resume-bert
Browse files- README.md +156 -82
- config.json +45 -3
- model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# TTC4900Model
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- F1: 0.
|
| 26 |
-
- Precision: 0.
|
| 27 |
-
- Recall: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -44,8 +44,8 @@ More information needed
|
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
- learning_rate: 5e-05
|
| 47 |
-
- train_batch_size:
|
| 48 |
-
- eval_batch_size:
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
|
@@ -57,79 +57,153 @@ The following hyperparameters were used during training:
|
|
| 57 |
|
| 58 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 59 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
| 66 |
-
|
|
| 67 |
-
|
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
|
| 134 |
|
| 135 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: t5-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
|
|
|
| 18 |
|
| 19 |
# TTC4900Model
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.5626
|
| 24 |
+
- Accuracy: 0.8360
|
| 25 |
+
- F1: 0.7230
|
| 26 |
+
- Precision: 0.7553
|
| 27 |
+
- Recall: 0.7035
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 44 |
|
| 45 |
The following hyperparameters were used during training:
|
| 46 |
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 32
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
|
|
|
| 57 |
|
| 58 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 59 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 60 |
+
| 1.5247 | 0.02 | 50 | 1.3656 | 0.5365 | 0.1841 | 0.1839 | 0.2054 |
|
| 61 |
+
| 1.3764 | 0.04 | 100 | 1.2543 | 0.5539 | 0.2163 | 0.2377 | 0.2461 |
|
| 62 |
+
| 1.3046 | 0.06 | 150 | 1.5517 | 0.4440 | 0.2151 | 0.2231 | 0.2624 |
|
| 63 |
+
| 1.2523 | 0.08 | 200 | 1.2396 | 0.5535 | 0.2195 | 0.4997 | 0.2627 |
|
| 64 |
+
| 1.1098 | 0.1 | 250 | 1.0067 | 0.6573 | 0.3306 | 0.5386 | 0.3212 |
|
| 65 |
+
| 1.0741 | 0.12 | 300 | 1.0024 | 0.6414 | 0.3577 | 0.5714 | 0.3656 |
|
| 66 |
+
| 1.0024 | 0.14 | 350 | 0.9799 | 0.7002 | 0.4266 | 0.5953 | 0.4209 |
|
| 67 |
+
| 1.0388 | 0.16 | 400 | 0.9474 | 0.7050 | 0.4228 | 0.5023 | 0.4189 |
|
| 68 |
+
| 0.9636 | 0.18 | 450 | 0.8516 | 0.7154 | 0.4555 | 0.5558 | 0.4595 |
|
| 69 |
+
| 0.9631 | 0.2 | 500 | 0.8184 | 0.7273 | 0.4893 | 0.6215 | 0.4590 |
|
| 70 |
+
| 0.8994 | 0.22 | 550 | 0.8795 | 0.7371 | 0.5013 | 0.6266 | 0.4755 |
|
| 71 |
+
