|
--- |
|
base_model: roneneldan/TinyStories-33M |
|
library_name: Distily |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: distily_bench_obj_cross_v2.2 |
|
results: [] |
|
--- |
|
|
|
# distily_bench_obj_cross_v2.2 |
|
|
|
This student model is distilled from the teacher model [roneneldan/TinyStories-33M](https://huggingface.co/roneneldan/TinyStories-33M) using the dataset (unspecified). |
|
|
|
The [Distily](https://github.com/lapp0/distily) library was used for this distillation. |
|
|
|
It achieves the following results on the evaluation set: |
|
- eval_enwikippl: 173.8350 |
|
- eval_frwikippl: 60887.2422 |
|
- eval_zhwikippl: 328379.5312 |
|
- eval_tinystoriesppl: 10.2239 |
|
- eval_loss: 1.1755 |
|
- eval_runtime: 13.1746 |
|
- eval_samples_per_second: 75.903 |
|
- eval_steps_per_second: 9.488 |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
--> |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- distillation_objective: DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl, layer_mapper=None, projector=None), hs_loss_component=LossComponent(label=hs, weight=0, loss_fn=None, layer_mapper=None, projector=None), attn_loss_component=LossComponent(label=attn, weight=0, loss_fn=None, layer_mapper=None, projector=None)) |
|
- train_embeddings: True |
|
- learning_rate: 0.004 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.5 |
|
- num_epochs: 1.0 |
|
|
|
### Resource Usage |
|
Peak GPU Memory: 6.6047 GB |
|
|
|
### Eval-Phase Metrics |
|
| step | epoch | enwikippl | frwikippl | loss | runtime | samples_per_second | steps_per_second | tinystoriesppl | zhwikippl | |
|
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | |
|
| **teacher eval** | | 169.9865 | 47377.9414 | | | | | 3.9789 | 4998.1294 | |
|
| 0 | 0 | 52669.6523 | 72993.9297 | 6.5530 | 13.1454 | 76.072 | 9.509 | 39454.2930 | 71157.1797 | |
|
| 500 | 0.0051 | 44956.75 | 68626.6641 | 6.4185 | 13.0649 | 76.541 | 9.568 | 32178.2012 | 70101.9766 | |
|
| 1000 | 0.0101 | 33763.7852 | 61252.8203 | 6.1768 | 13.1033 | 76.317 | 9.54 | 22370.0684 | 68183.5859 | |
|
| 1500 | 0.0152 | 33690.6094 | 61252.8203 | 6.1762 | 13.0831 | 76.434 | 9.554 | 22336.8125 | 68147.2422 | |
|
| 2000 | 0.0202 | 21711.3809 | 51603.3672 | 5.8095 | 13.0769 | 76.47 | 9.559 | 12725.5420 | 65753.9297 | |
|
| 2500 | 0.0253 | 21691.2031 | 51559.7812 | 5.8095 | 13.0773 | 76.468 | 9.559 | 12706.6240 | 65613.7344 | |
|
| 3000 | 0.0303 | 21677.7617 | 51559.7812 | 5.8095 | 13.0957 | 76.361 | 9.545 | 12702.4199 | 65648.7891 | |
|
| 3500 | 0.0354 | 9303.9834 | 38552.1719 | 5.1132 | 13.1366 | 76.123 | 9.515 | 4258.6343 | 63461.6641 | |
|
| 4000 | 0.0404 | 9057.9209 | 38432.9023 | 5.1118 | 13.086 | 76.418 | 9.552 | 4096.3477 | 62520.5195 | |
|
| 4500 | 0.0455 | 8782.9141 | 38216.9688 | 5.1102 | 13.103 | 76.318 | 9.54 | 3909.0979 | 61741.4727 | |
|
