End of training
Browse files- README.md +159 -59
- model.safetensors +1 -1
- training_args.bin +0 -0
README.md
CHANGED
@@ -14,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
-
- Mean Iou: 0.
|
19 |
-
- Mean Accuracy: 0.
|
20 |
-
- Overall Accuracy: 0.
|
21 |
-
- Per Category Iou: [0.
|
22 |
-
- Per Category Accuracy: [0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -44,63 +44,163 @@ The following hyperparameters were used during training:
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- num_epochs:
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch | Step
|
53 |
-
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
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 |
|
105 |
|
106 |
### Framework versions
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.0066
|
18 |
+
- Mean Iou: 0.9629
|
19 |
+
- Mean Accuracy: 0.9797
|
20 |
+
- Overall Accuracy: 0.9836
|
21 |
+
- Per Category Iou: [0.9692175312609669, 0.9409913155132091, 0.9786172086221661]
|
22 |
+
- Per Category Accuracy: [0.987259136430285, 0.9605042508276654, 0.9912807638727336]
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 150
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
|
53 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:-------------:|:----------------:|:------------------------------------------------------------:|:------------------------------------------------------------:|
|
54 |
+
| 0.0644 | 1.0 | 703 | 0.0602 | 0.9215 | 0.9561 | 0.9656 | [0.9488900547265257, 0.858714880567619, 0.956821518780209] | [0.9750296555181103, 0.9095148319868143, 0.9837895725347586] |
|
55 |
+
| 0.0594 | 2.0 | 1406 | 0.0515 | 0.9276 | 0.9621 | 0.9679 | [0.9498494262089401, 0.8745879807633978, 0.9583459684709161] | [0.9747017105780725, 0.9332846754222092, 0.9783558790238072] |
|
56 |
+
| 0.0557 | 3.0 | 2109 | 0.0509 | 0.9273 | 0.9602 | 0.9682 | [0.9516704869008551, 0.8698636007361549, 0.9602165778842959] | [0.982021029018859, 0.9173631910754904, 0.9810805853534331] |
|
57 |
+
| 0.0542 | 4.0 | 2812 | 0.0460 | 0.9305 | 0.9618 | 0.9697 | [0.9514638086703642, 0.8769434427599598, 0.9631025471791594] | [0.9771301423130867, 0.9230748391287825, 0.985061931059963] |
|
58 |
+
| 0.0538 | 5.0 | 3515 | 0.0447 | 0.9316 | 0.9623 | 0.9702 | [0.9499686626332431, 0.880516769586933, 0.9643916679409397] | [0.972741543135194, 0.9265187116263822, 0.9875414921750425] |
|
59 |
+
| 0.0509 | 6.0 | 4218 | 0.0434 | 0.9338 | 0.9645 | 0.9709 | [0.9517432911664182, 0.8860351150900324, 0.9637545034132892] | [0.9760356886207853, 0.9338053998522474, 0.9836627081143814] |
|
60 |
+
| 0.0495 | 7.0 | 4921 | 0.0415 | 0.9346 | 0.9641 | 0.9714 | [0.9519500096020929, 0.8866501910431814, 0.965227753180207] | [0.9739650243448873, 0.9307452978457196, 0.9874817830361603] |
|
61 |
+
| 0.0473 | 8.0 | 5624 | 0.0393 | 0.9359 | 0.9642 | 0.9722 | [0.9570126030790405, 0.8853964186808599, 0.9653558577278415] | [0.9828867941543495, 0.9232989265176934, 0.9863489762483582] |
|
62 |
+
| 0.0469 | 9.0 | 6327 | 0.0396 | 0.9361 | 0.9640 | 0.9723 | [0.9565153205113766, 0.8858389646611121, 0.9658720149436106] | [0.9810315868200781, 0.9230764761875282, 0.9879226323032873] |
|
63 |
+
| 0.0445 | 10.0 | 7030 | 0.0383 | 0.9382 | 0.9670 | 0.9728 | [0.9548345124022747, 0.8941359287598728, 0.9655050223799434] | [0.9783271217537259, 0.9387489079994646, 0.9839140351147748] |
|
64 |
+
| 0.0448 | 11.0 | 7733 | 0.0362 | 0.9403 | 0.9674 | 0.9738 | [0.957445014043969, 0.8971003391404624, 0.9663794895449994] | [0.9808007786355918, 0.9356333356548291, 0.9857758770135236] |
|
65 |
+
| 0.0436 | 12.0 | 8436 | 0.0380 | 0.9377 | 0.9649 | 0.9731 | [0.9568320234926181, 0.8885953911553187, 0.9675573931999086] | [0.9809814801064592, 0.9251014379993896, 0.9887158871130656] |
|
66 |
+
| 0.0433 | 13.0 | 9139 | 0.0361 | 0.9393 | 0.9669 | 0.9735 | [0.958794603986862, 0.8932653255806002, 0.965856313133857] | [0.983646340250856, 0.9325787337664039, 0.9844714195762458] |
