Commit
•
df23032
1
Parent(s):
f70cad9
End of training
Browse files- README.md +138 -0
- model.safetensors +1 -1
- trainer_state.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: microsoft/conditional-detr-resnet-50
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ms-cond-detr-res-50-vehicles
|
| 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 |
+
# ms-cond-detr-res-50-vehicles
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.2453
|
| 20 |
+
- Map: 0.3085
|
| 21 |
+
- Map 50: 0.5989
|
| 22 |
+
- Map 75: 0.2888
|
| 23 |
+
- Map Small: 0.0295
|
| 24 |
+
- Map Medium: 0.272
|
| 25 |
+
- Map Large: 0.5812
|
| 26 |
+
- Mar 1: 0.1973
|
| 27 |
+
- Mar 10: 0.4012
|
| 28 |
+
- Mar 100: 0.4549
|
| 29 |
+
- Mar Small: 0.1586
|
| 30 |
+
- Mar Medium: 0.435
|
| 31 |
+
- Mar Large: 0.6786
|
| 32 |
+
- Map Motorbike: 0.2
|
| 33 |
+
- Mar 100 Motorbike: 0.3339
|
| 34 |
+
- Map Car: 0.3354
|
| 35 |
+
- Mar 100 Car: 0.4573
|
| 36 |
+
- Map Bus: 0.3511
|
| 37 |
+
- Mar 100 Bus: 0.5331
|
| 38 |
+
- Map Container: 0.3477
|
| 39 |
+
- Mar 100 Container: 0.4953
|
| 40 |
+
|
| 41 |
+
## Model description
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Intended uses & limitations
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training and evaluation data
|
| 50 |
+
|
| 51 |
+
More information needed
|
| 52 |
+
|
| 53 |
+
## Training procedure
|
| 54 |
+
|
| 55 |
+
### Training hyperparameters
|
| 56 |
+
|
| 57 |
+
The following hyperparameters were used during training:
|
| 58 |
+
- learning_rate: 0.0001
|
| 59 |
+
- train_batch_size: 4
|
| 60 |
+
- eval_batch_size: 8
|
| 61 |
+
- seed: 42
|
| 62 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 63 |
+
- lr_scheduler_type: cosine_with_restarts
|
| 64 |
+
- num_epochs: 60
|
| 65 |
+
- mixed_precision_training: Native AMP
|
| 66 |
+
|
| 67 |
+
### Training results
|
| 68 |
+
|
| 69 |
+
| Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Motorbike | Mar 100 Motorbike | Map Car | Mar 100 Car | Map Bus | Mar 100 Bus | Map Container | Mar 100 Container |
|
| 70 |
+
|:-------------:|:-----:|:------:|:---------------:|:------:|:------:|:------:|:---------:|:----------:|:---------:|:------:|:------:|:-------:|:---------:|:----------:|:---------:|:-------------:|:-----------------:|:-------:|:-----------:|:-------:|:-----------:|:-------------:|:-----------------:|
