Commit
•
6259946
1
Parent(s):
040bb60
Evaluation on the test set completed on 2024_11_15.
Browse files- README.md +145 -0
- all_results.json +17 -0
- logs/events.out.tfevents.1731645940.datavisu2 +2 -2
- logs/events.out.tfevents.1731665544.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +1383 -0
README.md
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/dinov2-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.4668
|
| 19 |
+
- Rmse: 0.1546
|
| 20 |
+
- Mae: 0.1143
|
| 21 |
+
- Kl Divergence: 0.3931
|
| 22 |
+
- Explained Variance: 0.4690
|
| 23 |
+
- Learning Rate: 0.0000
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.001
|
| 43 |
+
- train_batch_size: 32
|
| 44 |
+
- eval_batch_size: 32
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 150
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rmse | Mae | Kl Divergence | Explained Variance | Rate |
|
| 54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:-------------:|:------------------:|:------:|
|
| 55 |
+
| No log | 1.0 | 219 | 0.4855 | 0.1771 | 0.1364 | 0.3101 | 0.3433 | 0.001 |
|
| 56 |
+
| No log | 2.0 | 438 | 0.4760 | 0.1688 | 0.1247 | 0.5077 | 0.3891 | 0.001 |
|
| 57 |
+
| 0.5195 | 3.0 | 657 | 0.4777 | 0.1707 | 0.1230 | 0.7896 | 0.3848 | 0.001 |
|
| 58 |
+
| 0.5195 | 4.0 | 876 | 0.4743 | 0.1672 | 0.1238 | 0.4932 | 0.4037 | 0.001 |
|
| 59 |
+
| 0.4742 | 5.0 | 1095 | 0.4746 | 0.1669 | 0.1277 | 0.2901 | 0.4132 | 0.001 |
|
| 60 |
+
| 0.4742 | 6.0 | 1314 | 0.4750 | 0.1674 | 0.1253 | 0.4399 | 0.4022 | 0.001 |
|
| 61 |
+
| 0.4706 | 7.0 | 1533 | 0.4745 | 0.1671 | 0.1259 | 0.4868 | 0.4020 | 0.001 |
|
| 62 |
+
| 0.4706 | 8.0 | 1752 | 0.4742 | 0.1672 | 0.1257 | 0.3241 | 0.4111 | 0.001 |
|
| 63 |
+
| 0.4706 | 9.0 | 1971 | 0.4730 | 0.1658 | 0.1236 | 0.4560 | 0.4107 | 0.001 |
|
| 64 |
+
| 0.4678 | 10.0 | 2190 | 0.4751 | 0.1679 | 0.1269 | 0.2141 | 0.4190 | 0.001 |
|
| 65 |
+
| 0.4678 | 11.0 | 2409 | 0.4733 | 0.1663 | 0.1265 | 0.2530 | 0.4189 | 0.001 |
|
| 66 |
+
| 0.4674 | 12.0 | 2628 | 0.4758 | 0.1684 | 0.1264 | 0.3966 | 0.4074 | 0.001 |
|
| 67 |
+
| 0.4674 | 13.0 | 2847 | 0.4722 | 0.1650 | 0.1223 | 0.6055 | 0.4142 | 0.001 |
|
| 68 |
+
| 0.4676 | 14.0 | 3066 | 0.4747 | 0.1666 | 0.1250 | 0.4203 | 0.4071 | 0.001 |
|
| 69 |
+
| 0.4676 | 15.0 | 3285 | 0.4733 | 0.1662 | 0.1227 | 0.6553 | 0.4153 | 0.001 |
|
| 70 |
+
| 0.4663 | 16.0 | 3504 | 0.4735 | 0.1656 | 0.1241 | 0.3576 | 0.4176 | 0.001 |
|
| 71 |
+
| 0.4663 | 17.0 | 3723 | 0.4722 | 0.1643 | 0.1221 | 0.4545 | 0.4231 | 0.001 |
|
| 72 |
+
| 0.4663 | 18.0 | 3942 | 0.4724 | 0.1647 | 0.1225 | 0.4902 | 0.4209 | 0.001 |
|
| 73 |
+
| 0.4655 | 19.0 | 4161 | 0.4729 | 0.1650 | 0.1261 | 0.3158 | 0.4224 | 0.001 |
|
| 74 |
+
| 0.4655 | 20.0 | 4380 | 0.4697 | 0.1623 | 0.1203 | 0.4574 | 0.4342 | 0.0001 |
|
| 75 |
+
| 0.4635 | 21.0 | 4599 | 0.4689 | 0.1613 | 0.1197 | 0.4569 | 0.4383 | 0.0001 |
|
| 76 |
+
| 0.4635 | 22.0 | 4818 | 0.4691 | 0.1617 | 0.1202 | 0.4535 | 0.4374 | 0.0001 |
|
| 77 |
+
| 0.4615 | 23.0 | 5037 | 0.4691 | 0.1614 | 0.1210 | 0.2971 | 0.4442 | 0.0001 |
|
| 78 |
+
| 0.4615 | 24.0 | 5256 | 0.4692 | 0.1616 | 0.1196 | 0.3916 | 0.4406 | 0.0001 |
|
| 79 |
+
| 0.4615 | 25.0 | 5475 | 0.4677 | 0.1601 | 0.1181 | 0.4516 | 0.4465 | 0.0001 |
|
| 80 |
+
| 0.4601 | 26.0 | 5694 | 0.4680 | 0.1605 | 0.1171 | 0.6089 | 0.4434 | 0.0001 |
|
| 81 |
+
| 0.4601 | 27.0 | 5913 | 0.4675 | 0.1600 | 0.1182 | 0.4741 | 0.4461 | 0.0001 |
|
| 82 |
+
| 0.4585 | 28.0 | 6132 | 0.4681 | 0.1606 | 0.1200 | 0.3356 | 0.4489 | 0.0001 |
|
| 83 |
+
| 0.4585 | 29.0 | 6351 | 0.4678 | 0.1603 | 0.1181 | 0.4330 | 0.4460 | 0.0001 |
|
| 84 |
+
| 0.4578 | 30.0 | 6570 | 0.4680 | 0.1602 | 0.1194 | 0.3160 | 0.4504 | 0.0001 |
|
| 85 |
+
| 0.4578 | 31.0 | 6789 | 0.4677 | 0.1600 | 0.1179 | 0.4190 | 0.4468 | 0.0001 |
|
| 86 |
+
| 0.4579 | 32.0 | 7008 | 0.4675 | 0.1598 | 0.1188 | 0.3706 | 0.4504 | 0.0001 |
|
| 87 |
+
| 0.4579 | 33.0 | 7227 | 0.4671 | 0.1593 | 0.1181 | 0.3504 | 0.4546 | 0.0001 |
|
| 88 |
+
| 0.4579 | 34.0 | 7446 | 0.4670 | 0.1594 | 0.1180 | 0.3881 | 0.4533 | 0.0001 |
|
| 89 |
+
| 0.4569 | 35.0 | 7665 | 0.4663 | 0.1587 | 0.1166 | 0.4398 | 0.4556 | 0.0001 |
|
| 90 |
+
| 0.4569 | 36.0 | 7884 | 0.4666 | 0.1587 | 0.1170 | 0.4382 | 0.4544 | 0.0001 |
|
| 91 |
+
| 0.4572 | 37.0 | 8103 | 0.4658 | 0.1581 | 0.1163 | 0.4330 | 0.4594 | 0.0001 |
|
| 92 |
+
| 0.4572 | 38.0 | 8322 | 0.4659 | 0.1583 | 0.1162 | 0.4878 | 0.4567 | 0.0001 |
|
| 93 |
+
| 0.4572 | 39.0 | 8541 | 0.4670 | 0.1595 | 0.1178 | 0.3791 | 0.4552 | 0.0001 |
|
| 94 |
+
| 0.4572 | 40.0 | 8760 | 0.4665 | 0.1588 | 0.1178 | 0.3889 | 0.4568 | 0.0001 |
|
| 95 |
+
| 0.4572 | 41.0 | 8979 | 0.4666 | 0.1589 | 0.1184 | 0.3222 | 0.4591 | 0.0001 |
|
| 96 |
+
| 0.4559 | 42.0 | 9198 | 0.4655 | 0.1579 | 0.1164 | 0.4262 | 0.4607 | 0.0001 |
|
| 97 |
+
| 0.4559 | 43.0 | 9417 | 0.4656 | 0.1579 | 0.1162 | 0.4611 | 0.4603 | 0.0001 |
|
| 98 |
+
| 0.4554 | 44.0 | 9636 | 0.4656 | 0.1580 | 0.1164 | 0.4586 | 0.4616 | 0.0001 |
|
| 99 |
+
| 0.4554 | 45.0 | 9855 | 0.4660 | 0.1583 | 0.1158 | 0.4368 | 0.4597 | 0.0001 |
|
| 100 |
+
| 0.4557 | 46.0 | 10074 | 0.4660 | 0.1582 | 0.1164 | 0.4118 | 0.4604 | 0.0001 |
|
| 101 |
+
| 0.4557 | 47.0 | 10293 | 0.4652 | 0.1577 | 0.1154 | 0.5424 | 0.4614 | 0.0001 |
|
| 102 |
+
| 0.4551 | 48.0 | 10512 | 0.4660 | 0.1586 | 0.1160 | 0.5251 | 0.4596 | 0.0001 |
|
| 103 |
+
| 0.4551 | 49.0 | 10731 | 0.4660 | 0.1585 | 0.1161 | 0.5007 | 0.4572 | 0.0001 |
|
| 104 |
+
| 0.4551 | 50.0 | 10950 | 0.4666 | 0.1586 | 0.1185 | 0.2424 | 0.4659 | 0.0001 |
|
| 105 |
+
| 0.4545 | 51.0 | 11169 | 0.4661 | 0.1584 | 0.1162 | 0.4171 | 0.4589 | 0.0001 |
|
| 106 |
+
| 0.4545 | 52.0 | 11388 | 0.4650 | 0.1575 | 0.1155 | 0.4912 | 0.4630 | 0.0001 |
|
| 107 |
+
| 0.4548 | 53.0 | 11607 | 0.4654 | 0.1578 | 0.1169 | 0.4030 | 0.4644 | 0.0001 |
|
| 108 |
+
| 0.4548 | 54.0 | 11826 | 0.4661 | 0.1585 | 0.1153 | 0.4811 | 0.4595 | 0.0001 |
|
| 109 |
+
| 0.455 | 55.0 | 12045 | 0.4653 | 0.1576 | 0.1167 | 0.3774 | 0.4638 | 0.0001 |
|
| 110 |
+
| 0.455 | 56.0 | 12264 | 0.4654 | 0.1575 | 0.1176 | 0.3254 | 0.4670 | 0.0001 |
|
| 111 |
+
| 0.455 | 57.0 | 12483 | 0.4654 | 0.1575 | 0.1162 | 0.3649 | 0.4662 | 0.0001 |
|
| 112 |
+
| 0.4531 | 58.0 | 12702 | 0.4665 | 0.1584 | 0.1166 | 0.4075 | 0.4607 | 0.0001 |
|
| 113 |
+
| 0.4531 | 59.0 | 12921 | 0.4652 | 0.1575 | 0.1157 | 0.4202 | 0.4654 | 1e-05 |
|
| 114 |
+
| 0.4538 | 60.0 | 13140 | 0.4653 | 0.1571 | 0.1157 | 0.4084 | 0.4669 | 1e-05 |
|
| 115 |
+
| 0.4538 | 61.0 | 13359 | 0.4654 | 0.1573 | 0.1153 | 0.4497 | 0.4661 | 1e-05 |
|
| 116 |
+
| 0.4529 | 62.0 | 13578 | 0.4648 | 0.1568 | 0.1153 | 0.4112 | 0.4682 | 1e-05 |
|
| 117 |
+
| 0.4529 | 63.0 | 13797 | 0.4648 | 0.1567 | 0.1152 | 0.3748 | 0.4702 | 1e-05 |
|
| 118 |
+
| 0.4527 | 64.0 | 14016 | 0.4652 | 0.1571 | 0.1162 | 0.3044 | 0.4721 | 1e-05 |
|
| 119 |
+
| 0.4527 | 65.0 | 14235 | 0.4648 | 0.1569 | 0.1153 | 0.4685 | 0.4670 | 1e-05 |
|
| 120 |
+
| 0.4527 | 66.0 | 14454 | 0.4650 | 0.1573 | 0.1148 | 0.5087 | 0.4671 | 1e-05 |
|
| 121 |
+
| 0.4531 | 67.0 | 14673 | 0.4646 | 0.1568 | 0.1155 | 0.4274 | 0.4690 | 1e-05 |
|
| 122 |
+
| 0.4531 | 68.0 | 14892 | 0.4646 | 0.1566 | 0.1144 | 0.4969 | 0.4680 | 1e-05 |
|
| 123 |
+
| 0.452 | 69.0 | 15111 | 0.4644 | 0.1564 | 0.1145 | 0.4480 | 0.4696 | 1e-05 |
|
| 124 |
+
| 0.452 | 70.0 | 15330 | 0.4648 | 0.1567 | 0.1150 | 0.4291 | 0.4692 | 1e-05 |
|
| 125 |
+
| 0.4524 | 71.0 | 15549 | 0.4645 | 0.1565 | 0.1156 | 0.3797 | 0.4711 | 1e-05 |
|
| 126 |
+
| 0.4524 | 72.0 | 15768 | 0.4647 | 0.1569 | 0.1150 | 0.4280 | 0.4690 | 1e-05 |
|
| 127 |
+
| 0.4524 | 73.0 | 15987 | 0.4641 | 0.1563 | 0.1142 | 0.4592 | 0.4707 | 1e-05 |
|
| 128 |
+
| 0.4515 | 74.0 | 16206 | 0.4642 | 0.1564 | 0.1151 | 0.4321 | 0.4706 | 1e-05 |
|
| 129 |
+
