
+
| 0.1337 | 8.9968 | 1056 | 0.2509 | 0.7679 |
|
| 68 |
+
| 0.1292 | 9.9936 | 1173 | 0.2452 | 0.7682 |
|
| 69 |
+
| 0.1232 | 10.9989 | 1291 | 0.2604 | 0.7656 |
|
| 70 |
+
| 0.1214 | 11.9957 | 1408 | 0.2679 | 0.7653 |
|
| 71 |
+
| 0.119 | 12.9925 | 1525 | 0.2421 | 0.7681 |
|
| 72 |
+
| 0.1165 | 13.9979 | 1643 | 0.2545 | 0.7654 |
|
| 73 |
+
| 0.1161 | 14.9947 | 1760 | 0.2666 | 0.7630 |
|
| 74 |
+
| 0.1193 | 16.0 | 1878 | 0.2661 | 0.7645 |
|
| 75 |
+
| 0.1264 | 16.9968 | 1995 | 0.2994 | 0.7626 |
|
| 76 |
+
| 0.1201 | 17.9936 | 2112 | 0.2607 | 0.7647 |
|
| 77 |
+
| 0.1144 | 18.9989 | 2230 | 0.2665 | 0.7655 |
|
| 78 |
+
| 0.1147 | 19.9957 | 2347 | 0.2606 | 0.7646 |
|
| 79 |
+
| 0.1143 | 20.9925 | 2464 | 0.2834 | 0.7645 |
|
| 80 |
+
| 0.1105 | 21.9979 | 2582 | 0.2843 | 0.7645 |
|
| 81 |
+
| 0.1103 | 22.9947 | 2699 | 0.2959 | 0.7639 |
|
| 82 |
+
| 0.1081 | 24.0 | 2817 | 0.3331 | 0.7640 |
|
| 83 |
+
| 0.1093 | 24.9968 | 2934 | 0.3566 | 0.7640 |
|
| 84 |
+
| 0.1086 | 25.9936 | 3051 | 0.2995 | 0.7630 |
|
| 85 |
+
| 0.1124 | 26.9989 | 3169 | 0.2889 | 0.7624 |
|
| 86 |
+
| 0.1169 | 27.9957 | 3286 | 0.3392 | 0.7630 |
|
| 87 |
+
| 0.1225 | 28.9925 | 3403 | 0.2916 | 0.7633 |
|
| 88 |
+
| 0.1179 | 29.9979 | 3521 | 0.2572 | 0.7645 |
|
| 89 |
+
| 0.1139 | 30.9947 | 3638 | 0.3382 | 0.7635 |
|
| 90 |
+
| 0.1141 | 32.0 | 3756 | 0.3028 | 0.7635 |
|
| 91 |
+
| 0.1119 | 32.9968 | 3873 | 0.3388 | 0.7637 |
|
| 92 |
+
| 0.1124 | 33.9936 | 3990 | 0.3304 | 0.7636 |
|
| 93 |
+
| 0.1089 | 34.9989 | 4108 | 0.3556 | 0.7641 |
|
| 94 |
+
| 0.1095 | 35.9957 | 4225 | 0.3314 | 0.7641 |
|
| 95 |
+
| 0.1082 | 36.9925 | 4342 | 0.3770 | 0.7640 |
|
| 96 |
+
| 0.1071 | 37.9979 | 4460 | 0.3392 | 0.7645 |
|
| 97 |
+
| 0.1076 | 38.9947 | 4577 | 0.3363 | 0.7640 |
|
| 98 |
+
| 0.1074 | 40.0 | 4695 | 0.3731 | 0.7629 |
|
| 99 |
+
| 0.1289 | 40.9968 | 4812 | 0.3028 | 0.7634 |
|
| 100 |
+
| 0.1264 | 41.9936 | 4929 | 0.3093 | 0.7639 |
|
| 101 |
+
| 0.1126 | 42.9989 | 5047 | 0.3074 | 0.7643 |
|
| 102 |
+
| 0.1122 | 43.9957 | 5164 | 0.3375 | 0.7646 |
|
| 103 |
+
| 0.1096 | 44.9925 | 5281 | 0.3388 | 0.7645 |
|
| 104 |
+
| 0.1077 | 45.9979 | 5399 | 0.3173 | 0.7644 |
|
| 105 |
+
| 0.1063 | 46.9947 | 5516 | 0.3343 | 0.7643 |
|
| 106 |
+
| 0.1086 | 48.0 | 5634 | 0.3137 | 0.7644 |
|
| 107 |
+
| 0.1052 | 48.9968 | 5751 | 0.3941 | 0.7645 |
|
| 108 |
+
| 0.1078 | 49.8403 | 5850 | 0.3920 | 0.7643 |
|
| 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
|