|
| 71 |
+
| 2.051 | 1.0 | 2305 | 1.8960 | 0.0623 | 0.1484 | 0.0432 | 0.0085 | 0.0546 | 0.1451 | 0.0883 | 0.2294 | 0.2984 | 0.0421 | 0.2854 | 0.4778 | 0.0269 | 0.2141 | 0.0878 | 0.3206 | 0.0489 | 0.3264 | 0.0856 | 0.3323 |
|
| 72 |
+
| 1.7617 | 2.0 | 4610 | 1.6729 | 0.1472 | 0.3286 | 0.1129 | 0.0156 | 0.1211 | 0.3455 | 0.1272 | 0.3047 | 0.3573 | 0.0626 | 0.3404 | 0.6163 | 0.0705 | 0.2297 | 0.2083 | 0.3575 | 0.1128 | 0.4427 | 0.1971 | 0.3994 |
|
| 73 |
+
| 1.6489 | 3.0 | 6915 | 1.5874 | 0.1778 | 0.3853 | 0.1458 | 0.0131 | 0.1542 | 0.3729 | 0.1417 | 0.3206 | 0.365 | 0.0747 | 0.343 | 0.6265 | 0.1172 | 0.2491 | 0.2354 | 0.3691 | 0.1352 | 0.4474 | 0.2234 | 0.3944 |
|
| 74 |
+
| 1.5998 | 4.0 | 9220 | 1.5528 | 0.1929 | 0.4053 | 0.1639 | 0.0144 | 0.1638 | 0.4082 | 0.1504 | 0.3294 | 0.3756 | 0.07 | 0.3567 | 0.6317 | 0.1219 | 0.2477 | 0.2425 | 0.3745 | 0.1675 | 0.4699 | 0.2398 | 0.4104 |
|
| 75 |
+
| 1.552 | 5.0 | 11525 | 1.5257 | 0.2026 | 0.4239 | 0.1723 | 0.0163 | 0.1671 | 0.4281 | 0.1528 | 0.3307 | 0.3791 | 0.0996 | 0.3542 | 0.6259 | 0.1269 | 0.2577 | 0.2487 | 0.3765 | 0.1926 | 0.4657 | 0.2421 | 0.4165 |
|
| 76 |
+
| 1.5478 | 6.0 | 13830 | 1.5408 | 0.1996 | 0.424 | 0.164 | 0.0161 | 0.1588 | 0.4241 | 0.1529 | 0.3225 | 0.37 | 0.0782 | 0.3413 | 0.6196 | 0.1162 | 0.2455 | 0.2419 | 0.3579 | 0.1989 | 0.4587 | 0.2416 | 0.4178 |
|
| 77 |
+
| 1.5026 | 7.0 | 16135 | 1.4731 | 0.2228 | 0.4631 | 0.1881 | 0.0224 | 0.1862 | 0.4556 | 0.1628 | 0.3411 | 0.3918 | 0.1103 | 0.3684 | 0.6375 | 0.1395 | 0.266 | 0.2595 | 0.3906 | 0.2327 | 0.4761 | 0.2596 | 0.4347 |
|
| 78 |
+
| 1.4959 | 8.0 | 18440 | 1.4506 | 0.2326 | 0.4723 | 0.2016 | 0.02 | 0.1948 | 0.4815 | 0.1679 | 0.3488 | 0.3983 | 0.1042 | 0.3758 | 0.6462 | 0.146 | 0.2752 | 0.2738 | 0.4008 | 0.2383 | 0.4799 | 0.2721 | 0.4372 |
|
| 79 |
+
| 1.4923 | 9.0 | 20745 | 1.4424 | 0.2329 | 0.4795 | 0.2007 | 0.025 | 0.194 | 0.4755 | 0.1668 | 0.3462 | 0.3973 | 0.1091 | 0.3766 | 0.6412 | 0.1455 | 0.2741 | 0.27 | 0.4004 | 0.2454 | 0.4772 | 0.2706 | 0.4375 |
|
| 80 |
+
| 1.4813 | 10.0 | 23050 | 1.4419 | 0.2347 | 0.4795 | 0.2034 | 0.0219 | 0.1962 | 0.4789 | 0.1701 | 0.3484 | 0.3954 | 0.0978 | 0.3714 | 0.6499 | 0.1452 | 0.2714 | 0.2691 | 0.3916 | 0.2558 | 0.4847 | 0.2689 | 0.434 |
|
| 81 |
+