|
67 |
+
| 0.0417 | 14.0 | 9842 | 0.0342 | 0.9407 | 0.9670 | 0.9743 | [0.9600771510865321, 0.894093256801968, 0.9678304589796617] | [0.9868027998611579, 0.9282458585133847, 0.9859813021759077] |
|
68 |
+
| 0.0412 | 15.0 | 10545 | 0.0330 | 0.9422 | 0.9676 | 0.9749 | [0.9584029515410957, 0.8990055611097977, 0.9690572821834622] | [0.9808707905800149, 0.9328364607161251, 0.9892094456200264] |
|
69 |
+
| 0.0408 | 16.0 | 11248 | 0.0323 | 0.9432 | 0.9689 | 0.9753 | [0.9592513845946194, 0.90111842764418, 0.9691455184085999] | [0.9835475527549636, 0.9363874008485175, 0.9866347121275111] |
|
70 |
+
| 0.041 | 17.0 | 11951 | 0.0320 | 0.9431 | 0.9682 | 0.9753 | [0.9595691381438718, 0.9004062270005743, 0.9693793367274567] | [0.9821184740838905, 0.9334352648626791, 0.9890147171783757] |
|
71 |
+
| 0.0394 | 18.0 | 12654 | 0.0324 | 0.9426 | 0.9680 | 0.9750 | [0.9582686676555241, 0.9007288570225, 0.9689165074803285] | [0.9790397791168115, 0.9355476096761232, 0.9895368177737062] |
|
72 |
+
| 0.0382 | 19.0 | 13357 | 0.0301 | 0.9455 | 0.9701 | 0.9762 | [0.9588638242347168, 0.907231685601286, 0.970450376418907] | [0.981077210200008, 0.9408003023208292, 0.9883717283264806] |
|
73 |
+
| 0.0376 | 20.0 | 14060 | 0.0307 | 0.9446 | 0.9690 | 0.9760 | [0.9589674005708341, 0.9040449961697249, 0.970932772720938] | [0.9802715654131231, 0.9364152208651283, 0.9904151213569217] |
|
74 |
+
| 0.0374 | 21.0 | 14763 | 0.0311 | 0.9438 | 0.9690 | 0.9755 | [0.9573458046337128, 0.9036942376460201, 0.9703032303103111] | [0.9781772448077471, 0.9393956460246569, 0.9895027982643313] |
|
75 |
+
| 0.0381 | 22.0 | 15466 | 0.0294 | 0.9459 | 0.9700 | 0.9765 | [0.9623733947171658, 0.9054363695777944, 0.9699137555977049] | [0.9859171423410915, 0.9367571066092684, 0.9874283038074311] |
|
76 |
+
| 0.0364 | 23.0 | 16169 | 0.0284 | 0.9468 | 0.9710 | 0.9767 | [0.9593273628994687, 0.9105318366922983, 0.9705468917582745] | [0.9806120611182436, 0.9443446642720423, 0.9881121195705256] |
|
77 |
+
| 0.0355 | 24.0 | 16872 | 0.0277 | 0.9462 | 0.9694 | 0.9768 | [0.9617693240266973, 0.9047501672031698, 0.9720646168231932] | [0.9842734866950329, 0.9329935484812502, 0.9909904474346409] |
|
78 |
+
| 0.0351 | 25.0 | 17575 | 0.0270 | 0.9476 | 0.9710 | 0.9772 | [0.9608154314127586, 0.9101178014252029, 0.9718080308315211] | [0.9824806092606405, 0.9413361994904614, 0.9892765834017737] |
|
79 |
+
| 0.034 | 26.0 | 18278 | 0.0272 | 0.9480 | 0.9719 | 0.9771 | [0.9601502166075315, 0.913009884175695, 0.9707571967259514] | [0.9820325263932185, 0.9466118309217378, 0.9871239088223774] |
|
80 |
+
| 0.0344 | 27.0 | 18981 | 0.0262 | 0.9488 | 0.9721 | 0.9775 | [0.9610291616089548, 0.9138020622066821, 0.9714401382168945] | [0.9829688237453795, 0.945485814002556, 0.9878522964426623] |
|
81 |
+
| 0.0332 | 28.0 | 19684 | 0.0265 | 0.9482 | 0.9718 | 0.9773 | [0.9612863009635559, 0.9123821477614371, 0.9710095584404448] | [0.9826317322907677, 0.9446683427286697, 0.9879750221727271] |
|
82 |
+
| 0.0333 | 29.0 | 20387 | 0.0294 | 0.9459 | 0.9698 | 0.9766 | [0.9617738173790127, 0.9048911824517005, 0.9709824327566654] | [0.9844162468305143, 0.9359338856656411, 0.9890328469169108] |
|
83 |
+
| 0.0328 | 30.0 | 21090 | 0.0259 | 0.9491 | 0.9724 | 0.9776 | [0.963554876496053, 0.9134236893404624, 0.9702009378676808] | [0.9855390906874351, 0.9451134330482452, 0.9864310194401416] |
|
84 |
+
| 0.0323 | 31.0 | 21793 | 0.0245 | 0.9497 | 0.9721 | 0.9781 | [0.963104705908238, 0.9132362637553983, 0.9726794488344207] | [0.9848953726087067, 0.9423553883444232, 0.9891913465060496] |
|
85 |
+
| 0.0316 | 32.0 | 22496 | 0.0249 | 0.9498 | 0.9728 | 0.9779 | [0.9618619911221874, 0.9162336898230669, 0.9713578264582455] | [0.9820750795245765, 0.9482254517775548, 0.9880744951131408] |
|
86 |
+
| 0.0305 | 33.0 | 23199 | 0.0253 | 0.9492 | 0.9721 | 0.9778 | [0.9619740832502129, 0.9134094510831107, 0.9721247074138021] | [0.9842442422562293, 0.9435898104951776, 0.9884312274683914] |