| 0.9249 | 0.24 | 600 | 0.8099 | 0.7503 | 0.5343 | 0.6028 | 0.5132 |
|
| 72 |
+
| 0.8182 | 0.26 | 650 | 0.7670 | 0.7454 | 0.5381 | 0.5897 | 0.5362 |
|
| 73 |
+
| 0.8872 | 0.28 | 700 | 0.7848 | 0.7471 | 0.5722 | 0.6469 | 0.5761 |
|
| 74 |
+
| 0.8227 | 0.31 | 750 | 0.8970 | 0.7366 | 0.5019 | 0.6595 | 0.4832 |
|
| 75 |
+
| 0.7964 | 0.33 | 800 | 0.7660 | 0.7523 | 0.5409 | 0.5435 | 0.5837 |
|
| 76 |
+
| 0.7897 | 0.35 | 850 | 0.9406 | 0.7072 | 0.5390 | 0.6241 | 0.5189 |
|
| 77 |
+
| 0.8045 | 0.37 | 900 | 0.8252 | 0.7215 | 0.4806 | 0.6539 | 0.4352 |
|
| 78 |
+
| 0.7349 | 0.39 | 950 | 0.7106 | 0.7828 | 0.6034 | 0.6272 | 0.5884 |
|
| 79 |
+
| 0.7794 | 0.41 | 1000 | 0.6791 | 0.7837 | 0.5893 | 0.6250 | 0.5803 |
|
| 80 |
+
| 0.7159 | 0.43 | 1050 | 0.6934 | 0.7842 | 0.5837 | 0.6654 | 0.5587 |
|
| 81 |
+
| 0.7128 | 0.45 | 1100 | 0.7069 | 0.7843 | 0.6076 | 0.6533 | 0.5776 |
|
| 82 |
+
| 0.7849 | 0.47 | 1150 | 0.7099 | 0.7620 | 0.5944 | 0.7678 | 0.5965 |
|
| 83 |
+
| 0.741 | 0.49 | 1200 | 0.7663 | 0.7478 | 0.5749 | 0.7549 | 0.5704 |
|
| 84 |
+
| 0.6905 | 0.51 | 1250 | 0.6842 | 0.7925 | 0.6148 | 0.6396 | 0.6041 |
|
| 85 |
+
| 0.7195 | 0.53 | 1300 | 0.7248 | 0.7720 | 0.5769 | 0.7638 | 0.5497 |
|
| 86 |
+
| 0.7394 | 0.55 | 1350 | 0.6870 | 0.7911 | 0.6002 | 0.6628 | 0.5739 |
|
| 87 |
+
| 0.6696 | 0.57 | 1400 | 0.6674 | 0.7987 | 0.6290 | 0.6450 | 0.6199 |
|
| 88 |
+
| 0.7133 | 0.59 | 1450 | 0.6785 | 0.7938 | 0.6141 | 0.6470 | 0.6134 |
|
| 89 |
+
| 0.6743 | 0.61 | 1500 | 0.6901 | 0.7965 | 0.6184 | 0.8136 | 0.5925 |
|
| 90 |
+
| 0.684 | 0.63 | 1550 | 0.6921 | 0.7957 | 0.6297 | 0.6979 | 0.6063 |
|
| 91 |
+
| 0.6555 | 0.65 | 1600 | 0.7061 | 0.7790 | 0.6010 | 0.6025 | 0.6244 |
|
| 92 |
+
| 0.6188 | 0.67 | 1650 | 0.7503 | 0.7781 | 0.5902 | 0.8093 | 0.5338 |
|
| 93 |
+
| 0.7457 | 0.69 | 1700 | 0.6710 | 0.7978 | 0.6026 | 0.6432 | 0.6066 |
|
| 94 |
+
| 0.7393 | 0.71 | 1750 | 0.6759 | 0.7930 | 0.6339 | 0.7666 | 0.6475 |
|
| 95 |
+
| 0.7628 | 0.73 | 1800 | 0.6377 | 0.8089 | 0.6456 | 0.6942 | 0.6522 |
|
| 96 |
+
| 0.735 | 0.75 | 1850 | 0.7434 | 0.7930 | 0.6283 | 0.6680 | 0.6121 |
|
| 97 |
+
| 0.7296 | 0.77 | 1900 | 0.6502 | 0.8126 | 0.6487 | 0.7385 | 0.6379 |
|
| 98 |
+
| 0.6928 | 0.79 | 1950 | 0.6253 | 0.8136 | 0.6511 | 0.7353 | 0.6320 |
|
| 99 |
+
| 0.6352 | 0.81 | 2000 | 0.6476 | 0.8059 | 0.6374 | 0.8051 | 0.6263 |
|
| 100 |
+
| 0.6468 | 0.83 | 2050 | 0.6562 | 0.8032 | 0.6314 | 0.7535 | 0.6204 |
|
| 101 |
+
| 0.7292 | 0.85 | 2100 | 0.6385 | 0.7957 | 0.5927 | 0.6855 | 0.5790 |
|
| 102 |
+
| 0.6161 | 0.87 | 2150 | 0.6428 | 0.8056 | 0.6205 | 0.6775 | 0.6026 |
|
| 103 |
+
| 0.6515 | 0.89 | 2200 | 0.6184 | 0.8162 | 0.6405 | 0.6590 | 0.6361 |
|
| 104 |
+
| 0.6213 | 0.92 | 2250 | 0.6490 | 0.8047 | 0.6320 | 0.6843 | 0.6086 |
|
| 105 |
+
| 0.6625 | 0.94 | 2300 | 0.7454 | 0.7734 | 0.5984 | 0.6586 | 0.6370 |
|
| 106 |
+
| 0.698 | 0.96 | 2350 | 0.7369 | 0.7873 | 0.6150 | 0.7827 | 0.5866 |
|
| 107 |
+
| 0.6565 | 0.98 | 2400 | 0.6749 | 0.7957 | 0.6368 | 0.7346 | 0.6125 |
|
| 108 |
+
| 0.7032 | 1.0 | 2450 | 0.6655 | 0.8008 | 0.6351 | 0.6600 | 0.6236 |
|
| 109 |
+
| 0.5442 | 1.02 | 2500 | 0.6429 | 0.8187 | 0.6571 | 0.7666 | 0.6432 |
|
| 110 |
+
| 0.6461 | 1.04 | 2550 | 0.6369 | 0.8037 | 0.6342 | 0.7544 | 0.6066 |
|
| 111 |
+
| 0.5382 | 1.06 | 2600 | 0.6912 | 0.8069 | 0.6448 | 0.6517 | 0.6407 |
|
| 112 |
+
| 0.5253 | 1.08 | 2650 | 0.7129 | 0.8041 | 0.6166 | 0.8399 | 0.5795 |
|
| 113 |
+
| 0.5729 | 1.1 | 2700 | 0.7291 | 0.7814 | 0.6351 | 0.6685 | 0.6547 |
|
| 114 |
+
| 0.6183 | 1.12 | 2750 | 0.6339 | 0.8145 | 0.6687 | 0.7169 | 0.6531 |
|
| 115 |
+
| 0.5461 | 1.14 | 2800 | 0.6108 | 0.8176 | 0.6838 | 0.7399 | 0.6695 |
|
| 116 |
+
| 0.5827 | 1.16 | 2850 | 0.6113 | 0.8182 | 0.6759 | 0.7503 | 0.6471 |
|
| 117 |
+
| 0.5903 | 1.18 | 2900 | 0.6881 | 0.8022 | 0.6551 | 0.7410 | 0.6453 |
|
| 118 |
+
| 0.5672 | 1.2 | 2950 | 0.5965 | 0.8214 | 0.6741 | 0.7804 | 0.6591 |
|
| 119 |
+
| 0.543 | 1.22 | 3000 | 0.6554 | 0.8164 | 0.6557 | 0.7584 | 0.6656 |
|
| 120 |
+
| 0.6311 | 1.24 | 3050 | 0.6137 | 0.8219 | 0.6840 | 0.7789 | 0.6486 |
|
| 121 |
+
| 0.661 | 1.26 | 3100 | 0.6244 | 0.8184 | 0.6805 | 0.7788 | 0.6517 |
|
| 122 |
+
| 0.5055 | 1.28 | 3150 | 0.6356 | 0.8145 | 0.6768 | 0.7629 | 0.6542 |
|
| 123 |
+
| 0.4951 | 1.3 | 3200 | 0.6167 | 0.8175 | 0.6770 | 0.7676 | 0.6644 |
|
| 124 |
+
| 0.5633 | 1.32 | 3250 | 0.6051 | 0.8232 | 0.6655 | 0.7882 | 0.6432 |
|
| 125 |
+
| 0.551 | 1.34 | 3300 | 0.6193 | 0.8211 | 0.6860 | 0.7320 | 0.6629 |
|
| 126 |
+
| 0.5962 | 1.36 | 3350 | 0.6165 | 0.8087 | 0.6533 | 0.7449 | 0.6251 |
|
| 127 |
+
| 0.5257 | 1.38 | 3400 | 0.5966 | 0.8193 | 0.6935 | 0.7627 | 0.6739 |
|
| 128 |
+
| 0.5366 | 1.4 | 3450 | 0.6110 | 0.8198 | 0.6911 | 0.7669 | 0.6519 |
|
| 129 |
+
| 0.5844 | 1.42 | 3500 | 0.6151 | 0.8223 | 0.6760 | 0.7847 | 0.6455 |
|
| 130 |
+
| 0.5652 | 1.44 | 3550 | 0.5907 | 0.8252 | 0.6723 | 0.7723 | 0.6646 |
|
| 131 |
+
| 0.5488 | 1.46 | 3600 | 0.6074 | 0.8268 | 0.7047 | 0.7835 | 0.6759 |
|
| 132 |
+
| 0.5235 | 1.48 | 3650 | 0.6133 | 0.8142 | 0.6850 | 0.7856 | 0.6568 |
|
| 133 |
+
| 0.5418 | 1.5 | 3700 | 0.6413 | 0.8215 | 0.6872 | 0.7915 | 0.6452 |
|
| 134 |
+
| 0.5564 | 1.53 | 3750 | 0.5809 | 0.8286 | 0.7049 | 0.7748 | 0.6855 |
|
| 135 |
+
| 0.5976 | 1.55 | 3800 | 0.5913 | 0.8244 | 0.6979 | 0.7594 | 0.6806 |
|
| 136 |
+
| 0.5032 | 1.57 | 3850 | 0.6211 | 0.8250 | 0.6663 | 0.7811 | 0.6485 |
|
| 137 |
+
| 0.535 | 1.59 | 3900 | 0.5805 | 0.8287 | 0.7001 | 0.7859 | 0.6694 |
|
| 138 |
+
| 0.5223 | 1.61 | 3950 | 0.6010 | 0.8189 | 0.6861 | 0.7607 | 0.6813 |
|
| 139 |
+
| 0.4967 | 1.63 | 4000 | 0.6011 | 0.8295 | 0.7019 | 0.7836 | 0.6717 |
|
| 140 |
+
| 0.507 | 1.65 | 4050 | 0.6121 | 0.8196 | 0.7075 | 0.7632 | 0.6866 |
|
| 141 |
+
| 0.585 | 1.67 | 4100 | 0.6019 | 0.8235 | 0.6669 | 0.7633 | 0.6364 |
|
| 142 |
+
| 0.5733 | 1.69 | 4150 | 0.5797 | 0.8302 | 0.6892 | 0.7955 | 0.6579 |
|
| 143 |
+
| 0.5482 | 1.71 | 4200 | 0.5895 | 0.8282 | 0.6960 | 0.7557 | 0.6862 |
|
| 144 |
+
| 0.5603 | 1.73 | 4250 | 0.5730 | 0.8270 | 0.7211 | 0.7751 | 0.6974 |
|
| 145 |
+
| 0.5017 | 1.75 | 4300 | 0.5956 | 0.8310 | 0.7061 | 0.7879 | 0.6721 |
|
| 146 |
+
| 0.5655 | 1.77 | 4350 | 0.5619 | 0.8326 | 0.7107 | 0.7976 | 0.6725 |
|
| 147 |
+
| 0.5659 | 1.79 | 4400 | 0.6281 | 0.8125 | 0.7087 | 0.7859 | 0.6691 |
|
| 148 |
+
| 0.5058 | 1.81 | 4450 | 0.5696 | 0.8307 | 0.7146 | 0.7723 | 0.6985 |
|
| 149 |
+
| 0.5106 | 1.83 | 4500 | 0.5951 | 0.8189 | 0.7095 | 0.7160 | 0.7131 |
|
| 150 |
+
| 0.5845 | 1.85 | 4550 | 0.5668 | 0.8336 | 0.7136 | 0.8014 | 0.6853 |
|
| 151 |
+
| 0.5256 | 1.87 | 4600 | 0.5658 | 0.8295 | 0.7087 | 0.7588 | 0.6973 |
|
| 152 |
+
| 0.5136 | 1.89 | 4650 | 0.5933 | 0.8300 | 0.6825 | 0.7629 | 0.6743 |
|
| 153 |
+
| 0.5515 | 1.91 | 4700 | 0.5753 | 0.8175 | 0.6839 | 0.8091 | 0.6319 |
|
| 154 |
+
| 0.5548 | 1.93 | 4750 | 0.5473 | 0.8346 | 0.7275 | 0.7792 | 0.6979 |
|
| 155 |
+
| 0.5377 | 1.95 | 4800 | 0.5725 | 0.8302 | 0.7307 | 0.7563 | 0.7166 |
|
| 156 |
+
| 0.5204 | 1.97 | 4850 | 0.5768 | 0.8288 | 0.6997 | 0.7873 | 0.6671 |
|
| 157 |
+
| 0.5688 | 1.99 | 4900 | 0.5480 | 0.8361 | 0.7244 | 0.8019 | 0.6887 |
|
| 158 |
+
| 0.4596 | 2.01 | 4950 | 0.6084 | 0.8298 | 0.7231 | 0.7653 | 0.7014 |
|
| 159 |
+
| 0.4357 | 2.03 | 5000 | 0.6180 | 0.8333 | 0.7251 | 0.7579 | 0.7046 |
|
| 160 |
+
| 0.4787 | 2.05 | 5050 | 0.5744 | 0.8293 | 0.7216 | 0.7789 | 0.6925 |
|
| 161 |
+
| 0.5183 | 2.07 | 5100 | 0.5747 | 0.8299 | 0.7263 | 0.7687 | 0.7092 |
|
| 162 |
+
| 0.532 | 2.09 | 5150 | 0.5626 | 0.8308 | 0.7150 | 0.7873 | 0.6920 |
|
| 163 |
+
| 0.4789 | 2.11 | 5200 | 0.5659 | 0.8308 | 0.7297 | 0.7603 | 0.7215 |
|
| 164 |
+
| 0.5121 | 2.14 | 5250 | 0.5739 | 0.8329 | 0.7229 | 0.7850 | 0.6880 |
|
| 165 |
+
| 0.4516 | 2.16 | 5300 | 0.5592 | 0.8376 | 0.7306 | 0.7966 | 0.6999 |
|
| 166 |
+
| 0.4789 | 2.18 | 5350 | 0.5679 | 0.8329 | 0.7232 | 0.7427 | 0.7122 |
|
| 167 |
+
| 0.4191 | 2.2 | 5400 | 0.5953 | 0.8282 | 0.7331 | 0.7701 | 0.7203 |
|
| 168 |
+
| 0.4519 | 2.22 | 5450 | 0.5779 | 0.8319 | 0.7233 | 0.7727 | 0.7047 |
|
| 169 |
+
| 0.4544 | 2.24 | 5500 | 0.5890 | 0.8330 | 0.7262 | 0.7535 | 0.7208 |
|
| 170 |
+
| 0.4191 | 2.26 | 5550 | 0.5872 | 0.8356 | 0.7307 | 0.7909 | 0.6951 |
|
| 171 |
+
| 0.459 | 2.28 | 5600 | 0.5952 | 0.8274 | 0.7241 | 0.7376 | 0.7178 |
|
| 172 |
+
| 0.4666 | 2.3 | 5650 | 0.5940 | 0.8310 | 0.7151 | 0.7634 | 0.7057 |
|
| 173 |
+
| 0.4608 | 2.32 | 5700 | 0.6021 | 0.8324 | 0.7202 | 0.7683 | 0.7026 |
|
| 174 |
+
| 0.4022 | 2.34 | 5750 | 0.5873 | 0.8346 | 0.7289 | 0.7705 | 0.7072 |
|
| 175 |
+
| 0.4588 | 2.36 | 5800 | 0.5611 | 0.8327 | 0.7271 | 0.7769 | 0.7070 |
|
| 176 |
+
| 0.3523 | 2.38 | 5850 | 0.5999 | 0.8370 | 0.7255 | 0.7761 | 0.7029 |
|
| 177 |
+
| 0.422 | 2.4 | 5900 | 0.5940 | 0.8367 | 0.7239 | 0.7769 | 0.7047 |
|
| 178 |
+
| 0.4827 | 2.42 | 5950 | 0.6002 | 0.8368 | 0.7194 | 0.7864 | 0.6945 |
|
| 179 |
+
| 0.4287 | 2.44 | 6000 | 0.5737 | 0.8380 | 0.7206 | 0.7678 | 0.7080 |
|
| 180 |
+
| 0.3921 | 2.46 | 6050 | 0.5859 | 0.8334 | 0.7258 | 0.7612 | 0.7166 |
|
| 181 |
+
| 0.4183 | 2.48 | 6100 | 0.5747 | 0.8400 | 0.7326 | 0.7756 | 0.7083 |
|
| 182 |
+
| 0.3758 | 2.5 | 6150 | 0.5781 | 0.8382 | 0.7276 | 0.7611 | 0.7126 |
|
| 183 |
+
| 0.4809 | 2.52 | 6200 | 0.5657 | 0.8383 | 0.7333 | 0.7778 | 0.7055 |
|
| 184 |
+
| 0.4405 | 2.54 | 6250 | 0.5809 | 0.8320 | 0.7345 | 0.7538 | 0.7242 |
|
| 185 |
+
| 0.3864 | 2.56 | 6300 | 0.5704 | 0.8393 | 0.7361 | 0.7742 | 0.7175 |
|
| 186 |
+
| 0.4576 | 2.58 | 6350 | 0.5602 | 0.8404 | 0.7353 | 0.7862 | 0.7098 |
|
| 187 |
+
| 0.4447 | 2.6 | 6400 | 0.5542 | 0.8391 | 0.7365 | 0.7695 | 0.7183 |
|
| 188 |
+
| 0.4523 | 2.62 | 6450 | 0.5484 | 0.8384 | 0.7396 | 0.7802 | 0.7149 |
|
| 189 |
+
| 0.456 | 2.64 | 6500 | 0.5608 | 0.8392 | 0.7351 | 0.7816 | 0.7123 |
|
| 190 |
+
| 0.4648 | 2.66 | 6550 | 0.5637 | 0.8394 | 0.7364 | 0.7808 | 0.7107 |
|
| 191 |
+
| 0.3735 | 2.68 | 6600 | 0.5752 | 0.8377 | 0.7385 | 0.7749 | 0.7213 |
|
| 192 |
+
| 0.4042 | 2.7 | 6650 | 0.5647 | 0.8361 | 0.7322 | 0.7790 | 0.7134 |
|
| 193 |
+
| 0.425 | 2.72 | 6700 | 0.5722 | 0.8380 | 0.7364 | 0.7829 | 0.7090 |
|
| 194 |
+
| 0.3668 | 2.75 | 6750 | 0.5900 | 0.8391 | 0.7363 | 0.7693 | 0.7204 |
|
| 195 |
+
| 0.4614 | 2.77 | 6800 | 0.5616 | 0.8396 | 0.7364 | 0.7779 | 0.7158 |
|
| 196 |
+
| 0.4351 | 2.79 | 6850 | 0.5634 | 0.8390 | 0.7359 | 0.7657 | 0.7220 |
|
| 197 |
+
| 0.4008 | 2.81 | 6900 | 0.5679 | 0.8388 | 0.7354 | 0.7716 | 0.7168 |
|
| 198 |
+
| 0.4538 | 2.83 | 6950 | 0.5610 | 0.8366 | 0.7425 | 0.7593 | 0.7350 |
|
| 199 |
+
| 0.3839 | 2.85 | 7000 | 0.5657 | 0.8404 | 0.7376 | 0.7820 | 0.7142 |
|
| 200 |
+
| 0.424 | 2.87 | 7050 | 0.5595 | 0.8395 | 0.7399 | 0.7754 | 0.7217 |
|
| 201 |
+
| 0.4125 | 2.89 | 7100 | 0.5581 | 0.8382 | 0.7411 | 0.7622 | 0.7301 |
|
| 202 |
+
| 0.3748 | 2.91 | 7150 | 0.5620 | 0.8388 | 0.7411 | 0.7660 | 0.7270 |
|
| 203 |
+
| 0.3782 | 2.93 | 7200 | 0.5601 | 0.8394 | 0.7421 | 0.7689 | 0.7266 |
|
| 204 |
+
| 0.4413 | 2.95 | 7250 | 0.5559 | 0.8396 | 0.7426 | 0.7680 | 0.7280 |
|
| 205 |
+
| 0.4182 | 2.97 | 7300 | 0.5530 | 0.8400 | 0.7429 | 0.7692 | 0.7274 |
|
| 206 |
+
| 0.4383 | 2.99 | 7350 | 0.5519 | 0.8405 | 0.7438 | 0.7715 | 0.7276 |
|
| 207 |
|
| 208 |
|
| 209 |
### Framework versions
|
config.json
CHANGED
|
@@ -1,11 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
|
@@ -18,8 +23,10 @@
|
|
| 18 |
"5": "Obj",
|
| 19 |
"6": "QC"
|
| 20 |
},
|
|
|
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"intermediate_size": 3072,
|
|
|
|
| 23 |
"label2id": {
|
| 24 |
"Edu": 4,
|
| 25 |
"Exp": 1,
|
|
@@ -30,16 +37,51 @@
|
|
| 30 |
"Sum": 3
|
| 31 |
},
|
| 32 |
"layer_norm_eps": 1e-12,
|
|
|
|
| 33 |
"max_position_embeddings": 512,
|
| 34 |
"model_type": "bert",
|
|
|
|
| 35 |
"num_attention_heads": 12,
|
|
|
|
| 36 |
"num_hidden_layers": 12,
|
|
|
|
|
|
|
| 37 |
"pad_token_id": 0,
|
| 38 |
"position_embedding_type": "absolute",
|
| 39 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
"torch_dtype": "float32",
|
| 41 |
"transformers_version": "4.38.2",
|
| 42 |
"type_vocab_size": 2,
|
| 43 |
"use_cache": true,
|
| 44 |
-
"vocab_size":
|
| 45 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "t5-base",
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