| 1.4833 | 11.0 | 25355 | 1.4289 | 0.2451 | 0.4962 | 0.2143 | 0.0243 | 0.2044 | 0.5032 | 0.1738 | 0.3561 | 0.4058 | 0.1005 | 0.3869 | 0.6609 | 0.1465 | 0.2732 | 0.2791 | 0.4023 | 0.2705 | 0.5024 | 0.2843 | 0.4454 |
|
| 82 |
+
| 1.444 | 12.0 | 27660 | 1.4114 | 0.2497 | 0.5054 | 0.2185 | 0.0247 | 0.2101 | 0.5069 | 0.175 | 0.358 | 0.4062 | 0.1037 | 0.384 | 0.658 | 0.1532 | 0.278 | 0.2836 | 0.4052 | 0.2717 | 0.4934 | 0.2905 | 0.4483 |
|
| 83 |
+
| 1.4389 | 13.0 | 29965 | 1.4145 | 0.2491 | 0.5044 | 0.2154 | 0.0243 | 0.2081 | 0.5069 | 0.1778 | 0.3591 | 0.4036 | 0.0958 | 0.3811 | 0.6548 | 0.152 | 0.2712 | 0.2703 | 0.3905 | 0.2809 | 0.5021 | 0.2931 | 0.4506 |
|
| 84 |
+
| 1.4721 | 14.0 | 32270 | 1.4252 | 0.2426 | 0.4967 | 0.2135 | 0.0224 | 0.1982 | 0.5026 | 0.1728 | 0.3474 | 0.3944 | 0.1061 | 0.3668 | 0.6479 | 0.1402 | 0.27 | 0.2734 | 0.3894 | 0.2701 | 0.4776 | 0.2865 | 0.4408 |
|
| 85 |
+
| 1.4151 | 15.0 | 34575 | 1.3890 | 0.257 | 0.5144 | 0.2303 | 0.0218 | 0.2172 | 0.5145 | 0.1789 | 0.3604 | 0.4054 | 0.1104 | 0.3819 | 0.6357 | 0.1563 | 0.2845 | 0.284 | 0.4023 | 0.2907 | 0.4884 | 0.2968 | 0.4466 |
|
| 86 |
+
| 1.4085 | 16.0 | 36880 | 1.3739 | 0.2624 | 0.5264 | 0.2343 | 0.0266 | 0.2188 | 0.5278 | 0.1806 | 0.3683 | 0.42 | 0.1048 | 0.3994 | 0.6689 | 0.1615 | 0.2912 | 0.2917 | 0.4123 | 0.2938 | 0.5113 | 0.3026 | 0.465 |
|
| 87 |
+
| 1.3936 | 17.0 | 39185 | 1.3773 | 0.2668 | 0.5317 | 0.2387 | 0.0255 | 0.2246 | 0.5238 | 0.1833 | 0.3691 | 0.4148 | 0.1057 | 0.393 | 0.6592 | 0.1591 | 0.2889 | 0.2917 | 0.4058 | 0.3055 | 0.5058 | 0.311 | 0.4589 |
|
| 88 |
+
| 1.4062 | 18.0 | 41490 | 1.3631 | 0.2687 | 0.5359 | 0.2387 | 0.0249 | 0.226 | 0.5344 | 0.1848 | 0.3696 | 0.4176 | 0.1045 | 0.3957 | 0.6661 | 0.165 | 0.2953 | 0.2967 | 0.4178 | 0.3014 | 0.5015 | 0.3116 | 0.4559 |
|
| 89 |
+
| 1.3825 | 19.0 | 43795 | 1.3477 | 0.2706 | 0.5411 | 0.2421 | 0.0256 | 0.232 | 0.5328 | 0.1835 | 0.3693 | 0.421 | 0.1243 | 0.3959 | 0.6464 | 0.1661 | 0.2991 | 0.3005 | 0.4221 | 0.3013 | 0.4967 | 0.3143 | 0.4661 |
|
| 90 |
+
| 1.3704 | 20.0 | 46100 | 1.3514 | 0.2736 | 0.5439 | 0.2437 | 0.0268 | 0.2335 | 0.5431 | 0.1861 | 0.3721 | 0.4213 | 0.1239 | 0.3999 | 0.66 | 0.1642 | 0.2892 | 0.3013 | 0.4247 | 0.3137 | 0.5033 | 0.3152 | 0.468 |
|
| 91 |
+
| 1.3847 | 21.0 | 48405 | 1.3406 | 0.2773 | 0.548 | 0.2525 | 0.0339 | 0.2389 | 0.5483 | 0.1878 | 0.3785 | 0.4315 | 0.1327 | 0.4104 | 0.6629 | 0.1707 | 0.3051 | 0.3109 | 0.4344 | 0.3134 | 0.5139 | 0.3142 | 0.4725 |