|
87 |
+
| 0.0309 | 34.0 | 23902 | 0.0233 | 0.9518 | 0.9742 | 0.9786 | [0.9627873694381874, 0.9208971321288586, 0.9716191028744446] | [0.9833334253979698, 0.9523100231507058, 0.9869693641762011] |
|
88 |
+
| 0.0306 | 35.0 | 24605 | 0.0234 | 0.9514 | 0.9742 | 0.9785 | [0.9640633992652178, 0.918858070095666, 0.9712314537303415] | [0.9849803889478246, 0.9515956666136652, 0.9859238461295317] |
|
89 |
+
| 0.0304 | 36.0 | 25308 | 0.0233 | 0.9507 | 0.9726 | 0.9786 | [0.9623740811921626, 0.9158835928639305, 0.9738562357152244] | [0.9830946589750302, 0.9441557736461631, 0.9906012574224906] |
|
90 |
+
| 0.0301 | 37.0 | 26011 | 0.0230 | 0.9509 | 0.9727 | 0.9787 | [0.9632679549222042, 0.9156238636961606, 0.9738248600940046] | [0.9854968779811278, 0.9426184057888713, 0.9898906101713565] |
|
91 |
+
| 0.0293 | 38.0 | 26714 | 0.0222 | 0.9522 | 0.9741 | 0.9790 | [0.9628341038507403, 0.9207075111218522, 0.9730614445026444] | [0.9834675592911246, 0.9502198784509834, 0.9885331634982827] |
|
92 |
+
| 0.0293 | 39.0 | 27417 | 0.0229 | 0.9516 | 0.9741 | 0.9786 | [0.9621065427103511, 0.9205669130175268, 0.9722516840326719] | [0.983122528867402, 0.9518272106055213, 0.9873343957867607] |
|
93 |
+
| 0.0284 | 40.0 | 28120 | 0.0227 | 0.9514 | 0.9736 | 0.9786 | [0.9632565545023931, 0.9186293568120393, 0.9721963074479065] | [0.9837980028225732, 0.9488561685875837, 0.9881227331674576] |
|
94 |
+
| 0.0281 | 41.0 | 28823 | 0.0214 | 0.9521 | 0.9736 | 0.9792 | [0.9646667171352951, 0.9181894725489236, 0.9735845756291637] | [0.985618390454944, 0.9456720893272684, 0.9894248018891852] |
|
95 |
+
| 0.0274 | 42.0 | 29526 | 0.0203 | 0.9535 | 0.9744 | 0.9797 | [0.9640444516340392, 0.9222104329042415, 0.9742595606980595] | [0.9846780915026567, 0.948503072983862, 0.9898894989373825] |
|
96 |
+
| 0.0279 | 43.0 | 30229 | 0.0219 | 0.9526 | 0.9740 | 0.9792 | [0.9622845033728894, 0.9215969001346226, 0.9740492207007744] | [0.981892457542573, 0.9498366070631877, 0.9903131328277875] |
|
97 |
+
| 0.0271 | 44.0 | 30932 | 0.0211 | 0.9526 | 0.9739 | 0.9793 | [0.9638488450502855, 0.9199867127166081, 0.9738747203133774] | [0.9849460959412856, 0.9473312184198017, 0.9894295005714214] |
|
98 |
+
| 0.0271 | 45.0 | 31635 | 0.0202 | 0.9541 | 0.9748 | 0.9799 | [0.9656159722050082, 0.9225063292335267, 0.9741266970989171] | [0.9858285226349258, 0.94925062987083, 0.989327153297461] |
|
99 |
+
| 0.0265 | 46.0 | 32338 | 0.0209 | 0.9529 | 0.9741 | 0.9794 | [0.9656771412708731, 0.919781942390742, 0.9732876590013864] | [0.9865358745057092, 0.9469456411748703, 0.9888144719412875] |
|
100 |
+
| 0.0267 | 47.0 | 33041 | 0.0197 | 0.9542 | 0.9748 | 0.9799 | [0.963775425004481, 0.9239493373447729, 0.9747729931565428] | [0.9835161116111149, 0.9507712478221754, 0.9902508162265097] |
|
101 |
+
| 0.0259 | 48.0 | 33744 | 0.0198 | 0.9538 | 0.9745 | 0.9799 | [0.9652553159863687, 0.921794203102663, 0.9744257714741004] | [0.9854631566317498, 0.9481204404482598, 0.9899405369513187] |
|
102 |
+
| 0.0254 | 49.0 | 34447 | 0.0193 | 0.9543 | 0.9748 | 0.9800 | [0.9659089616504476, 0.9227580497685877, 0.9742185011450962] | [0.9861386883949486, 0.948657655250541, 0.9895942256957763] |
|
103 |
+
| 0.0252 | 50.0 | 35150 | 0.0184 | 0.9551 | 0.9755 | 0.9803 | [0.9648975826259499, 0.9255623898515872, 0.974955308716621] | [0.9845925035063781, 0.9519886605332797, 0.9898466551802698] |
|
104 |
+
| 0.0254 | 51.0 | 35853 | 0.0190 | 0.9552 | 0.9757 | 0.9802 | [0.9644075669316847, 0.9271735181516738, 0.9740344749036136] | [0.984193846502473, 0.9539906436303087, 0.9889583373664783] |
|
105 |
+
| 0.0251 | 52.0 | 36556 | 0.0189 | 0.9555 | 0.9764 | 0.9802 | [0.9659094646352488, 0.9278659843731774, 0.9727047454747583] | [0.9856714774935365, 0.9569640713619062, 0.9866276641041567] |
|
106 |
+
| 0.0251 | 53.0 | 37259 | 0.0184 | 0.9548 | 0.9750 | 0.9803 | [0.9660789255898211, 0.9234079498059568, 0.9748050006196802] | [0.986322729885183, 0.9487987018363716, 0.9899233434492812] |
