rntc commited on
Commit
adaa092
·
verified ·
1 Parent(s): 20878c5

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: almanach/camembertv2-base
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: medgemma-full-corrected
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # medgemma-full-corrected
16
+
17
+ This model is a fine-tuned version of [almanach/camembertv2-base](https://huggingface.co/almanach/camembertv2-base) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 3.0191
20
+ - Educational Score Mse: 0.1065
21
+ - Writing Quality Mse: 0.2074
22
+ - Content Richness Mse: 0.1078
23
+ - Terminology Precision Mse: 0.1990
24
+ - Rewriting Needed Mse: 0.0141
25
+ - Pretraining Suitable Mse: 0.0443
26
+ - Contains Bias Mse: 0.0022
27
+ - Writing Style Accuracy: 0.8773
28
+ - Content Type Accuracy: 0.8416
29
+ - Medical Subfield Accuracy: 0.7692
30
+ - Age Group Accuracy: 0.9508
31
+ - Sex Accuracy: 0.9824
32
+ - Assertion Type Accuracy: 0.9556
33
+ - Certainty Level Accuracy: 0.9411
34
+ - Contains Numbers Mse: 0.0260
35
+ - Contains Abbreviations Mse: 0.0426
36
+ - List Format Mse: 0.0377
37
+ - Interactive Elements Accuracy: 0.9958
38
+ - Content Novelty Accuracy: 0.9596
39
+ - Text Type Accuracy: 0.9528
40
+ - Combined Score: 0.5007
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 2e-05
60
+ - train_batch_size: 8
61
+ - eval_batch_size: 8
62
+ - seed: 42
63
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
64
+ - lr_scheduler_type: linear
65
+ - lr_scheduler_warmup_ratio: 0.1
66
+ - num_epochs: 3.0
67
+ - mixed_precision_training: Native AMP
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Validation Loss | Educational Score Mse | Writing Quality Mse | Content Richness Mse | Terminology Precision Mse | Rewriting Needed Mse | Pretraining Suitable Mse | Contains Bias Mse | Writing Style Accuracy | Content Type Accuracy | Medical Subfield Accuracy | Age Group Accuracy | Sex Accuracy | Assertion Type Accuracy | Certainty Level Accuracy | Contains Numbers Mse | Contains Abbreviations Mse | List Format Mse | Interactive Elements Accuracy | Content Novelty Accuracy | Text Type Accuracy | Combined Score |
72
+ |:-------------:|:------:|:------:|:---------------:|:---------------------:|:-------------------:|:--------------------:|:-------------------------:|:--------------------:|:------------------------:|:-----------------:|:----------------------:|:---------------------:|:-------------------------:|:------------------:|:------------:|:-----------------------:|:------------------------:|:--------------------:|:--------------------------:|:---------------:|:-----------------------------:|:------------------------:|:------------------:|:--------------:|
73
+ | 21.9755 | 0.0307 | 1500 | 19.5623 | 0.9803 | 2.0404 | 1.3504 | 2.3851 | 0.0271 | 0.2172 | 0.0023 | 0.4865 | 0.2696 | 0.2358 | 0.8673 | 0.9493 | 0.9257 | 0.9002 | 0.2533 | 0.2267 | 0.1589 | 0.9904 | 0.9382 | 0.7728 | 0.7489 |
74
+ | 10.2029 | 0.0615 | 3000 | 9.9561 | 0.1951 | 0.4303 | 0.1877 | 0.3501 | 0.0248 | 0.0784 | 0.0027 | 0.6173 | 0.4740 | 0.2358 | 0.8673 | 0.9493 | 0.9257 | 0.9002 | 0.1697 | 0.1662 | 0.1231 | 0.9904 | 0.9382 | 0.8387 | 0.4732 |
75
+ | 8.9208 | 0.0922 | 4500 | 8.7854 | 0.1761 | 0.3823 | 0.1752 | 0.3548 | 0.0231 | 0.0637 | 0.0025 | 0.6113 | 0.4832 | 0.2675 | 0.8673 | 0.9493 | 0.9257 | 0.9002 | 0.1235 | 0.1495 | 0.0977 | 0.9904 | 0.9382 | 0.9190 | 0.4700 |
76
+ | 8.1025 | 0.1229 | 6000 | 7.8528 | 0.1652 | 0.3151 | 0.1648 | 0.2810 | 0.0196 | 0.0670 | 0.0025 | 0.7482 | 0.6177 | 0.3126 | 0.8673 | 0.9493 | 0.9257 | 0.9002 | 0.1102 | 0.1298 | 0.0906 | 0.9904 | 0.9382 | 0.9218 | 0.4759 |
77
+ | 7.3399 | 0.1536 | 7500 | 7.2310 | 0.1521 | 0.3481 | 0.1613 | 0.2824 | 0.0198 | 0.0603 | 0.0025 | 0.7773 | 0.6475 | 0.3321 | 0.8673 | 0.9493 | 0.9257 | 0.9002 | 0.0974 | 0.0936 | 0.0885 | 0.9904 | 0.9382 | 0.9280 | 0.4781 |
78
+ | 6.9357 | 0.1844 | 9000 | 6.7256 | 0.1560 | 0.3093 | 0.1608 | 0.2768 | 0.0171 | 0.0639 | 0.0025 | 0.7966 | 0.7024 | 0.3618 | 0.8766 | 0.9493 | 0.9257 | 0.9002 | 0.0763 | 0.0847 | 0.0857 | 0.9904 | 0.9382 | 0.9292 | 0.4802 |
79
+ | 6.7497 | 0.2151 | 10500 | 6.3397 | 0.1479 | 0.3376 | 0.1534 | 0.3120 | 0.0174 | 0.0583 | 0.0024 | 0.8043 | 0.7214 | 0.3809 | 0.8902 | 0.9496 | 0.9257 | 0.9026 | 0.0794 | 0.0742 | 0.0737 | 0.9904 | 0.9382 | 0.9350 | 0.4847 |
80
+ | 6.0809 | 0.2458 | 12000 | 6.1028 | 0.1593 | 0.3313 | 0.1632 | 0.2846 | 0.0177 | 0.0739 | 0.0024 | 0.8017 | 0.7475 | 0.4089 | 0.9028 | 0.9573 | 0.9320 | 0.9126 | 0.0720 | 0.0724 | 0.0706 | 0.9904 | 0.9400 | 0.9234 | 0.4882 |
81
+ | 5.9007 | 0.2766 | 13500 | 5.7623 | 0.1598 | 0.2748 | 0.1745 | 0.2807 | 0.0175 | 0.0618 | 0.0024 | 0.8132 | 0.7494 | 0.4281 | 0.9068 | 0.9619 | 0.9386 | 0.9183 | 0.0577 | 0.0662 | 0.0682 | 0.9944 | 0.9410 | 0.9376 | 0.4876 |
82
