Commit
•
5726e4e
1
Parent(s):
7bcab23
Evaluation on the test set completed on 2024_11_27.
Browse files- README.md +124 -0
- all_results.json +17 -0
- logs/events.out.tfevents.1732687817.datavisu2 +2 -2
- logs/events.out.tfevents.1732696814.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +1047 -0
README.md
ADDED
|
@@ -0,0 +1,124 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/dinov2-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: bd_ortho-DinoVdeau-large-2024_11_27-batch-size64_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 |
+
# bd_ortho-DinoVdeau-large-2024_11_27-batch-size64_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: 0.4551
|
| 19 |
+
- Rmse: 0.0866
|
| 20 |
+
- Mae: 0.0630
|
| 21 |
+
- Kl Divergence: 0.1147
|
| 22 |
+
- Explained Variance: 0.6593
|
| 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: 64
|
| 44 |
+
- eval_batch_size: 64
|
| 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 | 221 | 0.4634 | 0.1018 | 0.0760 | 0.0696 | 0.5492 | 0.001 |
|
| 56 |
+
| No log | 2.0 | 442 | 0.4593 | 0.0952 | 0.0716 | 0.0038 | 0.6113 | 0.001 |
|
| 57 |
+
| 0.5185 | 3.0 | 663 | 0.4574 | 0.0918 | 0.0670 | 0.0583 | 0.6245 | 0.001 |
|
| 58 |
+
| 0.5185 | 4.0 | 884 | 0.4595 | 0.0955 | 0.0713 | -0.0650 | 0.6130 | 0.001 |
|
| 59 |
+
| 0.4806 | 5.0 | 1105 | 0.4593 | 0.0954 | 0.0702 | -0.0835 | 0.6206 | 0.001 |
|
| 60 |
+
| 0.4806 | 6.0 | 1326 | 0.4608 | 0.0977 | 0.0728 | -0.0705 | 0.6041 | 0.001 |
|
| 61 |
+
| 0.4786 | 7.0 | 1547 | 0.4581 | 0.0927 | 0.0683 | -0.0044 | 0.6283 | 0.001 |
|
| 62 |
+
| 0.4786 | 8.0 | 1768 | 0.4573 | 0.0916 | 0.0680 | 0.0799 | 0.6277 | 0.001 |
|
| 63 |
+
| 0.4786 | 9.0 | 1989 | 0.4594 | 0.0947 | 0.0706 | 0.0233 | 0.6196 | 0.001 |
|
| 64 |
+
| 0.4776 | 10.0 | 2210 | 0.4577 | 0.0918 | 0.0675 | 0.0885 | 0.6293 | 0.001 |
|
| 65 |
+
| 0.4776 | 11.0 | 2431 | 0.4564 | 0.0898 | 0.0662 | 0.1296 | 0.6422 | 0.001 |
|
| 66 |
+
| 0.4772 | 12.0 | 2652 | 0.4572 | 0.0913 | 0.0677 | -0.0061 | 0.6386 | 0.001 |
|
| 67 |
+
| 0.4772 | 13.0 | 2873 | 0.4623 | 0.1002 | 0.0747 | -0.2060 | 0.6186 | 0.001 |
|
| 68 |
+
| 0.4769 | 14.0 | 3094 | 0.4578 | 0.0925 | 0.0678 | -0.0371 | 0.6346 | 0.001 |
|
| 69 |
+
| 0.4769 | 15.0 | 3315 | 0.4575 | 0.0917 | 0.0667 | 0.0458 | 0.6340 | 0.001 |
|
| 70 |
+
| 0.4766 | 16.0 | 3536 | 0.4579 | 0.0926 | 0.0680 | 0.0151 | 0.6277 | 0.001 |
|
| 71 |
+
| 0.4766 | 17.0 | 3757 | 0.4592 | 0.0949 | 0.0702 | -0.0679 | 0.6246 | 0.001 |
|
| 72 |
+
| 0.4766 | 18.0 | 3978 | 0.4557 | 0.0887 | 0.0651 | 0.0421 | 0.6493 | 0.0001 |
|
| 73 |
+
| 0.4758 | 19.0 | 4199 | 0.4556 | 0.0885 | 0.0647 | 0.0468 | 0.6508 | 0.0001 |
|
| 74 |
+
| 0.4758 | 20.0 | 4420 | 0.4555 | 0.0884 | 0.0648 | 0.0405 | 0.6518 | 0.0001 |
|
| 75 |
+
| 0.4741 | 21.0 | 4641 | 0.4555 | 0.0884 | 0.0650 | 0.0475 | 0.6533 | 0.0001 |
|
| 76 |
+
| 0.4741 | 22.0 | 4862 | 0.4555 | 0.0883 | 0.0646 | 0.0570 | 0.6535 | 0.0001 |
|
| 77 |
+
| 0.4738 | 23.0 | 5083 | 0.4551 | 0.0874 | 0.0641 | 0.0887 | 0.6570 | 0.0001 |
|
| 78 |
+
| 0.4738 | 24.0 | 5304 | 0.4552 | 0.0878 | 0.0642 | 0.0555 | 0.6553 | 0.0001 |
|
| 79 |
+
| 0.4736 | 25.0 | 5525 | 0.4552 | 0.0878 | 0.0645 | 0.0238 | 0.6582 | 0.0001 |
|
| 80 |
+
| 0.4736 | 26.0 | 5746 | 0.4557 | 0.0885 | 0.0646 | 0.0409 | 0.6572 | 0.0001 |
|
| 81 |
+
| 0.4736 | 27.0 | 5967 | 0.4551 | 0.0876 | 0.0639 | 0.0548 | 0.6576 | 0.0001 |
|
| 82 |
+
| 0.4731 | 28.0 | 6188 | 0.4551 | 0.0876 | 0.0642 | 0.0273 | 0.6588 | 0.0001 |
|
| 83 |
+
| 0.4731 | 29.0 | 6409 | 0.4548 | 0.0869 | 0.0634 | 0.0744 | 0.6618 | 0.0001 |
|
| 84 |
+
| 0.4727 | 30.0 | 6630 | 0.4549 | 0.0873 | 0.0636 | 0.0492 | 0.6595 | 0.0001 |
|
| 85 |
+
| 0.4727 | 31.0 | 6851 | 0.4548 | 0.0869 | 0.0632 | 0.0688 | 0.6613 | 0.0001 |
|
| 86 |
+
| 0.4732 | 32.0 | 7072 | 0.4550 | 0.0874 | 0.0639 | 0.0271 | 0.6602 | 0.0001 |
|
| 87 |
+
| 0.4732 | 33.0 | 7293 | 0.4554 | 0.0882 | 0.0647 | -0.0174 | 0.6580 | 0.0001 |
|
| 88 |
+
| 0.4725 | 34.0 | 7514 | 0.4546 | 0.0866 | 0.0628 | 0.1094 | 0.6616 | 0.0001 |
|
| 89 |
+
| 0.4725 | 35.0 | 7735 | 0.4550 | 0.0874 | 0.0639 | 0.0571 | 0.6583 | 0.0001 |
|
| 90 |
+
| 0.4725 | 36.0 | 7956 | 0.4548 | 0.0869 | 0.0629 | 0.1453 | 0.6616 | 0.0001 |
|
| 91 |
+
| 0.4727 | 37.0 | 8177 | 0.4553 | 0.0881 | 0.0645 | -0.0152 | 0.6587 | 0.0001 |
|
| 92 |
+
| 0.4727 | 38.0 | 8398 | 0.4548 | 0.0870 | 0.0636 | 0.0490 | 0.6613 | 0.0001 |
|
| 93 |
+
| 0.4727 | 39.0 | 8619 | 0.4548 | 0.0870 | 0.0631 | 0.0726 | 0.6610 | 0.0001 |
|
| 94 |
+
| 0.4727 | 40.0 | 8840 | 0.4548 | 0.0870 | 0.0632 | 0.0637 | 0.6605 | 0.0001 |
|
| 95 |
+
| 0.4721 | 41.0 | 9061 | 0.4547 | 0.0869 | 0.0634 | 0.0390 | 0.6628 | 1e-05 |
|
| 96 |
+
| 0.4721 | 42.0 | 9282 | 0.4544 | 0.0862 | 0.0628 | 0.1115 | 0.6657 | 1e-05 |
|
| 97 |
+
| 0.4721 | 43.0 | 9503 | 0.4546 | 0.0866 | 0.0632 | 0.0533 | 0.6646 | 1e-05 |
|
| 98 |
+
| 0.4721 | 44.0 | 9724 | 0.4545 | 0.0864 | 0.0625 | 0.1350 | 0.6648 | 1e-05 |
|
| 99 |
+
| 0.4721 | 45.0 | 9945 | 0.4550 | 0.0874 | 0.0642 | 0.0044 | 0.6625 | 1e-05 |
|
| 100 |
+
| 0.4716 | 46.0 | 10166 | 0.4546 | 0.0867 | 0.0632 | 0.0389 | 0.6642 | 1e-05 |
|
| 101 |
+
| 0.4716 | 47.0 | 10387 | 0.4545 | 0.0866 | 0.0630 | 0.0370 | 0.6651 | 1e-05 |
|
| 102 |
+
| 0.4722 | 48.0 | 10608 | 0.4546 | 0.0868 | 0.0634 | 0.0194 | 0.6645 | 1e-05 |
|
| 103 |
+
| 0.4722 | 49.0 | 10829 | 0.4544 | 0.0862 | 0.0627 | 0.0667 | 0.6667 | 0.0000 |
|
| 104 |
+
| 0.4717 | 50.0 | 11050 | 0.4545 | 0.0865 | 0.0631 | 0.0548 | 0.6651 | 0.0000 |
|
| 105 |
+
| 0.4717 | 51.0 | 11271 | 0.4545 | 0.0865 | 0.0629 | 0.0428 | 0.6651 | 0.0000 |
|
| 106 |
+
| 0.4717 | 52.0 | 11492 | 0.4542 | 0.0859 | 0.0623 | 0.1236 | 0.6672 | 0.0000 |
|
| 107 |
+
| 0.4718 | 53.0 | 11713 | 0.4542 | 0.0859 | 0.0625 | 0.0887 | 0.6672 | 0.0000 |
|
| 108 |
+
| 0.4718 | 54.0 | 11934 | 0.4543 | 0.0862 | 0.0624 | 0.0917 | 0.6653 | 0.0000 |
|
| 109 |
+
| 0.4716 | 55.0 | 12155 | 0.4546 | 0.0865 | 0.0631 | 0.0774 | 0.6650 | 0.0000 |
|
| 110 |
+
| 0.4716 | 56.0 | 12376 | 0.4546 | 0.0866 | 0.0633 | 0.0473 | 0.6649 | 0.0000 |