|
107 |
+
| 0.0243 | 54.0 | 37962 | 0.0182 | 0.9547 | 0.9751 | 0.9803 | [0.964677130061807, 0.9240868367587143, 0.9754685041619142] | [0.984399071423231, 0.9500936951607156, 0.9906629396579171] |
|
108 |
+
| 0.0246 | 55.0 | 38665 | 0.0181 | 0.9555 | 0.9760 | 0.9804 | [0.9652588196054644, 0.9271448562388986, 0.9741874135037982] | [0.9851786769052819, 0.9542000474008363, 0.98856453617083] |
|
109 |
+
| 0.0247 | 56.0 | 39368 | 0.0171 | 0.9556 | 0.9751 | 0.9807 | [0.9668764848323738, 0.9237712198790987, 0.97602167762341] | [0.9869440955266093, 0.9471825355538465, 0.9912227697091182] |
|
110 |
+
| 0.0234 | 57.0 | 40071 | 0.0175 | 0.9554 | 0.9751 | 0.9806 | [0.9659033290417283, 0.9242774410862465, 0.9759142140243594] | [0.9855347936240572, 0.948296334424829, 0.9914061145649415] |
|
111 |
+
| 0.0232 | 58.0 | 40774 | 0.0169 | 0.9566 | 0.9767 | 0.9808 | [0.965772921393216, 0.9292838120308848, 0.9747147144121168] | [0.9853431022048496, 0.9560651963436851, 0.9885804215667328] |
|
112 |
+
| 0.0231 | 59.0 | 41477 | 0.0162 | 0.9565 | 0.9760 | 0.9810 | [0.9668704166973582, 0.9270338755766847, 0.9754748357999589] | [0.9867766256709264, 0.9513348751698286, 0.9899670271942796] |
|
113 |
+
| 0.0225 | 60.0 | 42180 | 0.0170 | 0.9559 | 0.9756 | 0.9808 | [0.9667364910399919, 0.9252502799674737, 0.9756315952770159] | [0.9868792863046617, 0.9493967972562736, 0.9903744169439557] |
|
114 |
+
| 0.0226 | 61.0 | 42883 | 0.0162 | 0.9570 | 0.9767 | 0.9810 | [0.9656834664832764, 0.9299447856540144, 0.9753185326304815] | [0.9852957124685235, 0.9554851385161821, 0.9893098591718748] |
|
115 |
+
| 0.0226 | 62.0 | 43586 | 0.0166 | 0.9561 | 0.9756 | 0.9809 | [0.9670135255807017, 0.9258183383655468, 0.9754792776692298] | [0.986957140871483, 0.9494775022560217, 0.9904411697312553] |
|
116 |
+
| 0.0225 | 63.0 | 44289 | 0.0168 | 0.9563 | 0.9759 | 0.9808 | [0.9658633984079354, 0.9275919591339042, 0.9753019850122024] | [0.985678684227632, 0.9518338287149627, 0.9901811366064205] |
|
117 |
+
| 0.0222 | 64.0 | 44992 | 0.0167 | 0.9558 | 0.9756 | 0.9808 | [0.9669921697416386, 0.9250847530141832, 0.9754481238595454] | [0.9872421729857692, 0.9496781916833483, 0.9899561904755655] |
|
118 |
+
| 0.0217 | 65.0 | 45695 | 0.0154 | 0.9573 | 0.9766 | 0.9813 | [0.9676949909839893, 0.9285896111491284, 0.9757470905817905] | [0.9873413330222833, 0.9524278314880005, 0.9898939569980889] |
|
119 |
+
| 0.0212 | 66.0 | 46398 | 0.0156 | 0.9580 | 0.9774 | 0.9813 | [0.9673406659874094, 0.9321843502497738, 0.9744747569384158] | [0.9866900677844084, 0.957487461003439, 0.9881469046938589] |
|
120 |
+
| 0.0215 | 67.0 | 47101 | 0.0153 | 0.9583 | 0.9777 | 0.9814 | [0.9674055187104679, 0.9328295188265814, 0.9745533030827458] | [0.9867960106294832, 0.9582294578799109, 0.9879589005302314] |
|
121 |
+
| 0.021 | 68.0 | 47804 | 0.0151 | 0.9573 | 0.9764 | 0.9814 | [0.9673727588182617, 0.9285476759781507, 0.9761020687161724] | [0.9872654439283972, 0.9516439997749244, 0.9903561909568085] |
|
122 |
+
| 0.0205 | 69.0 | 48507 | 0.0143 | 0.9586 | 0.9777 | 0.9817 | [0.9668348808674496, 0.9335526089970815, 0.975538278684172] | [0.9859748154831993, 0.9580925438692065, 0.9890573071891479] |
|
123 |
+
| 0.0201 | 70.0 | 49210 | 0.0149 | 0.9578 | 0.9768 | 0.9814 | [0.9662814622649897, 0.9307048673538354, 0.9762661042257195] | [0.9854181434476657, 0.9542085321565303, 0.9906798881634878] |
|
124 |
+
| 0.0198 | 71.0 | 49913 | 0.0145 | 0.9584 | 0.9775 | 0.9816 | [0.967006269024349, 0.9327651074421665, 0.9755072239840552] | [0.9861746835267419, 0.9570783560300714, 0.9892327071595515] |
|
125 |
+
| 0.0198 | 72.0 | 50616 | 0.0139 | 0.9590 | 0.9778 | 0.9818 | [0.9664973538737562, 0.934609366246807, 0.9759164757045634] | [0.9855979777981205, 0.9584057211929043, 0.9895003570495382] |
|
126 |
+
| 0.0192 | 73.0 | 51319 | 0.0146 | 0.9589 | 0.9780 | 0.9816 | [0.9672834350657578, 0.9347179231314434, 0.9746141369802527] | [0.9863913929756309, 0.9596022813691325, 0.9880577522296046] |