+ | 5.7305 | 0.3073 | 15000 | 5.4478 | 0.1432 | 0.2975 | 0.1485 | 0.2705 | 0.0185 | 0.0603 | 0.0025 | 0.8272 | 0.7751 | 0.4521 | 0.9143 | 0.9637 | 0.9402 | 0.9204 | 0.0486 | 0.0649 | 0.0627 | 0.9952 | 0.9445 | 0.9376 | 0.4894 |
83
+ | 5.4057 | 0.3380 | 16500 | 5.4789 | 0.1618 | 0.3611 | 0.1524 | 0.2914 | 0.0205 | 0.0626 | 0.0025 | 0.8129 | 0.7677 | 0.4731 | 0.9184 | 0.9645 | 0.9393 | 0.9213 | 0.0505 | 0.0633 | 0.0549 | 0.9948 | 0.9447 | 0.9351 | 0.4946 |
84
+ | 5.4087 | 0.3687 | 18000 | 5.0982 | 0.1348 | 0.2707 | 0.1390 | 0.2497 | 0.0168 | 0.0530 | 0.0024 | 0.8299 | 0.7838 | 0.4977 | 0.9219 | 0.9661 | 0.9353 | 0.9214 | 0.0415 | 0.0624 | 0.0554 | 0.9948 | 0.9380 | 0.9390 | 0.4877 |
85
+ | 5.0165 | 0.3995 | 19500 | 5.0364 | 0.1449 | 0.2657 | 0.1580 | 0.2903 | 0.0195 | 0.0572 | 0.0023 | 0.8238 | 0.7782 | 0.5170 | 0.9182 | 0.9668 | 0.9440 | 0.9253 | 0.0392 | 0.0574 | 0.0545 | 0.9954 | 0.9460 | 0.9440 | 0.4924 |
86
+ | 4.9326 | 0.4302 | 21000 | 4.7331 | 0.1310 | 0.2462 | 0.1358 | 0.2486 | 0.0161 | 0.0545 | 0.0024 | 0.8378 | 0.7925 | 0.5408 | 0.9213 | 0.9700 | 0.9407 | 0.9253 | 0.0374 | 0.0567 | 0.0506 | 0.9949 | 0.9462 | 0.9404 | 0.4895 |
87
+ | 4.7586 | 0.4609 | 22500 | 4.7080 | 0.1317 | 0.2579 | 0.1337 | 0.2440 | 0.0175 | 0.0526 | 0.0024 | 0.8338 | 0.7838 | 0.5550 | 0.9259 | 0.9720 | 0.9417 | 0.9253 | 0.0372 | 0.0594 | 0.0495 | 0.9949 | 0.9441 | 0.9437 | 0.4903 |
88
+ | 4.7594 | 0.4917 | 24000 | 4.5498 | 0.1304 | 0.2583 | 0.1362 | 0.2460 | 0.0163 | 0.0534 | 0.0023 | 0.8389 | 0.7957 | 0.5676 | 0.9287 | 0.9681 | 0.9437 | 0.9253 | 0.0365 | 0.0539 | 0.0502 | 0.9953 | 0.9457 | 0.9429 | 0.4918 |
89
+ | 4.5925 | 0.5224 | 25500 | 4.4950 | 0.1269 | 0.2485 | 0.1527 | 0.2515 | 0.0166 | 0.0524 | 0.0024 | 0.8367 | 0.7976 | 0.5791 | 0.9247 | 0.9717 | 0.9443 | 0.9244 | 0.0337 | 0.0537 | 0.0474 | 0.9950 | 0.9462 | 0.9463 | 0.4926 |
90
+ | 4.8652 | 0.5531 | 27000 | 4.3584 | 0.1316 | 0.2365 | 0.1368 | 0.2387 | 0.0168 | 0.0513 | 0.0023 | 0.8489 | 0.7997 | 0.5857 | 0.9274 | 0.9710 | 0.9471 | 0.9281 | 0.0350 | 0.0541 | 0.0492 | 0.9949 | 0.9461 | 0.9461 | 0.4924 |
91
+ | 4.3698 | 0.5838 | 28500 | 4.3289 | 0.1348 | 0.2636 | 0.1379 | 0.2378 | 0.0154 | 0.0510 | 0.0024 | 0.8482 | 0.8037 | 0.5964 | 0.9289 | 0.9750 | 0.9462 | 0.9245 | 0.0335 | 0.0522 | 0.0480 | 0.9951 | 0.9394 | 0.9450 | 0.4940 |
92
+ | 4.4026 | 0.6146 | 30000 | 4.2837 | 0.1287 | 0.2829 | 0.1355 | 0.2356 | 0.0166 | 0.0523 | 0.0023 | 0.8474 | 0.7949 | 0.6031 | 0.9262 | 0.9727 | 0.9478 | 0.9281 | 0.0345 | 0.0521 | 0.0476 | 0.9953 | 0.9477 | 0.9478 | 0.4949 |
93
+ | 4.3877 | 0.6453 | 31500 | 4.1740 | 0.1291 | 0.2768 | 0.1307 | 0.2352 | 0.0180 | 0.0533 | 0.0023 | 0.8407 | 0.8090 | 0.6208 | 0.9315 | 0.9735 | 0.9468 | 0.9295 | 0.0320 | 0.0519 | 0.0458 | 0.9955 | 0.9493 | 0.9479 | 0.4960 |
94
+ | 4.2281 | 0.6760 | 33000 | 4.1048 | 0.1307 | 0.2494 | 0.1258 | 0.2325 | 0.0164 | 0.0502 | 0.0023 | 0.8447 | 0.7983 | 0.6313 | 0.9307 | 0.9744 | 0.9463 | 0.9321 | 0.0329 | 0.0515 | 0.0469 | 0.9953 | 0.9491 | 0.9486 | 0.4945 |
95
+ | 4.0887 | 0.7068 | 34500 | 4.1142 | 0.1294 | 0.2347 | 0.1364 | 0.2359 | 0.0152 | 0.0538 | 0.0023 | 0.8405 | 0.7996 | 0.6355 | 0.9327 | 0.9739 | 0.9477 | 0.9289 | 0.0318 | 0.0549 | 0.0450 | 0.9954 | 0.9480 | 0.9434 | 0.4942 |
96
+ | 4.1462 | 0.7375 | 36000 | 3.9965 | 0.1242 | 0.2429 | 0.1300 | 0.2336 | 0.0151 | 0.0504 | 0.0023 | 0.8507 | 0.8082 | 0.6495 | 0.9307 | 0.9732 | 0.9493 | 0.9311 | 0.0330 | 0.0502 | 0.0481 | 0.9953 | 0.9467 | 0.9446 | 0.4955 |
97
+ | 3.9073 | 0.7682 | 37500 | 3.9478 | 0.1243 | 0.2462 | 0.1266 | 0.2368 | 0.0157 | 0.0507 | 0.0023 | 0.8523 | 0.8063 | 0.6567 | 0.9349 | 0.9744 | 0.9447 | 0.9286 | 0.0311 | 0.0549 | 0.0447 | 0.9953 | 0.9515 | 0.9475 | 0.4963 |
98
+ | 4.021 | 0.7990 | 39000 | 3.8320 | 0.1260 | 0.2269 | 0.1285 | 0.2258 | 0.0154 | 0.0488 | 0.0023 | 0.8527 | 0.8111 | 0.6688 | 0.9337 | 0.9752 | 0.9479 | 0.9315 | 0.0323 | 0.0503 | 0.0446 | 0.9955 | 0.9519 | 0.9498 | 0.4960 |
99
+ | 3.9901 | 0.8297 | 40500 | 3.8982 | 0.1236 | 0.2415 | 0.1293 | 0.2234 | 0.0160 | 0.0494 | 0.0022 | 0.8506 | 0.8033 | 0.6706 | 0.9280 | 0.9740 | 0.9496 | 0.9332 | 0.0321 | 0.0517 | 0.0444 | 0.9956 | 0.9459 | 0.9483 | 0.4956 |
100
+ | 3.9871 | 0.8604 | 42000 | 3.8129 | 0.1221 | 0.2235 | 0.1296 | 0.2299 | 0.0158 | 0.0485 | 0.0022 | 0.8513 | 0.8132 | 0.6761 | 0.9344 | 0.9763 | 0.9485 | 0.9328 | 0.0333 | 0.0498 | 0.0441 | 0.9950 | 0.9476 | 0.9502 | 0.4962 |
101
+ | 3.7565 | 0.8911 | 43500 | 3.7815 | 0.1259 | 0.2448 | 0.1264 | 0.2308 | 0.0166 | 0.0508 | 0.0022 | 0.8574 | 0.8131 | 0.6823 | 0.9372 | 0.9755 | 0.9480 | 0.9310 | 0.0309 | 0.0498 | 0.0436 | 0.9952 | 0.9528 | 0.9459 | 0.4980 |
102
+ | 4.106 | 0.9219 | 45000 | 3.8232 | 0.1263 | 0.2297 | 0.1342 | 0.2311 | 0.0147 | 0.0505 | 0.0023 | 0.8465 | 0.8104 | 0.6816 | 0.9319 | 0.9733 | 0.9489 | 0.9328 | 0.0306 | 0.0487 | 0.0441 | 0.9955 | 0.9530 | 0.9427 | 0.4964 |
103