| 5000 | 0.0505 | 8717.8486 | 38206.1836 | 5.1095 | 13.1133 | 76.259 | 9.532 | 3867.3118 | 61708.5078 | |
|
| 5500 | 0.0556 | 8717.8486 | 38206.1836 | 5.1097 | 13.0748 | 76.483 | 9.56 | 3868.5918 | 61675.6211 | |
|
| 6000 | 0.0606 | 8725.9502 | 38206.1836 | 5.1095 | 13.1774 | 75.888 | 9.486 | 3875.6340 | 61675.6211 | |
|
| 6500 | 0.0657 | 1777.1456 | 25311.8418 | 3.8983 | 13.1926 | 75.8 | 9.475 | 462.9113 | 63954.5195 | |
|
| 7000 | 0.0707 | 1634.0082 | 25035.2793 | 3.8856 | 13.0968 | 76.354 | 9.544 | 409.3667 | 61675.6211 | |
|
| 7500 | 0.0758 | 1540.2275 | 24880.5918 | 3.8800 | 13.0526 | 76.613 | 9.577 | 375.2083 | 59509.5859 | |
|
| 8000 | 0.0808 | 1508.3474 | 24884.1035 | 3.8793 | 13.0768 | 76.472 | 9.559 | 364.5079 | 58925.0273 | |
|
| 8500 | 0.0859 | 1464.3663 | 24786.1445 | 3.8795 | 13.0459 | 76.653 | 9.582 | 347.5009 | 58221.8125 | |
|
| 9000 | 0.0909 | 1450.2551 | 24782.6699 | 3.8793 | 13.094 | 76.371 | 9.546 | 341.6051 | 58066.7188 | |
|
| 9500 | 0.0960 | 1456.5604 | 24751.2559 | 3.8791 | 13.1265 | 76.182 | 9.523 | 345.3246 | 58221.8125 | |
|
| 10000 | 0.1010 | 1482.8590 | 24814.0996 | 3.8794 | 13.095 | 76.365 | 9.546 | 355.1973 | 58424.1094 | |
|
| 10500 | 0.1061 | 1474.3835 | 24800.1191 | 3.8794 | 13.0825 | 76.438 | 9.555 | 351.5170 | 58221.8125 | |
|
| 11000 | 0.1111 | 1489.4211 | 24772.2012 | 3.8791 | 13.1427 | 76.088 | 9.511 | 356.9635 | 58486.4883 | |
|
| 11500 | 0.1162 | 1478.0425 | 24779.1719 | 3.8794 | 13.0727 | 76.495 | 9.562 | 354.0248 | 58392.9141 | |
|
| 12000 | 0.1212 | 1481.9408 | 24779.1719 | 3.8796 | 13.0577 | 76.583 | 9.573 | 354.8745 | 58392.9141 | |
|
| 12500 | 0.1263 | 157.4985 | 35001.3008 | 2.6554 | 13.1308 | 76.157 | 9.52 | 12.3119 | 151077.2656 | |
|
| 13000 | 0.1313 | 169.6839 | 26583.5117 | 2.5062 | 13.0753 | 76.48 | 9.56 | 14.8852 | 101955.1797 | |
|
| 13500 | 0.1364 | 196.3011 | 21765.9062 | 2.4544 | 13.1825 | 75.858 | 9.482 | 19.3727 | 75017.1797 | |
|
| 14000 | 0.1414 | 190.3265 | 21478.0918 | 2.4500 | 13.1157 | 76.245 | 9.531 | 18.7379 | 77210.1953 | |
|
| 14500 | 0.1465 | 188.2079 | 21357.4160 | 2.4495 | 13.0923 | 76.381 | 9.548 | 18.4810 | 76187.0469 | |
|
| 15000 | 0.1515 | 189.2460 | 21231.4473 | 2.4492 | 13.0975 | 76.351 | 9.544 | 18.6923 | 74538.3828 | |
|
| 15500 | 0.1566 | 188.9237 | 21405.6016 | 2.4492 | 13.1439 | 76.081 | 9.51 | 18.5468 | 75358.2109 | |
|
| 16000 | 0.1616 | 188.8067 | 21514.4375 | 2.4490 | 13.0852 | 76.422 | 9.553 | 18.5162 | 76349.8281 | |
|
| 16500 | 0.1667 | 190.2086 | 21351.4102 | 2.4489 | 13.1595 | 75.99 | 9.499 | 18.8210 | 76146.375 | |
|
| 17000 | 0.1717 | 189.0994 | 21333.375 | 2.4491 | 13.098 | 76.348 | 9.543 | 18.6283 | 75579.6641 | |
|
| 17500 | 0.1768 | 189.0262 | 21484.1543 | 2.4490 | 13.1692 | 75.935 | 9.492 | 18.6006 | 76268.3984 | |
|
| 18000 | 0.1818 | 189.9141 | 21599.4473 | 2.4489 | 13.1461 | 76.068 | 9.509 | 18.7016 | 76922.3125 | |
|