|
127 |
+
| 0.0199 | 74.0 | 52022 | 0.0146 | 0.9584 | 0.9774 | 0.9816 | [0.9672412490206483, 0.9322729730460434, 0.9757134071550831] | [0.9863958634630914, 0.9562087284638309, 0.9895434458031176] |
|
128 |
+
| 0.0191 | 75.0 | 52725 | 0.0135 | 0.9594 | 0.9780 | 0.9820 | [0.9672857834352663, 0.9347080600072638, 0.9761483790431779] | [0.9862803758703641, 0.958231963378357, 0.9895333528236773] |
|
129 |
+
| 0.0191 | 76.0 | 53428 | 0.0136 | 0.9586 | 0.9771 | 0.9819 | [0.9683639306728838, 0.9306089456911991, 0.9767924850591034] | [0.9877462589856155, 0.9528951718316253, 0.9906626815366397] |
|
130 |
+
| 0.0192 | 77.0 | 54131 | 0.0155 | 0.9573 | 0.9767 | 0.9813 | [0.9666653274553076, 0.9291974052852782, 0.9759818457704846] | [0.9862981165116941, 0.9541943176952266, 0.9897141777158432] |
|
131 |
+
| 0.0186 | 78.0 | 54834 | 0.0133 | 0.9594 | 0.9779 | 0.9821 | [0.9675867186857483, 0.9343614431628988, 0.9762812540249828] | [0.9863968140839882, 0.9572191730283951, 0.9900001673413367] |
|
132 |
+
| 0.0181 | 79.0 | 55537 | 0.0126 | 0.9597 | 0.9779 | 0.9822 | [0.9676709815203923, 0.9344677056058559, 0.9768917197695184] | [0.9865061162177724, 0.9567999162943913, 0.9904815810234486] |
|
133 |
+
| 0.0185 | 80.0 | 56240 | 0.0135 | 0.9592 | 0.9776 | 0.9820 | [0.9678527148723075, 0.933410244541323, 0.9763922878137811] | [0.9865692425838082, 0.9558939340455185, 0.9904017559246763] |
|
134 |
+
| 0.0179 | 81.0 | 56943 | 0.0128 | 0.9599 | 0.9783 | 0.9822 | [0.9668663017399266, 0.9364197077238793, 0.976387738013329] | [0.9853747810039225, 0.959577945093389, 0.9899302383498438] |
|
135 |
+
| 0.018 | 82.0 | 57646 | 0.0138 | 0.9584 | 0.9771 | 0.9818 | [0.9667206995737143, 0.9318374506185433, 0.9767459910905895] | [0.9855220501655494, 0.9548544516523497, 0.9909909068030159] |
|
136 |
+
| 0.0178 | 83.0 | 58349 | 0.0120 | 0.9597 | 0.9778 | 0.9824 | [0.9683353004403408, 0.933517209084423, 0.977391704189171] | [0.9873083760234911, 0.9550141746827727, 0.9909998010497443] |
|
137 |
+
| 0.0174 | 84.0 | 59052 | 0.0125 | 0.9596 | 0.9778 | 0.9823 | [0.9676176300368217, 0.9338412362142535, 0.9772656590086047] | [0.9864110669743252, 0.9561990059320121, 0.9908402427258745] |
|
138 |
+
| 0.0179 | 85.0 | 59755 | 0.0123 | 0.9593 | 0.9774 | 0.9823 | [0.9685368915816713, 0.9317958965539012, 0.9776135888525478] | [0.9875912692407597, 0.9532209764682089, 0.9913874292094194] |
|
139 |
+
| 0.0173 | 86.0 | 60458 | 0.0131 | 0.9597 | 0.9782 | 0.9821 | [0.96664641952289, 0.9359068750890123, 0.9765577987757101] | [0.9853937548831725, 0.9590263461346902, 0.9900519447196098] |
|
140 |
+
| 0.0176 | 87.0 | 61161 | 0.0120 | 0.9600 | 0.9781 | 0.9824 | [0.9683733873165324, 0.9347767485177334, 0.9768842555488277] | [0.9871603425112784, 0.9567829667471345, 0.9903599621524208] |
|
141 |
+
| 0.0173 | 88.0 | 61864 | 0.0115 | 0.9602 | 0.9781 | 0.9825 | [0.9684900178047416, 0.9346731821044149, 0.9773994930070459] | [0.9871787896951667, 0.9560616227642282, 0.9909517161182191] |
|
142 |
+
| 0.0173 | 89.0 | 62567 | 0.0124 | 0.9599 | 0.9782 | 0.9822 | [0.9669799054441661, 0.935770533187539, 0.9768304904501294] | [0.9858737670511201, 0.9586542247140829, 0.9901158669227317] |
|
143 |
+
| 0.0169 | 90.0 | 63270 | 0.0120 | 0.9607 | 0.9790 | 0.9824 | [0.9685351844435351, 0.9382962538248609, 0.9753814241698671] | [0.987400117363142, 0.9613217720118794, 0.9882838402189918] |
|
144 |
+
| 0.0164 | 91.0 | 63973 | 0.0117 | 0.9600 | 0.9781 | 0.9824 | [0.9671807957090698, 0.9352859341608122, 0.9776706189363686] | [0.9855821255523557, 0.9572557972267965, 0.9913294306708671] |
|
145 |
+
| 0.0162 | 92.0 | 64676 | 0.0115 | 0.9603 | 0.9782 | 0.9825 | [0.967678800230417, 0.9358720821317598, 0.9773804850623149] | [0.9861650488554909, 0.9576129355670547, 0.9909369857056592] |
|
146 |
+