|
| 111 |
+
| 0.4717 | 57.0 | 12597 | 0.4549 | 0.0871 | 0.0639 | -0.0046 | 0.6658 | 0.0000 |
|
| 112 |
+
| 0.4717 | 58.0 | 12818 | 0.4544 | 0.0864 | 0.0627 | 0.0553 | 0.6656 | 0.0000 |
|
| 113 |
+
| 0.4716 | 59.0 | 13039 | 0.4545 | 0.0865 | 0.0631 | 0.0368 | 0.6654 | 0.0000 |
|
| 114 |
+
| 0.4716 | 60.0 | 13260 | 0.4544 | 0.0863 | 0.0629 | 0.0471 | 0.6660 | 0.0000 |
|
| 115 |
+
| 0.4716 | 61.0 | 13481 | 0.4542 | 0.0860 | 0.0624 | 0.0928 | 0.6670 | 0.0000 |
|
| 116 |
+
| 0.4718 | 62.0 | 13702 | 0.4545 | 0.0866 | 0.0632 | 0.0286 | 0.6661 | 0.0000 |
|
| 117 |
+
|
| 118 |
+
|
| 119 |
+
### Framework versions
|
| 120 |
+
|
| 121 |
+
- Transformers 4.41.0
|
| 122 |
+
- Pytorch 2.5.0+cu124
|
| 123 |
+
- Datasets 3.0.2
|
| 124 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 62.0,
|
| 3 |
+
"eval_explained_variance": 0.6593042016029358,
|
| 4 |
+
"eval_kl_divergence": 0.11466515809297562,
|
| 5 |
+
"eval_loss": 0.45506975054740906,
|
| 6 |
+
"eval_mae": 0.06304711848497391,
|
| 7 |
+
"eval_rmse": 0.08664286881685257,
|
| 8 |
+
"eval_runtime": 26.2102,
|
| 9 |
+
"eval_samples_per_second": 179.244,
|
| 10 |
+
"eval_steps_per_second": 2.823,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 12 |
+
"total_flos": 9.42369297866869e+19,
|
| 13 |
+
"train_loss": 0.4754439868851833,
|
| 14 |
+
"train_runtime": 8961.4221,
|
| 15 |
+
"train_samples_per_second": 235.894,
|
| 16 |
+
"train_steps_per_second": 3.699
|
| 17 |
+
}
|
logs/events.out.tfevents.1732687817.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 sha256:0d78e0e3d21c1058cf86741492b3a2c5a15d05f99fa19a27103dbd49a075da25
|
| 3 |
+
size 45983
|
logs/events.out.tfevents.1732696814.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3162ba9474c0885fdae82852ed9ddbce5e81310e1ac9741481981e97954f0960
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1222870688
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3221228a8d421eb77f2d313bbc5460b2bf904a37a4260e2372f65d2ff35418ce
|
| 3 |
size 1222870688
|
test_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 62.0,
|
| 3 |
+
"eval_explained_variance": 0.6593042016029358,
|
| 4 |
+
"eval_kl_divergence": 0.11466515809297562,
|
| 5 |
+
"eval_loss": 0.45506975054740906,
|
| 6 |
+
"eval_mae": 0.06304711848497391,
|
| 7 |
+
"eval_rmse": 0.08664286881685257,
|
| 8 |
+
"eval_runtime": 26.2102,
|
| 9 |
+
"eval_samples_per_second": 179.244,
|
| 10 |
+
"eval_steps_per_second": 2.823,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-07
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 62.0,
|
| 3 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 4 |
+
"total_flos": 9.42369297866869e+19,
|
| 5 |
+
"train_loss": 0.4754439868851833,
|
| 6 |
+
"train_runtime": 8961.4221,
|
| 7 |
+
"train_samples_per_second": 235.894,
|
| 8 |
+
"train_steps_per_second": 3.699
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1047 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.45421910285949707,
|
| 3 |
+
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/bd_ortho_ign/bd_ortho-DinoVdeau-large-2024_11_27-batch-size64_freeze_probs/checkpoint-11492",
|
| 4 |
+
"epoch": 62.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 13702,
|
| 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": 0.5492395758628845,
|
| 14 |
+
"eval_kl_divergence": 0.06964559853076935,
|
| 15 |
+
"eval_loss": 0.46336060762405396,
|
| 16 |
+
"eval_mae": 0.07600608468055725,
|
| 17 |
+
"eval_rmse": 0.10175278037786484,
|
| 18 |
+
"eval_runtime": 26.595,
|
| 19 |
+
"eval_samples_per_second": 176.65,
|
| 20 |
+
"eval_steps_per_second": 2.782,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"step": 221
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"eval_explained_variance": 0.6113448739051819,
|
| 27 |
+
"eval_kl_divergence": 0.0038063330575823784,
|
| 28 |
+
"eval_loss": 0.45933997631073,
|
| 29 |
+
"eval_mae": 0.07159148901700974,
|
| 30 |
+
"eval_rmse": 0.09520163387060165,
|
| 31 |
+
"eval_runtime": 25.5426,
|
| 32 |
+
"eval_samples_per_second": 183.928,
|
| 33 |
+
"eval_steps_per_second": 2.897,
|
| 34 |
+
"learning_rate": 0.001,
|
| 35 |
+
"step": 442
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 2.262443438914027,
|
| 39 |
+
"grad_norm": 0.16188210248947144,
|
| 40 |
+
"learning_rate": 0.001,
|
| 41 |
+
"loss": 0.5185,
|
| 42 |
+
"step": 500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_explained_variance": 0.6245184540748596,
|
| 47 |
+
"eval_kl_divergence": 0.05826142057776451,
|
| 48 |
+
"eval_loss": 0.457367479801178,
|
| 49 |
+
"eval_mae": 0.0670078918337822,
|
| 50 |
+
"eval_rmse": 0.0917908325791359,
|
| 51 |
+
"eval_runtime": 25.6126,
|
| 52 |
+
"eval_samples_per_second": 183.425,
|
| 53 |
+
"eval_steps_per_second": 2.889,
|
| 54 |
+
"learning_rate": 0.001,
|
| 55 |
+
"step": 663
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 4.0,
|
| 59 |
+
"eval_explained_variance": 0.6129782795906067,
|
| 60 |
+
"eval_kl_divergence": -0.06495417654514313,
|
| 61 |
+
"eval_loss": 0.459468811750412,
|
| 62 |
+
"eval_mae": 0.07134346663951874,
|
| 63 |
+
"eval_rmse": 0.09552835673093796,
|
| 64 |
+
"eval_runtime": 25.6003,
|
| 65 |
+
"eval_samples_per_second": 183.514,
|
| 66 |
+
"eval_steps_per_second": 2.891,
|
| 67 |
+
"learning_rate": 0.001,
|
| 68 |
+
"step": 884
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.524886877828054,
|
| 72 |
+
"grad_norm": 0.09988280385732651,
|
| 73 |
+
"learning_rate": 0.001,
|
| 74 |
+
"loss": 0.4806,
|
| 75 |
+
"step": 1000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"eval_explained_variance": 0.6206489205360413,
|
| 80 |
+
"eval_kl_divergence": -0.08347146958112717,
|
| 81 |
+
"eval_loss": 0.45927393436431885,
|
| 82 |
+
"eval_mae": 0.07016489654779434,
|
| 83 |
+
"eval_rmse": 0.0953657403588295,
|
| 84 |
+
"eval_runtime": 25.74,
|
| 85 |
+
"eval_samples_per_second": 182.518,
|
| 86 |
+
"eval_steps_per_second": 2.875,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"step": 1105