+ | 3.7534 | 0.9526 | 46500 | 3.7046 | 0.1218 | 0.2355 | 0.1250 | 0.2246 | 0.0149 | 0.0494 | 0.0023 | 0.8551 | 0.8180 | 0.6904 | 0.9355 | 0.9758 | 0.9480 | 0.9330 | 0.0315 | 0.0494 | 0.0433 | 0.9957 | 0.9519 | 0.9465 | 0.4974 |
104
+ | 3.9638 | 0.9833 | 48000 | 3.8129 | 0.1193 | 0.2239 | 0.1319 | 0.2463 | 0.0149 | 0.0484 | 0.0022 | 0.8361 | 0.7993 | 0.6925 | 0.9342 | 0.9766 | 0.9444 | 0.9297 | 0.0310 | 0.0485 | 0.0425 | 0.9955 | 0.9503 | 0.9480 | 0.4958 |
105
+ | 3.5715 | 1.0141 | 49500 | 3.6313 | 0.1194 | 0.2246 | 0.1221 | 0.2242 | 0.0149 | 0.0471 | 0.0022 | 0.8579 | 0.8147 | 0.7000 | 0.9377 | 0.9778 | 0.9512 | 0.9330 | 0.0317 | 0.0491 | 0.0463 | 0.9953 | 0.9525 | 0.9484 | 0.4975 |
106
+ | 3.5272 | 1.0448 | 51000 | 3.6330 | 0.1225 | 0.2300 | 0.1253 | 0.2228 | 0.0152 | 0.0494 | 0.0022 | 0.8613 | 0.8191 | 0.7021 | 0.9348 | 0.9776 | 0.9487 | 0.9328 | 0.0314 | 0.0497 | 0.0432 | 0.9952 | 0.9531 | 0.9484 | 0.4982 |
107
+ | 3.5379 | 1.0755 | 52500 | 3.6091 | 0.1208 | 0.2222 | 0.1270 | 0.2344 | 0.0147 | 0.0488 | 0.0022 | 0.8608 | 0.8195 | 0.7057 | 0.9348 | 0.9789 | 0.9498 | 0.9320 | 0.0305 | 0.0486 | 0.0432 | 0.9955 | 0.9531 | 0.9486 | 0.4986 |
108
+ | 3.3589 | 1.1062 | 54000 | 3.6755 | 0.1257 | 0.2435 | 0.1241 | 0.2228 | 0.0146 | 0.0488 | 0.0023 | 0.8531 | 0.8139 | 0.7021 | 0.9347 | 0.9766 | 0.9475 | 0.9341 | 0.0301 | 0.0490 | 0.0428 | 0.9955 | 0.9510 | 0.9478 | 0.4980 |
109
+ | 3.4707 | 1.1370 | 55500 | 3.6028 | 0.1206 | 0.2334 | 0.1237 | 0.2243 | 0.0152 | 0.0498 | 0.0022 | 0.8558 | 0.8214 | 0.7075 | 0.9362 | 0.9787 | 0.9512 | 0.9318 | 0.0296 | 0.0495 | 0.0421 | 0.9956 | 0.9524 | 0.9497 | 0.4985 |
110
+ | 3.3433 | 1.1677 | 57000 | 3.5433 | 0.1201 | 0.2161 | 0.1291 | 0.2455 | 0.0147 | 0.0475 | 0.0022 | 0.8630 | 0.8219 | 0.7150 | 0.9365 | 0.9789 | 0.9504 | 0.9337 | 0.0297 | 0.0481 | 0.0435 | 0.9953 | 0.9549 | 0.9481 | 0.4997 |
111
+ | 3.3679 | 1.1984 | 58500 | 3.5394 | 0.1178 | 0.2511 | 0.1250 | 0.2200 | 0.0147 | 0.0477 | 0.0022 | 0.8587 | 0.8195 | 0.7159 | 0.9409 | 0.9791 | 0.9510 | 0.9344 | 0.0290 | 0.0470 | 0.0425 | 0.9956 | 0.9538 | 0.9472 | 0.4997 |
112
+ | 3.3885 | 1.2292 | 60000 | 3.4935 | 0.1163 | 0.2315 | 0.1227 | 0.2240 | 0.0155 | 0.0472 | 0.0022 | 0.8622 | 0.8203 | 0.7220 | 0.9383 | 0.9790 | 0.9519 | 0.9343 | 0.0294 | 0.0467 | 0.0417 | 0.9956 | 0.9550 | 0.9497 | 0.4993 |
113
+ | 3.3306 | 1.2599 | 61500 | 3.4538 | 0.1194 | 0.2198 | 0.1204 | 0.2135 | 0.0161 | 0.0477 | 0.0022 | 0.8642 | 0.8214 | 0.7204 | 0.9413 | 0.9791 | 0.9518 | 0.9356 | 0.0301 | 0.0477 | 0.0444 | 0.9957 | 0.9557 | 0.9504 | 0.4989 |
114
+ | 3.5718 | 1.2906 | 63000 | 3.4483 | 0.1231 | 0.2407 | 0.1184 | 0.2098 | 0.0148 | 0.0470 | 0.0022 | 0.8633 | 0.8287 | 0.7220 | 0.9376 | 0.9790 | 0.9505 | 0.9350 | 0.0286 | 0.0481 | 0.0409 | 0.9953 | 0.9544 | 0.9497 | 0.4995 |
115
+ | 3.0728 | 1.3213 | 64500 | 3.4219 | 0.1170 | 0.2150 | 0.1194 | 0.2235 | 0.0148 | 0.0476 | 0.0022 | 0.8613 | 0.8230 | 0.7266 | 0.9417 | 0.9797 | 0.9510 | 0.9355 | 0.0294 | 0.0462 | 0.0416 | 0.9954 | 0.9550 | 0.9493 | 0.4988 |
116
+ | 3.3066 | 1.3521 | 66000 | 3.4526 | 0.1153 | 0.2343 | 0.1169 | 0.2101 | 0.0147 | 0.0470 | 0.0022 | 0.8612 | 0.8207 | 0.7244 | 0.9393 | 0.9776 | 0.9527 | 0.9345 | 0.0285 | 0.0460 | 0.0449 | 0.9953 | 0.9549 | 0.9501 | 0.4985 |
117
+ | 3.3204 | 1.3828 | 67500 | 3.4222 | 0.1165 | 0.2334 | 0.1187 | 0.2115 | 0.0155 | 0.0478 | 0.0022 | 0.8634 | 0.8223 | 0.7287 | 0.9426 | 0.9769 | 0.9513 | 0.9363 | 0.0295 | 0.0473 | 0.0417 | 0.9956 | 0.9554 | 0.9462 | 0.4991 |
118
+ | 3.2237 | 1.4135 | 69000 | 3.3706 | 0.1162 | 0.2230 | 0.1196 | 0.2169 | 0.0151 | 0.0476 | 0.0022 | 0.8635 | 0.8248 | 0.7316 | 0.9414 | 0.9799 | 0.9509 | 0.9369 | 0.0289 | 0.0459 | 0.0408 | 0.9957 | 0.9557 | 0.9494 | 0.4993 |
119
+ | 3.3159 | 1.4443 | 70500 | 3.3907 | 0.1246 | 0.2199 | 0.1167 | 0.2090 | 0.0147 | 0.0472 | 0.0022 | 0.8630 | 0.8235 | 0.7306 | 0.9441 | 0.9793 | 0.9511 | 0.9352 | 0.0298 | 0.0493 | 0.0406 | 0.9954 | 0.9553 | 0.9495 | 0.4990 |
120
+ | 3.2082 | 1.4750 | 72000 | 3.3536 | 0.1158 | 0.2209 | 0.1215 | 0.2135 | 0.0149 | 0.0473 | 0.0023 | 0.8637 | 0.8267 | 0.7342 | 0.9427 | 0.9800 | 0.9519 | 0.9366 | 0.0284 | 0.0460 | 0.0407 | 0.9958 | 0.9552 | 0.9486 | 0.4993 |
121
+ | 3.2581 | 1.5057 | 73500 | 3.3315 | 0.1143 | 0.2272 | 0.1179 | 0.2087 | 0.0149 | 0.0470 | 0.0022 | 0.8661 | 0.8239 | 0.7352 | 0.9445 | 0.9806 | 0.9494 | 0.9361 | 0.0282 | 0.0460 | 0.0406 | 0.9955 | 0.9549 | 0.9502 | 0.4992 |
122
+ | 3.1166 | 1.5364 | 75000 | 3.3129 | 0.1143 | 0.2274 | 0.1177 | 0.2132 | 0.0148 | 0.0464 | 0.0022 | 0.8654 | 0.8282 | 0.7397 | 0.9447 | 0.9813 | 0.9524 | 0.9370 | 0.0288 | 0.0463 | 0.0401 | 0.9959 | 0.9564 | 0.9497 | 0.5001 |
123
+ | 3.2024 | 1.5672 | 76500 | 3.3305 | 0.1159 | 0.2172 | 0.1149 | 0.2084 | 0.0151 | 0.0471 | 0.0022 | 0.8607 | 0.8227 | 0.7373 | 0.9426 | 0.9806 | 0.9518 | 0.9351 | 0.0285 | 0.0454 | 0.0404 | 0.9959 | 0.9565 | 0.9504 | 0.4984 |