| 0.0163 | 93.0 | 65379 | 0.0115 | 0.9602 | 0.9783 | 0.9825 | [0.9679751974551123, 0.9356549440319146, 0.9770787682903582] | [0.9869635254469652, 0.9574149712436157, 0.9903781268904512] |
|
147 |
+
| 0.0161 | 94.0 | 66082 | 0.0115 | 0.9595 | 0.9773 | 0.9824 | [0.967379140362912, 0.9323323924425675, 0.9787749419622164] | [0.9861292656864652, 0.9529445730738954, 0.992825002851912] |
|
148 |
+
| 0.0162 | 95.0 | 66785 | 0.0126 | 0.9595 | 0.9778 | 0.9822 | [0.9671138625077802, 0.9343389666126111, 0.9771193577288364] | [0.985883022758635, 0.9567853923890564, 0.9908032088849719] |
|
149 |
+
| 0.0157 | 96.0 | 67488 | 0.0111 | 0.9607 | 0.9785 | 0.9826 | [0.9685431317767654, 0.9364956746329776, 0.9769379328434297] | [0.9874231313812033, 0.9581495214992081, 0.9900627245641441] |
|
150 |
+
| 0.0155 | 97.0 | 68191 | 0.0110 | 0.9602 | 0.9780 | 0.9826 | [0.9673780371075875, 0.9351822837299785, 0.9781489448395797] | [0.9857437503741464, 0.956511764008958, 0.991842969514674] |
|
151 |
+
| 0.0153 | 98.0 | 68894 | 0.0106 | 0.9610 | 0.9788 | 0.9827 | [0.9679443337608646, 0.9378755659993178, 0.9772565251416925] | [0.9864703844336599, 0.959593327456359, 0.990345647358867] |
|
152 |
+
| 0.0158 | 99.0 | 69597 | 0.0103 | 0.9610 | 0.9786 | 0.9828 | [0.9677737338660091, 0.9372121387476409, 0.9780779792405301] | [0.9862304233114854, 0.9582422648699761, 0.9913185458278468] |
|
153 |
+
| 0.0155 | 100.0 | 70300 | 0.0104 | 0.9608 | 0.9784 | 0.9828 | [0.9682657646286412, 0.9362041244307882, 0.9779309416774175] | [0.9869386101871105, 0.9571233751455772, 0.9911956800998011] |
|
154 |
+
| 0.0147 | 101.0 | 71003 | 0.0099 | 0.9614 | 0.9788 | 0.9830 | [0.9684187834659572, 0.9379246169303714, 0.9778307024216076] | [0.9869229442116565, 0.9586235997370605, 0.9909439637300231] |
|
155 |
+
| 0.0148 | 102.0 | 71706 | 0.0101 | 0.9612 | 0.9788 | 0.9829 | [0.9676453129960675, 0.9381695914928828, 0.9778697225951213] | [0.9859449415792074, 0.9593510926723284, 0.9910914997272774] |
|
156 |
+
| 0.0149 | 103.0 | 72409 | 0.0099 | 0.9612 | 0.9787 | 0.9829 | [0.9688035974573844, 0.9369595175886385, 0.9778617882366799] | [0.9872567791473855, 0.9577156809674762, 0.9910463328786681] |
|
157 |
+
| 0.0143 | 104.0 | 73112 | 0.0107 | 0.9606 | 0.9784 | 0.9827 | [0.9686819599455223, 0.9355662097319184, 0.9775546324764184] | [0.9873767564969157, 0.9569961637025606, 0.9907564408094552] |
|
158 |
+
| 0.0146 | 105.0 | 73815 | 0.0097 | 0.9615 | 0.9790 | 0.9829 | [0.9686786490175888, 0.9385656495313478, 0.9771587952961006] | [0.9872932431665131, 0.959757582344529, 0.9900821361591926] |
|
159 |
+
| 0.0142 | 106.0 | 74518 | 0.0094 | 0.9616 | 0.9789 | 0.9831 | [0.9693983149593857, 0.9375819865204537, 0.977759181768692] | [0.9879063294137778, 0.958093013026286, 0.9907379960754629] |
|
160 |
+
| 0.0145 | 107.0 | 75221 | 0.0094 | 0.9615 | 0.9791 | 0.9830 | [0.9677304888589706, 0.9391294668668196, 0.9777763931115296] | [0.9858769786082037, 0.960602773814371, 0.9907868684956309] |
|
161 |
+
| 0.0141 | 108.0 | 75924 | 0.0094 | 0.9617 | 0.9791 | 0.9831 | [0.967707944885844, 0.9393642086756726, 0.9781109663544486] | [0.9858854571189044, 0.9602980912284326, 0.9911361722080164] |
|
162 |
+
| 0.0138 | 109.0 | 76627 | 0.0095 | 0.9621 | 0.9795 | 0.9831 | [0.9683069842379681, 0.9408203853976529, 0.9770472523443963] | [0.9864645329766535, 0.9622166542038915, 0.9898923732709293] |
|
163 |
+
| 0.0142 | 110.0 | 77330 | 0.0092 | 0.9617 | 0.9791 | 0.9831 | [0.9683636584287584, 0.9389140966171199, 0.9779244396064098] | [0.9866107294782145, 0.959672405379427, 0.9909502505143558] |
|
164 |
+
| 0.0135 | 111.0 | 78033 | 0.0091 | 0.9620 | 0.9793 | 0.9832 | [0.9679700403725364, 0.9403279298888509, 0.9778317088317193] | [0.986080758328274, 0.9611242269351924, 0.9908099244131213] |
|
165 |
+
| 0.0136 | 112.0 | 78736 | 0.0089 | 0.9623 | 0.9795 | 0.9832 | [0.9687913323741362, 0.9406188982781377, 0.977371366648687] | [0.9870778119173432, 0.9613594543092262, 0.9901459796134503] |
|
166 |
+