| 0.4515 | 75.0 | 16425 | 0.4645 | 0.1565 | 0.1152 | 0.3843 | 0.4708 | 1e-05 |
|
| 130 |
+
| 0.4521 | 76.0 | 16644 | 0.4646 | 0.1569 | 0.1147 | 0.5216 | 0.4675 | 1e-05 |
|
| 131 |
+
| 0.4521 | 77.0 | 16863 | 0.4648 | 0.1569 | 0.1152 | 0.4094 | 0.4691 | 1e-05 |
|
| 132 |
+
| 0.4519 | 78.0 | 17082 | 0.4643 | 0.1564 | 0.1149 | 0.4399 | 0.4709 | 1e-05 |
|
| 133 |
+
| 0.4519 | 79.0 | 17301 | 0.4646 | 0.1567 | 0.1147 | 0.4178 | 0.4697 | 1e-05 |
|
| 134 |
+
| 0.4517 | 80.0 | 17520 | 0.4644 | 0.1564 | 0.1150 | 0.4373 | 0.4700 | 0.0000 |
|
| 135 |
+
| 0.4517 | 81.0 | 17739 | 0.4645 | 0.1567 | 0.1151 | 0.4701 | 0.4688 | 0.0000 |
|
| 136 |
+
| 0.4517 | 82.0 | 17958 | 0.4644 | 0.1565 | 0.1146 | 0.4601 | 0.4703 | 0.0000 |
|
| 137 |
+
| 0.4514 | 83.0 | 18177 | 0.4646 | 0.1567 | 0.1147 | 0.4511 | 0.4684 | 0.0000 |
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
### Framework versions
|
| 141 |
+
|
| 142 |
+
- Transformers 4.41.0
|
| 143 |
+
- Pytorch 2.5.0+cu124
|
| 144 |
+
- Datasets 3.0.2
|
| 145 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 83.0,
|
| 3 |
+
"eval_explained_variance": 0.4690297544002533,
|
| 4 |
+
"eval_kl_divergence": 0.39311662316322327,
|
| 5 |
+
"eval_loss": 0.46676135063171387,
|
| 6 |
+
"eval_mae": 0.11432621628046036,
|
| 7 |
+
"eval_rmse": 0.1546144038438797,
|
| 8 |
+
"eval_runtime": 61.4305,
|
| 9 |
+
"eval_samples_per_second": 38.369,
|
| 10 |
+
"eval_steps_per_second": 1.205,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 12 |
+
"total_flos": 8.603009036605255e+19,
|
| 13 |
+
"train_loss": 0.45949580130708517,
|
| 14 |
+
"train_runtime": 19431.3015,
|
| 15 |
+
"train_samples_per_second": 54.06,
|
| 16 |
+
"train_steps_per_second": 1.691
|
| 17 |
+
}
|
logs/events.out.tfevents.1731645940.datavisu2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82cb032cea5b9414fdccda28f1b8e649b0e7dae9bdb952de73917a1e064c806b
|
| 3 |
+
size 59401
|
logs/events.out.tfevents.1731665544.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0515028d84acb2fc61e70ee5780613b9ccbfec4c83830626dd5e3847fc4eecb
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1222956704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45fc50bef10dc323eaf2356023658e6a6f37ae07d855a6afd234c5255a0ff422
|
| 3 |
size 1222956704
|
test_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 83.0,
|
| 3 |
+
"eval_explained_variance": 0.4690297544002533,
|
| 4 |
+
"eval_kl_divergence": 0.39311662316322327,
|
| 5 |
+
"eval_loss": 0.46676135063171387,
|
| 6 |
+
"eval_mae": 0.11432621628046036,
|
| 7 |
+
"eval_rmse": 0.1546144038438797,
|
| 8 |
+
"eval_runtime": 61.4305,
|
| 9 |
+
"eval_samples_per_second": 38.369,
|
| 10 |
+
"eval_steps_per_second": 1.205,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 83.0,
|
| 3 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 4 |
+
"total_flos": 8.603009036605255e+19,
|
| 5 |
+
"train_loss": 0.45949580130708517,
|
| 6 |
+
"train_runtime": 19431.3015,
|
| 7 |
+
"train_samples_per_second": 54.06,
|
| 8 |
+
"train_steps_per_second": 1.691
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.46414923667907715,
|
| 3 |
+
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/drone/drone-DinoVdeau-from-probs-large-2024_11_15-batch-size32_freeze_probs/checkpoint-15987",
|
| 4 |
+
"epoch": 83.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 18177,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_explained_variance": 0.3432542085647583,
|
| 14 |
+
"eval_kl_divergence": 0.31011611223220825,
|
| 15 |
+
"eval_loss": 0.4855400025844574,
|
| 16 |
+
"eval_mae": 0.1364378184080124,
|
| 17 |
+
"eval_rmse": 0.17712123692035675,
|
| 18 |
+
"eval_runtime": 55.3387,
|
| 19 |
+
"eval_samples_per_second": 42.538,
|
| 20 |
+
"eval_steps_per_second": 1.337,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"step": 219
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"eval_explained_variance": 0.38912513852119446,
|
| 27 |
+
"eval_kl_divergence": 0.5077245235443115,
|
| 28 |
+
"eval_loss": 0.47601452469825745,
|
| 29 |
+
"eval_mae": 0.12465938925743103,
|
| 30 |
+
"eval_rmse": 0.16875195503234863,
|
| 31 |
+
"eval_runtime": 54.843,
|
| 32 |
+
"eval_samples_per_second": 42.923,
|
| 33 |
+
"eval_steps_per_second": 1.349,
|
| 34 |
+
"learning_rate": 0.001,
|
| 35 |
+
"step": 438
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.2831050228310503,
|
| 39 |
+
"grad_norm": 0.35450002551078796,
|
| 40 |
+
"learning_rate": 0.001,
|
| 41 |
+
"loss": 0.5195,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_explained_variance": 0.3848476707935333,
|
| 47 |
+
"eval_kl_divergence": 0.7895973324775696,
|
| 48 |
+
"eval_loss": 0.4776814579963684,
|
| 49 |
+
"eval_mae": 0.12300346046686172,
|
| 50 |
+
"eval_rmse": 0.17065072059631348,
|
| 51 |
+
"eval_runtime": 56.2195,
|
| 52 |
+
"eval_samples_per_second": 41.872,
|
| 53 |
+
"eval_steps_per_second": 1.316,
|
| 54 |
+
"learning_rate": 0.001,
|
| 55 |
+
"step": 657
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 4.0,
|
| 59 |
+
"eval_explained_variance": 0.403704434633255,
|
| 60 |
+
"eval_kl_divergence": 0.49319207668304443,
|
| 61 |
+
"eval_loss": 0.47429159283638,
|
| 62 |
+
"eval_mae": 0.12376764416694641,
|
| 63 |
+
"eval_rmse": 0.1672389954328537,
|
| 64 |
+
"eval_runtime": 54.7793,
|
| 65 |
+
"eval_samples_per_second": 42.972,
|
| 66 |
+
"eval_steps_per_second": 1.351,
|
| 67 |
+
"learning_rate": 0.001,
|
| 68 |
+
"step": 876
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.566210045662101,
|
| 72 |
+
"grad_norm": 0.2313629388809204,
|
| 73 |
+
"learning_rate": 0.001,
|
| 74 |
+
"loss": 0.4742,
|
| 75 |
+
"step": 1000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"eval_explained_variance": 0.41316938400268555,
|
| 80 |
+
"eval_kl_divergence": 0.2900688648223877,
|
| 81 |
+
"eval_loss": 0.47457176446914673,
|
| 82 |
+
"eval_mae": 0.12771284580230713,
|
| 83 |
+
"eval_rmse": 0.16687722504138947,
|
| 84 |
+
"eval_runtime": 55.1273,
|
| 85 |
+
"eval_samples_per_second": 42.701,
|
| 86 |
+
"eval_steps_per_second": 1.342,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"step": 1095
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"eval_explained_variance": 0.40222811698913574,
|
| 93 |
+
"eval_kl_divergence": 0.43988940119743347,
|
| 94 |
+
"eval_loss": 0.4749792814254761,
|
| 95 |
+
"eval_mae": 0.1252531260251999,
|
| 96 |
+
"eval_rmse": 0.16735166311264038,
|
| 97 |
+
"eval_runtime": 53.136,
|
| 98 |
+
"eval_samples_per_second": 44.301,
|
| 99 |
+
"eval_steps_per_second": 1.393,
|
| 100 |
+
"learning_rate": 0.001,
|
| 101 |
+
"step": 1314
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 6.8493150684931505,
|
| 105 |
+
"grad_norm": 0.18959695100784302,
|
| 106 |
+
"learning_rate": 0.001,
|
| 107 |
+
"loss": 0.4706,
|
| 108 |
+
"step": 1500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 7.0,
|
| 112 |
+
"eval_explained_variance": 0.4019981324672699,
|
| 113 |
+
"eval_kl_divergence": 0.48684099316596985,
|
| 114 |
+
"eval_loss": 0.4744807779788971,
|
| 115 |
+
"eval_mae": 0.12594138085842133,
|
| 116 |
+
"eval_rmse": 0.16705705225467682,
|
| 117 |
+
"eval_runtime": 53.367,
|
| 118 |
+
"eval_samples_per_second": 44.11,
|
| 119 |
+
"eval_steps_per_second": 1.387,
|
| 120 |
+
"learning_rate": 0.001,
|
| 121 |
+
"step": 1533
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_explained_variance": 0.41111621260643005,
|
| 126 |
+
"eval_kl_divergence": 0.324148029088974,
|
| 127 |
+
"eval_loss": 0.47424906492233276,
|
| 128 |
+
"eval_mae": 0.12568950653076172,
|
| 129 |
+
"eval_rmse": 0.16722555458545685,
|
| 130 |
+
"eval_runtime": 55.5084,
|
| 131 |
+
"eval_samples_per_second": 42.408,
|
| 132 |
+
"eval_steps_per_second": 1.333,
|
| 133 |
+