124
+ | 3.2741 | 1.5979 | 78000 | 3.2938 | 0.1149 | 0.2103 | 0.1224 | 0.2128 | 0.0148 | 0.0465 | 0.0022 | 0.8656 | 0.8276 | 0.7403 | 0.9461 | 0.9800 | 0.9521 | 0.9368 | 0.0284 | 0.0448 | 0.0399 | 0.9957 | 0.9559 | 0.9509 | 0.4994 |
125
+ | 3.2547 | 1.6286 | 79500 | 3.3060 | 0.1142 | 0.2194 | 0.1154 | 0.2111 | 0.0145 | 0.0461 | 0.0022 | 0.8592 | 0.8269 | 0.7403 | 0.9437 | 0.9799 | 0.9534 | 0.9371 | 0.0291 | 0.0450 | 0.0396 | 0.9957 | 0.9537 | 0.9509 | 0.4989 |
126
+ | 3.0745 | 1.6594 | 81000 | 3.3017 | 0.1124 | 0.2269 | 0.1155 | 0.2074 | 0.0162 | 0.0479 | 0.0022 | 0.8658 | 0.8268 | 0.7397 | 0.9432 | 0.9802 | 0.9530 | 0.9361 | 0.0278 | 0.0454 | 0.0394 | 0.9958 | 0.9566 | 0.9510 | 0.4995 |
127
+ | 3.2289 | 1.6901 | 82500 | 3.2717 | 0.1114 | 0.2173 | 0.1140 | 0.2066 | 0.0150 | 0.0461 | 0.0023 | 0.8642 | 0.8279 | 0.7414 | 0.9441 | 0.9782 | 0.9533 | 0.9380 | 0.0277 | 0.0453 | 0.0401 | 0.9957 | 0.9567 | 0.9508 | 0.4988 |
128
+ | 3.2697 | 1.7208 | 84000 | 3.2704 | 0.1134 | 0.2180 | 0.1160 | 0.2098 | 0.0151 | 0.0462 | 0.0022 | 0.8631 | 0.8318 | 0.7445 | 0.9430 | 0.9802 | 0.9514 | 0.9354 | 0.0283 | 0.0450 | 0.0393 | 0.9956 | 0.9570 | 0.9514 | 0.4993 |
129
+ | 3.0788 | 1.7515 | 85500 | 3.2717 | 0.1128 | 0.2272 | 0.1174 | 0.2059 | 0.0159 | 0.0467 | 0.0022 | 0.8636 | 0.8286 | 0.7404 | 0.9447 | 0.9801 | 0.9540 | 0.9391 | 0.0284 | 0.0446 | 0.0398 | 0.9955 | 0.9560 | 0.9508 | 0.4997 |
130
+ | 3.2853 | 1.7823 | 87000 | 3.2489 | 0.1110 | 0.2271 | 0.1161 | 0.2115 | 0.0151 | 0.0463 | 0.0022 | 0.8679 | 0.8279 | 0.7432 | 0.9443 | 0.9813 | 0.9527 | 0.9359 | 0.0276 | 0.0448 | 0.0394 | 0.9956 | 0.9582 | 0.9517 | 0.5000 |
131
+ | 3.1586 | 1.8130 | 88500 | 3.2261 | 0.1111 | 0.2252 | 0.1133 | 0.2040 | 0.0145 | 0.0460 | 0.0022 | 0.8693 | 0.8311 | 0.7438 | 0.9463 | 0.9811 | 0.9529 | 0.9378 | 0.0273 | 0.0446 | 0.0393 | 0.9958 | 0.9564 | 0.9511 | 0.4996 |
132
+ | 3.0058 | 1.8437 | 90000 | 3.1774 | 0.1105 | 0.2102 | 0.1132 | 0.2069 | 0.0140 | 0.0453 | 0.0022 | 0.8682 | 0.8331 | 0.7500 | 0.9478 | 0.9811 | 0.9534 | 0.9390 | 0.0293 | 0.0449 | 0.0387 | 0.9957 | 0.9563 | 0.9524 | 0.4996 |
133
+ | 2.9714 | 1.8745 | 91500 | 3.2416 | 0.1146 | 0.2188 | 0.1154 | 0.2085 | 0.0150 | 0.0467 | 0.0022 | 0.8621 | 0.8272 | 0.7476 | 0.9475 | 0.9812 | 0.9540 | 0.9393 | 0.0278 | 0.0449 | 0.0391 | 0.9958 | 0.9576 | 0.9514 | 0.4998 |
134
+ | 3.0669 | 1.9052 | 93000 | 3.1565 | 0.1108 | 0.2146 | 0.1124 | 0.2049 | 0.0154 | 0.0463 | 0.0022 | 0.8705 | 0.8353 | 0.7532 | 0.9476 | 0.9806 | 0.9548 | 0.9395 | 0.0279 | 0.0448 | 0.0403 | 0.9957 | 0.9567 | 0.9500 | 0.5002 |
135
+ | 3.0294 | 1.9359 | 94500 | 3.1746 | 0.1097 | 0.2119 | 0.1120 | 0.2034 | 0.0140 | 0.0457 | 0.0022 | 0.8679 | 0.8323 | 0.7503 | 0.9459 | 0.9795 | 0.9540 | 0.9375 | 0.0281 | 0.0438 | 0.0386 | 0.9958 | 0.9574 | 0.9509 | 0.4990 |
136
+ | 3.2645 | 1.9666 | 96000 | 3.1593 | 0.1107 | 0.2047 | 0.1136 | 0.2123 | 0.0141 | 0.0454 | 0.0022 | 0.8722 | 0.8286 | 0.7534 | 0.9472 | 0.9822 | 0.9517 | 0.9391 | 0.0278 | 0.0442 | 0.0391 | 0.9957 | 0.9575 | 0.9526 | 0.4997 |
137
+ | 3.136 | 1.9974 | 97500 | 3.1353 | 0.1099 | 0.2040 | 0.1121 | 0.2082 | 0.0140 | 0.0458 | 0.0022 | 0.8708 | 0.8353 | 0.7532 | 0.9461 | 0.9812 | 0.9517 | 0.9388 | 0.0273 | 0.0436 | 0.0388 | 0.9956 | 0.9578 | 0.9520 | 0.4994 |
138
+ | 2.669 | 2.0281 | 99000 | 3.1879 | 0.1115 | 0.2324 | 0.1128 | 0.2086 | 0.0143 | 0.0459 | 0.0022 | 0.8716 | 0.8328 | 0.7525 | 0.9468 | 0.9811 | 0.9535 | 0.9389 | 0.0273 | 0.0443 | 0.0392 | 0.9956 | 0.9585 | 0.9514 | 0.5011 |
139
+ | 2.7518 | 2.0588 | 100500 | 3.1823 | 0.1114 | 0.2218 | 0.1117 | 0.2010 | 0.0146 | 0.0470 | 0.0022 | 0.8682 | 0.8333 | 0.7518 | 0.9474 | 0.9823 | 0.9528 | 0.9386 | 0.0275 | 0.0443 | 0.0404 | 0.9957 | 0.9578 | 0.9510 | 0.5000 |
140
+ | 2.6474 | 2.0896 | 102000 | 3.1413 | 0.1118 | 0.2116 | 0.1107 | 0.2033 | 0.0149 | 0.0455 | 0.0022 | 0.8713 | 0.8358 | 0.7548 | 0.9476 | 0.9811 | 0.9536 | 0.9387 | 0.0271 | 0.0440 | 0.0396 | 0.9957 | 0.9586 | 0.9516 | 0.5000 |
141
+ | 2.7432 | 2.1203 | 103500 | 3.1629 | 0.1085 | 0.2154 | 0.1121 | 0.2048 | 0.0148 | 0.0453 | 0.0022 | 0.8717 | 0.8353 | 0.7555 | 0.9462 | 0.9800 | 0.9545 | 0.9392 | 0.0269 | 0.0442 | 0.0402 | 0.9957 | 0.9587 | 0.9512 | 0.5001 |
142
+ | 2.7077 | 2.1510 | 105000 | 3.1593 | 0.1103 | 0.2126 | 0.1105 | 0.2041 | 0.0143 | 0.0456 | 0.0022 | 0.8700 | 0.8352 | 0.7563 | 0.9478 | 0.9813 | 0.9548 | 0.9389 | 0.0274 | 0.0448 | 0.0393 | 0.9957 | 0.9590 | 0.9514 | 0.5001 |
143
+ | 2.7707 | 2.1818 | 106500 | 3.1574 | 0.1089 | 0.2086 | 0.1123 | 0.2038 | 0.0140 | 0.0452 | 0.0022 | 0.8715 | 0.8325 | 0.7553 | 0.9472 | 0.9808 | 0.9553 | 0.9405 | 0.0273 | 0.0441 | 0.0390 | 0.9956 | 0.9555 | 0.9521 | 0.4996 |
144
+ | 2.6208 | 2.2125 | 108000 | 3.1553 | 0.1101 | 0.2242 | 0.1149 | 0.2119 | 0.0145 | 0.0454 | 0.0022 | 0.8707 | 0.8366 | 0.7595 | 0.9489 | 0.9814 | 0.9533 | 0.9393 | 0.0269 | 0.0444 | 0.0384 | 0.9959 | 0.9586 | 0.9522 | 0.5015 |