| 0.0139 | 113.0 | 79439 | 0.0092 | 0.9615 | 0.9789 | 0.9830 | [0.9688501404840005, 0.9377694773304518, 0.9779240904196521] | [0.9872297314136272, 0.9584068491663084, 0.9909950761178866] |
|
167 |
+
| 0.0136 | 114.0 | 80142 | 0.0088 | 0.9617 | 0.9788 | 0.9832 | [0.969048101666497, 0.9375285831616975, 0.9784175402711464] | [0.9872914446945462, 0.9576802645990029, 0.9915442531977234] |
|
168 |
+
| 0.0132 | 115.0 | 80845 | 0.0091 | 0.9616 | 0.9790 | 0.9831 | [0.96823991718996, 0.9384813615707703, 0.9781579255225712] | [0.98658060507277, 0.9592260373554645, 0.9911443008407863] |
|
169 |
+
| 0.0131 | 116.0 | 81548 | 0.0086 | 0.9621 | 0.9793 | 0.9832 | [0.9688492182759797, 0.9395083775763523, 0.9779841052180485] | [0.9870143772418274, 0.9597761390043351, 0.990970230851202] |
|
170 |
+
| 0.0129 | 117.0 | 82251 | 0.0085 | 0.9620 | 0.9791 | 0.9833 | [0.9693061290659299, 0.9383670709383501, 0.9782133297002469] | [0.9876113222031898, 0.9584860069459005, 0.9911491963951833] |
|
171 |
+
| 0.0127 | 118.0 | 82954 | 0.0084 | 0.9621 | 0.9792 | 0.9833 | [0.9694002434862922, 0.9389734399765844, 0.9780173018415159] | [0.9876993124441671, 0.9591490357020253, 0.990868137323582] |
|
172 |
+
| 0.0126 | 119.0 | 83657 | 0.0084 | 0.9621 | 0.9792 | 0.9832 | [0.9688877210695712, 0.9392884074744625, 0.9780389044191968] | [0.9871387736939047, 0.9595827863951674, 0.9909614678525808] |
|
173 |
+
| 0.0131 | 120.0 | 84360 | 0.0082 | 0.9623 | 0.9795 | 0.9833 | [0.9691304077322377, 0.9402794146879456, 0.9776196058317741] | [0.9873154671415317, 0.9607839283394704, 0.9904079420854602] |
|
174 |
+
| 0.0127 | 121.0 | 85063 | 0.0081 | 0.9626 | 0.9797 | 0.9833 | [0.9690667228997573, 0.9410734929684217, 0.9775551669651781] | [0.9872934487061664, 0.9614939726242052, 0.9902369520514571] |
|
175 |
+
| 0.0125 | 122.0 | 85766 | 0.0081 | 0.9623 | 0.9794 | 0.9833 | [0.9689032850777292, 0.9400098633080738, 0.9781328231469246] | [0.9870371086428653, 0.960270371032477, 0.9909470568104151] |
|
176 |
+
| 0.0123 | 123.0 | 86469 | 0.0082 | 0.9620 | 0.9791 | 0.9833 | [0.9687521807110532, 0.9387334939137629, 0.9785726745803575] | [0.9869141638145899, 0.9586928353435233, 0.9916080660274228] |
|
177 |
+
| 0.0125 | 124.0 | 87172 | 0.0079 | 0.9625 | 0.9795 | 0.9834 | [0.968405484088371, 0.9408674196365806, 0.978252057479581] | [0.9865067585291891, 0.9610519667628762, 0.9910471903663014] |
|
178 |
+
| 0.013 | 125.0 | 87875 | 0.0082 | 0.9621 | 0.9792 | 0.9832 | [0.9691789394135095, 0.9391165735674838, 0.9779006126999107] | [0.9876324414025718, 0.9591916491397401, 0.9907904428190825] |
|
179 |
+
| 0.0122 | 126.0 | 88578 | 0.0080 | 0.9621 | 0.9792 | 0.9834 | [0.9683365887361434, 0.939153109860424, 0.9789590980402502] | [0.9864211255711112, 0.9592140888230343, 0.9918618779919783] |
|
180 |
+
| 0.0123 | 127.0 | 89281 | 0.0078 | 0.9626 | 0.9796 | 0.9834 | [0.9689611038130307, 0.9408603433103387, 0.9780389313124326] | [0.9870172355276319, 0.9609942205138294, 0.9908095656682951] |
|
181 |
+
| 0.012 | 128.0 | 89984 | 0.0077 | 0.9625 | 0.9795 | 0.9834 | [0.9690097187969772, 0.9401745385210867, 0.978232465980128] | [0.9872581151551323, 0.960095624993443, 0.9910014504009576] |
|
182 |
+
| 0.0121 | 129.0 | 90687 | 0.0075 | 0.9625 | 0.9794 | 0.9835 | [0.969048078157809, 0.9398826692603933, 0.978641033957806] | [0.9871669968575556, 0.9595648985337514, 0.9914553063555036] |
|
183 |
+
| 0.0119 | 130.0 | 91390 | 0.0076 | 0.9624 | 0.9792 | 0.9835 | [0.9692013730033966, 0.9390981548838111, 0.9787956402289679] | [0.9873060508561626, 0.9586768041462945, 0.9917062089870172] |
|
184 |
+
| 0.0119 | 131.0 | 92093 | 0.0075 | 0.9622 | 0.9791 | 0.9834 | [0.969122061374489, 0.9383608422057673, 0.9790826565374158] | [0.9872148747505584, 0.9578784285637524, 0.992071144348965] |
|
185 |
+
| 0.0118 | 132.0 | 92796 | 0.0073 | 0.9625 | 0.9794 | 0.9835 | [0.9690383857242187, 0.93984435229497, 0.978737539863971] | [0.9871568804527422, 0.959494125689198, 0.9915308527659827] |