|
| 92 |
+
| 1.3711 | 22.0 | 50710 | 1.3297 | 0.2789 | 0.5529 | 0.2536 | 0.0291 | 0.2377 | 0.5527 | 0.1862 | 0.3778 | 0.4288 | 0.1326 | 0.4064 | 0.6636 | 0.1728 | 0.3041 | 0.3087 | 0.4286 | 0.3151 | 0.5073 | 0.3189 | 0.4753 |
|
| 93 |
+
| 1.3693 | 23.0 | 53015 | 1.3302 | 0.2779 | 0.5488 | 0.2495 | 0.0283 | 0.2358 | 0.5462 | 0.1869 | 0.378 | 0.4313 | 0.1338 | 0.4084 | 0.6569 | 0.1728 | 0.3068 | 0.3079 | 0.4265 | 0.3107 | 0.5203 | 0.32 | 0.4718 |
|
| 94 |
+
| 1.3678 | 24.0 | 55320 | 1.3459 | 0.2734 | 0.539 | 0.2477 | 0.0277 | 0.2312 | 0.5452 | 0.1841 | 0.3742 | 0.4272 | 0.1266 | 0.4043 | 0.6656 | 0.1696 | 0.3011 | 0.2993 | 0.4191 | 0.3079 | 0.5071 | 0.3169 | 0.4813 |
|
| 95 |
+
| 1.3554 | 25.0 | 57625 | 1.3141 | 0.2895 | 0.5625 | 0.2674 | 0.0326 | 0.2503 | 0.5526 | 0.1904 | 0.3872 | 0.4387 | 0.1254 | 0.4191 | 0.6709 | 0.1798 | 0.3112 | 0.3135 | 0.4361 | 0.3275 | 0.5216 | 0.337 | 0.4857 |
|
| 96 |
+
| 1.3444 | 26.0 | 59930 | 1.3255 | 0.2852 | 0.5566 | 0.2625 | 0.0312 | 0.2437 | 0.5484 | 0.1892 | 0.3827 | 0.4341 | 0.1121 | 0.4146 | 0.672 | 0.1754 | 0.3065 | 0.3115 | 0.4338 | 0.3259 | 0.5192 | 0.3282 | 0.477 |
|
| 97 |
+
| 1.3421 | 27.0 | 62235 | 1.3190 | 0.2839 | 0.5592 | 0.2576 | 0.0266 | 0.2448 | 0.5548 | 0.1903 | 0.3816 | 0.4325 | 0.1285 | 0.4114 | 0.6654 | 0.1765 | 0.3082 | 0.3134 | 0.4453 | 0.3208 | 0.5073 | 0.3251 | 0.4693 |
|
| 98 |
+
| 1.3477 | 28.0 | 64540 | 1.3217 | 0.2852 | 0.5581 | 0.2622 | 0.0268 | 0.2445 | 0.5491 | 0.188 | 0.3805 | 0.4326 | 0.1297 | 0.4122 | 0.66 | 0.1801 | 0.3109 | 0.3113 | 0.4292 | 0.3238 | 0.5124 | 0.3256 | 0.478 |
|
| 99 |
+
| 1.3577 | 29.0 | 66845 | 1.3081 | 0.2881 | 0.5656 | 0.2638 | 0.0267 | 0.2467 | 0.5512 | 0.1899 | 0.3833 | 0.4341 | 0.1252 | 0.4136 | 0.6641 | 0.1766 | 0.3109 | 0.3142 | 0.43 | 0.3304 | 0.5179 | 0.3312 | 0.4776 |
|
| 100 |
+
| 1.3362 | 30.0 | 69150 | 1.3103 | 0.288 | 0.5656 | 0.2622 | 0.0272 | 0.2476 | 0.5594 | 0.1908 | 0.383 | 0.4353 | 0.1275 | 0.411 | 0.6702 | 0.1775 | 0.3149 | 0.3093 | 0.4331 | 0.3324 | 0.5117 | 0.3328 | 0.4814 |
|
| 101 |
+
| 1.3399 | 31.0 | 71455 | 1.3057 | 0.2891 | 0.5684 | 0.2644 | 0.0308 | 0.2482 | 0.566 | 0.1914 | 0.3856 | 0.4356 | 0.1303 | 0.4131 | 0.678 | 0.1788 | 0.3142 | 0.3136 | 0.435 | 0.3291 | 0.5217 | 0.3346 | 0.4715 |
|
| 102 |
+