| 18500 | 0.1869 | 190.1939 | 21351.4102 | 2.4491 | 13.1761 | 75.895 | 9.487 | 18.8568 | 75579.6641 | |
|
| 19000 | 0.1919 | 188.3976 | 21315.3379 | 2.4494 | 13.1038 | 76.314 | 9.539 | 18.4749 | 75559.4922 | |
|
| 19500 | 0.1970 | 187.5166 | 21393.5605 | 2.4490 | 13.1202 | 76.218 | 9.527 | 18.3494 | 75519.2188 | |
|
| 20000 | 0.2020 | 190.0024 | 21520.4922 | 2.4490 | 13.1338 | 76.139 | 9.517 | 18.7658 | 75822.0234 | |
|
| 20500 | 0.2071 | 189.1580 | 21441.8262 | 2.4490 | 13.0779 | 76.465 | 9.558 | 18.5921 | 76227.6719 | |
|
| 21000 | 0.2121 | 189.8847 | 21496.2461 | 2.4490 | 13.1311 | 76.155 | 9.519 | 18.7434 | 76717.3984 | |
|
| 21500 | 0.2172 | 190.1055 | 21429.7441 | 2.4489 | 13.1056 | 76.304 | 9.538 | 18.7829 | 76105.7891 | |
|
| 22000 | 0.2222 | 189.7671 | 21575.1328 | 2.4489 | 13.0699 | 76.512 | 9.564 | 18.6738 | 76922.3125 | |
|
| 22500 | 0.2273 | 188.3319 | 21363.4473 | 2.4492 | 13.1296 | 76.164 | 9.52 | 18.4368 | 75358.2109 | |
|
| 23000 | 0.2323 | 189.4659 | 21393.5605 | 2.4492 | 13.1044 | 76.31 | 9.539 | 18.6908 | 75822.0234 | |
|
| 23500 | 0.2374 | 187.9821 | 21345.3828 | 2.4492 | 13.1019 | 76.325 | 9.541 | 18.3919 | 75984.0234 | |
|
| 24000 | 0.2424 | 189.4146 | 21532.625 | 2.4489 | 13.1461 | 76.068 | 9.509 | 18.6892 | 76512.9609 | |
|
| 24500 | 0.2475 | 258.9580 | 127264.7109 | 1.9007 | 13.0286 | 76.754 | 9.594 | 12.0471 | 1619514.5 | |
|
| 25000 | 0.2525 | 311.6756 | 205648.5469 | 1.6701 | 13.0855 | 76.42 | 9.553 | 12.6346 | 1182116.125 | |
|
| 25500 | 0.2576 | 182.4019 | 50272.4961 | 1.3738 | 13.088 | 76.406 | 9.551 | 10.9822 | 252693.0781 | |
|
| 26000 | 0.2626 | 162.9404 | 39467.0117 | 1.2816 | 13.1163 | 76.241 | 9.53 | 10.5132 | 214625.8125 | |
|
| 26500 | 0.2677 | 153.3747 | 36651.1523 | 1.2536 | 13.0665 | 76.532 | 9.566 | 10.3408 | 150033.0 | |
|
| 27000 | 0.2727 | 149.3994 | 32545.2773 | 1.2488 | 13.1249 | 76.191 | 9.524 | 10.5267 | 124175.5 | |
|
| 27500 | 0.2778 | 147.5134 | 31601.1426 | 1.2457 | 13.1132 | 76.259 | 9.532 | 10.4064 | 133272.7188 | |
|
| 28000 | 0.2828 | 145.7415 | 32339.6230 | 1.2452 | 13.0604 | 76.567 | 9.571 | 10.1394 | 135026.4219 | |
|
| 28500 | 0.2879 | 149.5152 | 32673.8711 | 1.2452 | 13.0107 | 76.86 | 9.607 | 10.3944 | 130458.2578 | |
|
| 29000 | 0.2929 | 146.3581 | 31681.3496 | 1.2453 | 13.0181 | 76.816 | 9.602 | 10.3806 | 125776.0312 | |
|
| 29500 | 0.2980 | 147.4791 | 31717.0820 | 1.2449 | 13.0769 | 76.471 | 9.559 | 10.3862 | 133415.0156 | |
|
| 30000 | 0.3030 | 147.3706 | 32067.4570 | 1.2448 | 13.1294 | 76.165 | 9.521 | 10.3447 | 132705.0312 | |
|
| 30500 | 0.3081 | 148.4822 | 33536.5156 | 1.2456 | 13.1014 | 76.328 | 9.541 | 10.3566 | 133985.7344 | |
|
| 31000 | 0.3131 | 149.1219 | 33244.8906 | 1.2444 | 13.0892 | 76.399 | 9.55 | 10.3648 | 139568.2031 | |
|
| 31500 | 0.3182 | 146.6759 | 33109.375 | 1.2451 | 13.1438 | 76.081 | 9.51 | 10.2519 | 139419.3438 | |
|
| 32000 | 0.3232 | 148.4764 | 32022.3203 | 1.2451 | 13.1327 | 76.146 | 9.518 | 10.3978 | 134307.8594 | |
|
| 32500 | 0.3283 | 146.0071 | 32230.5059 | 1.2448 | 13.1347 | 76.134 | 9.517 | 10.3272 | 132917.5625 | |
|
| 33000 | 0.3333 | 147.7707 | 34223.6719 | 1.2454 | 13.093 | 76.377 | 9.547 | 10.2033 | 142199.25 | |
|
| 33500 | 0.3384 | 150.1943 | 34843.8672 | 1.2452 | 13.1431 | 76.086 | 9.511 | 10.2392 | 145460.7969 | |
|
| 34000 | 0.3434 | 147.6906 | 32766.0488 | 1.2446 | 13.1388 | 76.111 | 9.514 | 10.3571 | 134200.3125 | |
|
| 34500 | 0.3485 | 147.1482 | 31941.25 | 1.2448 | 13.0898 | 76.395 | 9.549 | 10.3862 | 130736.9922 | |
|
| 35000 | 0.3535 | 149.6890 | 33423.3281 | 1.2452 | 13.0942 | 76.37 | 9.546 | 10.3541 | 139122.0938 | |
|
| 35500 | 0.3586 | 149.5325 | 33160.7266 | 1.2447 | 13.1322 | 76.148 | 9.519 | 10.4094 | 144686.7188 | |
|
| 36000 | 0.3636 | 145.3750 | 31777.4531 | 1.2452 | 13.0787 | 76.46 | 9.558 | 10.2125 | 133308.3125 | |
|
| 36500 | 0.3687 | 148.9487 | 32298.6602 | 1.2447 | 13.0705 | 76.508 | 9.563 | 10.4807 | 133985.7344 | |
|
| 37000 | 0.3737 | 150.1129 | 33116.3867 | 1.2452 | 13.1491 | 76.051 | 9.506 | 10.5128 | 142921.8594 | |
|
| 37500 | 0.3788 | 149.2490 | 32731.4746 | 1.2450 | 13.0425 | 76.672 | 9.584 | 10.4310 | 138160.3438 | |
|
| 38000 | 0.3838 | 148.4189 | 32858.4844 | 1.2451 | 13.1334 | 76.142 | 9.518 | 10.3965 | 137425.1094 | |
|
| 38500 | 0.3889 | 145.6230 | 32011.0527 | 1.2448 | 13.1597 | 75.989 | 9.499 | 10.2121 | 131858.0469 | |
|
| 39000 | 0.3939 | 147.8051 | 32844.6055 | 1.2449 | 13.2291 | 75.591 | 9.449 | 10.2214 | 133807.0938 | |
|
| 39500 | 0.3990 | 147.3307 | 32692.2910 | 1.2449 | 13.1731 | 75.912 | 9.489 | 10.4129 | 139047.8125 | |
|
| 40000 | 0.4040 | 147.6105 | 32385.2070 | 1.2452 | 13.0951 | 76.364 | 9.546 | 10.2328 | 134666.5938 | |
|
| 40500 | 0.4091 | 148.0744 | 32637.0918 | 1.2450 | 13.0333 | 76.727 | 9.591 | 10.4116 | 138899.5156 | |
|
| 41000 | 0.4141 | 149.1219 | 32618.7012 | 1.2450 | 13.1237 | 76.198 | 9.525 | 10.4560 | 136547.9844 | |
|
| 41500 | 0.4192 | 150.2699 | 33852.1289 | 1.2456 | 13.0975 | 76.35 | 9.544 | 10.4232 | 143993.5 | |
|
| 42000 | 0.4242 | 148.0400 | 31592.2227 | 1.2450 | 13.0907 | 76.39 | 9.549 | 10.4318 | 138603.375 | |
|
| 42500 | 0.4293 | 149.2722 | 33263.6328 | 1.2454 | 13.1088 | 76.284 | 9.536 | 10.3460 | 130110.7344 | |
|
| 43000 | 0.4343 | 146.9943 | 32357.8555 | 1.2455 | 13.1698 | 75.931 | 9.491 | 10.2769 | 135026.4219 | |
|
| 43500 | 0.4394 | 149.7238 | 33069.7734 | 1.2452 | 13.0987 | 76.343 | 9.543 | 10.4577 | 135893.7656 | |
|
| 44000 | 0.4444 | 149.3011 | 32772.9844 | 1.2455 | 13.0817 | 76.443 | 9.555 | 10.5380 | 136839.7344 | |
|
| 44500 | 0.4495 | 146.3694 | 31726.0059 | 1.2451 | 13.0363 | 76.709 | 9.589 | 10.3242 | 129625.6094 | |
|
| 45000 | 0.4545 | 149.3531 | 32362.4219 | 1.2452 | 13.0922 | 76.382 | 9.548 | 10.4348 | 130667.3203 | |
|
| 45500 | 0.4596 | 146.4262 | 32339.6230 | 1.2455 | 13.0782 | 76.463 | 9.558 | 10.2697 | 133842.8281 | |
|
| 46000 | 0.4646 | 147.8222 | 31521.1094 | 1.2453 | 13.2075 | 75.714 | 9.464 | 10.4232 | 131858.0469 | |
|
| 46500 | 0.4697 | 149.9443 | 32858.4844 | 1.2455 | 13.0535 | 76.608 | 9.576 | 10.4504 | 138899.5156 | |
|
| 47000 | 0.4747 | 147.2907 | 32312.3086 | 1.2446 | 13.1333 | 76.143 | 9.518 | 10.2999 | 129764.0156 | |
|
| 47500 | 0.4798 | 147.8280 | 32031.3594 | 1.2450 | 13.1307 | 76.157 | 9.52 | 10.2973 | 135170.5938 | |
|
| 48000 | 0.4848 | 150.8706 | 33652.4297 | 1.2459 | 13.1532 | 76.027 | 9.503 | 10.5084 | 143303.7344 | |
|
| 48500 | 0.4899 | 233.2175 | 134016.5312 | 1.2454 | 13.0411 | 76.681 | 9.585 | 10.7256 | 484649.75 | |
|
| 49000 | 0.4949 | 192.8943 | 80054.5391 | 1.1914 | 13.171 | 75.925 | 9.491 | 10.3118 | 439093.1875 | |
|
| 49500 | 0.5 | 181.6897 | 66668.6797 | 1.1807 | 13.0366 | 76.707 | 9.588 | 10.5398 | 372647.1562 | |
|
| 50000 | 0.5051 | 178.5919 | 64099.4805 | 1.1779 | 13.1197 | 76.222 | 9.528 | 10.2413 | 347117.8438 | |
|
| 50500 | 0.5101 | 170.0656 | 56934.7031 | 1.1777 | 13.1278 | 76.174 | 9.522 | 10.2163 | 286528.3438 | |
|
| 51000 | 0.5152 | 176.2691 | 60767.2773 | 1.1768 | 13.0822 | 76.44 | 9.555 | 10.2807 | 348044.9688 | |
|
| 51500 | 0.5202 | 175.1937 | 59547.1094 | 1.1764 | 13.098 | 76.348 | 9.543 | 10.2557 | 329608.5 | |
|
| 52000 | 0.5253 | 178.4812 | 65233.4531 | 1.1766 | 13.1056 | 76.303 | 9.538 | 10.2637 | 369380.6562 | |
|
| 52500 | 0.5303 | 176.5834 | 62161.0664 | 1.1768 | 13.1118 | 76.267 | 9.533 | 10.1969 | 350841.9688 | |
|
| 53000 | 0.5354 | 174.2125 | 60052.5039 | 1.1765 | 13.1029 | 76.319 | 9.54 | 10.2527 | 323423.5312 | |
|
| 53500 | 0.5404 | 176.9943 | 63707.9219 | 1.1763 | 13.0066 | 76.884 | 9.611 | 10.1889 | 362352.625 | |
|
| 54000 | 0.5455 | 179.0075 | 64104.0039 | 1.1762 | 13.2498 | 75.473 | 9.434 | 10.3481 | 362546.1875 | |
|
| 54500 | 0.5505 | 171.8867 | 60762.9922 | 1.1763 | 13.1655 | 75.956 | 9.495 | 10.0003 | 306454.5938 | |
|
| 55000 | 0.5556 | 176.8846 | 63207.3789 | 1.1763 | 13.1414 | 76.095 | 9.512 | 10.2701 | 337618.6875 | |
|
| 55500 | 0.5606 | 175.9485 | 63649.6211 | 1.1769 | 13.0975 | 76.35 | 9.544 | 10.1818 | 371951.9688 | |
|
| 56000 | 0.5657 | 172.9887 | 60955.8594 | 1.1764 | 13.1161 | 76.242 | 9.53 | 10.0738 | 341605.2812 | |
|
| 56500 | 0.5707 | 174.8141 | 59287.6406 | 1.1767 | 13.0894 | 76.398 | 9.55 | 10.1335 | 333144.7812 | |
|
| 57000 | 0.5758 | 175.8667 | 62415.5508 | 1.1766 | 13.0944 | 76.369 | 9.546 | 10.1214 | 344902.0312 | |
|
| 57500 | 0.5808 | 175.9553 | 64830.4531 | 1.1772 | 13.1232 | 76.201 | 9.525 | 10.1974 | 364485.8125 | |
|
| 58000 | 0.5859 | 177.7224 | 62728.4141 | 1.1767 | 13.1442 | 76.079 | 9.51 | 10.2901 | 352342.8125 | |
|
| 58500 | 0.5909 | 174.5569 | 59045.9727 | 1.1765 | 13.1927 | 75.799 | 9.475 | 10.2303 | 330136.375 | |
|
| 59000 | 0.5960 | 176.9120 | 62516.7031 | 1.1762 | 13.0404 | 76.685 | 9.586 | 10.3225 | 338159.4062 | |
|
| 59500 | 0.6010 | 176.6108 | 62340.8320 | 1.1763 | 13.1224 | 76.206 | 9.526 | 10.2863 | 350280.6562 | |
|
| 60000 | 0.6061 | 172.9151 | 62380.3789 | 1.1763 | 13.2135 | 75.68 | 9.46 | 10.0223 | 335106.0312 | |
|
| 60500 | 0.6111 | 172.8012 | 58879.8633 | 1.1761 | 13.1236 | 76.198 | 9.525 | 10.1251 | 328905.75 | |
|
| 61000 | 0.6162 | 175.1665 | 62723.9883 | 1.1760 | 13.0533 | 76.609 | 9.576 | 10.1293 | 365459.7188 | |
|
| 61500 | 0.6212 | 178.2050 | 62994.0508 | 1.1773 | 13.1683 | 75.94 | 9.493 | 10.3109 | 339062.9688 | |
|
| 62000 | 0.6263 | 175.7850 | 63131.7148 | 1.1769 | 13.1223 | 76.206 | 9.526 | 10.1310 | 348974.9375 | |
|
| 62500 | 0.6313 | 176.4672 | 61663.9766 | 1.1768 | 13.0971 | 76.353 | 9.544 | 10.2824 | 356028.25 | |
|
| 63000 | 0.6364 | 176.9943 | 63242.9531 | 1.1762 | 13.0327 | 76.73 | 9.591 | 10.2671 | 351779.0625 | |
|
| 63500 | 0.6414 | 173.9832 | 60442.8633 | 1.1762 | 13.0653 | 76.539 | 9.567 | 10.1339 | 318202.5938 | |
|
| 64000 | 0.6465 | 175.6557 | 59530.3594 | 1.1761 | 13.1488 | 76.052 | 9.507 | 10.2680 | 337258.5938 | |
|
| 64500 | 0.6515 | 174.9766 | 62375.9766 | 1.1759 | 13.1342 | 76.137 | 9.517 | 10.2570 | 332079.9375 | |
|
| 65000 | 0.6566 | 172.8950 | 59883.5625 | 1.1763 | 13.1758 | 75.897 | 9.487 | 10.2223 | 329256.9375 | |
|
| 65500 | 0.6616 | 177.9153 | 63189.5391 | 1.1765 | 13.0493 | 76.632 | 9.579 | 10.2252 | 350093.9688 | |
|
| 66000 | 0.6667 | 175.5877 | 60493.9570 | 1.1759 | 13.1408 | 76.099 | 9.512 | 10.2960 | 330841.75 | |
|
| 66500 | 0.6717 | 173.8889 | 62152.3555 | 1.1762 | 13.1111 | 76.271 | 9.534 | 10.1650 | 350093.9688 | |
|
| 67000 | 0.6768 | 176.5698 | 64266.7031 | 1.1761 | 13.0981 | 76.347 | 9.543 | 10.1851 | 362159.5 | |
|
| 67500 | 0.6818 | 175.3905 | 62012.3906 | 1.1764 | 13.1151 | 76.248 | 9.531 | 10.1159 | 334034.9062 | |
|
| 68000 | 0.6869 | 173.2368 | 58838.4375 | 1.1761 | 13.1682 | 75.94 | 9.493 | 10.1725 | 334927.125 | |
|
| 68500 | 0.6919 | 175.5400 | 60357.7852 | 1.1761 | 13.1647 | 75.961 | 9.495 | 10.2515 | 349161.0312 | |
|
| 69000 | 0.6970 | 174.6111 | 61942.5859 | 1.1762 | 13.139 | 76.109 | 9.514 | 10.2498 | 342518.0312 | |
|
| 69500 | 0.7020 | 172.1866 | 59681.4531 | 1.1761 | 13.228 | 75.597 | 9.45 | 10.1360 | 319052.8125 | |
|
| 70000 | 0.7071 | 172.8950 | 61750.8945 | 1.1764 | 13.2173 | 75.658 | 9.457 | 10.1486 | 327155.4375 | |
|
| 70500 | 0.7121 | 176.0235 | 61559.8594 | 1.1766 | 13.1184 | 76.229 | 9.529 | 10.2799 | 360232.2188 | |
|
| 71000 | 0.7172 | 173.2704 | 58788.6875 | 1.1767 | 13.1566 | 76.007 | 9.501 | 10.1553 | 317354.625 | |
|
| 71500 | 0.7222 | 174.7057 | 61872.8008 | 1.1759 | 13.2179 | 75.655 | 9.457 | 10.1285 | 343432.9062 | |
|
| 72000 | 0.7273 | 176.7477 | 62253.0820 | 1.1765 | 13.125 | 76.19 | 9.524 | 10.3417 | 350280.6562 | |
|
| 72500 | 0.7323 | 177.4336 | 63815.6719 | 1.1760 | 13.1259 | 76.185 | 9.523 | 10.2349 | 366045.0 | |
|
| 73000 | 0.7374 | 176.1736 | 60801.5391 | 1.1760 | 13.0704 | 76.509 | 9.564 | 10.2510 | 354322.4688 | |
|
| 73500 | 0.7424 | 175.7033 | 63739.3398 | 1.1767 | 13.1804 | 75.87 | 9.484 | 10.1076 | 346747.5938 | |
|
| 74000 | 0.7475 | 175.8123 | 61912.0508 | 1.1763 | 13.1949 | 75.787 | 9.473 | 10.2718 | 336898.875 | |
|
| 74500 | 0.7525 | 174.7870 | 59934.1836 | 1.1759 | 13.1044 | 76.31 | 9.539 | 10.2387 | 331018.4688 | |
|
| 75000 | 0.7576 | 171.5209 | 57795.2344 | 1.1760 | 13.1288 | 76.168 | 9.521 | 10.2443 | 294904.2812 | |
|
| 75500 | 0.7626 | 172.1866 | 59698.3008 | 1.1762 | 13.1549 | 76.018 | 9.502 | 10.1793 | 329432.5 | |
|
| 76000 | 0.7677 | 175.2344 | 61059.0117 | 1.1759 | 13.1045 | 76.31 | 9.539 | 10.2671 | 330665.4062 | |
|
| 76500 | 0.7727 | 173.0692 | 60733.0391 | 1.1755 | 13.1001 | 76.335 | 9.542 | 10.1364 | 317693.5 | |
|
| 77000 | 0.7778 | 174.3678 | 61872.8008 | 1.1757 | 13.1179 | 76.232 | 9.529 | 10.2459 | 329784.25 | |
|
| 77500 | 0.7828 | 172.8012 | 60596.3281 | 1.1760 | 13.1925 | 75.801 | 9.475 | 10.1671 | 324287.6875 | |
|
| 78000 | 0.7879 | 174.2125 | 60476.9375 | 1.1759 | 13.1527 | 76.03 | 9.504 | 10.3020 | 324633.9375 | |
|
| 78500 | 0.7929 | 173.1697 | 60255.8711 | 1.1757 | 13.142 | 76.092 | 9.511 | 10.2438 | 328379.5312 | |
|
| 79000 | 0.7980 | 174.3070 | 61248.4961 | 1.1757 | 13.1295 | 76.164 | 9.521 | 10.2045 | 332079.9375 | |
|
| 79500 | 0.8030 | 174.3542 | 61352.0898 | 1.1758 | 13.1433 | 76.084 | 9.511 | 10.2553 | 323423.5312 | |
|
| 80000 | 0.8081 | 173.6668 | 61265.7305 | 1.1757 | 13.1664 | 75.951 | 9.494 | 10.2290 | 334927.125 | |
|
| 80500 | 0.8131 | 174.2260 | 61213.9844 | 1.1757 | 13.1433 | 76.084 | 9.511 | 10.1881 | 336719.0 | |
|
| 81000 | 0.8182 | 175.9280 | 62958.5547 | 1.1758 | 13.1561 | 76.011 | 9.501 | 10.2430 | 347488.4688 | |
|
| 81500 | 0.8232 | 174.8141 | 62516.7031 | 1.1758 | 13.0732 | 76.492 | 9.562 | 10.2269 | 329784.25 | |
|
| 82000 | 0.8283 | 174.4420 | 61907.6836 | 1.1757 | 13.2691 | 75.363 | 9.42 | 10.2218 | 348974.9375 | |
|
| 82500 | 0.8333 | 172.8146 | 58631.5781 | 1.1761 | 13.0985 | 76.345 | 9.543 | 10.2506 | 327155.4375 | |
|
| 83000 | 0.8384 | 172.7477 | 59179.1836 | 1.1757 | 13.1399 | 76.104 | 9.513 | 10.1923 | 317185.5 | |
|
| 83500 | 0.8434 | 173.6601 | 60425.8594 | 1.1758 | 13.1157 | 76.244 | 9.531 | 10.2922 | 318882.4688 | |
|
| 84000 | 0.8485 | 173.7408 | 60835.7578 | 1.1757 | 13.1216 | 76.21 | 9.526 | 10.2100 | 320075.875 | |
|
| 84500 | 0.8535 | 173.5928 | 61768.3281 | 1.1760 | 13.1128 | 76.262 | 9.533 | 10.1826 | 335463.8438 | |
|
| 85000 | 0.8586 | 172.5203 | 60767.2773 | 1.1758 | 13.1532 | 76.027 | 9.503 | 10.1818 | 333678.6562 | |
|
| 85500 | 0.8636 | 174.4556 | 60852.9336 | 1.1758 | 13.336 | 74.985 | 9.373 | 10.2320 | 339062.9688 | |
|
| 86000 | 0.8687 | 174.2193 | 61334.8320 | 1.1757 | 13.2466 | 75.491 | 9.436 | 10.2375 | 324807.0625 | |
|
| 86500 | 0.8737 | 172.9083 | 59379.5938 | 1.1757 | 13.1541 | 76.022 | 9.503 | 10.2561 | 328029.2812 | |
|
| 87000 | 0.8788 | 174.4623 | 61872.8008 | 1.1757 | 13.1612 | 75.981 | 9.498 | 10.2303 | 336719.0 | |
|
| 87500 | 0.8838 | 174.3340 | 61859.7617 | 1.1757 | 13.1513 | 76.038 | 9.505 | 10.2654 | 334927.125 | |
|
| 88000 | 0.8889 | 174.1922 | 62174.2305 | 1.1757 | 13.3273 | 75.034 | 9.379 | 10.2290 | 335106.0312 | |
|
| 88500 | 0.8939 | 173.2838 | 60425.8594 | 1.1754 | 13.1058 | 76.302 | 9.538 | 10.1902 | 329960.4062 | |
|
| 89000 | 0.8990 | 174.5435 | 60801.5391 | 1.1756 | 13.0514 | 76.62 | 9.578 | 10.2468 | 326457.9375 | |
|
| 89500 | 0.9040 | 174.0236 | 61231.2109 | 1.1756 | 13.0562 | 76.592 | 9.574 | 10.1982 | 326980.7812 | |
|
| 90000 | 0.9091 | 174.1046 | 61369.4102 | 1.1756 | 13.1257 | 76.187 | 9.523 | 10.2109 | 329784.25 | |
|
| 90500 | 0.9141 | 173.1563 | 60052.5039 | 1.1754 | 13.0825 | 76.438 | 9.555 | 10.2185 | 320759.75 | |
|
| 91000 | 0.9192 | 173.7139 | 60733.0391 | 1.1756 | 13.1096 | 76.28 | 9.535 | 10.2227 | 324633.9375 | |
|
| 91500 | 0.9242 | 174.1315 | 61872.8008 | 1.1754 | 13.2152 | 75.67 | 9.459 | 10.2049 | 336719.0 | |
|
| 92000 | 0.9293 | 174.0372 | 61490.5039 | 1.1754 | 13.1908 | 75.811 | 9.476 | 10.2134 | 334927.125 | |
|
| 92500 | 0.9343 | 173.8215 | 61386.6797 | 1.1754 | 13.1765 | 75.893 | 9.487 | 10.2206 | 330312.7188 | |
|
| 93000 | 0.9394 | 173.9159 | 61041.7773 | 1.1756 | 13.158 | 75.999 | 9.5 | 10.2273 | 329081.125 | |
|
| 93500 | 0.9444 | 173.6062 | 60870.0586 | 1.1757 | 13.2142 | 75.676 | 9.46 | 10.2147 | 327679.4062 | |
|
| 94000 | 0.9495 | 173.7812 | 61162.2852 | 1.1758 | 13.1051 | 76.306 | 9.538 | 10.2172 | 327068.0938 | |
|
| 94500 | 0.9545 | 174.3273 | 61507.8633 | 1.1758 | 13.1923 | 75.802 | 9.475 | 10.2294 | 329256.9375 | |
|
| 95000 | 0.9596 | 173.5390 | 60664.6172 | 1.1756 | 13.0788 | 76.46 | 9.557 | 10.2096 | 328379.5312 | |
|
| 95500 | 0.9646 | 173.6870 | 60664.6172 | 1.1756 | 13.2337 | 75.565 | 9.446 | 10.2252 | 329256.9375 | |
|
| 96000 | 0.9697 | 173.6735 | 60698.8164 | 1.1755 | 13.1813 | 75.865 | 9.483 | 10.2117 | 328204.5 | |
|
| 96500 | 0.9747 | 173.9765 | 60955.8594 | 1.1755 | 13.1412 | 76.096 | 9.512 | 10.2307 | 328905.75 | |
|
| 97000 | 0.9798 | 173.8215 | 60835.7578 | 1.1755 | 13.2784 | 75.31 | 9.414 | 10.2227 | 327854.4375 | |
|
| 97500 | 0.9848 | 173.8215 | 60887.2422 | 1.1755 | 13.0893 | 76.398 | 9.55 | 10.2176 | 327854.4375 | |
|
| 98000 | 0.9899 | 173.8215 | 60852.9336 | 1.1755 | 13.1604 | 75.986 | 9.498 | 10.2142 | 328029.2812 | |
|
| 98500 | 0.9949 | 173.8350 | 60887.2422 | 1.1755 | 13.2337 | 75.565 | 9.446 | 10.2239 | 328379.5312 | |
|
| 99000 | 1.0 | 173.8350 | 60887.2422 | 1.1755 | 13.1746 | 75.903 | 9.488 | 10.2239 | 328379.5312 | |
|
|
|
### Framework versions |
|
- Distily 0.2.0 |
|
- Transformers 4.44.0 |
|
- Pytorch 2.3.0 |
|
- Datasets 2.20.0 |
|
|