|
186 |
+
| 0.0117 | 133.0 | 93499 | 0.0073 | 0.9627 | 0.9796 | 0.9835 | [0.9691180721875395, 0.9408458112942945, 0.9782270506589438] | [0.9871971726479134, 0.9607280587187418, 0.9909539079616086] |
|
187 |
+
| 0.0116 | 134.0 | 94202 | 0.0073 | 0.9625 | 0.9794 | 0.9835 | [0.9694006836733288, 0.9396550796148553, 0.9785404571043299] | [0.9875725458629621, 0.9593458620699947, 0.9912954899103564] |
|
188 |
+
| 0.0122 | 135.0 | 94905 | 0.0072 | 0.9628 | 0.9797 | 0.9835 | [0.9691274392491813, 0.9412225984443038, 0.9780899387591124] | [0.9871874673224067, 0.9613001608400236, 0.9907265293658343] |
|
189 |
+
| 0.0117 | 136.0 | 95608 | 0.0070 | 0.9629 | 0.9797 | 0.9836 | [0.9691230773787279, 0.9411462600198316, 0.978352234024845] | [0.9871871076280133, 0.960824455525491, 0.991054229639782] |
|
190 |
+
| 0.0113 | 137.0 | 96311 | 0.0070 | 0.9626 | 0.9794 | 0.9835 | [0.9692373191106431, 0.9397033547954136, 0.9788490905235756] | [0.9873135080917108, 0.9591667039579997, 0.9916645027134999] |
|
191 |
+
| 0.0116 | 138.0 | 97014 | 0.0070 | 0.9628 | 0.9796 | 0.9836 | [0.9690748071729751, 0.9406267188745966, 0.9786395532555509] | [0.987116973644421, 0.9602779673843396, 0.9913544115605958] |
|
192 |
+
| 0.0109 | 139.0 | 97717 | 0.0070 | 0.9627 | 0.9795 | 0.9836 | [0.9689676748470574, 0.9403530438264758, 0.9788306968708289] | [0.9869944655879089, 0.9598867702365191, 0.9916087747672014] |
|
193 |
+
| 0.0119 | 140.0 | 98420 | 0.0068 | 0.9630 | 0.9798 | 0.9836 | [0.9694171791438227, 0.9413859316145166, 0.9781638481383007] | [0.9875423764957185, 0.9610502598296718, 0.9907741680537951] |
|
194 |
+
| 0.0111 | 141.0 | 99123 | 0.0068 | 0.9628 | 0.9795 | 0.9836 | [0.968992054486061, 0.9405571081129813, 0.978841146740079] | [0.987006296964205, 0.9600244329021377, 0.9916010967529327] |
|
195 |
+
| 0.011 | 142.0 | 99826 | 0.0068 | 0.9631 | 0.9798 | 0.9836 | [0.9690262557302001, 0.9418523830686173, 0.9782879003822961] | [0.9870485096705123, 0.961594372239229, 0.9909037143104952] |
|
196 |
+
| 0.011 | 143.0 | 100529 | 0.0068 | 0.9630 | 0.9797 | 0.9836 | [0.9693670594350259, 0.941075091280133, 0.97845245148423] | [0.9874059688201484, 0.9606348262267632, 0.9911101719579888] |
|
197 |
+
| 0.0108 | 144.0 | 101232 | 0.0068 | 0.9628 | 0.9796 | 0.9836 | [0.9688858122449424, 0.9407034073369066, 0.9787364616899126] | [0.9869104576777153, 0.9602466935730581, 0.9915104961845629] |
|
198 |
+
| 0.011 | 145.0 | 101935 | 0.0067 | 0.9630 | 0.9797 | 0.9836 | [0.9692167021307575, 0.9412647429904929, 0.9784782542501246] | [0.987246463626033, 0.9608329203170539, 0.9911353453449413] |
|
199 |
+
| 0.011 | 146.0 | 102638 | 0.0066 | 0.9630 | 0.9798 | 0.9836 | [0.9692755568602468, 0.9413758458670632, 0.978464000364329] | [0.9873026466056539, 0.9609106905895385, 0.9911017808290046] |
|
200 |
+
| 0.0107 | 147.0 | 103341 | 0.0066 | 0.9630 | 0.9797 | 0.9836 | [0.9692395328714667, 0.9410463410149368, 0.9786018743718753] | [0.9872785406581842, 0.9605293058121265, 0.991269157165124] |
|
201 |
+
| 0.0106 | 148.0 | 104044 | 0.0066 | 0.9630 | 0.9797 | 0.9836 | [0.9691812568631686, 0.9412787850135675, 0.9785306435423181] | [0.9872042894584108, 0.9608338087208854, 0.9911813871809317] |
|
202 |
+
| 0.0109 | 149.0 | 104747 | 0.0066 | 0.9630 | 0.9797 | 0.9836 | [0.9690361569813096, 0.9413478367720466, 0.9786017265887093] | [0.9870385281510963, 0.9608913653106872, 0.9912703646477099] |
|
203 |
+
| 0.0107 | 150.0 | 105450 | 0.0066 | 0.9629 | 0.9797 | 0.9836 | [0.9692175312609669, 0.9409913155132091, 0.9786172086221661] | [0.987259136430285, 0.9605042508276654, 0.9912807638727336] |
|
204 |
|
205 |
|
206 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 309088476
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c6bd496e9504290c2f661e301fff9200da5b1e256a1cb707bdffd65334b161b
|
3 |
size 309088476
|
training_args.bin
CHANGED
Binary files a/training_args.bin and b/training_args.bin differ
|
|