| 1.326 | 32.0 | 73760 | 1.2957 | 0.2917 | 0.5725 | 0.2679 | 0.0368 | 0.2514 | 0.559 | 0.1915 | 0.3864 | 0.4393 | 0.1351 | 0.4159 | 0.6778 | 0.1808 | 0.3154 | 0.3187 | 0.4399 | 0.3311 | 0.5161 | 0.3363 | 0.4856 |
|
| 103 |
+
| 1.3187 | 33.0 | 76065 | 1.2895 | 0.2974 | 0.5776 | 0.2758 | 0.0287 | 0.2581 | 0.5698 | 0.1936 | 0.3929 | 0.4434 | 0.1412 | 0.4216 | 0.6729 | 0.1871 | 0.3198 | 0.3235 | 0.4415 | 0.3381 | 0.5274 | 0.3408 | 0.4849 |
|
| 104 |
+
| 1.3335 | 34.0 | 78370 | 1.2929 | 0.2955 | 0.5764 | 0.2743 | 0.0306 | 0.2556 | 0.5708 | 0.1928 | 0.3899 | 0.442 | 0.1343 | 0.4203 | 0.6816 | 0.1843 | 0.3194 | 0.3213 | 0.4456 | 0.339 | 0.5158 | 0.3375 | 0.4873 |
|
| 105 |
+
| 1.3051 | 35.0 | 80675 | 1.2900 | 0.296 | 0.5787 | 0.2742 | 0.0323 | 0.2572 | 0.5639 | 0.1922 | 0.3894 | 0.4397 | 0.1411 | 0.4174 | 0.6737 | 0.1874 | 0.3212 | 0.3218 | 0.4396 | 0.3348 | 0.5183 | 0.3402 | 0.4799 |
|
| 106 |
+
| 1.3155 | 36.0 | 82980 | 1.2911 | 0.2962 | 0.5795 | 0.2712 | 0.03 | 0.2557 | 0.5675 | 0.1942 | 0.391 | 0.4423 | 0.1422 | 0.4196 | 0.6705 | 0.1866 | 0.3209 | 0.3186 | 0.4403 | 0.3395 | 0.5222 | 0.3402 | 0.4859 |
|
| 107 |
+
| 1.321 | 37.0 | 85285 | 1.2856 | 0.2944 | 0.5775 | 0.2692 | 0.0338 | 0.2541 | 0.5649 | 0.1918 | 0.3885 | 0.4412 | 0.1388 | 0.4186 | 0.6679 | 0.1863 | 0.3215 | 0.3199 | 0.4421 | 0.3374 | 0.5225 | 0.3341 | 0.4788 |
|
| 108 |
+
| 1.3085 | 38.0 | 87590 | 1.2800 | 0.2988 | 0.5815 | 0.2739 | 0.0266 | 0.259 | 0.5778 | 0.1945 | 0.3932 | 0.446 | 0.1346 | 0.4254 | 0.6784 | 0.1873 | 0.3207 | 0.3222 | 0.4403 | 0.3469 | 0.536 | 0.3386 | 0.4869 |
|
| 109 |
+
| 1.3096 | 39.0 | 89895 | 1.2834 | 0.2971 | 0.582 | 0.2753 | 0.0327 | 0.2568 | 0.5674 | 0.1923 | 0.3902 | 0.4413 | 0.146 | 0.4171 | 0.6682 | 0.1866 | 0.3212 | 0.3233 | 0.4396 | 0.3432 | 0.5224 | 0.3352 | 0.4819 |
|
| 110 |
+
| 1.3095 | 40.0 | 92200 | 1.2760 | 0.3011 | 0.583 | 0.2793 | 0.0298 | 0.2606 | 0.5704 | 0.1948 | 0.3921 | 0.4461 | 0.1358 | 0.424 | 0.6631 | 0.1911 | 0.3254 | 0.3254 | 0.4489 | 0.3446 | 0.5202 | 0.3432 | 0.4897 |
|
| 111 |
+
| 1.2922 | 41.0 | 94505 | 1.2656 | 0.3032 | 0.5874 | 0.2819 | 0.0303 | 0.264 | 0.5716 | 0.197 | 0.3954 | 0.4498 | 0.1414 | 0.4287 | 0.6702 | 0.1932 | 0.3259 | 0.3279 | 0.4491 | 0.3458 | 0.5276 | 0.346 | 0.4964 |
|
| 112 |
+