145
+ | 2.6898 | 2.2432 | 109500 | 3.1535 | 0.1103 | 0.2134 | 0.1110 | 0.2011 | 0.0146 | 0.0454 | 0.0022 | 0.8699 | 0.8319 | 0.7549 | 0.9485 | 0.9800 | 0.9536 | 0.9389 | 0.0272 | 0.0442 | 0.0389 | 0.9956 | 0.9586 | 0.9504 | 0.4995 |
146
+ | 2.7349 | 2.2739 | 111000 | 3.1531 | 0.1100 | 0.2171 | 0.1114 | 0.2025 | 0.0147 | 0.0458 | 0.0022 | 0.8689 | 0.8346 | 0.7568 | 0.9478 | 0.9797 | 0.9547 | 0.9393 | 0.0274 | 0.0443 | 0.0393 | 0.9957 | 0.9589 | 0.9509 | 0.5001 |
147
+ | 2.6409 | 2.3047 | 112500 | 3.1212 | 0.1085 | 0.2086 | 0.1102 | 0.2053 | 0.0140 | 0.0448 | 0.0022 | 0.8706 | 0.8359 | 0.7579 | 0.9478 | 0.9812 | 0.9552 | 0.9388 | 0.0272 | 0.0437 | 0.0379 | 0.9959 | 0.9586 | 0.9517 | 0.4998 |
148
+ | 2.5878 | 2.3354 | 114000 | 3.1033 | 0.1081 | 0.2124 | 0.1112 | 0.2056 | 0.0145 | 0.0450 | 0.0022 | 0.8726 | 0.8371 | 0.7609 | 0.9494 | 0.9817 | 0.9553 | 0.9395 | 0.0273 | 0.0435 | 0.0385 | 0.9959 | 0.9568 | 0.9515 | 0.5004 |
149
+ | 2.8138 | 2.3661 | 115500 | 3.1168 | 0.1095 | 0.2167 | 0.1092 | 0.1995 | 0.0144 | 0.0455 | 0.0022 | 0.8720 | 0.8361 | 0.7595 | 0.9499 | 0.9825 | 0.9548 | 0.9393 | 0.0268 | 0.0437 | 0.0388 | 0.9960 | 0.9584 | 0.9511 | 0.5003 |
150
+ | 2.5645 | 2.3969 | 117000 | 3.0923 | 0.1097 | 0.2098 | 0.1117 | 0.2025 | 0.0143 | 0.0447 | 0.0022 | 0.8756 | 0.8375 | 0.7623 | 0.9488 | 0.9823 | 0.9550 | 0.9404 | 0.0267 | 0.0435 | 0.0390 | 0.9959 | 0.9585 | 0.9522 | 0.5006 |
151
+ | 2.5579 | 2.4276 | 118500 | 3.1074 | 0.1088 | 0.2156 | 0.1110 | 0.2032 | 0.0143 | 0.0453 | 0.0022 | 0.8740 | 0.8373 | 0.7632 | 0.9483 | 0.9822 | 0.9531 | 0.9384 | 0.0266 | 0.0435 | 0.0385 | 0.9959 | 0.9570 | 0.9515 | 0.5005 |
152
+ | 2.6895 | 2.4583 | 120000 | 3.0973 | 0.1091 | 0.2134 | 0.1095 | 0.1995 | 0.0144 | 0.0452 | 0.0022 | 0.8738 | 0.8376 | 0.7609 | 0.9488 | 0.9824 | 0.9541 | 0.9403 | 0.0267 | 0.0436 | 0.0380 | 0.9959 | 0.9588 | 0.9510 | 0.5003 |
153
+ | 2.6364 | 2.4890 | 121500 | 3.0971 | 0.1070 | 0.2192 | 0.1094 | 0.2006 | 0.0146 | 0.0451 | 0.0022 | 0.8724 | 0.8395 | 0.7628 | 0.9487 | 0.9826 | 0.9554 | 0.9406 | 0.0267 | 0.0434 | 0.0386 | 0.9958 | 0.9591 | 0.9513 | 0.5007 |
154
+ | 2.6646 | 2.5198 | 123000 | 3.0946 | 0.1085 | 0.2149 | 0.1089 | 0.1985 | 0.0140 | 0.0450 | 0.0022 | 0.8724 | 0.8378 | 0.7623 | 0.9498 | 0.9815 | 0.9549 | 0.9397 | 0.0264 | 0.0433 | 0.0378 | 0.9957 | 0.9590 | 0.9516 | 0.5002 |
155
+ | 2.6291 | 2.5505 | 124500 | 3.0940 | 0.1098 | 0.2122 | 0.1084 | 0.1982 | 0.0141 | 0.0450 | 0.0022 | 0.8708 | 0.8379 | 0.7637 | 0.9493 | 0.9818 | 0.9560 | 0.9383 | 0.0265 | 0.0433 | 0.0386 | 0.9957 | 0.9587 | 0.9517 | 0.5001 |
156
+ | 2.4625 | 2.5812 | 126000 | 3.0918 | 0.1076 | 0.2222 | 0.1088 | 0.1998 | 0.0144 | 0.0449 | 0.0022 | 0.8740 | 0.8385 | 0.7653 | 0.9497 | 0.9822 | 0.9554 | 0.9396 | 0.0264 | 0.0432 | 0.0380 | 0.9958 | 0.9589 | 0.9516 | 0.5009 |
157
+ | 2.5264 | 2.6120 | 127500 | 3.0677 | 0.1074 | 0.2135 | 0.1085 | 0.1998 | 0.0146 | 0.0448 | 0.0022 | 0.8756 | 0.8394 | 0.7638 | 0.9497 | 0.9825 | 0.9556 | 0.9401 | 0.0266 | 0.0430 | 0.0379 | 0.9958 | 0.9571 | 0.9523 | 0.5005 |
158
+ | 2.576 | 2.6427 | 129000 | 3.0619 | 0.1066 | 0.2107 | 0.1085 | 0.1979 | 0.0143 | 0.0445 | 0.0022 | 0.8734 | 0.8390 | 0.7656 | 0.9497 | 0.9818 | 0.9551 | 0.9405 | 0.0265 | 0.0431 | 0.0390 | 0.9959 | 0.9589 | 0.9526 | 0.5003 |
159
+ | 2.5217 | 2.6734 | 130500 | 3.0648 | 0.1069 | 0.2064 | 0.1105 | 0.2049 | 0.0141 | 0.0443 | 0.0022 | 0.8757 | 0.8402 | 0.7647 | 0.9506 | 0.9823 | 0.9554 | 0.9401 | 0.0264 | 0.0429 | 0.0379 | 0.9959 | 0.9592 | 0.9520 | 0.5006 |
160
+ | 2.626 | 2.7041 | 132000 | 3.0631 | 0.1079 | 0.2104 | 0.1082 | 0.1992 | 0.0141 | 0.0449 | 0.0022 | 0.8753 | 0.8406 | 0.7648 | 0.9498 | 0.9820 | 0.9552 | 0.9406 | 0.0264 | 0.0431 | 0.0379 | 0.9959 | 0.9595 | 0.9524 | 0.5005 |
161
+ | 2.5503 | 2.7349 | 133500 | 3.0462 | 0.1064 | 0.2073 | 0.1096 | 0.1981 | 0.0142 | 0.0444 | 0.0022 | 0.8761 | 0.8424 | 0.7659 | 0.9490 | 0.9818 | 0.9555 | 0.9407 | 0.0263 | 0.0429 | 0.0377 | 0.9959 | 0.9592 | 0.9527 | 0.5004 |
162
+ | 2.6859 | 2.7656 | 135000 | 3.0409 | 0.1064 | 0.2117 | 0.1083 | 0.1981 | 0.0139 | 0.0442 | 0.0022 | 0.8756 | 0.8399 | 0.7662 | 0.9503 | 0.9824 | 0.9559 | 0.9408 | 0.0262 | 0.0429 | 0.0378 | 0.9957 | 0.9587 | 0.9523 | 0.5005 |
163
+ | 2.5686 | 2.7963 | 136500 | 3.0302 | 0.1070 | 0.2084 | 0.1078 | 0.1985 | 0.0142 | 0.0443 | 0.0022 | 0.8763 | 0.8415 | 0.7686 | 0.9505 | 0.9822 | 0.9559 | 0.9408 | 0.0262 | 0.0429 | 0.0382 | 0.9958 | 0.9595 | 0.9521 | 0.5006 |
164
+ | 2.5467 | 2.8271 | 138000 | 3.0339 | 0.1066 | 0.2106 | 0.1080 | 0.1972 | 0.0140 | 0.0445 | 0.0022 | 0.8763 | 0.8417 | 0.7670 | 0.9504 | 0.9821 | 0.9559 | 0.9409 | 0.0261 | 0.0428 | 0.0379 | 0.9959 | 0.9592 | 0.9526 | 0.5006 |
165