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 6.0,
|
| 92 |
+
"eval_explained_variance": 0.6041414737701416,
|
| 93 |
+
"eval_kl_divergence": -0.07046143710613251,
|
| 94 |
+
"eval_loss": 0.46080395579338074,
|
| 95 |
+
"eval_mae": 0.07277411222457886,
|
| 96 |
+
"eval_rmse": 0.09773259609937668,
|
| 97 |
+
"eval_runtime": 25.4681,
|
| 98 |
+
"eval_samples_per_second": 184.466,
|
| 99 |
+
"eval_steps_per_second": 2.906,
|
| 100 |
+
"learning_rate": 0.001,
|
| 101 |
+
"step": 1326
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 6.787330316742081,
|
| 105 |
+
"grad_norm": 0.08271574974060059,
|
| 106 |
+
"learning_rate": 0.001,
|
| 107 |
+
"loss": 0.4786,
|
| 108 |
+
"step": 1500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 7.0,
|
| 112 |
+
"eval_explained_variance": 0.628325879573822,
|
| 113 |
+
"eval_kl_divergence": -0.004442690871655941,
|
| 114 |
+
"eval_loss": 0.4581476151943207,
|
| 115 |
+
"eval_mae": 0.06827609241008759,
|
| 116 |
+
"eval_rmse": 0.09274852275848389,
|
| 117 |
+
"eval_runtime": 26.0251,
|
| 118 |
+
"eval_samples_per_second": 180.518,
|
| 119 |
+
"eval_steps_per_second": 2.843,
|
| 120 |
+
"learning_rate": 0.001,
|
| 121 |
+
"step": 1547
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"eval_explained_variance": 0.6276748776435852,
|
| 126 |
+
"eval_kl_divergence": 0.07988782227039337,
|
| 127 |
+
"eval_loss": 0.4573117196559906,
|
| 128 |
+
"eval_mae": 0.06800529360771179,
|
| 129 |
+
"eval_rmse": 0.09162522107362747,
|
| 130 |
+
"eval_runtime": 25.7197,
|
| 131 |
+
"eval_samples_per_second": 182.662,
|
| 132 |
+
"eval_steps_per_second": 2.877,
|
| 133 |
+
"learning_rate": 0.001,
|
| 134 |
+
"step": 1768
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 9.0,
|
| 138 |
+
"eval_explained_variance": 0.6196129322052002,
|
| 139 |
+
"eval_kl_divergence": 0.02327939122915268,
|
| 140 |
+
"eval_loss": 0.45939013361930847,
|
| 141 |
+
"eval_mae": 0.07057134807109833,
|
| 142 |
+
"eval_rmse": 0.09471722692251205,
|
| 143 |
+
"eval_runtime": 25.8299,
|
| 144 |
+
"eval_samples_per_second": 181.883,
|
| 145 |
+
"eval_steps_per_second": 2.865,
|
| 146 |
+
"learning_rate": 0.001,
|
| 147 |
+
"step": 1989
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 9.049773755656108,
|
| 151 |
+
"grad_norm": 0.05649600923061371,
|
| 152 |
+
"learning_rate": 0.001,
|
| 153 |
+
"loss": 0.4776,
|
| 154 |
+
"step": 2000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 10.0,
|
| 158 |
+
"eval_explained_variance": 0.6293186545372009,
|
| 159 |
+
"eval_kl_divergence": 0.0885055735707283,
|
| 160 |
+
"eval_loss": 0.45772281289100647,
|
| 161 |
+
"eval_mae": 0.06745484471321106,
|
| 162 |
+
"eval_rmse": 0.09179002046585083,
|
| 163 |
+
"eval_runtime": 25.5273,
|
| 164 |
+
"eval_samples_per_second": 184.039,
|
| 165 |
+
"eval_steps_per_second": 2.899,
|
| 166 |
+
"learning_rate": 0.001,
|
| 167 |
+
"step": 2210
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 11.0,
|
| 171 |
+
"eval_explained_variance": 0.6422439813613892,
|
| 172 |
+
"eval_kl_divergence": 0.1296330839395523,
|
| 173 |
+
"eval_loss": 0.45641985535621643,
|
| 174 |
+
"eval_mae": 0.06617596000432968,
|
| 175 |
+
"eval_rmse": 0.08975591510534286,
|
| 176 |
+
"eval_runtime": 25.7282,
|
| 177 |
+
"eval_samples_per_second": 182.601,
|
| 178 |
+
"eval_steps_per_second": 2.876,
|
| 179 |
+
"learning_rate": 0.001,
|
| 180 |
+
"step": 2431
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 11.312217194570136,
|
| 184 |
+
"grad_norm": 0.04163961857557297,
|
| 185 |
+
"learning_rate": 0.001,
|
| 186 |
+
"loss": 0.4772,
|
| 187 |
+
"step": 2500
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 12.0,
|
| 191 |
+
"eval_explained_variance": 0.6385617256164551,
|
| 192 |
+
"eval_kl_divergence": -0.006057058461010456,
|
| 193 |
+
"eval_loss": 0.45718902349472046,
|
| 194 |
+
"eval_mae": 0.06766870617866516,
|
| 195 |
+
"eval_rmse": 0.09130751341581345,
|
| 196 |
+
"eval_runtime": 25.6849,
|
| 197 |
+
"eval_samples_per_second": 182.909,
|
| 198 |
+
"eval_steps_per_second": 2.881,
|
| 199 |
+
"learning_rate": 0.001,
|
| 200 |
+
"step": 2652
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 13.0,
|
| 204 |
+
"eval_explained_variance": 0.6186209321022034,
|
| 205 |
+
"eval_kl_divergence": -0.20600058138370514,
|
| 206 |
+
"eval_loss": 0.4622880220413208,
|
| 207 |
+
"eval_mae": 0.07468675822019577,
|
| 208 |
+
"eval_rmse": 0.10024455189704895,
|
| 209 |
+
"eval_runtime": 25.9645,
|
| 210 |
+
"eval_samples_per_second": 180.939,
|
| 211 |
+
"eval_steps_per_second": 2.85,
|
| 212 |
+
"learning_rate": 0.001,
|
| 213 |
+
"step": 2873
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 13.574660633484163,
|
| 217 |
+
"grad_norm": 0.0532899908721447,
|
| 218 |
+
"learning_rate": 0.001,
|
| 219 |
+
"loss": 0.4769,
|
| 220 |
+
"step": 3000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 14.0,
|
| 224 |
+
"eval_explained_variance": 0.6346250176429749,
|
| 225 |
+
"eval_kl_divergence": -0.0371401272714138,
|
| 226 |
+
"eval_loss": 0.45775285363197327,
|
| 227 |
+
"eval_mae": 0.06778896600008011,
|
| 228 |
+
"eval_rmse": 0.092497818171978,
|
| 229 |
+
"eval_runtime": 25.7017,
|
| 230 |
+
"eval_samples_per_second": 182.79,
|
| 231 |
+
"eval_steps_per_second": 2.879,
|
| 232 |
+
"learning_rate": 0.001,
|
| 233 |
+
"step": 3094
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"eval_explained_variance": 0.6340083479881287,
|
| 238 |
+
"eval_kl_divergence": 0.04575105383992195,
|
| 239 |
+
"eval_loss": 0.4575214684009552,
|
| 240 |
+
"eval_mae": 0.0666513592004776,
|
| 241 |
+
"eval_rmse": 0.0916559174656868,
|
| 242 |
+
"eval_runtime": 26.025,
|
| 243 |
+
"eval_samples_per_second": 180.519,
|
| 244 |
+
"eval_steps_per_second": 2.843,
|
| 245 |
+
"learning_rate": 0.001,
|
| 246 |
+
"step": 3315
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.83710407239819,
|
| 250 |
+
"grad_norm": 0.0473792664706707,
|
| 251 |
+
"learning_rate": 0.001,
|
| 252 |
+
"loss": 0.4766,
|
| 253 |
+
"step": 3500
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 16.0,
|
| 257 |
+
"eval_explained_variance": 0.6277230381965637,
|
| 258 |
+
"eval_kl_divergence": 0.01510859839618206,
|
| 259 |
+
"eval_loss": 0.4578736424446106,
|
| 260 |
+
"eval_mae": 0.06800080835819244,
|
| 261 |
+
"eval_rmse": 0.09264300018548965,
|
| 262 |
+
"eval_runtime": 25.6671,
|
| 263 |
+
"eval_samples_per_second": 183.036,
|
| 264 |
+
"eval_steps_per_second": 2.883,
|
| 265 |
+
"learning_rate": 0.001,
|
| 266 |
+
"step": 3536
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 17.0,
|
| 270 |
+
"eval_explained_variance": 0.6246375441551208,
|
| 271 |
+
"eval_kl_divergence": -0.06794208288192749,
|
| 272 |
+
"eval_loss": 0.4592094421386719,
|
| 273 |
+
"eval_mae": 0.07020581513643265,
|
| 274 |
+
"eval_rmse": 0.09485668689012527,
|
| 275 |
+
"eval_runtime": 25.9387,
|
| 276 |
+
"eval_samples_per_second": 181.119,
|
| 277 |
+
"eval_steps_per_second": 2.853,
|
| 278 |
+
"learning_rate": 0.001,
|
| 279 |
+
"step": 3757
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 18.0,
|
| 283 |
+
"eval_explained_variance": 0.6493042707443237,
|
| 284 |
+
"eval_kl_divergence": 0.04208216443657875,
|
| 285 |
+
"eval_loss": 0.45573291182518005,
|
| 286 |
+
"eval_mae": 0.06506813317537308,
|
| 287 |
+
"eval_rmse": 0.08873652666807175,
|
| 288 |
+
"eval_runtime": 25.6229,
|
| 289 |
+
"eval_samples_per_second": 183.352,
|
| 290 |
+
"eval_steps_per_second": 2.888,
|
| 291 |
+
"learning_rate": 0.0001,
|
| 292 |
+
"step": 3978
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 18.099547511312217,
|
| 296 |
+
"grad_norm": 0.048517756164073944,
|
| 297 |
+
"learning_rate": 0.0001,
|
| 298 |
+
"loss": 0.4758,
|
| 299 |
+
"step": 4000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 19.0,
|
| 303 |
+
"eval_explained_variance": 0.6507542729377747,
|
| 304 |
+
"eval_kl_divergence": 0.04677804559469223,
|
| 305 |
+
"eval_loss": 0.4555513262748718,
|
| 306 |
+
"eval_mae": 0.06473750621080399,
|
| 307 |
+
"eval_rmse": 0.08847790211439133,
|
| 308 |
+
"eval_runtime": 25.7638,
|
| 309 |
+
"eval_samples_per_second": 182.349,
|
| 310 |
+
"eval_steps_per_second": 2.872,
|
| 311 |
+
"learning_rate": 0.0001,
|
| 312 |
+
"step": 4199
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 20.0,
|
| 316 |
+
"eval_explained_variance": 0.6518434882164001,
|
| 317 |
+
"eval_kl_divergence": 0.0404924675822258,
|
| 318 |
+
"eval_loss": 0.45553284883499146,
|
| 319 |
+
"eval_mae": 0.06476090103387833,
|
| 320 |
+
"eval_rmse": 0.08838176727294922,
|
| 321 |
+
"eval_runtime": 25.6331,
|
| 322 |
+
"eval_samples_per_second": 183.279,
|
| 323 |
+
"eval_steps_per_second": 2.887,
|
| 324 |
+
"learning_rate": 0.0001,
|
| 325 |
+
"step": 4420
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 20.361990950226243,
|
| 329 |
+
"grad_norm": 0.04679996892809868,
|
| 330 |
+
"learning_rate": 0.0001,
|
| 331 |
+
"loss": 0.4741,
|
| 332 |
+
"step": 4500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 21.0,
|
| 336 |
+
"eval_explained_variance": 0.6532743573188782,
|
| 337 |
+
"eval_kl_divergence": 0.047539714723825455,
|
| 338 |
+
"eval_loss": 0.4555487334728241,
|
| 339 |
+
"eval_mae": 0.06497333198785782,
|
| 340 |
+
"eval_rmse": 0.08836204558610916,
|
| 341 |
+
"eval_runtime": 25.803,
|
| 342 |
+
"eval_samples_per_second": 182.072,
|
| 343 |
+
"eval_steps_per_second": 2.868,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"step": 4641
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.0,
|
| 349 |
+
"eval_explained_variance": 0.6534684300422668,
|
| 350 |
+
"eval_kl_divergence": 0.0570099912583828,
|
| 351 |
+
"eval_loss": 0.45551028847694397,
|
| 352 |
+
"eval_mae": 0.06458985060453415,
|
| 353 |
+
"eval_rmse": 0.08831282705068588,
|
| 354 |
+
"eval_runtime": 25.9625,
|
| 355 |
+
"eval_samples_per_second": 180.953,
|
| 356 |
+
"eval_steps_per_second": 2.85,
|
| 357 |
+
"learning_rate": 0.0001,
|
| 358 |
+
"step": 4862
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 22.624434389140273,
|
| 362 |
+
"grad_norm": 0.05471302196383476,
|
| 363 |
+
"learning_rate": 0.0001,
|
| 364 |
+
"loss": 0.4738,
|
| 365 |
+
"step": 5000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 23.0,
|
| 369 |
+
"eval_explained_variance": 0.6569964289665222,
|
| 370 |
+
"eval_kl_divergence": 0.08867427706718445,
|
| 371 |
+
"eval_loss": 0.45505577325820923,
|
| 372 |
+
"eval_mae": 0.0640987753868103,
|
| 373 |
+
"eval_rmse": 0.08740502595901489,
|
| 374 |
+
"eval_runtime": 25.8915,
|
| 375 |
+
"eval_samples_per_second": 181.45,
|
| 376 |
+
"eval_steps_per_second": 2.858,
|
| 377 |
+
"learning_rate": 0.0001,
|
| 378 |
+
"step": 5083
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 24.0,
|
| 382 |
+
"eval_explained_variance": 0.6552526354789734,
|
| 383 |
+
"eval_kl_divergence": 0.055539198219776154,
|
| 384 |
+
"eval_loss": 0.4552234709262848,
|
| 385 |
+
"eval_mae": 0.06417837738990784,
|
| 386 |
+
"eval_rmse": 0.08780523389577866,
|
| 387 |
+
"eval_runtime": 27.2231,
|
| 388 |
+
"eval_samples_per_second": 172.574,
|
| 389 |
+
"eval_steps_per_second": 2.718,
|
| 390 |
+
"learning_rate": 0.0001,
|
| 391 |
+
"step": 5304
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 24.8868778280543,
|
| 395 |
+
"grad_norm": 0.0545237734913826,
|
| 396 |
+
"learning_rate": 0.0001,
|
| 397 |
+
"loss": 0.4736,
|
| 398 |
+
"step": 5500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 25.0,
|
| 402 |
+
"eval_explained_variance": 0.6582456231117249,
|
| 403 |
+
"eval_kl_divergence": 0.023763582110404968,
|
| 404 |
+
"eval_loss": 0.45521080493927,
|
| 405 |
+
"eval_mae": 0.06447087973356247,
|
| 406 |
+
"eval_rmse": 0.08778873831033707,
|
| 407 |
+
"eval_runtime": 25.7982,
|
| 408 |
+
"eval_samples_per_second": 182.106,
|
| 409 |
+
"eval_steps_per_second": 2.868,
|
| 410 |
+
"learning_rate": 0.0001,
|
| 411 |
+
"step": 5525
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 26.0,
|
| 415 |
+
"eval_explained_variance": 0.6571853756904602,
|
| 416 |
+
"eval_kl_divergence": 0.040941931307315826,
|
| 417 |
+
"eval_loss": 0.4557025730609894,
|
| 418 |
+
"eval_mae": 0.06462270766496658,
|
| 419 |
+
"eval_rmse": 0.08846313506364822,
|
| 420 |
+
"eval_runtime": 25.5822,
|
| 421 |
+
"eval_samples_per_second": 183.643,
|
| 422 |
+
"eval_steps_per_second": 2.893,
|
| 423 |
+
"learning_rate": 0.0001,
|
| 424 |
+
"step": 5746
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 27.0,
|
| 428 |
+
"eval_explained_variance": 0.6576172709465027,
|
| 429 |
+
"eval_kl_divergence": 0.05476689711213112,
|
| 430 |
+
"eval_loss": 0.4550967216491699,
|
| 431 |
+
"eval_mae": 0.06391049176454544,
|
| 432 |
+
"eval_rmse": 0.08758416771888733,
|
| 433 |
+
"eval_runtime": 26.0908,
|
| 434 |
+
"eval_samples_per_second": 180.064,
|
| 435 |
+
"eval_steps_per_second": 2.836,
|
| 436 |
+
"learning_rate": 0.0001,
|
| 437 |
+
"step": 5967
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 27.149321266968325,
|
| 441 |
+
"grad_norm": 0.05160004645586014,
|
| 442 |
+
"learning_rate": 0.0001,
|
| 443 |
+
"loss": 0.4731,
|
| 444 |
+
"step": 6000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 28.0,
|
| 448 |
+
"eval_explained_variance": 0.658767580986023,
|
| 449 |
+
"eval_kl_divergence": 0.027325255796313286,
|
| 450 |
+
"eval_loss": 0.45512688159942627,
|
| 451 |
+
"eval_mae": 0.0641704872250557,
|
| 452 |
+
"eval_rmse": 0.08764084428548813,
|
| 453 |
+
"eval_runtime": 25.6818,
|
| 454 |
+
"eval_samples_per_second": 182.931,
|
| 455 |
+
"eval_steps_per_second": 2.881,
|
| 456 |
+
"learning_rate": 0.0001,
|
| 457 |
+
"step": 6188
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 29.0,
|
| 461 |
+
"eval_explained_variance": 0.6617770195007324,
|
| 462 |
+
"eval_kl_divergence": 0.0744185745716095,
|
| 463 |
+
"eval_loss": 0.45477041602134705,
|
| 464 |
+
"eval_mae": 0.0634256973862648,
|
| 465 |
+
"eval_rmse": 0.08693012595176697,
|
| 466 |
+
"eval_runtime": 25.726,
|
| 467 |
+
"eval_samples_per_second": 182.617,
|
| 468 |
+
"eval_steps_per_second": 2.876,
|
| 469 |
+
"learning_rate": 0.0001,
|
| 470 |
+
"step": 6409
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 29.41176470588235,
|
| 474 |
+
"grad_norm": 0.07741276919841766,
|
| 475 |
+
"learning_rate": 0.0001,
|
| 476 |
+
"loss": 0.4727,
|
| 477 |
+
"step": 6500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 30.0,
|
| 481 |
+
"eval_explained_variance": 0.6594749093055725,
|
| 482 |
+
"eval_kl_divergence": 0.049223385751247406,
|
| 483 |
+
"eval_loss": 0.4549327790737152,
|
| 484 |
+
"eval_mae": 0.06360659003257751,
|
| 485 |
+
"eval_rmse": 0.0873405933380127,
|
| 486 |
+
"eval_runtime": 25.4772,
|
| 487 |
+
"eval_samples_per_second": 184.4,
|
| 488 |
+
"eval_steps_per_second": 2.905,
|
| 489 |
+
"learning_rate": 0.0001,
|
| 490 |
+
"step": 6630
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 31.0,
|
| 494 |
+
"eval_explained_variance": 0.6613443493843079,
|
| 495 |
+
"eval_kl_divergence": 0.06878047436475754,
|
| 496 |
+
"eval_loss": 0.4547973871231079,
|
| 497 |
+
"eval_mae": 0.06322694569826126,
|
| 498 |
+
"eval_rmse": 0.08694975823163986,
|
| 499 |
+
"eval_runtime": 25.8257,
|
| 500 |
+
"eval_samples_per_second": 181.912,
|
| 501 |
+
"eval_steps_per_second": 2.865,
|
| 502 |
+
"learning_rate": 0.0001,
|
| 503 |
+
"step": 6851
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 31.67420814479638,
|
| 507 |
+
"grad_norm": 0.055884115397930145,
|
| 508 |
+
"learning_rate": 0.0001,
|
| 509 |
+
"loss": 0.4732,
|
| 510 |
+
"step": 7000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 32.0,
|
| 514 |
+
"eval_explained_variance": 0.6602151393890381,
|
| 515 |
+
"eval_kl_divergence": 0.027085499837994576,
|
| 516 |
+
"eval_loss": 0.454988956451416,
|
| 517 |
+
"eval_mae": 0.063857302069664,
|
| 518 |
+
"eval_rmse": 0.08743549138307571,
|
| 519 |
+
"eval_runtime": 25.6292,
|
| 520 |
+
"eval_samples_per_second": 183.307,
|
| 521 |
+
"eval_steps_per_second": 2.887,
|
| 522 |
+
"learning_rate": 0.0001,
|
| 523 |
+
"step": 7072
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 33.0,
|
| 527 |
+
"eval_explained_variance": 0.6580324172973633,
|
| 528 |
+
"eval_kl_divergence": -0.017361771315336227,
|
| 529 |
+
"eval_loss": 0.455375999212265,
|
| 530 |
+
"eval_mae": 0.0646858736872673,
|
| 531 |
+
"eval_rmse": 0.08816961199045181,
|
| 532 |
+
"eval_runtime": 25.8246,
|
| 533 |
+
"eval_samples_per_second": 181.919,
|
| 534 |
+
"eval_steps_per_second": 2.865,
|
| 535 |
+
"learning_rate": 0.0001,
|
| 536 |
+
"step": 7293
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 33.93665158371041,
|
| 540 |
+
"grad_norm": 0.08047891408205032,
|
| 541 |
+
"learning_rate": 0.0001,
|
| 542 |
+
"loss": 0.4725,
|
| 543 |
+
"step": 7500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 34.0,
|
| 547 |
+
"eval_explained_variance": 0.6616186499595642,
|
| 548 |
+
"eval_kl_divergence": 0.10939505696296692,
|
| 549 |
+
"eval_loss": 0.45461305975914,
|
| 550 |
+
"eval_mae": 0.0628495141863823,
|
| 551 |
+
"eval_rmse": 0.08664888888597488,
|
| 552 |
+
"eval_runtime": 25.7346,
|
| 553 |
+
"eval_samples_per_second": 182.556,
|
| 554 |
+
"eval_steps_per_second": 2.876,
|
| 555 |
+
"learning_rate": 0.0001,
|
| 556 |
+
"step": 7514
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 35.0,
|
| 560 |
+
"eval_explained_variance": 0.6582692265510559,
|
| 561 |
+
"eval_kl_divergence": 0.05707371234893799,
|
| 562 |
+
"eval_loss": 0.45498156547546387,
|
| 563 |
+
"eval_mae": 0.06386271119117737,
|
| 564 |
+
"eval_rmse": 0.08741921186447144,
|
| 565 |
+
"eval_runtime": 25.7857,
|
| 566 |
+
"eval_samples_per_second": 182.194,
|
| 567 |
+
"eval_steps_per_second": 2.87,
|
| 568 |
+
"learning_rate": 0.0001,
|
| 569 |
+
"step": 7735
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 36.0,
|
| 573 |
+
"eval_explained_variance": 0.6615896224975586,
|
| 574 |
+
"eval_kl_divergence": 0.14533284306526184,
|
| 575 |
+
"eval_loss": 0.4548388123512268,
|
| 576 |
+
"eval_mae": 0.0629100501537323,
|
| 577 |
+
"eval_rmse": 0.08686337620019913,
|
| 578 |
+
"eval_runtime": 29.7733,
|
| 579 |
+
"eval_samples_per_second": 157.793,
|
| 580 |
+
"eval_steps_per_second": 2.485,
|
| 581 |
+
"learning_rate": 0.0001,
|
| 582 |
+
"step": 7956
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 36.199095022624434,
|
| 586 |
+
"grad_norm": 0.07811417430639267,
|
| 587 |
+
"learning_rate": 0.0001,
|
| 588 |
+
"loss": 0.4727,
|
| 589 |
+
"step": 8000
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 37.0,
|
| 593 |
+
"eval_explained_variance": 0.6586756110191345,
|
| 594 |
+
"eval_kl_divergence": -0.015241213142871857,
|
| 595 |
+
"eval_loss": 0.45526784658432007,
|
| 596 |
+
"eval_mae": 0.06451455503702164,
|
| 597 |
+
"eval_rmse": 0.08806425333023071,
|
| 598 |
+
"eval_runtime": 25.6924,
|
| 599 |
+
"eval_samples_per_second": 182.855,
|
| 600 |
+
"eval_steps_per_second": 2.88,
|
| 601 |
+
"learning_rate": 0.0001,
|
| 602 |
+
"step": 8177
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 38.0,
|
| 606 |
+
"eval_explained_variance": 0.6612560153007507,
|
| 607 |
+
"eval_kl_divergence": 0.049000147730112076,
|
| 608 |
+
"eval_loss": 0.45479556918144226,
|
| 609 |
+
"eval_mae": 0.06361590325832367,
|
| 610 |
+
"eval_rmse": 0.08704841136932373,
|
| 611 |
+
"eval_runtime": 26.1103,
|
| 612 |
+
"eval_samples_per_second": 179.929,
|
| 613 |
+
"eval_steps_per_second": 2.834,
|
| 614 |
+
"learning_rate": 0.0001,
|
| 615 |
+
"step": 8398
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 38.46153846153846,
|
| 619 |
+
"grad_norm": 0.062047556042671204,
|
| 620 |
+
"learning_rate": 0.0001,
|
| 621 |
+
"loss": 0.4727,
|
| 622 |
+
"step": 8500
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 39.0,
|
| 626 |
+
"eval_explained_variance": 0.6610231995582581,
|
| 627 |
+
"eval_kl_divergence": 0.07255241274833679,
|
| 628 |
+
"eval_loss": 0.454780250787735,
|
| 629 |
+
"eval_mae": 0.06311424821615219,
|
| 630 |
+
"eval_rmse": 0.08698847889900208,
|
| 631 |
+
"eval_runtime": 25.6403,
|
| 632 |
+
"eval_samples_per_second": 183.227,
|
| 633 |
+
"eval_steps_per_second": 2.886,
|
| 634 |
+
"learning_rate": 0.0001,
|
| 635 |
+
"step": 8619
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 40.0,
|
| 639 |
+
"eval_explained_variance": 0.6605435013771057,
|
| 640 |
+
"eval_kl_divergence": 0.06372024863958359,
|
| 641 |
+
"eval_loss": 0.45476558804512024,
|
| 642 |
+
"eval_mae": 0.06323693692684174,
|
| 643 |
+
"eval_rmse": 0.08702895045280457,
|
| 644 |
+
"eval_runtime": 26.038,
|
| 645 |
+
"eval_samples_per_second": 180.429,
|
| 646 |
+
"eval_steps_per_second": 2.842,
|
| 647 |
+
"learning_rate": 0.0001,
|
| 648 |
+
"step": 8840
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 40.723981900452486,
|
| 652 |
+
"grad_norm": 0.08612842857837677,
|
| 653 |
+
"learning_rate": 1e-05,
|
| 654 |
+
"loss": 0.4721,
|
| 655 |
+
"step": 9000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 41.0,
|
| 659 |
+
"eval_explained_variance": 0.6628013253211975,
|
| 660 |
+
"eval_kl_divergence": 0.039023660123348236,
|
| 661 |
+
"eval_loss": 0.45470812916755676,
|
| 662 |
+
"eval_mae": 0.0634213536977768,
|
| 663 |
+
"eval_rmse": 0.08692529052495956,
|
| 664 |
+
"eval_runtime": 25.9883,
|
| 665 |
+
"eval_samples_per_second": 180.774,
|
| 666 |
+
"eval_steps_per_second": 2.847,
|
| 667 |
+
"learning_rate": 1e-05,
|
| 668 |
+
"step": 9061
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 42.0,
|
| 672 |
+
"eval_explained_variance": 0.6656690239906311,
|
| 673 |
+
"eval_kl_divergence": 0.11149828135967255,
|
| 674 |
+
"eval_loss": 0.4543863534927368,
|
| 675 |
+
"eval_mae": 0.06281669437885284,
|
| 676 |
+
"eval_rmse": 0.08619723469018936,
|
| 677 |
+
"eval_runtime": 26.3115,
|
| 678 |
+
"eval_samples_per_second": 178.553,
|
| 679 |
+
"eval_steps_per_second": 2.812,
|
| 680 |
+
"learning_rate": 1e-05,
|
| 681 |
+
"step": 9282
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 42.98642533936652,
|
| 685 |
+
"grad_norm": 0.06828662008047104,
|
| 686 |
+
"learning_rate": 1e-05,
|
| 687 |
+
"loss": 0.4721,
|
| 688 |
+
"step": 9500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 43.0,
|
| 692 |
+
"eval_explained_variance": 0.6645870804786682,
|
| 693 |
+
"eval_kl_divergence": 0.05330301821231842,
|
| 694 |
+
"eval_loss": 0.4545557498931885,
|
| 695 |
+
"eval_mae": 0.06320130825042725,
|
| 696 |
+
"eval_rmse": 0.0865868553519249,
|
| 697 |
+
"eval_runtime": 25.8985,
|
| 698 |
+
"eval_samples_per_second": 181.4,
|
| 699 |
+
"eval_steps_per_second": 2.857,
|
| 700 |
+
"learning_rate": 1e-05,
|
| 701 |
+
"step": 9503
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 44.0,
|
| 705 |
+
"eval_explained_variance": 0.6648023128509521,
|
| 706 |
+
"eval_kl_divergence": 0.13496889173984528,
|
| 707 |
+
"eval_loss": 0.45448434352874756,
|
| 708 |
+
"eval_mae": 0.06253467500209808,
|
| 709 |
+
"eval_rmse": 0.08635282516479492,
|
| 710 |
+
"eval_runtime": 26.0508,
|
| 711 |
+
"eval_samples_per_second": 180.34,
|
| 712 |
+
"eval_steps_per_second": 2.841,
|
| 713 |
+
"learning_rate": 1e-05,
|
| 714 |
+
"step": 9724
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 45.0,
|
| 718 |
+
"eval_explained_variance": 0.6624875068664551,
|
| 719 |
+
"eval_kl_divergence": 0.004431928042322397,
|
| 720 |
+
"eval_loss": 0.4550137519836426,
|
| 721 |
+
"eval_mae": 0.06418145447969437,
|
| 722 |
+
"eval_rmse": 0.0874209776520729,
|
| 723 |
+
"eval_runtime": 25.8495,
|
| 724 |
+
"eval_samples_per_second": 181.744,
|
| 725 |
+
"eval_steps_per_second": 2.863,
|
| 726 |
+
"learning_rate": 1e-05,
|
| 727 |
+
"step": 9945
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 45.248868778280546,
|
| 731 |
+
"grad_norm": 0.07514863461256027,
|
| 732 |
+
"learning_rate": 1e-05,
|
| 733 |
+
"loss": 0.4716,
|
| 734 |
+
"step": 10000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 46.0,
|
| 738 |
+
"eval_explained_variance": 0.6642169952392578,
|
| 739 |
+
"eval_kl_divergence": 0.03887256979942322,
|
| 740 |
+
"eval_loss": 0.4545902609825134,
|
| 741 |
+
"eval_mae": 0.06316760927438736,
|
| 742 |
+
"eval_rmse": 0.08669499307870865,
|
| 743 |
+
"eval_runtime": 25.9222,
|
| 744 |
+
"eval_samples_per_second": 181.235,
|
| 745 |
+
"eval_steps_per_second": 2.855,
|
| 746 |
+
"learning_rate": 1e-05,
|
| 747 |
+
"step": 10166
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 47.0,
|
| 751 |
+
"eval_explained_variance": 0.6651113629341125,
|
| 752 |
+
"eval_kl_divergence": 0.037030890583992004,
|
| 753 |
+
"eval_loss": 0.4544997215270996,
|
| 754 |
+
"eval_mae": 0.06298934668302536,
|
| 755 |
+
"eval_rmse": 0.0865601971745491,
|
| 756 |
+
"eval_runtime": 25.9565,
|
| 757 |
+
"eval_samples_per_second": 180.995,
|
| 758 |
+
"eval_steps_per_second": 2.851,
|
| 759 |
+
"learning_rate": 1e-05,
|
| 760 |
+
"step": 10387
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 47.51131221719457,
|
| 764 |
+
"grad_norm": 0.057216282933950424,
|
| 765 |
+
"learning_rate": 1e-05,
|
| 766 |
+
"loss": 0.4722,
|
| 767 |
+
"step": 10500
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 48.0,
|
| 771 |
+
"eval_explained_variance": 0.6645199060440063,
|
| 772 |
+
"eval_kl_divergence": 0.019425788894295692,
|
| 773 |
+
"eval_loss": 0.4546374976634979,
|
| 774 |
+
"eval_mae": 0.06339576095342636,
|
| 775 |
+
"eval_rmse": 0.08680880069732666,
|
| 776 |
+
"eval_runtime": 25.7117,
|
| 777 |
+
"eval_samples_per_second": 182.718,
|
| 778 |
+
"eval_steps_per_second": 2.878,
|
| 779 |
+
"learning_rate": 1e-05,
|
| 780 |
+
"step": 10608
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 49.0,
|
| 784 |
+
"eval_explained_variance": 0.6666774153709412,
|
| 785 |
+
"eval_kl_divergence": 0.0667150691151619,
|
| 786 |
+
"eval_loss": 0.45436596870422363,
|
| 787 |
+
"eval_mae": 0.06269881874322891,
|
| 788 |
+
"eval_rmse": 0.08620164543390274,
|
| 789 |
+
"eval_runtime": 27.6905,
|
| 790 |
+
"eval_samples_per_second": 169.661,
|
| 791 |
+
"eval_steps_per_second": 2.672,
|
| 792 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 793 |
+
"step": 10829
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 49.7737556561086,
|
| 797 |
+
"grad_norm": 0.07466714084148407,
|
| 798 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 799 |
+
"loss": 0.4717,
|
| 800 |
+
"step": 11000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 50.0,
|
| 804 |
+
"eval_explained_variance": 0.6650940179824829,
|
| 805 |
+
"eval_kl_divergence": 0.05483337119221687,
|
| 806 |
+
"eval_loss": 0.45450592041015625,
|
| 807 |
+
"eval_mae": 0.06310971826314926,
|
| 808 |
+
"eval_rmse": 0.08650273084640503,
|
| 809 |
+
"eval_runtime": 27.7128,
|
| 810 |
+
"eval_samples_per_second": 169.524,
|
| 811 |
+
"eval_steps_per_second": 2.67,
|
| 812 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 813 |
+
"step": 11050
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 51.0,
|
| 817 |
+
"eval_explained_variance": 0.6651105284690857,
|
| 818 |
+
"eval_kl_divergence": 0.04277108237147331,
|
| 819 |
+
"eval_loss": 0.4544804096221924,
|
| 820 |
+
"eval_mae": 0.06292647123336792,
|
| 821 |
+
"eval_rmse": 0.08647629618644714,
|
| 822 |
+
"eval_runtime": 26.6553,
|
| 823 |
+
"eval_samples_per_second": 176.25,
|
| 824 |
+
"eval_steps_per_second": 2.776,
|
| 825 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 826 |
+
"step": 11271
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 52.0,
|
| 830 |
+
"eval_explained_variance": 0.667234480381012,
|
| 831 |
+
"eval_kl_divergence": 0.12364839017391205,
|
| 832 |
+
"eval_loss": 0.45421910285949707,
|
| 833 |
+
"eval_mae": 0.06233237311244011,
|
| 834 |
+
"eval_rmse": 0.08589440584182739,
|
| 835 |
+
"eval_runtime": 25.8544,
|
| 836 |
+
"eval_samples_per_second": 181.71,
|
| 837 |
+
"eval_steps_per_second": 2.862,
|
| 838 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 839 |
+
"step": 11492
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 52.036199095022624,
|
| 843 |
+
"grad_norm": 0.08442794531583786,
|
| 844 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 845 |
+
"loss": 0.4718,
|
| 846 |
+
"step": 11500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 53.0,
|
| 850 |
+
"eval_explained_variance": 0.6671742796897888,
|
| 851 |
+
"eval_kl_divergence": 0.08869530260562897,
|
| 852 |
+
"eval_loss": 0.4542272686958313,
|
| 853 |
+
"eval_mae": 0.06253313273191452,
|
| 854 |
+
"eval_rmse": 0.08594661206007004,
|
| 855 |
+
"eval_runtime": 25.9744,
|
| 856 |
+
"eval_samples_per_second": 180.871,
|
| 857 |
+
"eval_steps_per_second": 2.849,
|
| 858 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 859 |
+
"step": 11713
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 54.0,
|
| 863 |
+
"eval_explained_variance": 0.6653165221214294,
|
| 864 |
+
"eval_kl_divergence": 0.09171402454376221,
|
| 865 |
+
"eval_loss": 0.4543103575706482,
|
| 866 |
+
"eval_mae": 0.0623968206346035,
|
| 867 |
+
"eval_rmse": 0.08615261316299438,
|
| 868 |
+
"eval_runtime": 26.0699,
|
| 869 |
+
"eval_samples_per_second": 180.208,
|
| 870 |
+
"eval_steps_per_second": 2.839,
|
| 871 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 872 |
+
"step": 11934
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 54.29864253393665,
|
| 876 |
+
"grad_norm": 0.08775485306978226,
|
| 877 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 878 |
+
"loss": 0.4716,
|
| 879 |
+
"step": 12000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 55.0,
|
| 883 |
+
"eval_explained_variance": 0.6649713516235352,
|
| 884 |
+
"eval_kl_divergence": 0.07737051695585251,
|
| 885 |
+
"eval_loss": 0.45456644892692566,
|
| 886 |
+
"eval_mae": 0.06305743753910065,
|
| 887 |
+
"eval_rmse": 0.0865490511059761,
|
| 888 |
+
"eval_runtime": 26.0104,
|
| 889 |
+
"eval_samples_per_second": 180.62,
|
| 890 |
+
"eval_steps_per_second": 2.845,
|
| 891 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 892 |
+
"step": 12155
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 56.0,
|
| 896 |
+
"eval_explained_variance": 0.6649186611175537,
|
| 897 |
+
"eval_kl_divergence": 0.04731013998389244,
|
| 898 |
+
"eval_loss": 0.45458319783210754,
|
| 899 |
+
"eval_mae": 0.06328658014535904,
|
| 900 |
+
"eval_rmse": 0.08663744479417801,
|
| 901 |
+
"eval_runtime": 25.8104,
|
| 902 |
+
"eval_samples_per_second": 182.019,
|
| 903 |
+
"eval_steps_per_second": 2.867,
|
| 904 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 905 |
+
"step": 12376
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 56.56108597285068,
|
| 909 |
+
"grad_norm": 0.0692247599363327,
|
| 910 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 911 |
+
"loss": 0.4717,
|
| 912 |
+
"step": 12500
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 57.0,
|
| 916 |
+
"eval_explained_variance": 0.6657507419586182,
|
| 917 |
+
"eval_kl_divergence": -0.004581684246659279,
|
| 918 |
+
"eval_loss": 0.4548773169517517,
|
| 919 |
+
"eval_mae": 0.0639243796467781,
|
| 920 |
+
"eval_rmse": 0.0871059000492096,
|
| 921 |
+
"eval_runtime": 25.4962,
|
| 922 |
+
"eval_samples_per_second": 184.262,
|
| 923 |
+
"eval_steps_per_second": 2.902,
|
| 924 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 925 |
+
"step": 12597
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 58.0,
|
| 929 |
+
"eval_explained_variance": 0.6655800342559814,
|
| 930 |
+
"eval_kl_divergence": 0.0553017221391201,
|
| 931 |
+
"eval_loss": 0.45440155267715454,
|
| 932 |
+
"eval_mae": 0.06271661818027496,
|
| 933 |
+
"eval_rmse": 0.08635643124580383,
|
| 934 |
+
"eval_runtime": 26.1057,
|
| 935 |
+
"eval_samples_per_second": 179.961,
|
| 936 |
+
"eval_steps_per_second": 2.835,
|
| 937 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 938 |
+
"step": 12818
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 58.8235294117647,
|
| 942 |
+
"grad_norm": 0.07922232896089554,
|
| 943 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 944 |
+
"loss": 0.4716,
|
| 945 |
+
"step": 13000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 59.0,
|
| 949 |
+
"eval_explained_variance": 0.6654148101806641,
|
| 950 |
+
"eval_kl_divergence": 0.03675610199570656,
|
| 951 |
+
"eval_loss": 0.45448538661003113,
|
| 952 |
+
"eval_mae": 0.06308572739362717,
|
| 953 |
+
"eval_rmse": 0.08650225400924683,
|
| 954 |
+
"eval_runtime": 25.8122,
|
| 955 |
+
"eval_samples_per_second": 182.007,
|
| 956 |
+
"eval_steps_per_second": 2.867,
|
| 957 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 958 |
+
"step": 13039
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 60.0,
|
| 962 |
+
"eval_explained_variance": 0.6660366058349609,
|
| 963 |
+
"eval_kl_divergence": 0.047148581594228745,
|
| 964 |
+
"eval_loss": 0.4544091522693634,
|
| 965 |
+
"eval_mae": 0.06294982880353928,
|
| 966 |
+
"eval_rmse": 0.08633282780647278,
|
| 967 |
+
"eval_runtime": 26.4937,
|
| 968 |
+
"eval_samples_per_second": 177.325,
|
| 969 |
+
"eval_steps_per_second": 2.793,
|
| 970 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 971 |
+
"step": 13260
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 61.0,
|
| 975 |
+
"eval_explained_variance": 0.6669723987579346,
|
| 976 |
+
"eval_kl_divergence": 0.09280110895633698,
|
| 977 |
+
"eval_loss": 0.4542348086833954,
|
| 978 |
+
"eval_mae": 0.062441930174827576,
|
| 979 |
+
"eval_rmse": 0.08595842123031616,
|
| 980 |
+
"eval_runtime": 26.0483,
|
| 981 |
+
"eval_samples_per_second": 180.357,
|
| 982 |
+
"eval_steps_per_second": 2.841,
|
| 983 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 984 |
+
"step": 13481
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 61.085972850678736,
|
| 988 |
+
"grad_norm": 0.07845129072666168,
|
| 989 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 990 |
+
"loss": 0.4718,
|
| 991 |
+
"step": 13500
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 62.0,
|
| 995 |
+
"eval_explained_variance": 0.6661055088043213,
|
| 996 |
+
"eval_kl_divergence": 0.028626998886466026,
|
| 997 |
+
"eval_loss": 0.4545469284057617,
|
| 998 |
+
"eval_mae": 0.06315190345048904,
|
| 999 |
+
"eval_rmse": 0.0865735188126564,
|
| 1000 |
+
"eval_runtime": 25.8503,
|
| 1001 |
+
"eval_samples_per_second": 181.739,
|
| 1002 |
+
"eval_steps_per_second": 2.863,
|
| 1003 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1004 |
+
"step": 13702
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 62.0,
|
| 1008 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1009 |
+
"step": 13702,
|
| 1010 |
+
"total_flos": 9.42369297866869e+19,
|
| 1011 |
+
"train_loss": 0.4754439868851833,
|
| 1012 |
+
"train_runtime": 8961.4221,
|
| 1013 |
+
"train_samples_per_second": 235.894,
|
| 1014 |
+
"train_steps_per_second": 3.699
|
| 1015 |
+
}
|
| 1016 |
+
],
|
| 1017 |
+
"logging_steps": 500,
|
| 1018 |
+
"max_steps": 33150,
|
| 1019 |
+
"num_input_tokens_seen": 0,
|
| 1020 |
+
"num_train_epochs": 150,
|
| 1021 |
+
"save_steps": 500,
|
| 1022 |
+
"stateful_callbacks": {
|
| 1023 |
+
"EarlyStoppingCallback": {
|
| 1024 |
+
"args": {
|
| 1025 |
+
"early_stopping_patience": 10,
|
| 1026 |
+
"early_stopping_threshold": 0.0
|
| 1027 |
+
},
|
| 1028 |
+
"attributes": {
|
| 1029 |
+
"early_stopping_patience_counter": 0
|
| 1030 |
+
}
|
| 1031 |
+
},
|
| 1032 |
+
"TrainerControl": {
|
| 1033 |
+
"args": {
|
| 1034 |
+
"should_epoch_stop": false,
|
| 1035 |
+
"should_evaluate": false,
|
| 1036 |
+
"should_log": false,
|
| 1037 |
+
"should_save": true,
|
| 1038 |
+
"should_training_stop": true
|
| 1039 |
+
},
|
| 1040 |
+
"attributes": {}
|
| 1041 |
+
}
|
| 1042 |
+
},
|
| 1043 |
+
"total_flos": 9.42369297866869e+19,
|
| 1044 |
+
"train_batch_size": 64,
|
| 1045 |
+
"trial_name": null,
|
| 1046 |
+
"trial_params": null
|
| 1047 |
+
}
|