| 1.2981 | 42.0 | 96810 | 1.2713 | 0.2998 | 0.5854 | 0.2756 | 0.0303 | 0.2612 | 0.5711 | 0.1941 | 0.3916 | 0.4466 | 0.164 | 0.4239 | 0.6682 | 0.1911 | 0.3274 | 0.3246 | 0.4467 | 0.3414 | 0.5222 | 0.342 | 0.4902 |
|
| 113 |
+
| 1.2935 | 43.0 | 99115 | 1.2610 | 0.3037 | 0.5903 | 0.2813 | 0.0348 | 0.2644 | 0.5758 | 0.1945 | 0.3989 | 0.4522 | 0.1547 | 0.431 | 0.6741 | 0.1955 | 0.3307 | 0.3275 | 0.4481 | 0.3471 | 0.5334 | 0.3447 | 0.4967 |
|
| 114 |
+
| 1.2847 | 44.0 | 101420 | 1.2659 | 0.3033 | 0.5896 | 0.2786 | 0.0268 | 0.2663 | 0.5694 | 0.1948 | 0.3953 | 0.4484 | 0.1437 | 0.4272 | 0.6741 | 0.1945 | 0.3281 | 0.3254 | 0.4491 | 0.3481 | 0.5268 | 0.3454 | 0.4898 |
|
| 115 |
+
| 1.2921 | 45.0 | 103725 | 1.2572 | 0.3062 | 0.5916 | 0.2824 | 0.0314 | 0.2681 | 0.5699 | 0.1955 | 0.397 | 0.4515 | 0.1435 | 0.4311 | 0.6712 | 0.1973 | 0.3305 | 0.3286 | 0.4495 | 0.3505 | 0.5297 | 0.3484 | 0.4962 |
|
| 116 |
+
| 1.2763 | 46.0 | 106030 | 1.2569 | 0.3055 | 0.5917 | 0.2824 | 0.0329 | 0.2678 | 0.5765 | 0.1953 | 0.3975 | 0.4506 | 0.144 | 0.4301 | 0.6723 | 0.1965 | 0.3298 | 0.3306 | 0.4499 | 0.3482 | 0.5298 | 0.3467 | 0.493 |
|
| 117 |
+
| 1.2791 | 47.0 | 108335 | 1.2564 | 0.3049 | 0.593 | 0.2806 | 0.0322 | 0.2679 | 0.5726 | 0.1956 | 0.3959 | 0.4482 | 0.1452 | 0.4258 | 0.6679 | 0.1953 | 0.33 | 0.3318 | 0.4511 | 0.3465 | 0.5209 | 0.3458 | 0.4908 |
|
| 118 |
+
| 1.2792 | 48.0 | 110640 | 1.2534 | 0.3065 | 0.5926 | 0.2831 | 0.0297 | 0.2681 | 0.5738 | 0.196 | 0.3991 | 0.4509 | 0.1507 | 0.4311 | 0.6753 | 0.1961 | 0.3286 | 0.335 | 0.453 | 0.3493 | 0.5296 | 0.3455 | 0.4924 |
|
| 119 |
+
| 1.2819 | 49.0 | 112945 | 1.2541 | 0.3053 | 0.5921 | 0.2825 | 0.0279 | 0.267 | 0.5698 | 0.1953 | 0.3973 | 0.4501 | 0.1504 | 0.429 | 0.6678 | 0.1949 | 0.3292 | 0.3319 | 0.4526 | 0.3477 | 0.5252 | 0.3467 | 0.4931 |
|
| 120 |
+
| 1.2875 | 50.0 | 115250 | 1.2501 | 0.3077 | 0.5945 | 0.2867 | 0.0295 | 0.2708 | 0.5778 | 0.197 | 0.3999 | 0.4529 | 0.156 | 0.4327 | 0.6791 | 0.196 | 0.3303 | 0.335 | 0.4548 | 0.353 | 0.5313 | 0.3467 | 0.495 |
|
| 121 |
+
| 1.2744 | 51.0 | 117555 | 1.2519 | 0.3055 | 0.5938 | 0.2859 | 0.0293 | 0.2683 | 0.5779 | 0.1954 | 0.3983 | 0.4515 | 0.1574 | 0.4307 | 0.6792 | 0.1965 | 0.3323 | 0.3304 | 0.4514 | 0.3491 | 0.5298 | 0.3461 | 0.4927 |
|
| 122 |
+
| 1.2703 | 52.0 | 119860 | 1.2508 | 0.3076 | 0.5957 | 0.2871 | 0.0292 | 0.2705 | 0.5757 | 0.1964 | 0.4 | 0.4531 | 0.1567 | 0.4329 | 0.6751 | 0.1971 | 0.3309 | 0.3356 | 0.4556 | 0.3493 | 0.5316 | 0.3485 | 0.4943 |