+ | 2.5381 | 2.8578 | 139500 | 3.0343 | 0.1065 | 0.2119 | 0.1085 | 0.1995 | 0.0141 | 0.0443 | 0.0022 | 0.8756 | 0.8409 | 0.7685 | 0.9507 | 0.9826 | 0.9561 | 0.9411 | 0.0260 | 0.0429 | 0.0377 | 0.9958 | 0.9598 | 0.9530 | 0.5009 |
166
+ | 2.5265 | 2.8885 | 141000 | 3.0265 | 0.1061 | 0.2063 | 0.1087 | 0.2007 | 0.0140 | 0.0442 | 0.0022 | 0.8762 | 0.8413 | 0.7680 | 0.9511 | 0.9826 | 0.9561 | 0.9407 | 0.0261 | 0.0428 | 0.0381 | 0.9959 | 0.9595 | 0.9526 | 0.5007 |
167
+ | 2.5177 | 2.9192 | 142500 | 3.0246 | 0.1061 | 0.2089 | 0.1091 | 0.2007 | 0.0140 | 0.0443 | 0.0022 | 0.8772 | 0.8417 | 0.7691 | 0.9511 | 0.9826 | 0.9560 | 0.9410 | 0.0260 | 0.0427 | 0.0376 | 0.9958 | 0.9590 | 0.9526 | 0.5009 |
168
+ | 2.5464 | 2.9500 | 144000 | 3.0267 | 0.1068 | 0.2083 | 0.1077 | 0.1987 | 0.0142 | 0.0445 | 0.0022 | 0.8771 | 0.8413 | 0.7691 | 0.9505 | 0.9826 | 0.9556 | 0.9410 | 0.0260 | 0.0426 | 0.0377 | 0.9958 | 0.9591 | 0.9527 | 0.5007 |
169
+ | 2.521 | 2.9807 | 145500 | 3.0211 | 0.1065 | 0.2085 | 0.1081 | 0.1992 | 0.0141 | 0.0444 | 0.0022 | 0.8775 | 0.8415 | 0.7693 | 0.9508 | 0.9825 | 0.9556 | 0.9412 | 0.0260 | 0.0426 | 0.0377 | 0.9958 | 0.9595 | 0.9528 | 0.5008 |
170
+
171
+
172
+ ### Framework versions
173
+
174
+ - Transformers 4.55.0
175
+ - Pytorch 2.8.0+cu128
176
+ - Datasets 4.0.0
177
+ - Tokenizers 0.21.4
all_results.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_age_group_accuracy": 0.9507732018160449,
4
+ "eval_assertion_type_accuracy": 0.9555898688668157,
5
+ "eval_certainty_level_accuracy": 0.9410707289530087,
6
+ "eval_combined_score": 0.50069516733328,
7
+ "eval_contains_abbreviations_mse": 0.04261943158702095,
8
+ "eval_contains_bias_mse": 0.0021768044219123476,
9
+ "eval_contains_numbers_mse": 0.025998229564773438,
10
+ "eval_content_novelty_accuracy": 0.9595538245258233,
11
+ "eval_content_richness_mse": 0.10781483429761957,
12
+ "eval_content_type_accuracy": 0.8416261436703464,
13
+ "eval_educational_score_mse": 0.10651316780347395,
14
+ "eval_interactive_elements_accuracy": 0.995805581802678,
15
+ "eval_list_format_mse": 0.037734842254519035,
16
+ "eval_loss": 3.019087076187134,
17
+ "eval_medical_subfield_accuracy": 0.7692378603857943,
18
+ "eval_pretraining_suitable_mse": 0.04433586844755282,
19
+ "eval_rewriting_needed_mse": 0.014078832977989616,
20
+ "eval_runtime": 164.0384,
21
+ "eval_samples": 43391,
22
+ "eval_samples_per_second": 264.517,
23
+ "eval_sex_accuracy": 0.9823926620727801,
24
+ "eval_steps_per_second": 33.065,
25
+ "eval_terminology_precision_mse": 0.19903373313855105,
26
+ "eval_text_type_accuracy": 0.952824318407043,
27
+ "eval_writing_quality_mse": 0.20744471332426925,
28
+ "eval_writing_style_accuracy": 0.8772786983475837,
29
+ "total_flos": 6.212372812618752e+17,
30
+ "train_loss": 4.096821991530293,
31
+ "train_runtime": 39193.5988,
32
+ "train_samples": 390505,
33
+ "train_samples_per_second": 29.89,
34
+ "train_steps_per_second": 3.736
35
+ }
config.json ADDED
@@ -0,0 +1,400 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "MultiTaskClsModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "text-classification",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label_dict": {
15
+ "age_group": {
16
+ "0": "adult",
17
+ "1": "elderly",
18
+ "2": "not_specified",
19
+ "3": "pediatric"
20
+ },
21
+ "assertion_type": {
22
+ "0": "factual",
23
+ "1": "hypothetical",
24
+ "2": "mixed",
25
+ "3": "opinion",
26
+ "4": "recommendation"
27
+ },
28
+ "certainty_level": {
29
+ "0": "definitive",
30
+ "1": "possible",
31
+ "2": "probable",
32
+ "3": "uncertain"
33
+ },
34
+ "contains_abbreviations": null,
35
+ "contains_bias": null,
36
+ "contains_numbers": null,
37
+ "content_novelty": {
38
+ "0": "established",
39
+ "1": "outdated",
40
+ "2": "recent_developments"
41
+ },
42
+ "content_richness": null,
43
+ "content_type": {
44
+ "0": "background_review",
45
+ "1": "clinical_guidance",
46
+ "2": "drug_information",
47
+ "3": "medical_knowledge",
48
+ "4": "other",
49
+ "5": "patient_case",
50
+ "6": "policy_administrative",
51
+ "7": "research_findings",
52
+ "8": "research_methodology"
53
+ },
54
+ "educational_score": null,
55
+ "interactive_elements": {
56
+ "0": "instructions",
57
+ "1": "none",
58
+ "2": "questions",
59
+ "3": "tasks"
60
+ },
61
+ "list_format": null,
62
+ "medical_subfield": {
63
+ "0": "anatomical_pathology",
64
+ "1": "anesthesiology",
65
+ "2": "biology_medicine",
66
+ "3": "cardiology",
67
+ "4": "dentistry",
68
+ "5": "dermatology",
69
+ "6": "digestive_surgery",
70
+ "7": "endocrinology",
71
+ "8": "gastroenterology",
72
+ "9": "general_medicine",
73
+ "10": "general_surgery",
74
+ "11": "genetics",
75
+ "12": "geriatrics",
76
+ "13": "gynecology_medical",
77
+ "14": "gynecology_obstetrics",
78
+ "15": "hematology",
79
+ "16": "intensive_care",
80
+ "17": "internal_medicine",
81
+ "18": "maxillofacial_surgery",
82
+ "19": "midwifery",
83
+ "20": "nephrology",
84