+
"d_ff": 3072,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_start_token_id": 0,
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
"hidden_act": "gelu",
|
| 15 |
"hidden_dropout_prob": 0.1,
|
| 16 |
"hidden_size": 768,
|
|
|
|
| 23 |
"5": "Obj",
|
| 24 |
"6": "QC"
|
| 25 |
},
|
| 26 |
+
"initializer_factor": 1.0,
|
| 27 |
"initializer_range": 0.02,
|
| 28 |
"intermediate_size": 3072,
|
| 29 |
+
"is_encoder_decoder": true,
|
| 30 |
"label2id": {
|
| 31 |
"Edu": 4,
|
| 32 |
"Exp": 1,
|
|
|
|
| 37 |
"Sum": 3
|
| 38 |
},
|
| 39 |
"layer_norm_eps": 1e-12,
|
| 40 |
+
"layer_norm_epsilon": 1e-06,
|
| 41 |
"max_position_embeddings": 512,
|
| 42 |
"model_type": "bert",
|
| 43 |
+
"n_positions": 512,
|
| 44 |
"num_attention_heads": 12,
|
| 45 |
+
"num_heads": 12,
|
| 46 |
"num_hidden_layers": 12,
|
| 47 |
+
"num_layers": 12,
|
| 48 |
+
"output_past": true,
|
| 49 |
"pad_token_id": 0,
|
| 50 |
"position_embedding_type": "absolute",
|
| 51 |
"problem_type": "single_label_classification",
|
| 52 |
+
"relative_attention_num_buckets": 32,
|
| 53 |
+
"task_specific_params": {
|
| 54 |
+
"summarization": {
|
| 55 |
+
"early_stopping": true,
|
| 56 |
+
"length_penalty": 2.0,
|
| 57 |
+
"max_length": 200,
|
| 58 |
+
"min_length": 30,
|
| 59 |
+
"no_repeat_ngram_size": 3,
|
| 60 |
+
"num_beams": 4,
|
| 61 |
+
"prefix": "summarize: "
|
| 62 |
+
},
|
| 63 |
+
"translation_en_to_de": {
|
| 64 |
+
"early_stopping": true,
|
| 65 |
+
"max_length": 300,
|
| 66 |
+
"num_beams": 4,
|
| 67 |
+
"prefix": "translate English to German: "
|
| 68 |
+
},
|
| 69 |
+
"translation_en_to_fr": {
|
| 70 |
+
"early_stopping": true,
|
| 71 |
+
"max_length": 300,
|
| 72 |
+
"num_beams": 4,
|
| 73 |
+
"prefix": "translate English to French: "
|
| 74 |
+
},
|
| 75 |
+
"translation_en_to_ro": {
|
| 76 |
+
"early_stopping": true,
|
| 77 |
+
"max_length": 300,
|
| 78 |
+
"num_beams": 4,
|
| 79 |
+
"prefix": "translate English to Romanian: "
|
| 80 |
+
}
|
| 81 |
+
},
|
| 82 |
"torch_dtype": "float32",
|
| 83 |
"transformers_version": "4.38.2",
|
| 84 |
"type_vocab_size": 2,
|
| 85 |
"use_cache": true,
|
| 86 |
+
"vocab_size": 32128
|
| 87 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be2bcc1488bbb33b342d06cdf43b31725195440c5b923737d63a7013515ff4b0
|
| 3 |
+
size 442907668
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9c5a7984785f057e0b43ffc6f1dcaae001f0197a2a208d07e16ab98eedbddcf
|
| 3 |
size 4856
|