|
| 123 |
+
| 1.2697 | 53.0 | 122165 | 1.2478 | 0.3089 | 0.5969 | 0.2891 | 0.0292 | 0.2729 | 0.5734 | 0.1982 | 0.4002 | 0.4545 | 0.1496 | 0.4349 | 0.6754 | 0.1971 | 0.3309 | 0.3364 | 0.4586 | 0.3545 | 0.5327 | 0.3478 | 0.4959 |
|
| 124 |
+
| 1.268 | 54.0 | 124470 | 1.2474 | 0.3087 | 0.598 | 0.2878 | 0.0289 | 0.2726 | 0.5743 | 0.1978 | 0.4014 | 0.455 | 0.1567 | 0.4354 | 0.6771 | 0.2006 | 0.3333 | 0.3345 | 0.4574 | 0.3532 | 0.5352 | 0.3464 | 0.494 |
|
| 125 |
+
| 1.2765 | 55.0 | 126775 | 1.2466 | 0.3091 | 0.5973 | 0.2896 | 0.0301 | 0.2729 | 0.5784 | 0.1975 | 0.4006 | 0.4543 | 0.1526 | 0.4341 | 0.6781 | 0.1991 | 0.3329 | 0.3361 | 0.4577 | 0.3544 | 0.5321 | 0.3469 | 0.4944 |
|
| 126 |
+
| 1.2748 | 56.0 | 129080 | 1.2461 | 0.3087 | 0.5979 | 0.2883 | 0.0304 | 0.2726 | 0.5786 | 0.1977 | 0.4015 | 0.4548 | 0.1549 | 0.435 | 0.6773 | 0.1995 | 0.3333 | 0.3356 | 0.4574 | 0.3522 | 0.5339 | 0.3476 | 0.4949 |
|
| 127 |
+
| 1.2771 | 57.0 | 131385 | 1.2454 | 0.3097 | 0.5975 | 0.2886 | 0.0303 | 0.2729 | 0.5833 | 0.1977 | 0.4019 | 0.4556 | 0.1552 | 0.4356 | 0.681 | 0.2002 | 0.3336 | 0.3358 | 0.4576 | 0.3528 | 0.5347 | 0.3499 | 0.4966 |
|
| 128 |
+
| 1.2787 | 58.0 | 133690 | 1.2455 | 0.3095 | 0.5973 | 0.2894 | 0.0297 | 0.2738 | 0.5805 | 0.1975 | 0.4017 | 0.4557 | 0.1576 | 0.4362 | 0.6781 | 0.2011 | 0.3337 | 0.3362 | 0.4585 | 0.3521 | 0.5339 | 0.3485 | 0.4966 |
|
| 129 |
+
| 1.2801 | 59.0 | 135995 | 1.2446 | 0.3092 | 0.5975 | 0.2889 | 0.0299 | 0.2724 | 0.5825 | 0.1976 | 0.4018 | 0.4561 | 0.1593 | 0.4361 | 0.6803 | 0.1997 | 0.3341 | 0.3355 | 0.4578 | 0.3524 | 0.5351 | 0.3491 | 0.4975 |
|
| 130 |
+
| 1.2623 | 60.0 | 138300 | 1.2453 | 0.3085 | 0.5989 | 0.2888 | 0.0295 | 0.272 | 0.5812 | 0.1973 | 0.4012 | 0.4549 | 0.1586 | 0.435 | 0.6786 | 0.2 | 0.3339 | 0.3354 | 0.4573 | 0.3511 | 0.5331 | 0.3477 | 0.4953 |
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
### Framework versions
|
| 134 |
+
|
| 135 |
+
- Transformers 4.45.1
|
| 136 |
+
- Pytorch 2.4.0
|
| 137 |
+
- Datasets 3.0.1
|
| 138 |
+
- Tokenizers 0.20.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 174078768
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a68e503e13640d28811d472b8d21e6fddc35baebaa6f7da965e59e7497e71bc
|
| 3 |
size 174078768
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|