+ "21": "neurology",
85
+ "22": "neurosurgery",
86
+ "23": "nuclear_medicine",
87
+ "24": "occupational_medicine",
88
+ "25": "oncology",
89
+ "26": "ophthalmology",
90
+ "27": "oral_surgery",
91
+ "28": "orthodontics",
92
+ "29": "orthopedic_surgery",
93
+ "30": "other",
94
+ "31": "otolaryngology",
95
+ "32": "pediatric_surgery",
96
+ "33": "pediatrics",
97
+ "34": "pharmacy",
98
+ "35": "plastic_surgery",
99
+ "36": "pneumology",
100
+ "37": "psychiatry",
101
+ "38": "public_health",
102
+ "39": "radiology",
103
+ "40": "rehabilitation",
104
+ "41": "rheumatology",
105
+ "42": "thoracic_surgery",
106
+ "43": "urologic_surgery",
107
+ "44": "vascular_surgery"
108
+ },
109
+ "pretraining_suitable": null,
110
+ "rewriting_needed": null,
111
+ "sex": {
112
+ "0": "female",
113
+ "1": "male",
114
+ "2": "not_specified"
115
+ },
116
+ "terminology_precision": null,
117
+ "text_type": {
118
+ "0": "incomplete",
119
+ "1": "meaningful"
120
+ },
121
+ "writing_quality": null,
122
+ "writing_style": {
123
+ "0": "academic",
124
+ "1": "clinical",
125
+ "2": "other",
126
+ "3": "pedagogical",
127
+ "4": "regulatory"
128
+ }
129
+ },
130
+ "initializer_range": 0.02,
131
+ "intermediate_size": 3072,
132
+ "label2id_dict": {
133
+ "age_group": {
134
+ "adult": 0,
135
+ "elderly": 1,
136
+ "not_specified": 2,
137
+ "pediatric": 3
138
+ },
139
+ "assertion_type": {
140
+ "factual": 0,
141
+ "hypothetical": 1,
142
+ "mixed": 2,
143
+ "opinion": 3,
144
+ "recommendation": 4
145
+ },
146
+ "certainty_level": {
147
+ "definitive": 0,
148
+ "possible": 1,
149
+ "probable": 2,
150
+ "uncertain": 3
151
+ },
152
+ "contains_abbreviations": null,
153
+ "contains_bias": null,
154
+ "contains_numbers": null,
155
+ "content_novelty": {
156
+ "established": 0,
157
+ "outdated": 1,
158
+ "recent_developments": 2
159
+ },
160
+ "content_richness": null,
161
+ "content_type": {
162
+ "background_review": 0,
163
+ "clinical_guidance": 1,
164
+ "drug_information": 2,
165
+ "medical_knowledge": 3,
166
+ "other": 4,
167
+ "patient_case": 5,
168
+ "policy_administrative": 6,
169
+ "research_findings": 7,
170
+ "research_methodology": 8
171
+ },
172
+ "educational_score": null,
173
+ "interactive_elements": {
174
+ "instructions": 0,
175
+ "none": 1,
176
+ "questions": 2,
177
+ "tasks": 3
178
+ },
179
+ "list_format": null,
180
+ "medical_subfield": {
181
+ "anatomical_pathology": 0,
182
+ "anesthesiology": 1,
183
+ "biology_medicine": 2,
184
+ "cardiology": 3,
185
+ "dentistry": 4,
186
+ "dermatology": 5,
187
+ "digestive_surgery": 6,
188
+ "endocrinology": 7,
189
+ "gastroenterology": 8,
190
+ "general_medicine": 9,
191
+ "general_surgery": 10,
192
+ "genetics": 11,
193
+ "geriatrics": 12,
194
+ "gynecology_medical": 13,
195
+ "gynecology_obstetrics": 14,
196
+ "hematology": 15,
197
+ "intensive_care": 16,
198
+ "internal_medicine": 17,
199
+ "maxillofacial_surgery": 18,
200
+ "midwifery": 19,
201
+ "nephrology": 20,
202
+ "neurology": 21,
203
+ "neurosurgery": 22,
204
+ "nuclear_medicine": 23,
205
+ "occupational_medicine": 24,
206
+ "oncology": 25,
207
+ "ophthalmology": 26,
208
+ "oral_surgery": 27,
209
+ "orthodontics": 28,
210
+ "orthopedic_surgery": 29,
211
+ "other": 30,
212
+ "otolaryngology": 31,
213
+ "pediatric_surgery": 32,
214
+ "pediatrics": 33,
215
+ "pharmacy": 34,
216
+ "plastic_surgery": 35,
217
+ "pneumology": 36,
218
+ "psychiatry": 37,
219
+ "public_health": 38,
220
+ "radiology": 39,
221
+ "rehabilitation": 40,
222
+ "rheumatology": 41,
223
+ "thoracic_surgery": 42,
224
+ "urologic_surgery": 43,
225
+ "vascular_surgery": 44
226
+ },
227
+ "pretraining_suitable": null,
228
+ "rewriting_needed": null,
229
+ "sex": {
230
+ "female": 0,
231
+ "male": 1,
232
+ "not_specified": 2
233
+ },
234
+ "terminology_precision": null,
235
+ "text_type": {
236
+ "incomplete": 0,
237
+ "meaningful": 1
238
+ },
239
+ "writing_quality": null,
240
+ "writing_style": {
241
+ "academic": 0,
242
+ "clinical": 1,
243
+ "other": 2,
244
+ "pedagogical": 3,
245
+ "regulatory": 4
246
+ }
247
+ },
248
+ "labels_list": [
249
+ null,
250
+ null,
251
+ null,
252
+ null,
253
+ null,
254
+ null,
255
+ null,
256
+ [
257
+ "academic",
258
+ "clinical",
259
+ "other",
260
+ "pedagogical",
261
+ "regulatory"
262
+ ],
263
+ [
264
+ "background_review",
265
+ "clinical_guidance",
266
+ "drug_information",
267
+ "medical_knowledge",
268
+ "other",
269
+ "patient_case",
270
+ "policy_administrative",
271
+ "research_findings",
272
+ "research_methodology"
273
+ ],
274
+ [
275
+ "anatomical_pathology",
276
+ "anesthesiology",
277
+ "biology_medicine",
278
+ "cardiology",
279
+ "dentistry",
280
+ "dermatology",
281
+ "digestive_surgery",
282
+ "endocrinology",
283
+ "gastroenterology",
284
+ "general_medicine",
285
+ "general_surgery",
286
+ "genetics",
287
+ "geriatrics",
288
+ "gynecology_medical",