"learning_rate": 0.001,
|
| 134 |
+
"step": 1752
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 9.0,
|
| 138 |
+
"eval_explained_variance": 0.4107116162776947,
|
| 139 |
+
"eval_kl_divergence": 0.4560392200946808,
|
| 140 |
+
"eval_loss": 0.4729686379432678,
|
| 141 |
+
"eval_mae": 0.12355945259332657,
|
| 142 |
+
"eval_rmse": 0.16584673523902893,
|
| 143 |
+
"eval_runtime": 55.1596,
|
| 144 |
+
"eval_samples_per_second": 42.676,
|
| 145 |
+
"eval_steps_per_second": 1.342,
|
| 146 |
+
"learning_rate": 0.001,
|
| 147 |
+
"step": 1971
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 9.132420091324201,
|
| 151 |
+
"grad_norm": 0.18577350676059723,
|
| 152 |
+
"learning_rate": 0.001,
|
| 153 |
+
"loss": 0.4678,
|
| 154 |
+
"step": 2000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 10.0,
|
| 158 |
+
"eval_explained_variance": 0.4190339744091034,
|
| 159 |
+
"eval_kl_divergence": 0.2140849530696869,
|
| 160 |
+
"eval_loss": 0.4750550389289856,
|
| 161 |
+
"eval_mae": 0.12685616314411163,
|
| 162 |
+
"eval_rmse": 0.1679263859987259,
|
| 163 |
+
"eval_runtime": 56.0284,
|
| 164 |
+
"eval_samples_per_second": 42.014,
|
| 165 |
+
"eval_steps_per_second": 1.321,
|
| 166 |
+
"learning_rate": 0.001,
|
| 167 |
+
"step": 2190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 11.0,
|
| 171 |
+
"eval_explained_variance": 0.41887199878692627,
|
| 172 |
+
"eval_kl_divergence": 0.2529982030391693,
|
| 173 |
+
"eval_loss": 0.4733181595802307,
|
| 174 |
+
"eval_mae": 0.12647458910942078,
|
| 175 |
+
"eval_rmse": 0.16627688705921173,
|
| 176 |
+
"eval_runtime": 55.5532,
|
| 177 |
+
"eval_samples_per_second": 42.374,
|
| 178 |
+
"eval_steps_per_second": 1.332,
|
| 179 |
+
"learning_rate": 0.001,
|
| 180 |
+
"step": 2409
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 11.415525114155251,
|
| 184 |
+
"grad_norm": 0.14618106186389923,
|
| 185 |
+
"learning_rate": 0.001,
|
| 186 |
+
"loss": 0.4674,
|
| 187 |
+
"step": 2500
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 12.0,
|
| 191 |
+
"eval_explained_variance": 0.4073503315448761,
|
| 192 |
+
"eval_kl_divergence": 0.3965540826320648,
|
| 193 |
+
"eval_loss": 0.4758349061012268,
|
| 194 |
+
"eval_mae": 0.1263781040906906,
|
| 195 |
+
"eval_rmse": 0.1683548092842102,
|
| 196 |
+
"eval_runtime": 53.8367,
|
| 197 |
+
"eval_samples_per_second": 43.725,
|
| 198 |
+
"eval_steps_per_second": 1.375,
|
| 199 |
+
"learning_rate": 0.001,
|
| 200 |
+
"step": 2628
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.0,
|
| 204 |
+
"eval_explained_variance": 0.41419240832328796,
|
| 205 |
+
"eval_kl_divergence": 0.6054547429084778,
|
| 206 |
+
"eval_loss": 0.4722050428390503,
|
| 207 |
+
"eval_mae": 0.12233959883451462,
|
| 208 |
+
"eval_rmse": 0.16495703160762787,
|
| 209 |
+
"eval_runtime": 54.7322,
|
| 210 |
+
"eval_samples_per_second": 43.009,
|
| 211 |
+
"eval_steps_per_second": 1.352,
|
| 212 |
+
"learning_rate": 0.001,
|
| 213 |
+
"step": 2847
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 13.698630136986301,
|
| 217 |
+
"grad_norm": 0.15461835265159607,
|
| 218 |
+
"learning_rate": 0.001,
|
| 219 |
+
"loss": 0.4676,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 14.0,
|
| 224 |
+
"eval_explained_variance": 0.40708938241004944,
|
| 225 |
+
"eval_kl_divergence": 0.4203389585018158,
|
| 226 |
+
"eval_loss": 0.4747372567653656,
|
| 227 |
+
"eval_mae": 0.12501581013202667,
|
| 228 |
+
"eval_rmse": 0.16655980050563812,
|
| 229 |
+
"eval_runtime": 55.2289,
|
| 230 |
+
"eval_samples_per_second": 42.623,
|
| 231 |
+
"eval_steps_per_second": 1.34,
|
| 232 |
+
"learning_rate": 0.001,
|
| 233 |
+
"step": 3066
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"eval_explained_variance": 0.41527059674263,
|
| 238 |
+
"eval_kl_divergence": 0.6553499102592468,
|
| 239 |
+
"eval_loss": 0.47325292229652405,
|
| 240 |
+
"eval_mae": 0.12266030162572861,
|
| 241 |
+
"eval_rmse": 0.16621644794940948,
|
| 242 |
+
"eval_runtime": 54.2502,
|
| 243 |
+
"eval_samples_per_second": 43.392,
|
| 244 |
+
"eval_steps_per_second": 1.364,
|
| 245 |
+
"learning_rate": 0.001,
|
| 246 |
+
"step": 3285
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.981735159817351,
|
| 250 |
+
"grad_norm": 0.10063416510820389,
|
| 251 |
+
"learning_rate": 0.001,
|
| 252 |
+
"loss": 0.4663,
|
| 253 |
+
"step": 3500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 16.0,
|
| 257 |
+
"eval_explained_variance": 0.4175969660282135,
|
| 258 |
+
"eval_kl_divergence": 0.35757607221603394,
|
| 259 |
+
"eval_loss": 0.4734710156917572,
|
| 260 |
+
"eval_mae": 0.12411689758300781,
|
| 261 |
+
"eval_rmse": 0.16558559238910675,
|
| 262 |
+
"eval_runtime": 53.6921,
|
| 263 |
+
"eval_samples_per_second": 43.843,
|
| 264 |
+
"eval_steps_per_second": 1.378,
|
| 265 |
+
"learning_rate": 0.001,
|
| 266 |
+
"step": 3504
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 17.0,
|
| 270 |
+
"eval_explained_variance": 0.4231180250644684,
|
| 271 |
+
"eval_kl_divergence": 0.4545155465602875,
|
| 272 |
+
"eval_loss": 0.4721581041812897,
|
| 273 |
+
"eval_mae": 0.12205825001001358,
|
| 274 |
+
"eval_rmse": 0.16431300342082977,
|
| 275 |
+
"eval_runtime": 54.0719,
|
| 276 |
+
"eval_samples_per_second": 43.535,
|
| 277 |
+
"eval_steps_per_second": 1.369,
|
| 278 |
+
"learning_rate": 0.001,
|
| 279 |
+
"step": 3723
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 18.0,
|
| 283 |
+
"eval_explained_variance": 0.42092254757881165,
|
| 284 |
+
"eval_kl_divergence": 0.49019381403923035,
|
| 285 |
+
"eval_loss": 0.4723944365978241,
|
| 286 |
+
"eval_mae": 0.12245010584592819,
|
| 287 |
+
"eval_rmse": 0.16473934054374695,
|
| 288 |
+
"eval_runtime": 53.2446,
|
| 289 |
+
"eval_samples_per_second": 44.211,
|
| 290 |
+
"eval_steps_per_second": 1.39,
|
| 291 |
+
"learning_rate": 0.001,
|
| 292 |
+
"step": 3942
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 18.264840182648403,
|
| 296 |
+
"grad_norm": 0.11052733659744263,
|
| 297 |
+
"learning_rate": 0.001,
|
| 298 |
+
"loss": 0.4655,
|
| 299 |
+
"step": 4000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 19.0,
|
| 303 |
+
"eval_explained_variance": 0.42237523198127747,
|
| 304 |
+
"eval_kl_divergence": 0.3157788813114166,
|
| 305 |
+
"eval_loss": 0.47289156913757324,
|
| 306 |
+
"eval_mae": 0.12610264122486115,
|
| 307 |
+
"eval_rmse": 0.164999321103096,
|
| 308 |
+
"eval_runtime": 54.353,
|
| 309 |
+
"eval_samples_per_second": 43.309,
|
| 310 |
+
"eval_steps_per_second": 1.361,
|
| 311 |
+
"learning_rate": 0.001,
|
| 312 |
+
"step": 4161
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 20.0,
|
| 316 |
+
"eval_explained_variance": 0.43422555923461914,
|
| 317 |
+
"eval_kl_divergence": 0.45738106966018677,
|
| 318 |
+
"eval_loss": 0.4697262644767761,
|
| 319 |
+
"eval_mae": 0.12028751522302628,
|
| 320 |
+
"eval_rmse": 0.16227416694164276,
|
| 321 |
+
"eval_runtime": 52.1033,
|
| 322 |
+
"eval_samples_per_second": 45.179,
|
| 323 |
+
"eval_steps_per_second": 1.42,
|
| 324 |
+
"learning_rate": 0.0001,
|
| 325 |
+
"step": 4380
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 20.54794520547945,
|
| 329 |
+
"grad_norm": 0.10903308540582657,
|
| 330 |
+
"learning_rate": 0.0001,
|
| 331 |
+
"loss": 0.4635,
|
| 332 |
+
"step": 4500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 21.0,
|
| 336 |
+
"eval_explained_variance": 0.43825283646583557,
|
| 337 |
+
"eval_kl_divergence": 0.45688703656196594,
|
| 338 |
+
"eval_loss": 0.46890661120414734,
|
| 339 |
+
"eval_mae": 0.11968808621168137,
|
| 340 |
+
"eval_rmse": 0.16127373278141022,
|
| 341 |
+
"eval_runtime": 52.3325,
|
| 342 |
+
"eval_samples_per_second": 44.982,
|
| 343 |
+
"eval_steps_per_second": 1.414,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"step": 4599
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"eval_explained_variance": 0.4373685419559479,
|
| 350 |
+
"eval_kl_divergence": 0.45346954464912415,
|
| 351 |
+
"eval_loss": 0.46905258297920227,
|
| 352 |
+
"eval_mae": 0.12017489224672318,
|
| 353 |
+
"eval_rmse": 0.16165030002593994,
|
| 354 |
+
"eval_runtime": 51.1815,
|
| 355 |
+
"eval_samples_per_second": 45.993,
|
| 356 |
+
"eval_steps_per_second": 1.446,
|
| 357 |
+
"learning_rate": 0.0001,
|
| 358 |
+
"step": 4818
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 22.831050228310502,
|
| 362 |
+
"grad_norm": 0.09725002944469452,
|
| 363 |
+
"learning_rate": 0.0001,
|
| 364 |
+
"loss": 0.4615,
|
| 365 |
+
"step": 5000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 23.0,
|
| 369 |
+
"eval_explained_variance": 0.4442131519317627,
|
| 370 |
+
"eval_kl_divergence": 0.2970678508281708,
|
| 371 |
+
"eval_loss": 0.4691086411476135,
|
| 372 |
+
"eval_mae": 0.1210075318813324,
|
| 373 |
+
"eval_rmse": 0.1613779515028,
|
| 374 |
+
"eval_runtime": 50.785,
|
| 375 |
+
"eval_samples_per_second": 46.352,
|
| 376 |
+
"eval_steps_per_second": 1.457,
|
| 377 |
+
"learning_rate": 0.0001,
|
| 378 |
+
"step": 5037
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 24.0,
|
| 382 |
+
"eval_explained_variance": 0.4405536353588104,
|
| 383 |
+
"eval_kl_divergence": 0.39161574840545654,
|
| 384 |
+
"eval_loss": 0.46915334463119507,
|
| 385 |
+
"eval_mae": 0.11959254741668701,
|
| 386 |
+
"eval_rmse": 0.16161170601844788,
|
| 387 |
+
"eval_runtime": 50.8712,
|
| 388 |
+
"eval_samples_per_second": 46.274,
|
| 389 |
+
"eval_steps_per_second": 1.455,
|
| 390 |
+
"learning_rate": 0.0001,
|
| 391 |
+
"step": 5256
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 25.0,
|
| 395 |
+
"eval_explained_variance": 0.4465361535549164,
|
| 396 |
+
"eval_kl_divergence": 0.4515945613384247,
|
| 397 |
+
"eval_loss": 0.4676876664161682,
|
| 398 |
+
"eval_mae": 0.11813607066869736,
|
| 399 |
+
"eval_rmse": 0.16005758941173553,
|
| 400 |
+
"eval_runtime": 50.537,
|
| 401 |
+
"eval_samples_per_second": 46.58,
|
| 402 |
+
"eval_steps_per_second": 1.464,
|
| 403 |
+
"learning_rate": 0.0001,
|
| 404 |
+
"step": 5475
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 25.114155251141554,
|
| 408 |
+
"grad_norm": 0.10921537131071091,
|
| 409 |
+
"learning_rate": 0.0001,
|
| 410 |
+
"loss": 0.4601,
|
| 411 |
+
"step": 5500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 26.0,
|
| 415 |
+
"eval_explained_variance": 0.4434172809123993,
|
| 416 |
+
"eval_kl_divergence": 0.6089490652084351,
|
| 417 |
+
"eval_loss": 0.4679708480834961,
|
| 418 |
+
"eval_mae": 0.11711684614419937,
|
| 419 |
+
"eval_rmse": 0.1605486422777176,
|
| 420 |
+
"eval_runtime": 49.8832,
|
| 421 |
+
"eval_samples_per_second": 47.19,
|
| 422 |
+
"eval_steps_per_second": 1.483,
|
| 423 |
+
"learning_rate": 0.0001,
|
| 424 |
+
"step": 5694
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 27.0,
|
| 428 |
+
"eval_explained_variance": 0.4460805654525757,
|
| 429 |
+
"eval_kl_divergence": 0.4741028845310211,
|
| 430 |
+
"eval_loss": 0.4674595892429352,
|
| 431 |
+
"eval_mae": 0.11824781447649002,
|
| 432 |
+
"eval_rmse": 0.16004686057567596,
|
| 433 |
+
"eval_runtime": 49.7793,
|
| 434 |
+
"eval_samples_per_second": 47.289,
|
| 435 |
+
"eval_steps_per_second": 1.487,
|
| 436 |
+
"learning_rate": 0.0001,
|
| 437 |
+
"step": 5913
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 27.397260273972602,
|
| 441 |
+
"grad_norm": 0.11422494053840637,
|
| 442 |
+
"learning_rate": 0.0001,
|
| 443 |
+
"loss": 0.4585,
|
| 444 |
+
"step": 6000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 28.0,
|
| 448 |
+
"eval_explained_variance": 0.4489245116710663,
|
| 449 |
+
"eval_kl_divergence": 0.3355759084224701,
|
| 450 |
+
"eval_loss": 0.46810340881347656,
|
| 451 |
+
"eval_mae": 0.11996418237686157,
|
| 452 |
+
"eval_rmse": 0.16060088574886322,
|
| 453 |
+
"eval_runtime": 52.9491,
|
| 454 |
+
"eval_samples_per_second": 44.458,
|
| 455 |
+
"eval_steps_per_second": 1.398,
|
| 456 |
+
"learning_rate": 0.0001,
|
| 457 |
+
"step": 6132
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 29.0,
|
| 461 |
+
"eval_explained_variance": 0.4459850490093231,
|
| 462 |
+
"eval_kl_divergence": 0.43302619457244873,
|
| 463 |
+
"eval_loss": 0.4678303897380829,
|
| 464 |
+
"eval_mae": 0.11808297038078308,
|
| 465 |
+
"eval_rmse": 0.16026519238948822,
|
| 466 |
+
"eval_runtime": 50.5506,
|
| 467 |
+
"eval_samples_per_second": 46.567,
|
| 468 |
+
"eval_steps_per_second": 1.464,
|
| 469 |
+
"learning_rate": 0.0001,
|
| 470 |
+
"step": 6351
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 29.680365296803654,
|
| 474 |
+
"grad_norm": 0.11833047866821289,
|
| 475 |
+
"learning_rate": 0.0001,
|
| 476 |
+
"loss": 0.4578,
|
| 477 |
+
"step": 6500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 30.0,
|
| 481 |
+
"eval_explained_variance": 0.4503695070743561,
|
| 482 |
+
"eval_kl_divergence": 0.3159695267677307,
|
| 483 |
+
"eval_loss": 0.46800243854522705,
|
| 484 |
+
"eval_mae": 0.11937135457992554,
|
| 485 |
+
"eval_rmse": 0.160204216837883,
|
| 486 |
+
"eval_runtime": 50.0689,
|
| 487 |
+
"eval_samples_per_second": 47.015,
|
| 488 |
+
"eval_steps_per_second": 1.478,
|
| 489 |
+
"learning_rate": 0.0001,
|
| 490 |
+
"step": 6570
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 31.0,
|
| 494 |
+
"eval_explained_variance": 0.4467611014842987,
|
| 495 |
+
"eval_kl_divergence": 0.419010728597641,
|
| 496 |
+
"eval_loss": 0.4676785469055176,
|
| 497 |
+
"eval_mae": 0.11789224296808243,
|
| 498 |
+
"eval_rmse": 0.1599912792444229,
|
| 499 |
+
"eval_runtime": 50.2573,
|
| 500 |
+
"eval_samples_per_second": 46.839,
|
| 501 |
+
"eval_steps_per_second": 1.472,
|
| 502 |
+
"learning_rate": 0.0001,
|
| 503 |
+
"step": 6789
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 31.963470319634702,
|
| 507 |
+
"grad_norm": 0.1234586164355278,
|
| 508 |
+
"learning_rate": 0.0001,
|
| 509 |
+
"loss": 0.4579,
|
| 510 |
+
"step": 7000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 32.0,
|
| 514 |
+
"eval_explained_variance": 0.4503757953643799,
|
| 515 |
+
"eval_kl_divergence": 0.3705631494522095,
|
| 516 |
+
"eval_loss": 0.46752873063087463,
|
| 517 |
+
"eval_mae": 0.11878199130296707,
|
| 518 |
+
"eval_rmse": 0.159804567694664,
|
| 519 |
+
"eval_runtime": 50.3085,
|
| 520 |
+
"eval_samples_per_second": 46.791,
|
| 521 |
+
"eval_steps_per_second": 1.471,
|
| 522 |
+
"learning_rate": 0.0001,
|
| 523 |
+
"step": 7008
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 33.0,
|
| 527 |
+
"eval_explained_variance": 0.4545632600784302,
|
| 528 |
+
"eval_kl_divergence": 0.35043853521347046,
|
| 529 |
+
"eval_loss": 0.46710190176963806,
|
| 530 |
+
"eval_mae": 0.1181415393948555,
|
| 531 |
+
"eval_rmse": 0.1593446284532547,
|
| 532 |
+
"eval_runtime": 50.4199,
|
| 533 |
+
"eval_samples_per_second": 46.688,
|
| 534 |
+
"eval_steps_per_second": 1.468,
|
| 535 |
+
"learning_rate": 0.0001,
|
| 536 |
+
"step": 7227
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 34.0,
|
| 540 |
+
"eval_explained_variance": 0.4532606303691864,
|
| 541 |
+
"eval_kl_divergence": 0.3881392180919647,
|
| 542 |
+
"eval_loss": 0.4670344293117523,
|
| 543 |
+
"eval_mae": 0.11804797500371933,
|
| 544 |
+
"eval_rmse": 0.15942266583442688,
|
| 545 |
+
"eval_runtime": 50.088,
|
| 546 |
+
"eval_samples_per_second": 46.997,
|
| 547 |
+
"eval_steps_per_second": 1.477,
|
| 548 |
+
"learning_rate": 0.0001,
|
| 549 |
+
"step": 7446
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 34.24657534246575,
|
| 553 |
+
"grad_norm": 0.14323526620864868,
|
| 554 |
+
"learning_rate": 0.0001,
|
| 555 |
+
"loss": 0.4569,
|
| 556 |
+
"step": 7500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 35.0,
|
| 560 |
+
"eval_explained_variance": 0.4555685818195343,
|
| 561 |
+
"eval_kl_divergence": 0.43976902961730957,
|
| 562 |
+
"eval_loss": 0.4662601053714752,
|
| 563 |
+
"eval_mae": 0.11664538830518723,
|
| 564 |
+
"eval_rmse": 0.1586536318063736,
|
| 565 |
+
"eval_runtime": 49.8708,
|
| 566 |
+
"eval_samples_per_second": 47.202,
|
| 567 |
+
"eval_steps_per_second": 1.484,
|
| 568 |
+
"learning_rate": 0.0001,
|
| 569 |
+
"step": 7665
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 36.0,
|
| 573 |
+
"eval_explained_variance": 0.4544428884983063,
|
| 574 |
+
"eval_kl_divergence": 0.4382496476173401,
|
| 575 |
+
"eval_loss": 0.46657058596611023,
|
| 576 |
+
"eval_mae": 0.11700741201639175,
|
| 577 |
+
"eval_rmse": 0.15874631702899933,
|
| 578 |
+
"eval_runtime": 49.7975,
|
| 579 |
+
"eval_samples_per_second": 47.271,
|
| 580 |
+
"eval_steps_per_second": 1.486,
|
| 581 |
+
"learning_rate": 0.0001,
|
| 582 |
+
"step": 7884
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 36.529680365296805,
|
| 586 |
+
"grad_norm": 0.17629703879356384,
|
| 587 |
+
"learning_rate": 0.0001,
|
| 588 |
+
"loss": 0.4572,
|
| 589 |
+
"step": 8000
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 37.0,
|
| 593 |
+
"eval_explained_variance": 0.45941635966300964,
|
| 594 |
+
"eval_kl_divergence": 0.4330490827560425,
|
| 595 |
+
"eval_loss": 0.4657588005065918,
|
| 596 |
+
"eval_mae": 0.11633748561143875,
|
| 597 |
+
"eval_rmse": 0.15810036659240723,
|
| 598 |
+
"eval_runtime": 51.4251,
|
| 599 |
+
"eval_samples_per_second": 45.775,
|
| 600 |
+
"eval_steps_per_second": 1.439,
|
| 601 |
+
"learning_rate": 0.0001,
|
| 602 |
+
"step": 8103
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 38.0,
|
| 606 |
+
"eval_explained_variance": 0.4566784203052521,
|
| 607 |
+
"eval_kl_divergence": 0.4877949357032776,
|
| 608 |
+
"eval_loss": 0.4659184217453003,
|
| 609 |
+
"eval_mae": 0.11623784899711609,
|
| 610 |
+
"eval_rmse": 0.15832678973674774,
|
| 611 |
+
"eval_runtime": 49.7333,
|
| 612 |
+
"eval_samples_per_second": 47.332,
|
| 613 |
+
"eval_steps_per_second": 1.488,
|
| 614 |
+
"learning_rate": 0.0001,
|
| 615 |
+
"step": 8322
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 38.81278538812786,
|
| 619 |
+
"grad_norm": 0.1781003624200821,
|
| 620 |
+
"learning_rate": 0.0001,
|
| 621 |
+
"loss": 0.4572,
|
| 622 |
+
"step": 8500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 39.0,
|
| 626 |
+
"eval_explained_variance": 0.45519956946372986,
|
| 627 |
+
"eval_kl_divergence": 0.3790707290172577,
|
| 628 |
+
"eval_loss": 0.46703553199768066,
|
| 629 |
+
"eval_mae": 0.11782807856798172,
|
| 630 |
+
"eval_rmse": 0.15946339070796967,
|
| 631 |
+
"eval_runtime": 52.4,
|
| 632 |
+
"eval_samples_per_second": 44.924,
|
| 633 |
+
"eval_steps_per_second": 1.412,
|
| 634 |
+
"learning_rate": 0.0001,
|
| 635 |
+
"step": 8541
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 40.0,
|
| 639 |
+
"eval_explained_variance": 0.45683178305625916,
|
| 640 |
+
"eval_kl_divergence": 0.38892972469329834,
|
| 641 |
+
"eval_loss": 0.4664987027645111,
|
| 642 |
+
"eval_mae": 0.11783644556999207,
|
| 643 |
+
"eval_rmse": 0.15876977145671844,
|
| 644 |
+
"eval_runtime": 50.7398,
|
| 645 |
+
"eval_samples_per_second": 46.394,
|
| 646 |
+
"eval_steps_per_second": 1.458,
|
| 647 |
+
"learning_rate": 0.0001,
|
| 648 |
+
"step": 8760
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 41.0,
|
| 652 |
+
"eval_explained_variance": 0.4591364860534668,
|
| 653 |
+
"eval_kl_divergence": 0.3222128450870514,
|
| 654 |
+
"eval_loss": 0.46659526228904724,
|
| 655 |
+
"eval_mae": 0.11838778108358383,
|
| 656 |
+
"eval_rmse": 0.15888933837413788,
|
| 657 |
+
"eval_runtime": 50.0159,
|
| 658 |
+
"eval_samples_per_second": 47.065,
|
| 659 |
+
"eval_steps_per_second": 1.48,
|
| 660 |
+
"learning_rate": 0.0001,
|
| 661 |
+
"step": 8979
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 41.0958904109589,
|
| 665 |
+
"grad_norm": 0.13085126876831055,
|
| 666 |
+
"learning_rate": 0.0001,
|
| 667 |
+
"loss": 0.4559,
|
| 668 |
+
"step": 9000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 42.0,
|
| 672 |
+
"eval_explained_variance": 0.4606964886188507,
|
| 673 |
+
"eval_kl_divergence": 0.426244854927063,
|
| 674 |
+
"eval_loss": 0.4655005633831024,
|
| 675 |
+
"eval_mae": 0.11635158210992813,
|
| 676 |
+
"eval_rmse": 0.15787668526172638,
|
| 677 |
+
"eval_runtime": 49.9099,
|
| 678 |
+
"eval_samples_per_second": 47.165,
|
| 679 |
+
"eval_steps_per_second": 1.483,
|
| 680 |
+
"learning_rate": 0.0001,
|
| 681 |
+
"step": 9198
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 43.0,
|
| 685 |
+
"eval_explained_variance": 0.46034756302833557,
|
| 686 |
+
"eval_kl_divergence": 0.4611224830150604,
|
| 687 |
+
"eval_loss": 0.4656265676021576,
|
| 688 |
+
"eval_mae": 0.11616652458906174,
|
| 689 |
+
"eval_rmse": 0.1579464077949524,
|
| 690 |
+
"eval_runtime": 50.0123,
|
| 691 |
+
"eval_samples_per_second": 47.068,
|
| 692 |
+
"eval_steps_per_second": 1.48,
|
| 693 |
+
"learning_rate": 0.0001,
|
| 694 |
+
"step": 9417
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 43.37899543378995,
|
| 698 |
+
"grad_norm": 0.17523790895938873,
|
| 699 |
+
"learning_rate": 0.0001,
|
| 700 |
+
"loss": 0.4554,
|
| 701 |
+
"step": 9500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 44.0,
|
| 705 |
+
"eval_explained_variance": 0.4616149961948395,
|
| 706 |
+
"eval_kl_divergence": 0.45858410000801086,
|
| 707 |
+
"eval_loss": 0.4655725955963135,
|
| 708 |
+
"eval_mae": 0.11644264310598373,
|
| 709 |
+
"eval_rmse": 0.15800905227661133,
|
| 710 |
+
"eval_runtime": 50.6284,
|
| 711 |
+
"eval_samples_per_second": 46.496,
|
| 712 |
+
"eval_steps_per_second": 1.462,
|
| 713 |
+
"learning_rate": 0.0001,
|
| 714 |
+
"step": 9636
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 45.0,
|
| 718 |
+
"eval_explained_variance": 0.45969870686531067,
|
| 719 |
+
"eval_kl_divergence": 0.4367772340774536,
|
| 720 |
+
"eval_loss": 0.46600833535194397,
|
| 721 |
+
"eval_mae": 0.11579249054193497,
|
| 722 |
+
"eval_rmse": 0.15833592414855957,
|
| 723 |
+
"eval_runtime": 50.629,
|
| 724 |
+
"eval_samples_per_second": 46.495,
|
| 725 |
+
"eval_steps_per_second": 1.462,
|
| 726 |
+
"learning_rate": 0.0001,
|
| 727 |
+
"step": 9855
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 45.662100456621005,
|
| 731 |
+
"grad_norm": 0.1231347844004631,
|
| 732 |
+
"learning_rate": 0.0001,
|
| 733 |
+
"loss": 0.4557,
|
| 734 |
+
"step": 10000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 46.0,
|
| 738 |
+
"eval_explained_variance": 0.4603704512119293,
|
| 739 |
+
"eval_kl_divergence": 0.41175922751426697,
|
| 740 |
+
"eval_loss": 0.4660418927669525,
|
| 741 |
+
"eval_mae": 0.11639311909675598,
|
| 742 |
+
"eval_rmse": 0.1581837385892868,
|
| 743 |
+
"eval_runtime": 50.1537,
|
| 744 |
+
"eval_samples_per_second": 46.936,
|
| 745 |
+
"eval_steps_per_second": 1.475,
|
| 746 |
+
"learning_rate": 0.0001,
|
| 747 |
+
"step": 10074
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 47.0,
|
| 751 |
+
"eval_explained_variance": 0.4613979756832123,
|
| 752 |
+
"eval_kl_divergence": 0.5424114465713501,
|
| 753 |
+
"eval_loss": 0.46521857380867004,
|
| 754 |
+
"eval_mae": 0.11542114615440369,
|
| 755 |
+
"eval_rmse": 0.15771377086639404,
|
| 756 |
+
"eval_runtime": 49.6928,
|
| 757 |
+
"eval_samples_per_second": 47.371,
|
| 758 |
+
"eval_steps_per_second": 1.489,
|
| 759 |
+
"learning_rate": 0.0001,
|
| 760 |
+
"step": 10293
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 47.945205479452056,
|
| 764 |
+
"grad_norm": 0.46352267265319824,
|
| 765 |
+
"learning_rate": 0.0001,
|
| 766 |
+
"loss": 0.4551,
|
| 767 |
+
"step": 10500
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 48.0,
|
| 771 |
+
"eval_explained_variance": 0.45960724353790283,
|
| 772 |
+
"eval_kl_divergence": 0.525124728679657,
|
| 773 |
+
"eval_loss": 0.46598610281944275,
|
| 774 |
+
"eval_mae": 0.1159835234284401,
|
| 775 |
+
"eval_rmse": 0.15856431424617767,
|
| 776 |
+
"eval_runtime": 49.9974,
|
| 777 |
+
"eval_samples_per_second": 47.082,
|
| 778 |
+
"eval_steps_per_second": 1.48,
|
| 779 |
+
"learning_rate": 0.0001,
|
| 780 |
+
"step": 10512
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 49.0,
|
| 784 |
+
"eval_explained_variance": 0.4572352468967438,
|
| 785 |
+
"eval_kl_divergence": 0.5006867051124573,
|
| 786 |
+
"eval_loss": 0.46604350209236145,
|
| 787 |
+
"eval_mae": 0.11609696596860886,
|
| 788 |
+
"eval_rmse": 0.15853044390678406,
|
| 789 |
+
"eval_runtime": 50.2446,
|
| 790 |
+
"eval_samples_per_second": 46.851,
|
| 791 |
+
"eval_steps_per_second": 1.473,
|
| 792 |
+
"learning_rate": 0.0001,
|
| 793 |
+
"step": 10731
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 50.0,
|
| 797 |
+
"eval_explained_variance": 0.4658548831939697,
|
| 798 |
+
"eval_kl_divergence": 0.24239596724510193,
|
| 799 |
+
"eval_loss": 0.46660009026527405,
|
| 800 |
+
"eval_mae": 0.11854288727045059,
|
| 801 |
+
"eval_rmse": 0.15863054990768433,
|
| 802 |
+
"eval_runtime": 50.1897,
|
| 803 |
+
"eval_samples_per_second": 46.902,
|
| 804 |
+
"eval_steps_per_second": 1.474,
|
| 805 |
+
"learning_rate": 0.0001,
|
| 806 |
+
"step": 10950
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 50.22831050228311,
|
| 810 |
+
"grad_norm": 0.1688494235277176,
|
| 811 |
+
"learning_rate": 0.0001,
|
| 812 |
+
"loss": 0.4545,
|
| 813 |
+
"step": 11000
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 51.0,
|
| 817 |
+
"eval_explained_variance": 0.45888975262641907,
|
| 818 |
+
"eval_kl_divergence": 0.4170607030391693,
|
| 819 |
+
"eval_loss": 0.4660661220550537,
|
| 820 |
+
"eval_mae": 0.11618483066558838,
|
| 821 |
+
"eval_rmse": 0.15835459530353546,
|
| 822 |
+
"eval_runtime": 49.5535,
|
| 823 |
+
"eval_samples_per_second": 47.504,
|
| 824 |
+
"eval_steps_per_second": 1.493,
|
| 825 |
+
"learning_rate": 0.0001,
|
| 826 |
+
"step": 11169
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 52.0,
|
| 830 |
+
"eval_explained_variance": 0.46297597885131836,
|
| 831 |
+
"eval_kl_divergence": 0.49118655920028687,
|
| 832 |
+
"eval_loss": 0.4649689793586731,
|
| 833 |
+
"eval_mae": 0.11549883335828781,
|
| 834 |
+
"eval_rmse": 0.1575259119272232,
|
| 835 |
+
"eval_runtime": 50.3774,
|
| 836 |
+
"eval_samples_per_second": 46.727,
|
| 837 |
+
"eval_steps_per_second": 1.469,
|
| 838 |
+
"learning_rate": 0.0001,
|
| 839 |
+
"step": 11388
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 52.51141552511415,
|
| 843 |
+
"grad_norm": 0.2805333137512207,
|
| 844 |
+
"learning_rate": 0.0001,
|
| 845 |
+
"loss": 0.4548,
|
| 846 |
+
"step": 11500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 53.0,
|
| 850 |
+
"eval_explained_variance": 0.46440085768699646,
|
| 851 |
+
"eval_kl_divergence": 0.4030352830886841,
|
| 852 |
+
"eval_loss": 0.4653578996658325,
|
| 853 |
+
"eval_mae": 0.11687562614679337,
|
| 854 |
+
"eval_rmse": 0.15780305862426758,
|
| 855 |
+
"eval_runtime": 51.1877,
|
| 856 |
+
"eval_samples_per_second": 45.988,
|
| 857 |
+
"eval_steps_per_second": 1.446,
|
| 858 |
+
"learning_rate": 0.0001,
|
| 859 |
+
"step": 11607
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 54.0,
|
| 863 |
+
"eval_explained_variance": 0.4594965875148773,
|
| 864 |
+
"eval_kl_divergence": 0.4810858964920044,
|
| 865 |
+
"eval_loss": 0.4660585820674896,
|
| 866 |
+
"eval_mae": 0.11529505252838135,
|
| 867 |
+
"eval_rmse": 0.15853293240070343,
|
| 868 |
+
"eval_runtime": 51.2952,
|
| 869 |
+
"eval_samples_per_second": 45.891,
|
| 870 |
+
"eval_steps_per_second": 1.443,
|
| 871 |
+
"learning_rate": 0.0001,
|
| 872 |
+
"step": 11826
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 54.794520547945204,
|
| 876 |
+
"grad_norm": 0.22778521478176117,
|
| 877 |
+
"learning_rate": 0.0001,
|
| 878 |
+
"loss": 0.455,
|
| 879 |
+
"step": 12000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 55.0,
|
| 883 |
+
"eval_explained_variance": 0.46380600333213806,
|
| 884 |
+
"eval_kl_divergence": 0.3773800730705261,
|
| 885 |
+
"eval_loss": 0.46527624130249023,
|
| 886 |
+
"eval_mae": 0.11668615788221359,
|
| 887 |
+
"eval_rmse": 0.1576414853334427,
|
| 888 |
+
"eval_runtime": 50.6825,
|
| 889 |
+
"eval_samples_per_second": 46.446,
|
| 890 |
+
"eval_steps_per_second": 1.46,
|
| 891 |
+
"learning_rate": 0.0001,
|
| 892 |
+
"step": 12045
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 56.0,
|
| 896 |
+
"eval_explained_variance": 0.4669934809207916,
|
| 897 |
+
"eval_kl_divergence": 0.32541513442993164,
|
| 898 |
+
"eval_loss": 0.4654240906238556,
|
| 899 |
+
"eval_mae": 0.11757931858301163,
|
| 900 |
+
"eval_rmse": 0.1575363427400589,
|
| 901 |
+
"eval_runtime": 50.538,
|
| 902 |
+
"eval_samples_per_second": 46.579,
|
| 903 |
+
"eval_steps_per_second": 1.464,
|
| 904 |
+
"learning_rate": 0.0001,
|
| 905 |
+
"step": 12264
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 57.0,
|
| 909 |
+
"eval_explained_variance": 0.4661710560321808,
|
| 910 |
+
"eval_kl_divergence": 0.3648814857006073,
|
| 911 |
+
"eval_loss": 0.4654492139816284,
|
| 912 |
+
"eval_mae": 0.11615876108407974,
|
| 913 |
+
"eval_rmse": 0.15751774609088898,
|
| 914 |
+
"eval_runtime": 51.1673,
|
| 915 |
+
"eval_samples_per_second": 46.006,
|
| 916 |
+
"eval_steps_per_second": 1.446,
|
| 917 |
+
"learning_rate": 0.0001,
|
| 918 |
+
"step": 12483
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 57.077625570776256,
|
| 922 |
+
"grad_norm": 0.16715611517429352,
|
| 923 |
+
"learning_rate": 0.0001,
|
| 924 |
+
"loss": 0.4531,
|
| 925 |
+
"step": 12500
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 58.0,
|
| 929 |
+
"eval_explained_variance": 0.4606919586658478,
|
| 930 |
+
"eval_kl_divergence": 0.40749335289001465,
|
| 931 |
+
"eval_loss": 0.46654412150382996,
|
| 932 |
+
"eval_mae": 0.1166309341788292,
|
| 933 |
+
"eval_rmse": 0.15835203230381012,
|
| 934 |
+
"eval_runtime": 50.603,
|
| 935 |
+
"eval_samples_per_second": 46.519,
|
| 936 |
+
"eval_steps_per_second": 1.462,
|
| 937 |
+
"learning_rate": 0.0001,
|
| 938 |
+
"step": 12702
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 59.0,
|
| 942 |
+
"eval_explained_variance": 0.4653950035572052,
|
| 943 |
+
"eval_kl_divergence": 0.42019784450531006,
|
| 944 |
+
"eval_loss": 0.465238481760025,
|
| 945 |
+
"eval_mae": 0.11570876836776733,
|
| 946 |
+
"eval_rmse": 0.15746039152145386,
|
| 947 |
+
"eval_runtime": 50.3267,
|
| 948 |
+
"eval_samples_per_second": 46.774,
|
| 949 |
+
"eval_steps_per_second": 1.47,
|
| 950 |
+
"learning_rate": 1e-05,
|
| 951 |
+
"step": 12921
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 59.36073059360731,
|
| 955 |
+
"grad_norm": 0.19701753556728363,
|
| 956 |
+
"learning_rate": 1e-05,
|
| 957 |
+
"loss": 0.4538,
|
| 958 |
+
"step": 13000
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 60.0,
|
| 962 |
+
"eval_explained_variance": 0.4668855369091034,
|
| 963 |
+
"eval_kl_divergence": 0.4084234833717346,
|
| 964 |
+
"eval_loss": 0.46530231833457947,
|
| 965 |
+
"eval_mae": 0.11569295078516006,
|
| 966 |
+
"eval_rmse": 0.15709955990314484,
|
| 967 |
+
"eval_runtime": 51.1174,
|
| 968 |
+
"eval_samples_per_second": 46.051,
|
| 969 |
+
"eval_steps_per_second": 1.448,
|
| 970 |
+
"learning_rate": 1e-05,
|
| 971 |
+
"step": 13140
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 61.0,
|
| 975 |
+
"eval_explained_variance": 0.4661245346069336,
|
| 976 |
+
"eval_kl_divergence": 0.4496937096118927,
|
| 977 |
+
"eval_loss": 0.4653523564338684,
|
| 978 |
+
"eval_mae": 0.11528477817773819,
|
| 979 |
+
"eval_rmse": 0.15729330480098724,
|
| 980 |
+
"eval_runtime": 50.8416,
|
| 981 |
+
"eval_samples_per_second": 46.301,
|
| 982 |
+
"eval_steps_per_second": 1.456,
|
| 983 |
+
"learning_rate": 1e-05,
|
| 984 |
+
"step": 13359
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 61.64383561643836,
|
| 988 |
+
"grad_norm": 0.1874207705259323,
|
| 989 |
+
"learning_rate": 1e-05,
|
| 990 |
+
"loss": 0.4529,
|
| 991 |
+
"step": 13500
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 62.0,
|
| 995 |
+
"eval_explained_variance": 0.4681651294231415,
|
| 996 |
+
"eval_kl_divergence": 0.411173015832901,
|
| 997 |
+
"eval_loss": 0.46477487683296204,
|
| 998 |
+
"eval_mae": 0.11529665440320969,
|
| 999 |
+
"eval_rmse": 0.15684308111667633,
|
| 1000 |
+
"eval_runtime": 52.6214,
|
| 1001 |
+
"eval_samples_per_second": 44.735,
|
| 1002 |
+
"eval_steps_per_second": 1.406,
|
| 1003 |
+
"learning_rate": 1e-05,
|
| 1004 |
+
"step": 13578
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 63.0,
|
| 1008 |
+
"eval_explained_variance": 0.47016242146492004,
|
| 1009 |
+
"eval_kl_divergence": 0.3748082220554352,
|
| 1010 |
+
"eval_loss": 0.46481335163116455,
|
| 1011 |
+
"eval_mae": 0.11518841236829758,
|
| 1012 |
+
"eval_rmse": 0.15671293437480927,
|
| 1013 |
+
"eval_runtime": 53.2469,
|
| 1014 |
+
"eval_samples_per_second": 44.209,
|
| 1015 |
+
"eval_steps_per_second": 1.39,
|
| 1016 |
+
"learning_rate": 1e-05,
|
| 1017 |
+
"step": 13797
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 63.926940639269404,
|
| 1021 |
+
"grad_norm": 0.22562281787395477,
|
| 1022 |
+
"learning_rate": 1e-05,
|
| 1023 |
+
"loss": 0.4527,
|
| 1024 |
+
"step": 14000
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 64.0,
|
| 1028 |
+
"eval_explained_variance": 0.4721170663833618,
|
| 1029 |
+
"eval_kl_divergence": 0.3044198155403137,
|
| 1030 |
+
"eval_loss": 0.46523070335388184,
|
| 1031 |
+
"eval_mae": 0.11618036776781082,
|
| 1032 |
+
"eval_rmse": 0.15709933638572693,
|
| 1033 |
+
"eval_runtime": 53.3051,
|
| 1034 |
+
"eval_samples_per_second": 44.161,
|
| 1035 |
+
"eval_steps_per_second": 1.388,
|
| 1036 |
+
"learning_rate": 1e-05,
|
| 1037 |
+
"step": 14016
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 65.0,
|
| 1041 |
+
"eval_explained_variance": 0.46695852279663086,
|
| 1042 |
+
"eval_kl_divergence": 0.46853822469711304,
|
| 1043 |
+
"eval_loss": 0.46484872698783875,
|
| 1044 |
+
"eval_mae": 0.11532068997621536,
|
| 1045 |
+
"eval_rmse": 0.1568661779165268,
|
| 1046 |
+
"eval_runtime": 52.7599,
|
| 1047 |
+
"eval_samples_per_second": 44.617,
|
| 1048 |
+
"eval_steps_per_second": 1.403,
|
| 1049 |
+
"learning_rate": 1e-05,
|
| 1050 |
+
"step": 14235
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 66.0,
|
| 1054 |
+
"eval_explained_variance": 0.46712610125541687,
|
| 1055 |
+
"eval_kl_divergence": 0.508738100528717,
|
| 1056 |
+
"eval_loss": 0.46500927209854126,
|
| 1057 |
+
"eval_mae": 0.11475471407175064,
|
| 1058 |
+
"eval_rmse": 0.15729309618473053,
|
| 1059 |
+
"eval_runtime": 54.0149,
|
| 1060 |
+
"eval_samples_per_second": 43.581,
|
| 1061 |
+
"eval_steps_per_second": 1.37,
|
| 1062 |
+
"learning_rate": 1e-05,
|
| 1063 |
+
"step": 14454
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 66.21004566210046,
|
| 1067 |
+
"grad_norm": 0.18448679149150848,
|
| 1068 |
+
"learning_rate": 1e-05,
|
| 1069 |
+
"loss": 0.4531,
|
| 1070 |
+
"step": 14500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 67.0,
|
| 1074 |
+
"eval_explained_variance": 0.4690088927745819,
|
| 1075 |
+
"eval_kl_divergence": 0.42743220925331116,
|
| 1076 |
+
"eval_loss": 0.4645930230617523,
|
| 1077 |
+
"eval_mae": 0.1155417189002037,
|
| 1078 |
+
"eval_rmse": 0.1567572057247162,
|
| 1079 |
+
"eval_runtime": 52.5655,
|
| 1080 |
+
"eval_samples_per_second": 44.782,
|
| 1081 |
+
"eval_steps_per_second": 1.408,
|
| 1082 |
+
"learning_rate": 1e-05,
|
| 1083 |
+
"step": 14673
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 68.0,
|
| 1087 |
+
"eval_explained_variance": 0.4680323302745819,
|
| 1088 |
+
"eval_kl_divergence": 0.49686378240585327,
|
| 1089 |
+
"eval_loss": 0.46456360816955566,
|
| 1090 |
+
"eval_mae": 0.11437365412712097,
|
| 1091 |
+
"eval_rmse": 0.1566230058670044,
|
| 1092 |
+
"eval_runtime": 50.8799,
|
| 1093 |
+
"eval_samples_per_second": 46.266,
|
| 1094 |
+
"eval_steps_per_second": 1.454,
|
| 1095 |
+
"learning_rate": 1e-05,
|
| 1096 |
+
"step": 14892
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 68.4931506849315,
|
| 1100 |
+
"grad_norm": 0.21752646565437317,
|
| 1101 |
+
"learning_rate": 1e-05,
|
| 1102 |
+
"loss": 0.452,
|
| 1103 |
+
"step": 15000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 69.0,
|
| 1107 |
+
"eval_explained_variance": 0.4696376323699951,
|
| 1108 |
+
"eval_kl_divergence": 0.44800856709480286,
|
| 1109 |
+
"eval_loss": 0.464430034160614,
|
| 1110 |
+
"eval_mae": 0.11452987045049667,
|
| 1111 |
+
"eval_rmse": 0.15642575919628143,
|
| 1112 |
+
"eval_runtime": 61.8405,
|
| 1113 |
+
"eval_samples_per_second": 38.066,
|
| 1114 |
+
"eval_steps_per_second": 1.197,
|
| 1115 |
+
"learning_rate": 1e-05,
|
| 1116 |
+
"step": 15111
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 70.0,
|
| 1120 |
+
"eval_explained_variance": 0.4692017734050751,
|
| 1121 |
+
"eval_kl_divergence": 0.42908576130867004,
|
| 1122 |
+
"eval_loss": 0.4648461937904358,
|
| 1123 |
+
"eval_mae": 0.11500384658575058,
|
| 1124 |
+
"eval_rmse": 0.15674862265586853,
|
| 1125 |
+
"eval_runtime": 60.5787,
|
| 1126 |
+
"eval_samples_per_second": 38.859,
|
| 1127 |
+
"eval_steps_per_second": 1.222,
|
| 1128 |
+
"learning_rate": 1e-05,
|
| 1129 |
+
"step": 15330
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 70.77625570776256,
|
| 1133 |
+
"grad_norm": 0.23285503685474396,
|
| 1134 |
+
"learning_rate": 1e-05,
|
| 1135 |
+
"loss": 0.4524,
|
| 1136 |
+
"step": 15500
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 71.0,
|
| 1140 |
+
"eval_explained_variance": 0.4711233675479889,
|
| 1141 |
+
"eval_kl_divergence": 0.37966692447662354,
|
| 1142 |
+
"eval_loss": 0.4645022749900818,
|
| 1143 |
+
"eval_mae": 0.11555531620979309,
|
| 1144 |
+
"eval_rmse": 0.15646833181381226,
|
| 1145 |
+
"eval_runtime": 61.2584,
|
| 1146 |
+
"eval_samples_per_second": 38.427,
|
| 1147 |
+
"eval_steps_per_second": 1.208,
|
| 1148 |
+
"learning_rate": 1e-05,
|
| 1149 |
+
"step": 15549
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 72.0,
|
| 1153 |
+
"eval_explained_variance": 0.4690466821193695,
|
| 1154 |
+
"eval_kl_divergence": 0.42796915769577026,
|
| 1155 |
+
"eval_loss": 0.46473589539527893,
|
| 1156 |
+
"eval_mae": 0.11497951298952103,
|
| 1157 |
+
"eval_rmse": 0.15693025290966034,
|
| 1158 |
+
"eval_runtime": 61.782,
|
| 1159 |
+
"eval_samples_per_second": 38.102,
|
| 1160 |
+
"eval_steps_per_second": 1.198,
|
| 1161 |
+
"learning_rate": 1e-05,
|
| 1162 |
+
"step": 15768
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 73.0,
|
| 1166 |
+
"eval_explained_variance": 0.4707035720348358,
|
| 1167 |
+
"eval_kl_divergence": 0.4591566324234009,
|
| 1168 |
+
"eval_loss": 0.46414923667907715,
|
| 1169 |
+
"eval_mae": 0.11423368006944656,
|
| 1170 |
+
"eval_rmse": 0.15631103515625,
|
| 1171 |
+
"eval_runtime": 62.9115,
|
| 1172 |
+
"eval_samples_per_second": 37.418,
|
| 1173 |
+
"eval_steps_per_second": 1.176,
|
| 1174 |
+
"learning_rate": 1e-05,
|
| 1175 |
+
"step": 15987
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 73.05936073059361,
|
| 1179 |
+
"grad_norm": 0.1904192417860031,
|
| 1180 |
+
"learning_rate": 1e-05,
|
| 1181 |
+
"loss": 0.4515,
|
| 1182 |
+
"step": 16000
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 74.0,
|
| 1186 |
+
"eval_explained_variance": 0.4705829620361328,
|
| 1187 |
+
"eval_kl_divergence": 0.43208685517311096,
|
| 1188 |
+
"eval_loss": 0.4641610085964203,
|
| 1189 |
+
"eval_mae": 0.11505597829818726,
|
| 1190 |
+
"eval_rmse": 0.1563975065946579,
|
| 1191 |
+
"eval_runtime": 61.932,
|
| 1192 |
+
"eval_samples_per_second": 38.009,
|
| 1193 |
+
"eval_steps_per_second": 1.195,
|
| 1194 |
+
"learning_rate": 1e-05,
|
| 1195 |
+
"step": 16206
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 75.0,
|
| 1199 |
+
"eval_explained_variance": 0.47077181935310364,
|
| 1200 |
+
"eval_kl_divergence": 0.3843104839324951,
|
| 1201 |
+
"eval_loss": 0.4644509255886078,
|
| 1202 |
+
"eval_mae": 0.11519055813550949,
|
| 1203 |
+
"eval_rmse": 0.15653057396411896,
|
| 1204 |
+
"eval_runtime": 62.3182,
|
| 1205 |
+
"eval_samples_per_second": 37.774,
|
| 1206 |
+
"eval_steps_per_second": 1.187,
|
| 1207 |
+
"learning_rate": 1e-05,
|
| 1208 |
+
"step": 16425
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 75.34246575342466,
|
| 1212 |
+
"grad_norm": 0.2563965618610382,
|
| 1213 |
+
"learning_rate": 1e-05,
|
| 1214 |
+
"loss": 0.4521,
|
| 1215 |
+
"step": 16500
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 76.0,
|
| 1219 |
+
"eval_explained_variance": 0.4675123989582062,
|
| 1220 |
+
"eval_kl_divergence": 0.5215911269187927,
|
| 1221 |
+
"eval_loss": 0.4646488130092621,
|
| 1222 |
+
"eval_mae": 0.1146780475974083,
|
| 1223 |
+
"eval_rmse": 0.1569206565618515,
|
| 1224 |
+
"eval_runtime": 66.0488,
|
| 1225 |
+
"eval_samples_per_second": 35.64,
|
| 1226 |
+
"eval_steps_per_second": 1.12,
|
| 1227 |
+
"learning_rate": 1e-05,
|
| 1228 |
+
"step": 16644
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 77.0,
|
| 1232 |
+
"eval_explained_variance": 0.46909868717193604,
|
| 1233 |
+
"eval_kl_divergence": 0.4094104468822479,
|
| 1234 |
+
"eval_loss": 0.46475714445114136,
|
| 1235 |
+
"eval_mae": 0.11523856967687607,
|
| 1236 |
+
"eval_rmse": 0.15687990188598633,
|
| 1237 |
+
"eval_runtime": 62.1685,
|
| 1238 |
+
"eval_samples_per_second": 37.865,
|
| 1239 |
+
"eval_steps_per_second": 1.19,
|
| 1240 |
+
"learning_rate": 1e-05,
|
| 1241 |
+
"step": 16863
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 77.62557077625571,
|
| 1245 |
+
"grad_norm": 0.16491472721099854,
|
| 1246 |
+
"learning_rate": 1e-05,
|
| 1247 |
+
"loss": 0.4519,
|
| 1248 |
+
"step": 17000
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 78.0,
|
| 1252 |
+
"eval_explained_variance": 0.47086599469184875,
|
| 1253 |
+
"eval_kl_divergence": 0.43988528847694397,
|
| 1254 |
+
"eval_loss": 0.46428272128105164,
|
| 1255 |
+
"eval_mae": 0.11493176966905594,
|
| 1256 |
+
"eval_rmse": 0.15638257563114166,
|
| 1257 |
+
"eval_runtime": 61.9923,
|
| 1258 |
+
"eval_samples_per_second": 37.972,
|
| 1259 |
+
"eval_steps_per_second": 1.194,
|
| 1260 |
+
"learning_rate": 1e-05,
|
| 1261 |
+
"step": 17082
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 79.0,
|
| 1265 |
+
"eval_explained_variance": 0.4697439670562744,
|
| 1266 |
+
"eval_kl_divergence": 0.4178011417388916,
|
| 1267 |
+
"eval_loss": 0.4645934998989105,
|
| 1268 |
+
"eval_mae": 0.11465150117874146,
|
| 1269 |
+
"eval_rmse": 0.15666015446186066,
|
| 1270 |
+
"eval_runtime": 63.0404,
|
| 1271 |
+
"eval_samples_per_second": 37.341,
|
| 1272 |
+
"eval_steps_per_second": 1.174,
|
| 1273 |
+
"learning_rate": 1e-05,
|
| 1274 |
+
"step": 17301
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 79.90867579908675,
|
| 1278 |
+
"grad_norm": 0.1647184044122696,
|
| 1279 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1280 |
+
"loss": 0.4517,
|
| 1281 |
+
"step": 17500
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 80.0,
|
| 1285 |
+
"eval_explained_variance": 0.4699563980102539,
|
| 1286 |
+
"eval_kl_divergence": 0.43727052211761475,
|
| 1287 |
+
"eval_loss": 0.46436014771461487,
|
| 1288 |
+
"eval_mae": 0.11501001566648483,
|
| 1289 |
+
"eval_rmse": 0.15643416345119476,
|
| 1290 |
+
"eval_runtime": 61.5606,
|
| 1291 |
+
"eval_samples_per_second": 38.239,
|
| 1292 |
+
"eval_steps_per_second": 1.202,
|
| 1293 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1294 |
+
"step": 17520
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 81.0,
|
| 1298 |
+
"eval_explained_variance": 0.468768835067749,
|
| 1299 |
+
"eval_kl_divergence": 0.47009941935539246,
|
| 1300 |
+
"eval_loss": 0.46448636054992676,
|
| 1301 |
+
"eval_mae": 0.11508657783269882,
|
| 1302 |
+
"eval_rmse": 0.15673168003559113,
|
| 1303 |
+
"eval_runtime": 62.9178,
|
| 1304 |
+
"eval_samples_per_second": 37.414,
|
| 1305 |
+
"eval_steps_per_second": 1.176,
|
| 1306 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1307 |
+
"step": 17739
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 82.0,
|
| 1311 |
+
"eval_explained_variance": 0.470253586769104,
|
| 1312 |
+
"eval_kl_divergence": 0.4601159989833832,
|
| 1313 |
+
"eval_loss": 0.4644375145435333,
|
| 1314 |
+
"eval_mae": 0.11455937474966049,
|
| 1315 |
+
"eval_rmse": 0.15652652084827423,
|
| 1316 |
+
"eval_runtime": 62.6023,
|
| 1317 |
+
"eval_samples_per_second": 37.602,
|
| 1318 |
+
"eval_steps_per_second": 1.182,
|
| 1319 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1320 |
+
"step": 17958
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 82.1917808219178,
|
| 1324 |
+
"grad_norm": 0.2432813197374344,
|
| 1325 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1326 |
+
"loss": 0.4514,
|
| 1327 |
+
"step": 18000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 83.0,
|
| 1331 |
+
"eval_explained_variance": 0.468420147895813,
|
| 1332 |
+
"eval_kl_divergence": 0.4510715901851654,
|
| 1333 |
+
"eval_loss": 0.46457409858703613,
|
| 1334 |
+
"eval_mae": 0.11468392610549927,
|
| 1335 |
+
"eval_rmse": 0.15669189393520355,
|
| 1336 |
+
"eval_runtime": 62.7877,
|
| 1337 |
+
"eval_samples_per_second": 37.491,
|
| 1338 |
+
"eval_steps_per_second": 1.179,
|
| 1339 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1340 |
+
"step": 18177
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 83.0,
|
| 1344 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1345 |
+
"step": 18177,
|
| 1346 |
+
"total_flos": 8.603009036605255e+19,
|
| 1347 |
+
"train_loss": 0.45949580130708517,
|
| 1348 |
+
"train_runtime": 19431.3015,
|
| 1349 |
+
"train_samples_per_second": 54.06,
|
| 1350 |
+
"train_steps_per_second": 1.691
|
| 1351 |
+
}
|
| 1352 |
+
],
|
| 1353 |
+
"logging_steps": 500,
|
| 1354 |
+
"max_steps": 32850,
|
| 1355 |
+
"num_input_tokens_seen": 0,
|
| 1356 |
+
"num_train_epochs": 150,
|
| 1357 |
+
"save_steps": 500,
|
| 1358 |
+
"stateful_callbacks": {
|
| 1359 |
+
"EarlyStoppingCallback": {
|
| 1360 |
+
"args": {
|
| 1361 |
+
"early_stopping_patience": 10,
|
| 1362 |
+
"early_stopping_threshold": 0.0
|
| 1363 |
+
},
|
| 1364 |
+
"attributes": {
|
| 1365 |
+
"early_stopping_patience_counter": 0
|
| 1366 |
+
}
|
| 1367 |
+
},
|
| 1368 |
+
"TrainerControl": {
|
| 1369 |
+
"args": {
|
| 1370 |
+
"should_epoch_stop": false,
|
| 1371 |
+
"should_evaluate": false,
|
| 1372 |
+
"should_log": false,
|
| 1373 |
+
"should_save": true,
|
| 1374 |
+
"should_training_stop": true
|
| 1375 |
+
},
|
| 1376 |
+
"attributes": {}
|
| 1377 |
+
}
|
| 1378 |
+
},
|
| 1379 |
+
"total_flos": 8.603009036605255e+19,
|
| 1380 |
+
"train_batch_size": 32,
|
| 1381 |
+
"trial_name": null,
|
| 1382 |
+
"trial_params": null
|
| 1383 |
+
}
|