289
+ "gynecology_obstetrics",
290
+ "hematology",
291
+ "intensive_care",
292
+ "internal_medicine",
293
+ "maxillofacial_surgery",
294
+ "midwifery",
295
+ "nephrology",
296
+ "neurology",
297
+ "neurosurgery",
298
+ "nuclear_medicine",
299
+ "occupational_medicine",
300
+ "oncology",
301
+ "ophthalmology",
302
+ "oral_surgery",
303
+ "orthodontics",
304
+ "orthopedic_surgery",
305
+ "other",
306
+ "otolaryngology",
307
+ "pediatric_surgery",
308
+ "pediatrics",
309
+ "pharmacy",
310
+ "plastic_surgery",
311
+ "pneumology",
312
+ "psychiatry",
313
+ "public_health",
314
+ "radiology",
315
+ "rehabilitation",
316
+ "rheumatology",
317
+ "thoracic_surgery",
318
+ "urologic_surgery",
319
+ "vascular_surgery"
320
+ ],
321
+ [
322
+ "adult",
323
+ "elderly",
324
+ "not_specified",
325
+ "pediatric"
326
+ ],
327
+ [
328
+ "female",
329
+ "male",
330
+ "not_specified"
331
+ ],
332
+ [
333
+ "factual",
334
+ "hypothetical",
335
+ "mixed",
336
+ "opinion",
337
+ "recommendation"
338
+ ],
339
+ [
340
+ "definitive",
341
+ "possible",
342
+ "probable",
343
+ "uncertain"
344
+ ],
345
+ null,
346
+ null,
347
+ null,
348
+ [
349
+ "instructions",
350
+ "none",
351
+ "questions",
352
+ "tasks"
353
+ ],
354
+ [
355
+ "established",
356
+ "outdated",
357
+ "recent_developments"
358
+ ],
359
+ [
360
+ "incomplete",
361
+ "meaningful"
362
+ ]
363
+ ],
364
+ "layer_norm_eps": 1e-07,
365
+ "max_position_embeddings": 1025,
366
+ "model_name": "camembertv2-base",
367
+ "model_type": "roberta",
368
+ "num_attention_heads": 12,
369
+ "num_hidden_layers": 12,
370
+ "pad_token_id": 0,
371
+ "position_biased_input": true,
372
+ "position_embedding_type": "absolute",
373
+ "problem_types": [
374
+ "regression",
375
+ "regression",
376
+ "regression",
377
+ "regression",
378
+ "regression",
379
+ "regression",
380
+ "regression",
381
+ "single_label_classification",
382
+ "single_label_classification",
383
+ "single_label_classification",
384
+ "single_label_classification",
385
+ "single_label_classification",
386
+ "single_label_classification",
387
+ "single_label_classification",
388
+ "regression",
389
+ "regression",
390
+ "regression",
391
+ "single_label_classification",
392
+ "single_label_classification",
393
+ "single_label_classification"
394
+ ],
395
+ "torch_dtype": "float32",
396
+ "transformers_version": "4.55.0",
397
+ "type_vocab_size": 1,
398
+ "use_cache": true,
399
+ "vocab_size": 32768
400
+ }
confusion_matrix.txt ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_age_group_accuracy": 0.9507732018160449,
4
+ "eval_assertion_type_accuracy": 0.9555898688668157,
5
+ "eval_certainty_level_accuracy": 0.9410707289530087,
6
+ "eval_combined_score": 0.50069516733328,
7
+ "eval_contains_abbreviations_mse": 0.04261943158702095,
8
+ "eval_contains_bias_mse": 0.0021768044219123476,
9
+ "eval_contains_numbers_mse": 0.025998229564773438,
10
+ "eval_content_novelty_accuracy": 0.9595538245258233,
11
+ "eval_content_richness_mse": 0.10781483429761957,
12
+ "eval_content_type_accuracy": 0.8416261436703464,
13
+ "eval_educational_score_mse": 0.10651316780347395,
14
+ "eval_interactive_elements_accuracy": 0.995805581802678,
15
+ "eval_list_format_mse": 0.037734842254519035,
16
+ "eval_loss": 3.019087076187134,
17
+ "eval_medical_subfield_accuracy": 0.7692378603857943,
18
+ "eval_pretraining_suitable_mse": 0.04433586844755282,
19
+ "eval_rewriting_needed_mse": 0.014078832977989616,
20
+ "eval_runtime": 164.0384,
21
+ "eval_samples": 43391,
22
+ "eval_samples_per_second": 264.517,
23
+ "eval_sex_accuracy": 0.9823926620727801,
24
+ "eval_steps_per_second": 33.065,
25
+ "eval_terminology_precision_mse": 0.19903373313855105,
26
+ "eval_text_type_accuracy": 0.952824318407043,
27
+ "eval_writing_quality_mse": 0.20744471332426925,
28
+ "eval_writing_style_accuracy": 0.8772786983475837
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf7cbe113e473b92b1b87aa4d0f4a7da765ba3d858839ef7ab88cb12a6f34ba2
3
+ size 449080576
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "[CLS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "[UNK]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "[CLS]",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "[CLS]",
48
+ "eos_token": "[SEP]",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "[MASK]",
52
+ "model_max_length": 1024,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "[UNK]"
58
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "total_flos": 6.212372812618752e+17,
4
+ "train_loss": 4.096821991530293,
5
+ "train_runtime": 39193.5988,
6
+ "train_samples": 390505,
7
+ "train_samples_per_second": 29.89,
8
+ "train_steps_per_second": 3.736
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8aa197df722ccd83792914af4081c52e045f02f38a8f2c92c7e6b8a5e2f229c
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff