Commit
•
3ea82a1
1
Parent(s):
eac6183
Evaluation on the test set completed on 2024_11_14.
Browse files- README.md +104 -152
- all_results.json +13 -13
- logs/events.out.tfevents.1731607061.datavisu2 +2 -2
- logs/events.out.tfevents.1731624072.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +9 -9
- train_results.json +5 -5
- trainer_state.json +681 -681
README.md
CHANGED
|
@@ -1,172 +1,124 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
-
|
| 4 |
-
-
|
| 5 |
-
license: cc0-1.0
|
| 6 |
tags:
|
| 7 |
-
- multilabel-image-classification
|
| 8 |
-
- multilabel
|
| 9 |
- generated_from_trainer
|
| 10 |
-
base_model: drone-DinoVdeau-from-binary-large-2024_11_14-batch-size16_freeze_probs
|
| 11 |
model-index:
|
| 12 |
- name: drone-DinoVdeau-from-binary-large-2024_11_14-batch-size16_freeze_probs
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
- Loss: 0.4693
|
| 20 |
-
- F1 Micro: 0.0000
|
| 21 |
-
- F1 Macro: 0.0000
|
| 22 |
-
- Accuracy: 0.0000
|
| 23 |
-
- RMSE: 0.1576
|
| 24 |
-
- MAE: 0.1172
|
| 25 |
-
- KL Divergence: 0.4185
|
| 26 |
-
|
| 27 |
-
---
|
| 28 |
|
| 29 |
-
#
|
| 30 |
-
drone-DinoVdeau-from-binary is a model built on top of drone-DinoVdeau-from-binary-large-2024_11_14-batch-size16_freeze_probs model for underwater multilabel image classification.The classification head is a combination of linear, ReLU, batch normalization, and dropout layers.
|
| 31 |
|
| 32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
-
|
| 35 |
|
| 36 |
-
|
| 37 |
|
| 38 |
-
|
| 39 |
-
You can use the raw model for classify diverse marine species, encompassing coral morphotypes classes taken from the Global Coral Reef Monitoring Network (GCRMN), habitats classes and seagrass species.
|
| 40 |
|
| 41 |
-
|
| 42 |
|
| 43 |
-
|
| 44 |
-
Details on the estimated number of images for each class are given in the following table:
|
| 45 |
-
| Class | train | test | val | Total |
|
| 46 |
-
|:------------------------|--------:|-------:|------:|--------:|
|
| 47 |
-
| Acropore_branched | 1220 | 363 | 362 | 1945 |
|
| 48 |
-
| Acropore_digitised | 586 | 195 | 189 | 970 |
|
| 49 |
-
| Acropore_tabular | 308 | 133 | 119 | 560 |
|
| 50 |
-
| Algae | 4777 | 1372 | 1384 | 7533 |
|
| 51 |
-
| Dead_coral | 2513 | 671 | 693 | 3877 |
|
| 52 |
-
| Millepore | 136 | 55 | 59 | 250 |
|
| 53 |
-
| No_acropore_encrusting | 252 | 88 | 93 | 433 |
|
| 54 |
-
| No_acropore_massive | 2158 | 725 | 726 | 3609 |
|
| 55 |
-
| No_acropore_sub_massive | 2036 | 582 | 612 | 3230 |
|
| 56 |
-
| Rock | 5976 | 1941 | 1928 | 9845 |
|
| 57 |
-
| Rubble | 4851 | 1486 | 1474 | 7811 |
|
| 58 |
-
| Sand | 6155 | 2019 | 1990 | 10164 |
|
| 59 |
|
| 60 |
-
|
| 61 |
|
| 62 |
-
|
| 63 |
|
| 64 |
-
|
| 65 |
|
| 66 |
The following hyperparameters were used during training:
|
| 67 |
-
|
| 68 |
-
-
|
| 69 |
-
-
|
| 70 |
-
-
|
| 71 |
-
-
|
| 72 |
-
-
|
| 73 |
-
-
|
| 74 |
-
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
51 | 0.46691644191741943 | 0.1181 | 0.1591 | 0.3955 | 1.0000000000000002e-06
|
| 151 |
-
52 | 0.466439425945282 | 0.1175 | 0.1588 | 0.4761 | 1.0000000000000002e-06
|
| 152 |
-
53 | 0.4667709469795227 | 0.1189 | 0.1590 | 0.4327 | 1.0000000000000002e-06
|
| 153 |
-
54 | 0.46701404452323914 | 0.1187 | 0.1592 | 0.3725 | 1.0000000000000002e-06
|
| 154 |
-
55 | 0.467383474111557 | 0.1199 | 0.1595 | 0.3841 | 1.0000000000000002e-06
|
| 155 |
-
56 | 0.46739572286605835 | 0.1190 | 0.1596 | 0.3822 | 1.0000000000000002e-06
|
| 156 |
-
57 | 0.46702033281326294 | 0.1186 | 0.1593 | 0.4675 | 1.0000000000000002e-06
|
| 157 |
-
58 | 0.46735846996307373 | 0.1189 | 0.1596 | 0.3738 | 1.0000000000000002e-06
|
| 158 |
-
59 | 0.46666717529296875 | 0.1185 | 0.1589 | 0.4204 | 1.0000000000000002e-07
|
| 159 |
-
60 | 0.46685320138931274 | 0.1178 | 0.1592 | 0.4532 | 1.0000000000000002e-07
|
| 160 |
-
61 | 0.46734780073165894 | 0.1189 | 0.1596 | 0.4032 | 1.0000000000000002e-07
|
| 161 |
-
62 | 0.4673011302947998 | 0.1189 | 0.1595 | 0.3407 | 1.0000000000000002e-07
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
---
|
| 165 |
-
|
| 166 |
-
# Framework Versions
|
| 167 |
-
|
| 168 |
-
- **Transformers**: 4.41.0
|
| 169 |
-
- **Pytorch**: 2.5.0+cu124
|
| 170 |
-
- **Datasets**: 3.0.2
|
| 171 |
-
- **Tokenizers**: 0.19.1
|
| 172 |
-
|
|
|
|
|
|
|
| 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-binary-large-2024_11_14-batch-size16_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-binary-large-2024_11_14-batch-size16_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: 0.4061
|
| 19 |
+
- Rmse: 0.2019
|
| 20 |
+
- Mae: 0.1446
|
| 21 |
+
- Kl Divergence: 0.9802
|
| 22 |
+
- Explained Variance: 0.3860
|
| 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: 16
|
| 44 |
+
- eval_batch_size: 16
|
| 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 | 438 | 0.4306 | 0.2210 | 0.1621 | 1.0069 | 0.2882 | 0.001 |
|
| 56 |
+
| 0.4808 | 2.0 | 876 | 0.4246 | 0.2179 | 0.1547 | 1.3119 | 0.3118 | 0.001 |
|
| 57 |
+
| 0.421 | 3.0 | 1314 | 0.4223 | 0.2158 | 0.1554 | 1.0982 | 0.3192 | 0.001 |
|
| 58 |
+
| 0.4151 | 4.0 | 1752 | 0.4191 | 0.2142 | 0.1552 | 1.0414 | 0.3351 | 0.001 |
|
| 59 |
+
| 0.4114 | 5.0 | 2190 | 0.4171 | 0.2123 | 0.1541 | 1.0698 | 0.3384 | 0.001 |
|
| 60 |
+
| 0.4089 | 6.0 | 2628 | 0.4209 | 0.2140 | 0.1520 | 1.1959 | 0.3311 | 0.001 |
|
| 61 |
+
| 0.4091 | 7.0 | 3066 | 0.4166 | 0.2126 | 0.1530 | 1.1709 | 0.3382 | 0.001 |
|
| 62 |
+
| 0.4071 | 8.0 | 3504 | 0.4195 | 0.2143 | 0.1556 | 0.9712 | 0.3346 | 0.001 |
|
| 63 |
+
| 0.4071 | 9.0 | 3942 | 0.4167 | 0.2121 | 0.1524 | 1.1432 | 0.3415 | 0.001 |
|
| 64 |
+
| 0.4062 | 10.0 | 4380 | 0.4186 | 0.2139 | 0.1535 | 0.9121 | 0.3420 | 0.001 |
|
| 65 |
+
| 0.4052 | 11.0 | 4818 | 0.4156 | 0.2114 | 0.1536 | 0.9950 | 0.3442 | 0.001 |
|
| 66 |
+
| 0.406 | 12.0 | 5256 | 0.4188 | 0.2139 | 0.1555 | 1.0106 | 0.3390 | 0.001 |
|
| 67 |
+
| 0.4058 | 13.0 | 5694 | 0.4163 | 0.2121 | 0.1553 | 1.1482 | 0.3425 | 0.001 |
|
| 68 |
+
| 0.4056 | 14.0 | 6132 | 0.4193 | 0.2138 | 0.1546 | 1.2111 | 0.3286 | 0.001 |
|
| 69 |
+
| 0.4033 | 15.0 | 6570 | 0.4162 | 0.2121 | 0.1542 | 1.2043 | 0.3402 | 0.001 |
|
| 70 |
+
| 0.4057 | 16.0 | 7008 | 0.4139 | 0.2102 | 0.1528 | 1.0828 | 0.3500 | 0.001 |
|
| 71 |
+
| 0.4057 | 17.0 | 7446 | 0.4171 | 0.2118 | 0.1564 | 1.0006 | 0.3430 | 0.001 |
|
| 72 |
+
| 0.405 | 18.0 | 7884 | 0.4146 | 0.2107 | 0.1507 | 1.0514 | 0.3499 | 0.001 |
|
| 73 |
+
| 0.4035 | 19.0 | 8322 | 0.4186 | 0.2114 | 0.1532 | 0.9575 | 0.3468 | 0.001 |
|
| 74 |
+
| 0.4031 | 20.0 | 8760 | 0.4143 | 0.2108 | 0.1513 | 1.1648 | 0.3487 | 0.001 |
|
| 75 |
+
| 0.4048 | 21.0 | 9198 | 0.4195 | 0.2123 | 0.1533 | 1.2950 | 0.3385 | 0.001 |
|
| 76 |
+
| 0.4055 | 22.0 | 9636 | 0.4340 | 0.2110 | 0.1524 | inf | 0.3463 | 0.001 |
|
| 77 |
+
| 0.4022 | 23.0 | 10074 | 0.4327 | 0.2085 | 0.1517 | nan | 0.3621 | 0.0001 |
|
| 78 |
+
| 0.3978 | 24.0 | 10512 | 0.4385 | 0.2092 | 0.1493 | nan | 0.3583 | 0.0001 |
|
| 79 |
+
| 0.3978 | 25.0 | 10950 | 0.4272 | 0.2074 | 0.1490 | inf | 0.3649 | 0.0001 |
|
| 80 |
+
| 0.3988 | 26.0 | 11388 | 0.4105 | 0.2075 | 0.1480 | 1.1903 | 0.3644 | 0.0001 |
|
| 81 |
+
| 0.3958 | 27.0 | 11826 | 0.4096 | 0.2067 | 0.1494 | 0.9915 | 0.3688 | 0.0001 |
|
| 82 |
+
| 0.3965 | 28.0 | 12264 | 0.4104 | 0.2075 | 0.1493 | 0.9669 | 0.3681 | 0.0001 |
|
| 83 |
+
| 0.396 | 29.0 | 12702 | 0.4097 | 0.2069 | 0.1469 | 1.0433 | 0.3696 | 0.0001 |
|
| 84 |
+
| 0.3936 | 30.0 | 13140 | 0.4094 | 0.2065 | 0.1490 | 0.9082 | 0.3731 | 0.0001 |
|
| 85 |
+
| 0.3944 | 31.0 | 13578 | 0.4091 | 0.2065 | 0.1470 | 1.0120 | 0.3705 | 0.0001 |
|
| 86 |
+
| 0.3941 | 32.0 | 14016 | 0.4084 | 0.2060 | 0.1483 | 0.9708 | 0.3742 | 0.0001 |
|
| 87 |
+
| 0.3941 | 33.0 | 14454 | 0.4082 | 0.2057 | 0.1474 | 0.9317 | 0.3755 | 0.0001 |
|
| 88 |
+
| 0.3933 | 34.0 | 14892 | 0.4085 | 0.2061 | 0.1481 | 0.9619 | 0.3747 | 0.0001 |
|
| 89 |
+
| 0.3926 | 35.0 | 15330 | 0.4073 | 0.2054 | 0.1466 | 1.0523 | 0.3758 | 0.0001 |
|
| 90 |
+
| 0.3936 | 36.0 | 15768 | 0.4074 | 0.2052 | 0.1460 | 1.0622 | 0.3771 | 0.0001 |
|
| 91 |
+
| 0.3935 | 37.0 | 16206 | 0.4066 | 0.2047 | 0.1456 | 1.0201 | 0.3802 | 0.0001 |
|
| 92 |
+
| 0.3927 | 38.0 | 16644 | 0.4064 | 0.2045 | 0.1459 | 1.0557 | 0.3800 | 0.0001 |
|
| 93 |
+
| 0.392 | 39.0 | 17082 | 0.4078 | 0.2056 | 0.1469 | 1.0055 | 0.3771 | 0.0001 |
|
| 94 |
+
| 0.3915 | 40.0 | 17520 | 0.4068 | 0.2049 | 0.1464 | 0.9849 | 0.3805 | 0.0001 |
|
| 95 |
+
| 0.3915 | 41.0 | 17958 | 0.4089 | 0.2063 | 0.1489 | 0.8999 | 0.3778 | 0.0001 |
|
| 96 |
+
| 0.3907 | 42.0 | 18396 | 0.4069 | 0.2049 | 0.1463 | 1.0617 | 0.3797 | 0.0001 |
|
| 97 |
+
| 0.3919 | 43.0 | 18834 | 0.4058 | 0.2041 | 0.1450 | 1.0520 | 0.3830 | 0.0001 |
|
| 98 |
+
| 0.3902 | 44.0 | 19272 | 0.4071 | 0.2050 | 0.1475 | 1.0054 | 0.3809 | 0.0001 |
|
| 99 |
+
| 0.3896 | 45.0 | 19710 | 0.4067 | 0.2047 | 0.1440 | 1.1386 | 0.3813 | 0.0001 |
|
| 100 |
+
| 0.3925 | 46.0 | 20148 | 0.4067 | 0.2047 | 0.1457 | 1.0253 | 0.3831 | 0.0001 |
|
| 101 |
+
| 0.3896 | 47.0 | 20586 | 0.4062 | 0.2043 | 0.1473 | 1.0430 | 0.3834 | 0.0001 |
|
| 102 |
+
| 0.3902 | 48.0 | 21024 | 0.4065 | 0.2048 | 0.1457 | 1.1041 | 0.3812 | 0.0001 |
|
| 103 |
+
| 0.3902 | 49.0 | 21462 | 0.4071 | 0.2052 | 0.1463 | 1.0702 | 0.3798 | 0.0001 |
|
| 104 |
+
| 0.3897 | 50.0 | 21900 | 0.4064 | 0.2042 | 0.1479 | 0.8917 | 0.3857 | 1e-05 |
|
| 105 |
+
| 0.3875 | 51.0 | 22338 | 0.4058 | 0.2041 | 0.1437 | 0.9960 | 0.3845 | 1e-05 |
|
| 106 |
+
| 0.3874 | 52.0 | 22776 | 0.4053 | 0.2037 | 0.1446 | 1.0567 | 0.3851 | 1e-05 |
|
| 107 |
+
| 0.3899 | 53.0 | 23214 | 0.4056 | 0.2039 | 0.1462 | 1.0205 | 0.3859 | 1e-05 |
|
| 108 |
+
| 0.3892 | 54.0 | 23652 | 0.4059 | 0.2041 | 0.1441 | 0.9905 | 0.3854 | 1e-05 |
|
| 109 |
+
| 0.3892 | 55.0 | 24090 | 0.4061 | 0.2041 | 0.1471 | 0.9379 | 0.3856 | 1e-05 |
|
| 110 |
+
| 0.3869 | 56.0 | 24528 | 0.4059 | 0.2041 | 0.1454 | 0.9696 | 0.3854 | 1e-05 |
|
| 111 |
+
| 0.3869 | 57.0 | 24966 | 0.4058 | 0.2041 | 0.1460 | 1.0591 | 0.3842 | 1e-05 |
|
| 112 |
+
| 0.3874 | 58.0 | 25404 | 0.4063 | 0.2043 | 0.1460 | 0.9276 | 0.3860 | 1e-05 |
|
| 113 |
+
| 0.3887 | 59.0 | 25842 | 0.4056 | 0.2038 | 0.1453 | 0.9794 | 0.3868 | 0.0000 |
|
| 114 |
+
| 0.3882 | 60.0 | 26280 | 0.4057 | 0.2040 | 0.1446 | 1.0349 | 0.3851 | 0.0000 |
|
| 115 |
+
| 0.389 | 61.0 | 26718 | 0.4058 | 0.2041 | 0.1449 | 0.9860 | 0.3857 | 0.0000 |
|
| 116 |
+
| 0.3882 | 62.0 | 27156 | 0.4054 | 0.2037 | 0.1446 | 0.9528 | 0.3865 | 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
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 62.0,
|
| 3 |
-
"eval_explained_variance": 0.
|
| 4 |
-
"eval_kl_divergence": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_mae": 0.
|
| 7 |
-
"eval_rmse": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 2.
|
| 11 |
-
"learning_rate": 1.0000000000000002e-
|
| 12 |
"total_flos": 6.42634409963284e+19,
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
-
"train_samples_per_second":
|
| 16 |
-
"train_steps_per_second": 3.
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 62.0,
|
| 3 |
+
"eval_explained_variance": 0.38597723841667175,
|
| 4 |
+
"eval_kl_divergence": 0.9802031517028809,
|
| 5 |
+
"eval_loss": 0.40605100989341736,
|
| 6 |
+
"eval_mae": 0.1445874720811844,
|
| 7 |
+
"eval_rmse": 0.2018682211637497,
|
| 8 |
+
"eval_runtime": 61.1056,
|
| 9 |
+
"eval_samples_per_second": 38.573,
|
| 10 |
+
"eval_steps_per_second": 2.422,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 12 |
"total_flos": 6.42634409963284e+19,
|
| 13 |
+
"train_loss": 0.3985773164651095,
|
| 14 |
+
"train_runtime": 16834.9641,
|
| 15 |
+
"train_samples_per_second": 62.397,
|
| 16 |
+
"train_steps_per_second": 3.903
|
| 17 |
}
|
logs/events.out.tfevents.1731607061.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 sha256:6b78d17ccbe193fb3e7efa694c7335abe32b4b424175235d19d34a204ae5784c
|
| 3 |
+
size 52031
|
logs/events.out.tfevents.1731624072.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9a76e82fce26948e90638211553f83c99a8ff5929731754be2434210688e4f
|
| 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 sha256:25b4e914eff7c60cd1a3ff535322cf77a16ee8e82564b50a87aafed111ab96d8
|
| 3 |
size 1222956704
|
test_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 62.0,
|
| 3 |
-
"eval_explained_variance": 0.
|
| 4 |
-
"eval_kl_divergence": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_mae": 0.
|
| 7 |
-
"eval_rmse": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 2.
|
| 11 |
-
"learning_rate": 1.0000000000000002e-
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 62.0,
|
| 3 |
+
"eval_explained_variance": 0.38597723841667175,
|
| 4 |
+
"eval_kl_divergence": 0.9802031517028809,
|
| 5 |
+
"eval_loss": 0.40605100989341736,
|
| 6 |
+
"eval_mae": 0.1445874720811844,
|
| 7 |
+
"eval_rmse": 0.2018682211637497,
|
| 8 |
+
"eval_runtime": 61.1056,
|
| 9 |
+
"eval_samples_per_second": 38.573,
|
| 10 |
+
"eval_steps_per_second": 2.422,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06
|
| 12 |
}
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 62.0,
|
| 3 |
-
"learning_rate": 1.0000000000000002e-
|
| 4 |
"total_flos": 6.42634409963284e+19,
|
| 5 |
-
"train_loss": 0.
|
| 6 |
-
"train_runtime":
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second": 3.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 62.0,
|
| 3 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 4 |
"total_flos": 6.42634409963284e+19,
|
| 5 |
+
"train_loss": 0.3985773164651095,
|
| 6 |
+
"train_runtime": 16834.9641,
|
| 7 |
+
"train_samples_per_second": 62.397,
|
| 8 |
+
"train_steps_per_second": 3.903
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/drone/drone-DinoVdeau-from-binary-large-2024_11_14-batch-size16_freeze_probs/checkpoint-22776",
|
| 4 |
"epoch": 62.0,
|
| 5 |
"eval_steps": 500,
|
|
@@ -10,1197 +10,1197 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_explained_variance": 0.
|
| 14 |
-
"eval_kl_divergence":
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_mae": 0.
|
| 17 |
-
"eval_rmse": 0.
|
| 18 |
-
"eval_runtime":
|
| 19 |
-
"eval_samples_per_second": 36.
|
| 20 |
-
"eval_steps_per_second": 2.
|
| 21 |
"learning_rate": 0.001,
|
| 22 |
"step": 438
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"epoch": 1.1415525114155252,
|
| 26 |
-
"grad_norm": 0.
|
| 27 |
"learning_rate": 0.001,
|
| 28 |
-
"loss": 0.
|
| 29 |
"step": 500
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
-
"eval_explained_variance": 0.
|
| 34 |
-
"eval_kl_divergence":
|
| 35 |
-
"eval_loss": 0.
|
| 36 |
-
"eval_mae": 0.
|
| 37 |
-
"eval_rmse": 0.
|
| 38 |
-
"eval_runtime":
|
| 39 |
-
"eval_samples_per_second":
|
| 40 |
-
"eval_steps_per_second": 2.
|
| 41 |
"learning_rate": 0.001,
|
| 42 |
"step": 876
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 2.2831050228310503,
|
| 46 |
-
"grad_norm": 0.
|
| 47 |
"learning_rate": 0.001,
|
| 48 |
-
"loss": 0.
|
| 49 |
"step": 1000
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 3.0,
|
| 53 |
-
"eval_explained_variance": 0.
|
| 54 |
-
"eval_kl_divergence":
|
| 55 |
-
"eval_loss": 0.
|
| 56 |
-
"eval_mae": 0.
|
| 57 |
-
"eval_rmse": 0.
|
| 58 |
-
"eval_runtime":
|
| 59 |
-
"eval_samples_per_second": 37.
|
| 60 |
-
"eval_steps_per_second": 2.
|
| 61 |
"learning_rate": 0.001,
|
| 62 |
"step": 1314
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 3.4246575342465753,
|
| 66 |
-
"grad_norm": 0.
|
| 67 |
"learning_rate": 0.001,
|
| 68 |
-
"loss": 0.
|
| 69 |
"step": 1500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 4.0,
|
| 73 |
-
"eval_explained_variance": 0.
|
| 74 |
-
"eval_kl_divergence":
|
| 75 |
-
"eval_loss": 0.
|
| 76 |
-
"eval_mae": 0.
|
| 77 |
-
"eval_rmse": 0.
|
| 78 |
-
"eval_runtime":
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second": 2.
|
| 81 |
"learning_rate": 0.001,
|
| 82 |
"step": 1752
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 4.566210045662101,
|
| 86 |
-
"grad_norm": 0.
|
| 87 |
"learning_rate": 0.001,
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 2000
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 5.0,
|
| 93 |
-
"eval_explained_variance": 0.
|
| 94 |
-
"eval_kl_divergence":
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_mae": 0.
|
| 97 |
-
"eval_rmse": 0.
|
| 98 |
-
"eval_runtime":
|
| 99 |
-
"eval_samples_per_second":
|
| 100 |
-
"eval_steps_per_second": 2.
|
| 101 |
"learning_rate": 0.001,
|
| 102 |
"step": 2190
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 5.707762557077626,
|
| 106 |
-
"grad_norm": 0.
|
| 107 |
"learning_rate": 0.001,
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 2500
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 6.0,
|
| 113 |
-
"eval_explained_variance": 0.
|
| 114 |
-
"eval_kl_divergence":
|
| 115 |
-
"eval_loss": 0.
|
| 116 |
-
"eval_mae": 0.
|
| 117 |
-
"eval_rmse": 0.
|
| 118 |
-
"eval_runtime":
|
| 119 |
-
"eval_samples_per_second":
|
| 120 |
-
"eval_steps_per_second": 2.
|
| 121 |
"learning_rate": 0.001,
|
| 122 |
"step": 2628
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 6.8493150684931505,
|
| 126 |
-
"grad_norm": 0.
|
| 127 |
"learning_rate": 0.001,
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 3000
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 7.0,
|
| 133 |
-
"eval_explained_variance": 0.
|
| 134 |
-
"eval_kl_divergence":
|
| 135 |
-
"eval_loss": 0.
|
| 136 |
-
"eval_mae": 0.
|
| 137 |
-
"eval_rmse": 0.
|
| 138 |
-
"eval_runtime":
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second": 2.
|
| 141 |
"learning_rate": 0.001,
|
| 142 |
"step": 3066
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 7.9908675799086755,
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
"learning_rate": 0.001,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 3500
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 8.0,
|
| 153 |
-
"eval_explained_variance": 0.
|
| 154 |
-
"eval_kl_divergence": 0.
|
| 155 |
-
"eval_loss": 0.
|
| 156 |
-
"eval_mae": 0.
|
| 157 |
-
"eval_rmse": 0.
|
| 158 |
-
"eval_runtime":
|
| 159 |
-
"eval_samples_per_second":
|
| 160 |
-
"eval_steps_per_second": 2.
|
| 161 |
"learning_rate": 0.001,
|
| 162 |
"step": 3504
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 9.0,
|
| 166 |
-
"eval_explained_variance": 0.
|
| 167 |
-
"eval_kl_divergence":
|
| 168 |
-
"eval_loss": 0.
|
| 169 |
-
"eval_mae": 0.
|
| 170 |
-
"eval_rmse": 0.
|
| 171 |
-
"eval_runtime":
|
| 172 |
-
"eval_samples_per_second":
|
| 173 |
-
"eval_steps_per_second": 2.
|
| 174 |
"learning_rate": 0.001,
|
| 175 |
"step": 3942
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"epoch": 9.132420091324201,
|
| 179 |
-
"grad_norm": 0.
|
| 180 |
"learning_rate": 0.001,
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 4000
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 10.0,
|
| 186 |
-
"eval_explained_variance": 0.
|
| 187 |
-
"eval_kl_divergence": 0.
|
| 188 |
-
"eval_loss": 0.
|
| 189 |
-
"eval_mae": 0.
|
| 190 |
-
"eval_rmse": 0.
|
| 191 |
-
"eval_runtime":
|
| 192 |
-
"eval_samples_per_second":
|
| 193 |
-
"eval_steps_per_second": 2.
|
| 194 |
"learning_rate": 0.001,
|
| 195 |
"step": 4380
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 10.273972602739725,
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
"learning_rate": 0.001,
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 4500
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 11.0,
|
| 206 |
-
"eval_explained_variance": 0.
|
| 207 |
-
"eval_kl_divergence": 0.
|
| 208 |
-
"eval_loss": 0.
|
| 209 |
-
"eval_mae": 0.
|
| 210 |
-
"eval_rmse": 0.
|
| 211 |
-
"eval_runtime":
|
| 212 |
-
"eval_samples_per_second":
|
| 213 |
-
"eval_steps_per_second": 2.
|
| 214 |
"learning_rate": 0.001,
|
| 215 |
"step": 4818
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 11.415525114155251,
|
| 219 |
-
"grad_norm": 0.
|
| 220 |
"learning_rate": 0.001,
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 5000
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 12.0,
|
| 226 |
-
"eval_explained_variance": 0.
|
| 227 |
-
"eval_kl_divergence":
|
| 228 |
-
"eval_loss": 0.
|
| 229 |
-
"eval_mae": 0.
|
| 230 |
-
"eval_rmse": 0.
|
| 231 |
-
"eval_runtime": 62.
|
| 232 |
-
"eval_samples_per_second": 37.
|
| 233 |
-
"eval_steps_per_second": 2.
|
| 234 |
"learning_rate": 0.001,
|
| 235 |
"step": 5256
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 12.557077625570777,
|
| 239 |
-
"grad_norm": 0.
|
| 240 |
"learning_rate": 0.001,
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 5500
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 13.0,
|
| 246 |
-
"eval_explained_variance": 0.
|
| 247 |
-
"eval_kl_divergence":
|
| 248 |
-
"eval_loss": 0.
|
| 249 |
-
"eval_mae": 0.
|
| 250 |
-
"eval_rmse": 0.
|
| 251 |
-
"eval_runtime":
|
| 252 |
-
"eval_samples_per_second":
|
| 253 |
-
"eval_steps_per_second": 2.
|
| 254 |
"learning_rate": 0.001,
|
| 255 |
"step": 5694
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 13.698630136986301,
|
| 259 |
-
"grad_norm": 0.
|
| 260 |
"learning_rate": 0.001,
|
| 261 |
-
"loss": 0.
|
| 262 |
"step": 6000
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 14.0,
|
| 266 |
-
"eval_explained_variance": 0.
|
| 267 |
-
"eval_kl_divergence":
|
| 268 |
-
"eval_loss": 0.
|
| 269 |
-
"eval_mae": 0.
|
| 270 |
-
"eval_rmse": 0.
|
| 271 |
-
"eval_runtime": 62.
|
| 272 |
-
"eval_samples_per_second": 37.
|
| 273 |
-
"eval_steps_per_second": 2.
|
| 274 |
"learning_rate": 0.001,
|
| 275 |
"step": 6132
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 14.840182648401827,
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
"learning_rate": 0.001,
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 6500
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 15.0,
|
| 286 |
-
"eval_explained_variance": 0.
|
| 287 |
-
"eval_kl_divergence":
|
| 288 |
-
"eval_loss": 0.
|
| 289 |
-
"eval_mae": 0.
|
| 290 |
-
"eval_rmse": 0.
|
| 291 |
-
"eval_runtime":
|
| 292 |
-
"eval_samples_per_second":
|
| 293 |
-
"eval_steps_per_second": 2.
|
| 294 |
"learning_rate": 0.001,
|
| 295 |
"step": 6570
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 15.981735159817351,
|
| 299 |
-
"grad_norm": 0.
|
| 300 |
-
"learning_rate": 0.
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 7000
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 16.0,
|
| 306 |
-
"eval_explained_variance": 0.
|
| 307 |
-
"eval_kl_divergence":
|
| 308 |
-
"eval_loss": 0.
|
| 309 |
-
"eval_mae": 0.
|
| 310 |
-
"eval_rmse": 0.
|
| 311 |
-
"eval_runtime":
|
| 312 |
-
"eval_samples_per_second":
|
| 313 |
-
"eval_steps_per_second": 2.
|
| 314 |
-
"learning_rate": 0.
|
| 315 |
"step": 7008
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 17.0,
|
| 319 |
-
"eval_explained_variance": 0.
|
| 320 |
-
"eval_kl_divergence":
|
| 321 |
-
"eval_loss": 0.
|
| 322 |
-
"eval_mae": 0.
|
| 323 |
-
"eval_rmse": 0.
|
| 324 |
-
"eval_runtime":
|
| 325 |
-
"eval_samples_per_second":
|
| 326 |
-
"eval_steps_per_second": 2.
|
| 327 |
-
"learning_rate": 0.
|
| 328 |
"step": 7446
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 17.123287671232877,
|
| 332 |
-
"grad_norm": 0.
|
| 333 |
-
"learning_rate": 0.
|
| 334 |
-
"loss": 0.
|
| 335 |
"step": 7500
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 18.0,
|
| 339 |
-
"eval_explained_variance": 0.
|
| 340 |
-
"eval_kl_divergence":
|
| 341 |
-
"eval_loss": 0.
|
| 342 |
-
"eval_mae": 0.
|
| 343 |
-
"eval_rmse": 0.
|
| 344 |
-
"eval_runtime":
|
| 345 |
-
"eval_samples_per_second":
|
| 346 |
-
"eval_steps_per_second": 2.
|
| 347 |
-
"learning_rate": 0.
|
| 348 |
"step": 7884
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 18.264840182648403,
|
| 352 |
-
"grad_norm": 0.
|
| 353 |
-
"learning_rate": 0.
|
| 354 |
-
"loss": 0.
|
| 355 |
"step": 8000
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 19.0,
|
| 359 |
-
"eval_explained_variance": 0.
|
| 360 |
-
"eval_kl_divergence": 0.
|
| 361 |
-
"eval_loss": 0.
|
| 362 |
-
"eval_mae": 0.
|
| 363 |
-
"eval_rmse": 0.
|
| 364 |
-
"eval_runtime":
|
| 365 |
-
"eval_samples_per_second":
|
| 366 |
-
"eval_steps_per_second": 2.
|
| 367 |
-
"learning_rate": 0.
|
| 368 |
"step": 8322
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 19.40639269406393,
|
| 372 |
-
"grad_norm": 0.
|
| 373 |
-
"learning_rate": 0.
|
| 374 |
-
"loss": 0.
|
| 375 |
"step": 8500
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 20.0,
|
| 379 |
-
"eval_explained_variance": 0.
|
| 380 |
-
"eval_kl_divergence":
|
| 381 |
-
"eval_loss": 0.
|
| 382 |
-
"eval_mae": 0.
|
| 383 |
-
"eval_rmse": 0.
|
| 384 |
-
"eval_runtime":
|
| 385 |
-
"eval_samples_per_second":
|
| 386 |
-
"eval_steps_per_second": 2.
|
| 387 |
-
"learning_rate": 0.
|
| 388 |
"step": 8760
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 20.54794520547945,
|
| 392 |
-
"grad_norm": 0.
|
| 393 |
-
"learning_rate": 0.
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 9000
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 21.0,
|
| 399 |
-
"eval_explained_variance": 0.
|
| 400 |
-
"eval_kl_divergence":
|
| 401 |
-
"eval_loss": 0.
|
| 402 |
-
"eval_mae": 0.
|
| 403 |
-
"eval_rmse": 0.
|
| 404 |
-
"eval_runtime": 62.
|
| 405 |
-
"eval_samples_per_second": 37.
|
| 406 |
-
"eval_steps_per_second": 2.
|
| 407 |
-
"learning_rate": 0.
|
| 408 |
"step": 9198
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 21.689497716894977,
|
| 412 |
-
"grad_norm": 0.
|
| 413 |
-
"learning_rate": 0.
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 9500
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 22.0,
|
| 419 |
-
"eval_explained_variance": 0.
|
| 420 |
-
"eval_kl_divergence":
|
| 421 |
-
"eval_loss": 0.
|
| 422 |
-
"eval_mae": 0.
|
| 423 |
-
"eval_rmse": 0.
|
| 424 |
-
"eval_runtime":
|
| 425 |
-
"eval_samples_per_second": 37.
|
| 426 |
-
"eval_steps_per_second": 2.
|
| 427 |
-
"learning_rate": 0.
|
| 428 |
"step": 9636
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 22.831050228310502,
|
| 432 |
-
"grad_norm": 0.
|
| 433 |
"learning_rate": 0.0001,
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 10000
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 23.0,
|
| 439 |
-
"eval_explained_variance": 0.
|
| 440 |
-
"eval_kl_divergence":
|
| 441 |
-
"eval_loss": 0.
|
| 442 |
-
"eval_mae": 0.
|
| 443 |
-
"eval_rmse": 0.
|
| 444 |
-
"eval_runtime": 61.
|
| 445 |
-
"eval_samples_per_second": 38.
|
| 446 |
-
"eval_steps_per_second": 2.
|
| 447 |
"learning_rate": 0.0001,
|
| 448 |
"step": 10074
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 23.972602739726028,
|
| 452 |
-
"grad_norm": 0.
|
| 453 |
"learning_rate": 0.0001,
|
| 454 |
-
"loss": 0.
|
| 455 |
"step": 10500
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 24.0,
|
| 459 |
-
"eval_explained_variance": 0.
|
| 460 |
-
"eval_kl_divergence":
|
| 461 |
-
"eval_loss": 0.
|
| 462 |
-
"eval_mae": 0.
|
| 463 |
-
"eval_rmse": 0.
|
| 464 |
-
"eval_runtime": 62.
|
| 465 |
-
"eval_samples_per_second": 37.
|
| 466 |
-
"eval_steps_per_second": 2.
|
| 467 |
"learning_rate": 0.0001,
|
| 468 |
"step": 10512
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 25.0,
|
| 472 |
-
"eval_explained_variance": 0.
|
| 473 |
-
"eval_kl_divergence":
|
| 474 |
-
"eval_loss": 0.
|
| 475 |
-
"eval_mae": 0.
|
| 476 |
-
"eval_rmse": 0.
|
| 477 |
-
"eval_runtime":
|
| 478 |
-
"eval_samples_per_second":
|
| 479 |
-
"eval_steps_per_second": 2.
|
| 480 |
"learning_rate": 0.0001,
|
| 481 |
"step": 10950
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"epoch": 25.114155251141554,
|
| 485 |
-
"grad_norm": 0.
|
| 486 |
"learning_rate": 0.0001,
|
| 487 |
-
"loss": 0.
|
| 488 |
"step": 11000
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 26.0,
|
| 492 |
-
"eval_explained_variance": 0.
|
| 493 |
-
"eval_kl_divergence":
|
| 494 |
-
"eval_loss": 0.
|
| 495 |
-
"eval_mae": 0.
|
| 496 |
-
"eval_rmse": 0.
|
| 497 |
-
"eval_runtime":
|
| 498 |
-
"eval_samples_per_second": 37.
|
| 499 |
-
"eval_steps_per_second": 2.
|
| 500 |
"learning_rate": 0.0001,
|
| 501 |
"step": 11388
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 26.255707762557076,
|
| 505 |
-
"grad_norm": 0.
|
| 506 |
"learning_rate": 0.0001,
|
| 507 |
-
"loss": 0.
|
| 508 |
"step": 11500
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 27.0,
|
| 512 |
-
"eval_explained_variance": 0.
|
| 513 |
-
"eval_kl_divergence": 0.
|
| 514 |
-
"eval_loss": 0.
|
| 515 |
-
"eval_mae": 0.
|
| 516 |
-
"eval_rmse": 0.
|
| 517 |
-
"eval_runtime":
|
| 518 |
-
"eval_samples_per_second":
|
| 519 |
-
"eval_steps_per_second": 2.
|
| 520 |
"learning_rate": 0.0001,
|
| 521 |
"step": 11826
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 27.397260273972602,
|
| 525 |
-
"grad_norm": 0.
|
| 526 |
"learning_rate": 0.0001,
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 12000
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 28.0,
|
| 532 |
-
"eval_explained_variance": 0.
|
| 533 |
-
"eval_kl_divergence": 0.
|
| 534 |
-
"eval_loss": 0.
|
| 535 |
-
"eval_mae": 0.
|
| 536 |
-
"eval_rmse": 0.
|
| 537 |
-
"eval_runtime":
|
| 538 |
-
"eval_samples_per_second":
|
| 539 |
-
"eval_steps_per_second": 2.
|
| 540 |
"learning_rate": 0.0001,
|
| 541 |
"step": 12264
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 28.538812785388128,
|
| 545 |
-
"grad_norm": 0.
|
| 546 |
"learning_rate": 0.0001,
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 12500
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 29.0,
|
| 552 |
-
"eval_explained_variance": 0.
|
| 553 |
-
"eval_kl_divergence":
|
| 554 |
-
"eval_loss": 0.
|
| 555 |
-
"eval_mae": 0.
|
| 556 |
-
"eval_rmse": 0.
|
| 557 |
-
"eval_runtime":
|
| 558 |
-
"eval_samples_per_second":
|
| 559 |
-
"eval_steps_per_second": 2.
|
| 560 |
"learning_rate": 0.0001,
|
| 561 |
"step": 12702
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 29.680365296803654,
|
| 565 |
-
"grad_norm": 0.
|
| 566 |
"learning_rate": 0.0001,
|
| 567 |
-
"loss": 0.
|
| 568 |
"step": 13000
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 30.0,
|
| 572 |
-
"eval_explained_variance": 0.
|
| 573 |
-
"eval_kl_divergence": 0.
|
| 574 |
-
"eval_loss": 0.
|
| 575 |
-
"eval_mae": 0.
|
| 576 |
-
"eval_rmse": 0.
|
| 577 |
-
"eval_runtime": 62.
|
| 578 |
-
"eval_samples_per_second": 37.
|
| 579 |
-
"eval_steps_per_second": 2.
|
| 580 |
"learning_rate": 0.0001,
|
| 581 |
"step": 13140
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 30.82191780821918,
|
| 585 |
-
"grad_norm": 0.
|
| 586 |
"learning_rate": 0.0001,
|
| 587 |
-
"loss": 0.
|
| 588 |
"step": 13500
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 31.0,
|
| 592 |
-
"eval_explained_variance": 0.
|
| 593 |
-
"eval_kl_divergence":
|
| 594 |
-
"eval_loss": 0.
|
| 595 |
-
"eval_mae": 0.
|
| 596 |
-
"eval_rmse": 0.
|
| 597 |
-
"eval_runtime":
|
| 598 |
-
"eval_samples_per_second":
|
| 599 |
-
"eval_steps_per_second": 2.
|
| 600 |
"learning_rate": 0.0001,
|
| 601 |
"step": 13578
|
| 602 |
},
|
| 603 |
{
|
| 604 |
"epoch": 31.963470319634702,
|
| 605 |
-
"grad_norm": 0.
|
| 606 |
-
"learning_rate":
|
| 607 |
-
"loss": 0.
|
| 608 |
"step": 14000
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 32.0,
|
| 612 |
-
"eval_explained_variance": 0.
|
| 613 |
-
"eval_kl_divergence": 0.
|
| 614 |
-
"eval_loss": 0.
|
| 615 |
-
"eval_mae": 0.
|
| 616 |
-
"eval_rmse": 0.
|
| 617 |
-
"eval_runtime":
|
| 618 |
-
"eval_samples_per_second": 36.
|
| 619 |
-
"eval_steps_per_second": 2.
|
| 620 |
-
"learning_rate":
|
| 621 |
"step": 14016
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 33.0,
|
| 625 |
-
"eval_explained_variance": 0.
|
| 626 |
-
"eval_kl_divergence": 0.
|
| 627 |
-
"eval_loss": 0.
|
| 628 |
-
"eval_mae": 0.
|
| 629 |
-
"eval_rmse": 0.
|
| 630 |
-
"eval_runtime":
|
| 631 |
-
"eval_samples_per_second": 37.
|
| 632 |
-
"eval_steps_per_second": 2.
|
| 633 |
-
"learning_rate":
|
| 634 |
"step": 14454
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 33.10502283105023,
|
| 638 |
-
"grad_norm": 0.
|
| 639 |
-
"learning_rate":
|
| 640 |
-
"loss": 0.
|
| 641 |
"step": 14500
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 34.0,
|
| 645 |
-
"eval_explained_variance": 0.
|
| 646 |
-
"eval_kl_divergence": 0.
|
| 647 |
-
"eval_loss": 0.
|
| 648 |
-
"eval_mae": 0.
|
| 649 |
-
"eval_rmse": 0.
|
| 650 |
-
"eval_runtime":
|
| 651 |
-
"eval_samples_per_second":
|
| 652 |
-
"eval_steps_per_second": 2.
|
| 653 |
-
"learning_rate":
|
| 654 |
"step": 14892
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 34.24657534246575,
|
| 658 |
-
"grad_norm": 0.
|
| 659 |
-
"learning_rate":
|
| 660 |
-
"loss": 0.
|
| 661 |
"step": 15000
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 35.0,
|
| 665 |
-
"eval_explained_variance": 0.
|
| 666 |
-
"eval_kl_divergence":
|
| 667 |
-
"eval_loss": 0.
|
| 668 |
-
"eval_mae": 0.
|
| 669 |
-
"eval_rmse": 0.
|
| 670 |
-
"eval_runtime":
|
| 671 |
-
"eval_samples_per_second":
|
| 672 |
-
"eval_steps_per_second": 2.
|
| 673 |
-
"learning_rate":
|
| 674 |
"step": 15330
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 35.38812785388128,
|
| 678 |
-
"grad_norm": 0.
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 15500
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 36.0,
|
| 685 |
-
"eval_explained_variance": 0.
|
| 686 |
-
"eval_kl_divergence":
|
| 687 |
-
"eval_loss": 0.
|
| 688 |
-
"eval_mae": 0.
|
| 689 |
-
"eval_rmse": 0.
|
| 690 |
-
"eval_runtime": 64.
|
| 691 |
-
"eval_samples_per_second": 36.
|
| 692 |
-
"eval_steps_per_second": 2.
|
| 693 |
-
"learning_rate":
|
| 694 |
"step": 15768
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 36.529680365296805,
|
| 698 |
-
"grad_norm": 0.
|
| 699 |
-
"learning_rate":
|
| 700 |
-
"loss": 0.
|
| 701 |
"step": 16000
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 37.0,
|
| 705 |
-
"eval_explained_variance": 0.
|
| 706 |
-
"eval_kl_divergence":
|
| 707 |
-
"eval_loss": 0.
|
| 708 |
-
"eval_mae": 0.
|
| 709 |
-
"eval_rmse": 0.
|
| 710 |
-
"eval_runtime": 63.
|
| 711 |
-
"eval_samples_per_second":
|
| 712 |
-
"eval_steps_per_second": 2.
|
| 713 |
-
"learning_rate":
|
| 714 |
"step": 16206
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 37.67123287671233,
|
| 718 |
-
"grad_norm": 0.
|
| 719 |
-
"learning_rate":
|
| 720 |
-
"loss": 0.
|
| 721 |
"step": 16500
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 38.0,
|
| 725 |
-
"eval_explained_variance": 0.
|
| 726 |
-
"eval_kl_divergence":
|
| 727 |
-
"eval_loss": 0.
|
| 728 |
-
"eval_mae": 0.
|
| 729 |
-
"eval_rmse": 0.
|
| 730 |
-
"eval_runtime": 63.
|
| 731 |
-
"eval_samples_per_second": 37.
|
| 732 |
-
"eval_steps_per_second": 2.
|
| 733 |
-
"learning_rate":
|
| 734 |
"step": 16644
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 38.81278538812786,
|
| 738 |
-
"grad_norm": 0.
|
| 739 |
-
"learning_rate":
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 17000
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 39.0,
|
| 745 |
-
"eval_explained_variance": 0.
|
| 746 |
-
"eval_kl_divergence":
|
| 747 |
-
"eval_loss": 0.
|
| 748 |
-
"eval_mae": 0.
|
| 749 |
-
"eval_rmse": 0.
|
| 750 |
-
"eval_runtime":
|
| 751 |
-
"eval_samples_per_second": 37.
|
| 752 |
-
"eval_steps_per_second": 2.
|
| 753 |
-
"learning_rate":
|
| 754 |
"step": 17082
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 39.954337899543376,
|
| 758 |
-
"grad_norm": 0.
|
| 759 |
-
"learning_rate":
|
| 760 |
-
"loss": 0.
|
| 761 |
"step": 17500
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 40.0,
|
| 765 |
-
"eval_explained_variance": 0.
|
| 766 |
-
"eval_kl_divergence": 0.
|
| 767 |
-
"eval_loss": 0.
|
| 768 |
-
"eval_mae": 0.
|
| 769 |
-
"eval_rmse": 0.
|
| 770 |
-
"eval_runtime":
|
| 771 |
-
"eval_samples_per_second":
|
| 772 |
-
"eval_steps_per_second": 2.
|
| 773 |
-
"learning_rate":
|
| 774 |
"step": 17520
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 41.0,
|
| 778 |
-
"eval_explained_variance": 0.
|
| 779 |
-
"eval_kl_divergence": 0.
|
| 780 |
-
"eval_loss": 0.
|
| 781 |
-
"eval_mae": 0.
|
| 782 |
-
"eval_rmse": 0.
|
| 783 |
-
"eval_runtime":
|
| 784 |
-
"eval_samples_per_second":
|
| 785 |
-
"eval_steps_per_second": 2.
|
| 786 |
-
"learning_rate":
|
| 787 |
"step": 17958
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 41.0958904109589,
|
| 791 |
-
"grad_norm": 0.
|
| 792 |
-
"learning_rate":
|
| 793 |
-
"loss": 0.
|
| 794 |
"step": 18000
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 42.0,
|
| 798 |
-
"eval_explained_variance": 0.
|
| 799 |
-
"eval_kl_divergence":
|
| 800 |
-
"eval_loss": 0.
|
| 801 |
-
"eval_mae": 0.
|
| 802 |
-
"eval_rmse": 0.
|
| 803 |
-
"eval_runtime":
|
| 804 |
-
"eval_samples_per_second":
|
| 805 |
-
"eval_steps_per_second": 2.
|
| 806 |
-
"learning_rate":
|
| 807 |
"step": 18396
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 42.23744292237443,
|
| 811 |
-
"grad_norm": 0.
|
| 812 |
-
"learning_rate":
|
| 813 |
-
"loss": 0.
|
| 814 |
"step": 18500
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"epoch": 43.0,
|
| 818 |
-
"eval_explained_variance": 0.
|
| 819 |
-
"eval_kl_divergence":
|
| 820 |
-
"eval_loss": 0.
|
| 821 |
-
"eval_mae": 0.
|
| 822 |
-
"eval_rmse": 0.
|
| 823 |
-
"eval_runtime": 64.
|
| 824 |
-
"eval_samples_per_second": 36.
|
| 825 |
-
"eval_steps_per_second": 2.
|
| 826 |
-
"learning_rate":
|
| 827 |
"step": 18834
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 43.37899543378995,
|
| 831 |
-
"grad_norm": 0.
|
| 832 |
-
"learning_rate":
|
| 833 |
-
"loss": 0.
|
| 834 |
"step": 19000
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 44.0,
|
| 838 |
-
"eval_explained_variance": 0.
|
| 839 |
-
"eval_kl_divergence":
|
| 840 |
-
"eval_loss": 0.
|
| 841 |
-
"eval_mae": 0.
|
| 842 |
-
"eval_rmse": 0.
|
| 843 |
-
"eval_runtime":
|
| 844 |
-
"eval_samples_per_second":
|
| 845 |
-
"eval_steps_per_second": 2.
|
| 846 |
-
"learning_rate":
|
| 847 |
"step": 19272
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 44.52054794520548,
|
| 851 |
-
"grad_norm": 0.
|
| 852 |
-
"learning_rate":
|
| 853 |
-
"loss": 0.
|
| 854 |
"step": 19500
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 45.0,
|
| 858 |
-
"eval_explained_variance": 0.
|
| 859 |
-
"eval_kl_divergence":
|
| 860 |
-
"eval_loss": 0.
|
| 861 |
-
"eval_mae": 0.
|
| 862 |
-
"eval_rmse": 0.
|
| 863 |
-
"eval_runtime":
|
| 864 |
-
"eval_samples_per_second":
|
| 865 |
-
"eval_steps_per_second": 2.
|
| 866 |
-
"learning_rate":
|
| 867 |
"step": 19710
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 45.662100456621005,
|
| 871 |
-
"grad_norm": 0.
|
| 872 |
-
"learning_rate":
|
| 873 |
-
"loss": 0.
|
| 874 |
"step": 20000
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 46.0,
|
| 878 |
-
"eval_explained_variance": 0.
|
| 879 |
-
"eval_kl_divergence":
|
| 880 |
-
"eval_loss": 0.
|
| 881 |
-
"eval_mae": 0.
|
| 882 |
-
"eval_rmse": 0.
|
| 883 |
-
"eval_runtime":
|
| 884 |
-
"eval_samples_per_second":
|
| 885 |
-
"eval_steps_per_second": 2.
|
| 886 |
-
"learning_rate":
|
| 887 |
"step": 20148
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 46.80365296803653,
|
| 891 |
-
"grad_norm": 0.
|
| 892 |
-
"learning_rate":
|
| 893 |
-
"loss": 0.
|
| 894 |
"step": 20500
|
| 895 |
},
|
| 896 |
{
|
| 897 |
"epoch": 47.0,
|
| 898 |
-
"eval_explained_variance": 0.
|
| 899 |
-
"eval_kl_divergence":
|
| 900 |
-
"eval_loss": 0.
|
| 901 |
-
"eval_mae": 0.
|
| 902 |
-
"eval_rmse": 0.
|
| 903 |
-
"eval_runtime":
|
| 904 |
-
"eval_samples_per_second":
|
| 905 |
-
"eval_steps_per_second": 2.
|
| 906 |
-
"learning_rate":
|
| 907 |
"step": 20586
|
| 908 |
},
|
| 909 |
{
|
| 910 |
"epoch": 47.945205479452056,
|
| 911 |
-
"grad_norm": 0.
|
| 912 |
-
"learning_rate":
|
| 913 |
-
"loss": 0.
|
| 914 |
"step": 21000
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 48.0,
|
| 918 |
-
"eval_explained_variance": 0.
|
| 919 |
-
"eval_kl_divergence":
|
| 920 |
-
"eval_loss": 0.
|
| 921 |
-
"eval_mae": 0.
|
| 922 |
-
"eval_rmse": 0.
|
| 923 |
-
"eval_runtime":
|
| 924 |
-
"eval_samples_per_second":
|
| 925 |
-
"eval_steps_per_second": 2.
|
| 926 |
-
"learning_rate":
|
| 927 |
"step": 21024
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 49.0,
|
| 931 |
-
"eval_explained_variance": 0.
|
| 932 |
-
"eval_kl_divergence":
|
| 933 |
-
"eval_loss": 0.
|
| 934 |
-
"eval_mae": 0.
|
| 935 |
-
"eval_rmse": 0.
|
| 936 |
-
"eval_runtime":
|
| 937 |
-
"eval_samples_per_second":
|
| 938 |
-
"eval_steps_per_second": 2.
|
| 939 |
-
"learning_rate":
|
| 940 |
"step": 21462
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"epoch": 49.08675799086758,
|
| 944 |
-
"grad_norm": 0.
|
| 945 |
-
"learning_rate":
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 21500
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 50.0,
|
| 951 |
-
"eval_explained_variance": 0.
|
| 952 |
-
"eval_kl_divergence": 0.
|
| 953 |
-
"eval_loss": 0.
|
| 954 |
-
"eval_mae": 0.
|
| 955 |
-
"eval_rmse": 0.
|
| 956 |
-
"eval_runtime":
|
| 957 |
-
"eval_samples_per_second":
|
| 958 |
-
"eval_steps_per_second": 2.
|
| 959 |
-
"learning_rate":
|
| 960 |
"step": 21900
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 50.22831050228311,
|
| 964 |
-
"grad_norm": 0.
|
| 965 |
-
"learning_rate":
|
| 966 |
-
"loss": 0.
|
| 967 |
"step": 22000
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 51.0,
|
| 971 |
-
"eval_explained_variance": 0.
|
| 972 |
-
"eval_kl_divergence": 0.
|
| 973 |
-
"eval_loss": 0.
|
| 974 |
-
"eval_mae": 0.
|
| 975 |
-
"eval_rmse": 0.
|
| 976 |
-
"eval_runtime":
|
| 977 |
-
"eval_samples_per_second":
|
| 978 |
-
"eval_steps_per_second": 2.
|
| 979 |
-
"learning_rate":
|
| 980 |
"step": 22338
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 51.36986301369863,
|
| 984 |
-
"grad_norm": 0.
|
| 985 |
-
"learning_rate":
|
| 986 |
-
"loss": 0.
|
| 987 |
"step": 22500
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 52.0,
|
| 991 |
-
"eval_explained_variance": 0.
|
| 992 |
-
"eval_kl_divergence":
|
| 993 |
-
"eval_loss": 0.
|
| 994 |
-
"eval_mae": 0.
|
| 995 |
-
"eval_rmse": 0.
|
| 996 |
-
"eval_runtime":
|
| 997 |
-
"eval_samples_per_second":
|
| 998 |
-
"eval_steps_per_second": 2.
|
| 999 |
-
"learning_rate":
|
| 1000 |
"step": 22776
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 52.51141552511415,
|
| 1004 |
-
"grad_norm": 0.
|
| 1005 |
-
"learning_rate":
|
| 1006 |
-
"loss": 0.
|
| 1007 |
"step": 23000
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 53.0,
|
| 1011 |
-
"eval_explained_variance": 0.
|
| 1012 |
-
"eval_kl_divergence":
|
| 1013 |
-
"eval_loss": 0.
|
| 1014 |
-
"eval_mae": 0.
|
| 1015 |
-
"eval_rmse": 0.
|
| 1016 |
-
"eval_runtime":
|
| 1017 |
-
"eval_samples_per_second":
|
| 1018 |
-
"eval_steps_per_second": 2.
|
| 1019 |
-
"learning_rate":
|
| 1020 |
"step": 23214
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 53.65296803652968,
|
| 1024 |
-
"grad_norm": 0.
|
| 1025 |
-
"learning_rate":
|
| 1026 |
-
"loss": 0.
|
| 1027 |
"step": 23500
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 54.0,
|
| 1031 |
-
"eval_explained_variance": 0.
|
| 1032 |
-
"eval_kl_divergence": 0.
|
| 1033 |
-
"eval_loss": 0.
|
| 1034 |
-
"eval_mae": 0.
|
| 1035 |
-
"eval_rmse": 0.
|
| 1036 |
-
"eval_runtime":
|
| 1037 |
-
"eval_samples_per_second":
|
| 1038 |
-
"eval_steps_per_second": 2.
|
| 1039 |
-
"learning_rate":
|
| 1040 |
"step": 23652
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 54.794520547945204,
|
| 1044 |
-
"grad_norm": 0.
|
| 1045 |
-
"learning_rate":
|
| 1046 |
-
"loss": 0.
|
| 1047 |
"step": 24000
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 55.0,
|
| 1051 |
-
"eval_explained_variance": 0.
|
| 1052 |
-
"eval_kl_divergence": 0.
|
| 1053 |
-
"eval_loss": 0.
|
| 1054 |
-
"eval_mae": 0.
|
| 1055 |
-
"eval_rmse": 0.
|
| 1056 |
-
"eval_runtime":
|
| 1057 |
-
"eval_samples_per_second":
|
| 1058 |
-
"eval_steps_per_second": 2.
|
| 1059 |
-
"learning_rate":
|
| 1060 |
"step": 24090
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
"epoch": 55.93607305936073,
|
| 1064 |
-
"grad_norm": 0.
|
| 1065 |
-
"learning_rate":
|
| 1066 |
-
"loss": 0.
|
| 1067 |
"step": 24500
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
"epoch": 56.0,
|
| 1071 |
-
"eval_explained_variance": 0.
|
| 1072 |
-
"eval_kl_divergence": 0.
|
| 1073 |
-
"eval_loss": 0.
|
| 1074 |
-
"eval_mae": 0.
|
| 1075 |
-
"eval_rmse": 0.
|
| 1076 |
-
"eval_runtime":
|
| 1077 |
-
"eval_samples_per_second":
|
| 1078 |
-
"eval_steps_per_second": 2.
|
| 1079 |
-
"learning_rate":
|
| 1080 |
"step": 24528
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 57.0,
|
| 1084 |
-
"eval_explained_variance": 0.
|
| 1085 |
-
"eval_kl_divergence":
|
| 1086 |
-
"eval_loss": 0.
|
| 1087 |
-
"eval_mae": 0.
|
| 1088 |
-
"eval_rmse": 0.
|
| 1089 |
-
"eval_runtime":
|
| 1090 |
-
"eval_samples_per_second":
|
| 1091 |
-
"eval_steps_per_second": 2.
|
| 1092 |
-
"learning_rate":
|
| 1093 |
"step": 24966
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 57.077625570776256,
|
| 1097 |
-
"grad_norm": 0.
|
| 1098 |
-
"learning_rate":
|
| 1099 |
-
"loss": 0.
|
| 1100 |
"step": 25000
|
| 1101 |
},
|
| 1102 |
{
|
| 1103 |
"epoch": 58.0,
|
| 1104 |
-
"eval_explained_variance": 0.
|
| 1105 |
-
"eval_kl_divergence": 0.
|
| 1106 |
-
"eval_loss": 0.
|
| 1107 |
-
"eval_mae": 0.
|
| 1108 |
-
"eval_rmse": 0.
|
| 1109 |
-
"eval_runtime":
|
| 1110 |
-
"eval_samples_per_second":
|
| 1111 |
-
"eval_steps_per_second": 2.
|
| 1112 |
-
"learning_rate":
|
| 1113 |
"step": 25404
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 58.21917808219178,
|
| 1117 |
-
"grad_norm": 0.
|
| 1118 |
-
"learning_rate": 1.0000000000000002e-
|
| 1119 |
-
"loss": 0.
|
| 1120 |
"step": 25500
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 59.0,
|
| 1124 |
-
"eval_explained_variance": 0.
|
| 1125 |
-
"eval_kl_divergence": 0.
|
| 1126 |
-
"eval_loss": 0.
|
| 1127 |
-
"eval_mae": 0.
|
| 1128 |
-
"eval_rmse": 0.
|
| 1129 |
-
"eval_runtime":
|
| 1130 |
-
"eval_samples_per_second":
|
| 1131 |
-
"eval_steps_per_second": 2.
|
| 1132 |
-
"learning_rate": 1.0000000000000002e-
|
| 1133 |
"step": 25842
|
| 1134 |
},
|
| 1135 |
{
|
| 1136 |
"epoch": 59.36073059360731,
|
| 1137 |
-
"grad_norm": 0.
|
| 1138 |
-
"learning_rate": 1.0000000000000002e-
|
| 1139 |
-
"loss": 0.
|
| 1140 |
"step": 26000
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
"epoch": 60.0,
|
| 1144 |
-
"eval_explained_variance": 0.
|
| 1145 |
-
"eval_kl_divergence":
|
| 1146 |
-
"eval_loss": 0.
|
| 1147 |
-
"eval_mae": 0.
|
| 1148 |
-
"eval_rmse": 0.
|
| 1149 |
-
"eval_runtime":
|
| 1150 |
-
"eval_samples_per_second":
|
| 1151 |
-
"eval_steps_per_second": 2.
|
| 1152 |
-
"learning_rate": 1.0000000000000002e-
|
| 1153 |
"step": 26280
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
"epoch": 60.50228310502283,
|
| 1157 |
-
"grad_norm": 0.
|
| 1158 |
-
"learning_rate": 1.0000000000000002e-
|
| 1159 |
-
"loss": 0.
|
| 1160 |
"step": 26500
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 61.0,
|
| 1164 |
-
"eval_explained_variance": 0.
|
| 1165 |
-
"eval_kl_divergence": 0.
|
| 1166 |
-
"eval_loss": 0.
|
| 1167 |
-
"eval_mae": 0.
|
| 1168 |
-
"eval_rmse": 0.
|
| 1169 |
-
"eval_runtime":
|
| 1170 |
-
"eval_samples_per_second":
|
| 1171 |
-
"eval_steps_per_second": 2.
|
| 1172 |
-
"learning_rate": 1.0000000000000002e-
|
| 1173 |
"step": 26718
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 61.64383561643836,
|
| 1177 |
-
"grad_norm": 0.
|
| 1178 |
-
"learning_rate": 1.0000000000000002e-
|
| 1179 |
-
"loss": 0.
|
| 1180 |
"step": 27000
|
| 1181 |
},
|
| 1182 |
{
|
| 1183 |
"epoch": 62.0,
|
| 1184 |
-
"eval_explained_variance": 0.
|
| 1185 |
-
"eval_kl_divergence": 0.
|
| 1186 |
-
"eval_loss": 0.
|
| 1187 |
-
"eval_mae": 0.
|
| 1188 |
-
"eval_rmse": 0.
|
| 1189 |
-
"eval_runtime":
|
| 1190 |
-
"eval_samples_per_second":
|
| 1191 |
-
"eval_steps_per_second": 2.
|
| 1192 |
-
"learning_rate": 1.0000000000000002e-
|
| 1193 |
"step": 27156
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 62.0,
|
| 1197 |
-
"learning_rate": 1.0000000000000002e-
|
| 1198 |
"step": 27156,
|
| 1199 |
"total_flos": 6.42634409963284e+19,
|
| 1200 |
-
"train_loss": 0.
|
| 1201 |
-
"train_runtime":
|
| 1202 |
-
"train_samples_per_second":
|
| 1203 |
-
"train_steps_per_second": 3.
|
| 1204 |
}
|
| 1205 |
],
|
| 1206 |
"logging_steps": 500,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.40528106689453125,
|
| 3 |
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/drone/drone-DinoVdeau-from-binary-large-2024_11_14-batch-size16_freeze_probs/checkpoint-22776",
|
| 4 |
"epoch": 62.0,
|
| 5 |
"eval_steps": 500,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_explained_variance": 0.2881631553173065,
|
| 14 |
+
"eval_kl_divergence": 1.006906509399414,
|
| 15 |
+
"eval_loss": 0.43063807487487793,
|
| 16 |
+
"eval_mae": 0.16208958625793457,
|
| 17 |
+
"eval_rmse": 0.22103922069072723,
|
| 18 |
+
"eval_runtime": 65.2687,
|
| 19 |
+
"eval_samples_per_second": 36.066,
|
| 20 |
+
"eval_steps_per_second": 2.268,
|
| 21 |
"learning_rate": 0.001,
|
| 22 |
"step": 438
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"epoch": 1.1415525114155252,
|
| 26 |
+
"grad_norm": 0.5616265535354614,
|
| 27 |
"learning_rate": 0.001,
|
| 28 |
+
"loss": 0.4808,
|
| 29 |
"step": 500
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 2.0,
|
| 33 |
+
"eval_explained_variance": 0.31177183985710144,
|
| 34 |
+
"eval_kl_divergence": 1.3118820190429688,
|
| 35 |
+
"eval_loss": 0.4245865046977997,
|
| 36 |
+
"eval_mae": 0.15473191440105438,
|
| 37 |
+
"eval_rmse": 0.21785493195056915,
|
| 38 |
+
"eval_runtime": 70.2445,
|
| 39 |
+
"eval_samples_per_second": 33.512,
|
| 40 |
+
"eval_steps_per_second": 2.107,
|
| 41 |
"learning_rate": 0.001,
|
| 42 |
"step": 876
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 2.2831050228310503,
|
| 46 |
+
"grad_norm": 0.5421963930130005,
|
| 47 |
"learning_rate": 0.001,
|
| 48 |
+
"loss": 0.421,
|
| 49 |
"step": 1000
|
| 50 |
},
|
| 51 |
{
|
| 52 |
"epoch": 3.0,
|
| 53 |
+
"eval_explained_variance": 0.3191607892513275,
|
| 54 |
+
"eval_kl_divergence": 1.0982407331466675,
|
| 55 |
+
"eval_loss": 0.422325998544693,
|
| 56 |
+
"eval_mae": 0.1554209440946579,
|
| 57 |
+
"eval_rmse": 0.21583305299282074,
|
| 58 |
+
"eval_runtime": 63.3078,
|
| 59 |
+
"eval_samples_per_second": 37.183,
|
| 60 |
+
"eval_steps_per_second": 2.338,
|
| 61 |
"learning_rate": 0.001,
|
| 62 |
"step": 1314
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 3.4246575342465753,
|
| 66 |
+
"grad_norm": 0.4156647324562073,
|
| 67 |
"learning_rate": 0.001,
|
| 68 |
+
"loss": 0.4151,
|
| 69 |
"step": 1500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 4.0,
|
| 73 |
+
"eval_explained_variance": 0.3350948095321655,
|
| 74 |
+
"eval_kl_divergence": 1.041384220123291,
|
| 75 |
+
"eval_loss": 0.41912660002708435,
|
| 76 |
+
"eval_mae": 0.15517595410346985,
|
| 77 |
+
"eval_rmse": 0.21416835486888885,
|
| 78 |
+
"eval_runtime": 63.7743,
|
| 79 |
+
"eval_samples_per_second": 36.911,
|
| 80 |
+
"eval_steps_per_second": 2.321,
|
| 81 |
"learning_rate": 0.001,
|
| 82 |
"step": 1752
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 4.566210045662101,
|
| 86 |
+
"grad_norm": 0.2765987813472748,
|
| 87 |
"learning_rate": 0.001,
|
| 88 |
+
"loss": 0.4114,
|
| 89 |
"step": 2000
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 5.0,
|
| 93 |
+
"eval_explained_variance": 0.33842501044273376,
|
| 94 |
+
"eval_kl_divergence": 1.0698424577713013,
|
| 95 |
+
"eval_loss": 0.41713497042655945,
|
| 96 |
+
"eval_mae": 0.15411676466464996,
|
| 97 |
+
"eval_rmse": 0.21232052147388458,
|
| 98 |
+
"eval_runtime": 61.7723,
|
| 99 |
+
"eval_samples_per_second": 38.108,
|
| 100 |
+
"eval_steps_per_second": 2.396,
|
| 101 |
"learning_rate": 0.001,
|
| 102 |
"step": 2190
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 5.707762557077626,
|
| 106 |
+
"grad_norm": 0.34299173951148987,
|
| 107 |
"learning_rate": 0.001,
|
| 108 |
+
"loss": 0.4089,
|
| 109 |
"step": 2500
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 6.0,
|
| 113 |
+
"eval_explained_variance": 0.3310842514038086,
|
| 114 |
+
"eval_kl_divergence": 1.1958788633346558,
|
| 115 |
+
"eval_loss": 0.42093637585639954,
|
| 116 |
+
"eval_mae": 0.1519818753004074,
|
| 117 |
+
"eval_rmse": 0.21403205394744873,
|
| 118 |
+
"eval_runtime": 61.4619,
|
| 119 |
+
"eval_samples_per_second": 38.3,
|
| 120 |
+
"eval_steps_per_second": 2.408,
|
| 121 |
"learning_rate": 0.001,
|
| 122 |
"step": 2628
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 6.8493150684931505,
|
| 126 |
+
"grad_norm": 0.30921000242233276,
|
| 127 |
"learning_rate": 0.001,
|
| 128 |
+
"loss": 0.4091,
|
| 129 |
"step": 3000
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 7.0,
|
| 133 |
+
"eval_explained_variance": 0.33822229504585266,
|
| 134 |
+
"eval_kl_divergence": 1.1708621978759766,
|
| 135 |
+
"eval_loss": 0.4166290760040283,
|
| 136 |
+
"eval_mae": 0.153007373213768,
|
| 137 |
+
"eval_rmse": 0.21260716021060944,
|
| 138 |
+
"eval_runtime": 60.3411,
|
| 139 |
+
"eval_samples_per_second": 39.012,
|
| 140 |
+
"eval_steps_per_second": 2.453,
|
| 141 |
"learning_rate": 0.001,
|
| 142 |
"step": 3066
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 7.9908675799086755,
|
| 146 |
+
"grad_norm": 0.21716275811195374,
|
| 147 |
"learning_rate": 0.001,
|
| 148 |
+
"loss": 0.4071,
|
| 149 |
"step": 3500
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 8.0,
|
| 153 |
+
"eval_explained_variance": 0.33456894755363464,
|
| 154 |
+
"eval_kl_divergence": 0.971220850944519,
|
| 155 |
+
"eval_loss": 0.41946443915367126,
|
| 156 |
+
"eval_mae": 0.15562371909618378,
|
| 157 |
+
"eval_rmse": 0.2142825573682785,
|
| 158 |
+
"eval_runtime": 62.8353,
|
| 159 |
+
"eval_samples_per_second": 37.463,
|
| 160 |
+
"eval_steps_per_second": 2.355,
|
| 161 |
"learning_rate": 0.001,
|
| 162 |
"step": 3504
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 9.0,
|
| 166 |
+
"eval_explained_variance": 0.3415004014968872,
|
| 167 |
+
"eval_kl_divergence": 1.1432474851608276,
|
| 168 |
+
"eval_loss": 0.41668570041656494,
|
| 169 |
+
"eval_mae": 0.1524006426334381,
|
| 170 |
+
"eval_rmse": 0.21208135783672333,
|
| 171 |
+
"eval_runtime": 62.325,
|
| 172 |
+
"eval_samples_per_second": 37.77,
|
| 173 |
+
"eval_steps_per_second": 2.375,
|
| 174 |
"learning_rate": 0.001,
|
| 175 |
"step": 3942
|
| 176 |
},
|
| 177 |
{
|
| 178 |
"epoch": 9.132420091324201,
|
| 179 |
+
"grad_norm": 0.2371012270450592,
|
| 180 |
"learning_rate": 0.001,
|
| 181 |
+
"loss": 0.4062,
|
| 182 |
"step": 4000
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 10.0,
|
| 186 |
+
"eval_explained_variance": 0.34203192591667175,
|
| 187 |
+
"eval_kl_divergence": 0.9120630025863647,
|
| 188 |
+
"eval_loss": 0.4186115860939026,
|
| 189 |
+
"eval_mae": 0.15351708233356476,
|
| 190 |
+
"eval_rmse": 0.2138604372739792,
|
| 191 |
+
"eval_runtime": 60.5397,
|
| 192 |
+
"eval_samples_per_second": 38.884,
|
| 193 |
+
"eval_steps_per_second": 2.445,
|
| 194 |
"learning_rate": 0.001,
|
| 195 |
"step": 4380
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 10.273972602739725,
|
| 199 |
+
"grad_norm": 0.2552158236503601,
|
| 200 |
"learning_rate": 0.001,
|
| 201 |
+
"loss": 0.4052,
|
| 202 |
"step": 4500
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 11.0,
|
| 206 |
+
"eval_explained_variance": 0.34416234493255615,
|
| 207 |
+
"eval_kl_divergence": 0.995019793510437,
|
| 208 |
+
"eval_loss": 0.41557687520980835,
|
| 209 |
+
"eval_mae": 0.15356659889221191,
|
| 210 |
+
"eval_rmse": 0.2114415019750595,
|
| 211 |
+
"eval_runtime": 61.7293,
|
| 212 |
+
"eval_samples_per_second": 38.134,
|
| 213 |
+
"eval_steps_per_second": 2.398,
|
| 214 |
"learning_rate": 0.001,
|
| 215 |
"step": 4818
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 11.415525114155251,
|
| 219 |
+
"grad_norm": 0.20953956246376038,
|
| 220 |
"learning_rate": 0.001,
|
| 221 |
+
"loss": 0.406,
|
| 222 |
"step": 5000
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 12.0,
|
| 226 |
+
"eval_explained_variance": 0.3389909565448761,
|
| 227 |
+
"eval_kl_divergence": 1.0105773210525513,
|
| 228 |
+
"eval_loss": 0.41883811354637146,
|
| 229 |
+
"eval_mae": 0.1555173546075821,
|
| 230 |
+
"eval_rmse": 0.21388684213161469,
|
| 231 |
+
"eval_runtime": 62.5745,
|
| 232 |
+
"eval_samples_per_second": 37.619,
|
| 233 |
+
"eval_steps_per_second": 2.365,
|
| 234 |
"learning_rate": 0.001,
|
| 235 |
"step": 5256
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 12.557077625570777,
|
| 239 |
+
"grad_norm": 0.18659397959709167,
|
| 240 |
"learning_rate": 0.001,
|
| 241 |
+
"loss": 0.4058,
|
| 242 |
"step": 5500
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 13.0,
|
| 246 |
+
"eval_explained_variance": 0.34248629212379456,
|
| 247 |
+
"eval_kl_divergence": 1.1481796503067017,
|
| 248 |
+
"eval_loss": 0.41630858182907104,
|
| 249 |
+
"eval_mae": 0.15531976521015167,
|
| 250 |
+
"eval_rmse": 0.21213315427303314,
|
| 251 |
+
"eval_runtime": 61.6003,
|
| 252 |
+
"eval_samples_per_second": 38.214,
|
| 253 |
+
"eval_steps_per_second": 2.403,
|
| 254 |
"learning_rate": 0.001,
|
| 255 |
"step": 5694
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 13.698630136986301,
|
| 259 |
+
"grad_norm": 0.19523686170578003,
|
| 260 |
"learning_rate": 0.001,
|
| 261 |
+
"loss": 0.4056,
|
| 262 |
"step": 6000
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 14.0,
|
| 266 |
+
"eval_explained_variance": 0.3286344110965729,
|
| 267 |
+
"eval_kl_divergence": 1.211091160774231,
|
| 268 |
+
"eval_loss": 0.4193180799484253,
|
| 269 |
+
"eval_mae": 0.15458153188228607,
|
| 270 |
+
"eval_rmse": 0.21381880342960358,
|
| 271 |
+
"eval_runtime": 62.0339,
|
| 272 |
+
"eval_samples_per_second": 37.947,
|
| 273 |
+
"eval_steps_per_second": 2.386,
|
| 274 |
"learning_rate": 0.001,
|
| 275 |
"step": 6132
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 14.840182648401827,
|
| 279 |
+
"grad_norm": 0.18541939556598663,
|
| 280 |
"learning_rate": 0.001,
|
| 281 |
+
"loss": 0.4033,
|
| 282 |
"step": 6500
|
| 283 |
},
|
| 284 |
{
|
| 285 |
"epoch": 15.0,
|
| 286 |
+
"eval_explained_variance": 0.3402325212955475,
|
| 287 |
+
"eval_kl_divergence": 1.2042615413665771,
|
| 288 |
+
"eval_loss": 0.416218638420105,
|
| 289 |
+
"eval_mae": 0.15419499576091766,
|
| 290 |
+
"eval_rmse": 0.2121332883834839,
|
| 291 |
+
"eval_runtime": 62.9591,
|
| 292 |
+
"eval_samples_per_second": 37.389,
|
| 293 |
+
"eval_steps_per_second": 2.351,
|
| 294 |
"learning_rate": 0.001,
|
| 295 |
"step": 6570
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 15.981735159817351,
|
| 299 |
+
"grad_norm": 0.16085268557071686,
|
| 300 |
+
"learning_rate": 0.001,
|
| 301 |
+
"loss": 0.4057,
|
| 302 |
"step": 7000
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 16.0,
|
| 306 |
+
"eval_explained_variance": 0.35001620650291443,
|
| 307 |
+
"eval_kl_divergence": 1.0827727317810059,
|
| 308 |
+
"eval_loss": 0.41389620304107666,
|
| 309 |
+
"eval_mae": 0.1527981460094452,
|
| 310 |
+
"eval_rmse": 0.21022744476795197,
|
| 311 |
+
"eval_runtime": 62.4108,
|
| 312 |
+
"eval_samples_per_second": 37.718,
|
| 313 |
+
"eval_steps_per_second": 2.371,
|
| 314 |
+
"learning_rate": 0.001,
|
| 315 |
"step": 7008
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 17.0,
|
| 319 |
+
"eval_explained_variance": 0.3429690897464752,
|
| 320 |
+
"eval_kl_divergence": 1.0005594491958618,
|
| 321 |
+
"eval_loss": 0.4171081781387329,
|
| 322 |
+
"eval_mae": 0.15638333559036255,
|
| 323 |
+
"eval_rmse": 0.21180683374404907,
|
| 324 |
+
"eval_runtime": 63.4048,
|
| 325 |
+
"eval_samples_per_second": 37.127,
|
| 326 |
+
"eval_steps_per_second": 2.334,
|
| 327 |
+
"learning_rate": 0.001,
|
| 328 |
"step": 7446
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 17.123287671232877,
|
| 332 |
+
"grad_norm": 0.17030780017375946,
|
| 333 |
+
"learning_rate": 0.001,
|
| 334 |
+
"loss": 0.405,
|
| 335 |
"step": 7500
|
| 336 |
},
|
| 337 |
{
|
| 338 |
"epoch": 18.0,
|
| 339 |
+
"eval_explained_variance": 0.3499327600002289,
|
| 340 |
+
"eval_kl_divergence": 1.0514436960220337,
|
| 341 |
+
"eval_loss": 0.4146382212638855,
|
| 342 |
+
"eval_mae": 0.1507440060377121,
|
| 343 |
+
"eval_rmse": 0.2107054442167282,
|
| 344 |
+
"eval_runtime": 64.4758,
|
| 345 |
+
"eval_samples_per_second": 36.51,
|
| 346 |
+
"eval_steps_per_second": 2.295,
|
| 347 |
+
"learning_rate": 0.001,
|
| 348 |
"step": 7884
|
| 349 |
},
|
| 350 |
{
|
| 351 |
"epoch": 18.264840182648403,
|
| 352 |
+
"grad_norm": 0.16620762646198273,
|
| 353 |
+
"learning_rate": 0.001,
|
| 354 |
+
"loss": 0.4035,
|
| 355 |
"step": 8000
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 19.0,
|
| 359 |
+
"eval_explained_variance": 0.3467938005924225,
|
| 360 |
+
"eval_kl_divergence": 0.9575299024581909,
|
| 361 |
+
"eval_loss": 0.41857486963272095,
|
| 362 |
+
"eval_mae": 0.1531781703233719,
|
| 363 |
+
"eval_rmse": 0.21135376393795013,
|
| 364 |
+
"eval_runtime": 65.1272,
|
| 365 |
+
"eval_samples_per_second": 36.145,
|
| 366 |
+
"eval_steps_per_second": 2.272,
|
| 367 |
+
"learning_rate": 0.001,
|
| 368 |
"step": 8322
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 19.40639269406393,
|
| 372 |
+
"grad_norm": 0.21431417763233185,
|
| 373 |
+
"learning_rate": 0.001,
|
| 374 |
+
"loss": 0.4031,
|
| 375 |
"step": 8500
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 20.0,
|
| 379 |
+
"eval_explained_variance": 0.34868308901786804,
|
| 380 |
+
"eval_kl_divergence": 1.164780855178833,
|
| 381 |
+
"eval_loss": 0.41434723138809204,
|
| 382 |
+
"eval_mae": 0.15129883587360382,
|
| 383 |
+
"eval_rmse": 0.21083922684192657,
|
| 384 |
+
"eval_runtime": 62.809,
|
| 385 |
+
"eval_samples_per_second": 37.479,
|
| 386 |
+
"eval_steps_per_second": 2.356,
|
| 387 |
+
"learning_rate": 0.001,
|
| 388 |
"step": 8760
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 20.54794520547945,
|
| 392 |
+
"grad_norm": 0.16674350202083588,
|
| 393 |
+
"learning_rate": 0.001,
|
| 394 |
+
"loss": 0.4048,
|
| 395 |
"step": 9000
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 21.0,
|
| 399 |
+
"eval_explained_variance": 0.3385157585144043,
|
| 400 |
+
"eval_kl_divergence": 1.2949873208999634,
|
| 401 |
+
"eval_loss": 0.4195358157157898,
|
| 402 |
+
"eval_mae": 0.15333952009677887,
|
| 403 |
+
"eval_rmse": 0.21233241260051727,
|
| 404 |
+
"eval_runtime": 62.2788,
|
| 405 |
+
"eval_samples_per_second": 37.798,
|
| 406 |
+
"eval_steps_per_second": 2.376,
|
| 407 |
+
"learning_rate": 0.001,
|
| 408 |
"step": 9198
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 21.689497716894977,
|
| 412 |
+
"grad_norm": 0.2121485322713852,
|
| 413 |
+
"learning_rate": 0.001,
|
| 414 |
+
"loss": 0.4055,
|
| 415 |
"step": 9500
|
| 416 |
},
|
| 417 |
{
|
| 418 |
"epoch": 22.0,
|
| 419 |
+
"eval_explained_variance": 0.34627434611320496,
|
| 420 |
+
"eval_kl_divergence": Infinity,
|
| 421 |
+
"eval_loss": 0.4339658319950104,
|
| 422 |
+
"eval_mae": 0.15240180492401123,
|
| 423 |
+
"eval_rmse": 0.21100641787052155,
|
| 424 |
+
"eval_runtime": 63.2767,
|
| 425 |
+
"eval_samples_per_second": 37.202,
|
| 426 |
+
"eval_steps_per_second": 2.339,
|
| 427 |
+
"learning_rate": 0.001,
|
| 428 |
"step": 9636
|
| 429 |
},
|
| 430 |
{
|
| 431 |
"epoch": 22.831050228310502,
|
| 432 |
+
"grad_norm": 0.17502234876155853,
|
| 433 |
"learning_rate": 0.0001,
|
| 434 |
+
"loss": 0.4022,
|
| 435 |
"step": 10000
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 23.0,
|
| 439 |
+
"eval_explained_variance": 0.362075537443161,
|
| 440 |
+
"eval_kl_divergence": NaN,
|
| 441 |
+
"eval_loss": 0.43265336751937866,
|
| 442 |
+
"eval_mae": 0.1517171412706375,
|
| 443 |
+
"eval_rmse": 0.2084527164697647,
|
| 444 |
+
"eval_runtime": 61.7803,
|
| 445 |
+
"eval_samples_per_second": 38.103,
|
| 446 |
+
"eval_steps_per_second": 2.396,
|
| 447 |
"learning_rate": 0.0001,
|
| 448 |
"step": 10074
|
| 449 |
},
|
| 450 |
{
|
| 451 |
"epoch": 23.972602739726028,
|
| 452 |
+
"grad_norm": 0.20596392452716827,
|
| 453 |
"learning_rate": 0.0001,
|
| 454 |
+
"loss": 0.3978,
|
| 455 |
"step": 10500
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 24.0,
|
| 459 |
+
"eval_explained_variance": 0.3582542836666107,
|
| 460 |
+
"eval_kl_divergence": NaN,
|
| 461 |
+
"eval_loss": 0.4384593963623047,
|
| 462 |
+
"eval_mae": 0.14925144612789154,
|
| 463 |
+
"eval_rmse": 0.20924808084964752,
|
| 464 |
+
"eval_runtime": 62.266,
|
| 465 |
+
"eval_samples_per_second": 37.806,
|
| 466 |
+
"eval_steps_per_second": 2.377,
|
| 467 |
"learning_rate": 0.0001,
|
| 468 |
"step": 10512
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 25.0,
|
| 472 |
+
"eval_explained_variance": 0.3649435043334961,
|
| 473 |
+
"eval_kl_divergence": Infinity,
|
| 474 |
+
"eval_loss": 0.4271779954433441,
|
| 475 |
+
"eval_mae": 0.14897416532039642,
|
| 476 |
+
"eval_rmse": 0.20736177265644073,
|
| 477 |
+
"eval_runtime": 63.0259,
|
| 478 |
+
"eval_samples_per_second": 37.35,
|
| 479 |
+
"eval_steps_per_second": 2.348,
|
| 480 |
"learning_rate": 0.0001,
|
| 481 |
"step": 10950
|
| 482 |
},
|
| 483 |
{
|
| 484 |
"epoch": 25.114155251141554,
|
| 485 |
+
"grad_norm": 0.14978627860546112,
|
| 486 |
"learning_rate": 0.0001,
|
| 487 |
+
"loss": 0.3988,
|
| 488 |
"step": 11000
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 26.0,
|
| 492 |
+
"eval_explained_variance": 0.36444517970085144,
|
| 493 |
+
"eval_kl_divergence": 1.1902661323547363,
|
| 494 |
+
"eval_loss": 0.41048941016197205,
|
| 495 |
+
"eval_mae": 0.148028165102005,
|
| 496 |
+
"eval_rmse": 0.20754428207874298,
|
| 497 |
+
"eval_runtime": 62.2088,
|
| 498 |
+
"eval_samples_per_second": 37.84,
|
| 499 |
+
"eval_steps_per_second": 2.379,
|
| 500 |
"learning_rate": 0.0001,
|
| 501 |
"step": 11388
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 26.255707762557076,
|
| 505 |
+
"grad_norm": 0.13278695940971375,
|
| 506 |
"learning_rate": 0.0001,
|
| 507 |
+
"loss": 0.3958,
|
| 508 |
"step": 11500
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 27.0,
|
| 512 |
+
"eval_explained_variance": 0.3687790632247925,
|
| 513 |
+
"eval_kl_divergence": 0.9915334582328796,
|
| 514 |
+
"eval_loss": 0.4096038341522217,
|
| 515 |
+
"eval_mae": 0.1493707150220871,
|
| 516 |
+
"eval_rmse": 0.20674215257167816,
|
| 517 |
+
"eval_runtime": 63.9932,
|
| 518 |
+
"eval_samples_per_second": 36.785,
|
| 519 |
+
"eval_steps_per_second": 2.313,
|
| 520 |
"learning_rate": 0.0001,
|
| 521 |
"step": 11826
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 27.397260273972602,
|
| 525 |
+
"grad_norm": 0.16862636804580688,
|
| 526 |
"learning_rate": 0.0001,
|
| 527 |
+
"loss": 0.3965,
|
| 528 |
"step": 12000
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 28.0,
|
| 532 |
+
"eval_explained_variance": 0.3680773675441742,
|
| 533 |
+
"eval_kl_divergence": 0.9668822288513184,
|
| 534 |
+
"eval_loss": 0.4104350507259369,
|
| 535 |
+
"eval_mae": 0.1493188589811325,
|
| 536 |
+
"eval_rmse": 0.20746104419231415,
|
| 537 |
+
"eval_runtime": 64.0647,
|
| 538 |
+
"eval_samples_per_second": 36.744,
|
| 539 |
+
"eval_steps_per_second": 2.31,
|
| 540 |
"learning_rate": 0.0001,
|
| 541 |
"step": 12264
|
| 542 |
},
|
| 543 |
{
|
| 544 |
"epoch": 28.538812785388128,
|
| 545 |
+
"grad_norm": 0.16052192449569702,
|
| 546 |
"learning_rate": 0.0001,
|
| 547 |
+
"loss": 0.396,
|
| 548 |
"step": 12500
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 29.0,
|
| 552 |
+
"eval_explained_variance": 0.3695773184299469,
|
| 553 |
+
"eval_kl_divergence": 1.0432541370391846,
|
| 554 |
+
"eval_loss": 0.40966179966926575,
|
| 555 |
+
"eval_mae": 0.1468651443719864,
|
| 556 |
+
"eval_rmse": 0.20694835484027863,
|
| 557 |
+
"eval_runtime": 63.2767,
|
| 558 |
+
"eval_samples_per_second": 37.202,
|
| 559 |
+
"eval_steps_per_second": 2.339,
|
| 560 |
"learning_rate": 0.0001,
|
| 561 |
"step": 12702
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 29.680365296803654,
|
| 565 |
+
"grad_norm": 0.14418508112430573,
|
| 566 |
"learning_rate": 0.0001,
|
| 567 |
+
"loss": 0.3936,
|
| 568 |
"step": 13000
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 30.0,
|
| 572 |
+
"eval_explained_variance": 0.373136430978775,
|
| 573 |
+
"eval_kl_divergence": 0.908222496509552,
|
| 574 |
+
"eval_loss": 0.4094092547893524,
|
| 575 |
+
"eval_mae": 0.14899054169654846,
|
| 576 |
+
"eval_rmse": 0.20645444095134735,
|
| 577 |
+
"eval_runtime": 62.5038,
|
| 578 |
+
"eval_samples_per_second": 37.662,
|
| 579 |
+
"eval_steps_per_second": 2.368,
|
| 580 |
"learning_rate": 0.0001,
|
| 581 |
"step": 13140
|
| 582 |
},
|
| 583 |
{
|
| 584 |
"epoch": 30.82191780821918,
|
| 585 |
+
"grad_norm": 0.19649599492549896,
|
| 586 |
"learning_rate": 0.0001,
|
| 587 |
+
"loss": 0.3944,
|
| 588 |
"step": 13500
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 31.0,
|
| 592 |
+
"eval_explained_variance": 0.3705109655857086,
|
| 593 |
+
"eval_kl_divergence": 1.0120004415512085,
|
| 594 |
+
"eval_loss": 0.40909385681152344,
|
| 595 |
+
"eval_mae": 0.14699043333530426,
|
| 596 |
+
"eval_rmse": 0.20654882490634918,
|
| 597 |
+
"eval_runtime": 63.2971,
|
| 598 |
+
"eval_samples_per_second": 37.19,
|
| 599 |
+
"eval_steps_per_second": 2.338,
|
| 600 |
"learning_rate": 0.0001,
|
| 601 |
"step": 13578
|
| 602 |
},
|
| 603 |
{
|
| 604 |
"epoch": 31.963470319634702,
|
| 605 |
+
"grad_norm": 0.228424534201622,
|
| 606 |
+
"learning_rate": 0.0001,
|
| 607 |
+
"loss": 0.3941,
|
| 608 |
"step": 14000
|
| 609 |
},
|
| 610 |
{
|
| 611 |
"epoch": 32.0,
|
| 612 |
+
"eval_explained_variance": 0.37417080998420715,
|
| 613 |
+
"eval_kl_divergence": 0.9708234071731567,
|
| 614 |
+
"eval_loss": 0.4084269404411316,
|
| 615 |
+
"eval_mae": 0.14826728403568268,
|
| 616 |
+
"eval_rmse": 0.2059999257326126,
|
| 617 |
+
"eval_runtime": 64.3761,
|
| 618 |
+
"eval_samples_per_second": 36.566,
|
| 619 |
+
"eval_steps_per_second": 2.299,
|
| 620 |
+
"learning_rate": 0.0001,
|
| 621 |
"step": 14016
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 33.0,
|
| 625 |
+
"eval_explained_variance": 0.37551748752593994,
|
| 626 |
+
"eval_kl_divergence": 0.9317126870155334,
|
| 627 |
+
"eval_loss": 0.40824124217033386,
|
| 628 |
+
"eval_mae": 0.14738227427005768,
|
| 629 |
+
"eval_rmse": 0.20570062100887299,
|
| 630 |
+
"eval_runtime": 63.4848,
|
| 631 |
+
"eval_samples_per_second": 37.08,
|
| 632 |
+
"eval_steps_per_second": 2.331,
|
| 633 |
+
"learning_rate": 0.0001,
|
| 634 |
"step": 14454
|
| 635 |
},
|
| 636 |
{
|
| 637 |
"epoch": 33.10502283105023,
|
| 638 |
+
"grad_norm": 0.2595873773097992,
|
| 639 |
+
"learning_rate": 0.0001,
|
| 640 |
+
"loss": 0.3933,
|
| 641 |
"step": 14500
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 34.0,
|
| 645 |
+
"eval_explained_variance": 0.37467464804649353,
|
| 646 |
+
"eval_kl_divergence": 0.9618669748306274,
|
| 647 |
+
"eval_loss": 0.40851354598999023,
|
| 648 |
+
"eval_mae": 0.14805640280246735,
|
| 649 |
+
"eval_rmse": 0.20609329640865326,
|
| 650 |
+
"eval_runtime": 65.3615,
|
| 651 |
+
"eval_samples_per_second": 36.015,
|
| 652 |
+
"eval_steps_per_second": 2.264,
|
| 653 |
+
"learning_rate": 0.0001,
|
| 654 |
"step": 14892
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 34.24657534246575,
|
| 658 |
+
"grad_norm": 0.26568445563316345,
|
| 659 |
+
"learning_rate": 0.0001,
|
| 660 |
+
"loss": 0.3926,
|
| 661 |
"step": 15000
|
| 662 |
},
|
| 663 |
{
|
| 664 |
"epoch": 35.0,
|
| 665 |
+
"eval_explained_variance": 0.375776082277298,
|
| 666 |
+
"eval_kl_divergence": 1.0522711277008057,
|
| 667 |
+
"eval_loss": 0.4072923958301544,
|
| 668 |
+
"eval_mae": 0.14664247632026672,
|
| 669 |
+
"eval_rmse": 0.20538650453090668,
|
| 670 |
+
"eval_runtime": 64.7697,
|
| 671 |
+
"eval_samples_per_second": 36.344,
|
| 672 |
+
"eval_steps_per_second": 2.285,
|
| 673 |
+
"learning_rate": 0.0001,
|
| 674 |
"step": 15330
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 35.38812785388128,
|
| 678 |
+
"grad_norm": 0.15931576490402222,
|
| 679 |
+
"learning_rate": 0.0001,
|
| 680 |
+
"loss": 0.3936,
|
| 681 |
"step": 15500
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 36.0,
|
| 685 |
+
"eval_explained_variance": 0.3770906925201416,
|
| 686 |
+
"eval_kl_divergence": 1.0621892213821411,
|
| 687 |
+
"eval_loss": 0.40741708874702454,
|
| 688 |
+
"eval_mae": 0.1460237056016922,
|
| 689 |
+
"eval_rmse": 0.20519912242889404,
|
| 690 |
+
"eval_runtime": 64.23,
|
| 691 |
+
"eval_samples_per_second": 36.65,
|
| 692 |
+
"eval_steps_per_second": 2.304,
|
| 693 |
+
"learning_rate": 0.0001,
|
| 694 |
"step": 15768
|
| 695 |
},
|
| 696 |
{
|
| 697 |
"epoch": 36.529680365296805,
|
| 698 |
+
"grad_norm": 0.22164444625377655,
|
| 699 |
+
"learning_rate": 0.0001,
|
| 700 |
+
"loss": 0.3935,
|
| 701 |
"step": 16000
|
| 702 |
},
|
| 703 |
{
|
| 704 |
"epoch": 37.0,
|
| 705 |
+
"eval_explained_variance": 0.38024798035621643,
|
| 706 |
+
"eval_kl_divergence": 1.020066261291504,
|
| 707 |
+
"eval_loss": 0.40657544136047363,
|
| 708 |
+
"eval_mae": 0.1456020027399063,
|
| 709 |
+
"eval_rmse": 0.20468135178089142,
|
| 710 |
+
"eval_runtime": 63.8016,
|
| 711 |
+
"eval_samples_per_second": 36.896,
|
| 712 |
+
"eval_steps_per_second": 2.32,
|
| 713 |
+
"learning_rate": 0.0001,
|
| 714 |
"step": 16206
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 37.67123287671233,
|
| 718 |
+
"grad_norm": 0.2097047120332718,
|
| 719 |
+
"learning_rate": 0.0001,
|
| 720 |
+
"loss": 0.3927,
|
| 721 |
"step": 16500
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 38.0,
|
| 725 |
+
"eval_explained_variance": 0.3799835741519928,
|
| 726 |
+
"eval_kl_divergence": 1.0557153224945068,
|
| 727 |
+
"eval_loss": 0.406360387802124,
|
| 728 |
+
"eval_mae": 0.14585663378238678,
|
| 729 |
+
"eval_rmse": 0.20454762876033783,
|
| 730 |
+
"eval_runtime": 63.2021,
|
| 731 |
+
"eval_samples_per_second": 37.246,
|
| 732 |
+
"eval_steps_per_second": 2.342,
|
| 733 |
+
"learning_rate": 0.0001,
|
| 734 |
"step": 16644
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 38.81278538812786,
|
| 738 |
+
"grad_norm": 0.34068891406059265,
|
| 739 |
+
"learning_rate": 0.0001,
|
| 740 |
+
"loss": 0.392,
|
| 741 |
"step": 17000
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 39.0,
|
| 745 |
+
"eval_explained_variance": 0.377095103263855,
|
| 746 |
+
"eval_kl_divergence": 1.005536675453186,
|
| 747 |
+
"eval_loss": 0.4077896773815155,
|
| 748 |
+
"eval_mae": 0.14692139625549316,
|
| 749 |
+
"eval_rmse": 0.2055957317352295,
|
| 750 |
+
"eval_runtime": 62.5136,
|
| 751 |
+
"eval_samples_per_second": 37.656,
|
| 752 |
+
"eval_steps_per_second": 2.367,
|
| 753 |
+
"learning_rate": 0.0001,
|
| 754 |
"step": 17082
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 39.954337899543376,
|
| 758 |
+
"grad_norm": 0.23111671209335327,
|
| 759 |
+
"learning_rate": 0.0001,
|
| 760 |
+
"loss": 0.3915,
|
| 761 |
"step": 17500
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 40.0,
|
| 765 |
+
"eval_explained_variance": 0.38054999709129333,
|
| 766 |
+
"eval_kl_divergence": 0.9849128723144531,
|
| 767 |
+
"eval_loss": 0.4068063199520111,
|
| 768 |
+
"eval_mae": 0.14637430012226105,
|
| 769 |
+
"eval_rmse": 0.20490336418151855,
|
| 770 |
+
"eval_runtime": 62.8552,
|
| 771 |
+
"eval_samples_per_second": 37.451,
|
| 772 |
+
"eval_steps_per_second": 2.355,
|
| 773 |
+
"learning_rate": 0.0001,
|
| 774 |
"step": 17520
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 41.0,
|
| 778 |
+
"eval_explained_variance": 0.3777576982975006,
|
| 779 |
+
"eval_kl_divergence": 0.899895191192627,
|
| 780 |
+
"eval_loss": 0.40890073776245117,
|
| 781 |
+
"eval_mae": 0.1488751471042633,
|
| 782 |
+
"eval_rmse": 0.20631897449493408,
|
| 783 |
+
"eval_runtime": 63.9481,
|
| 784 |
+
"eval_samples_per_second": 36.811,
|
| 785 |
+
"eval_steps_per_second": 2.314,
|
| 786 |
+
"learning_rate": 0.0001,
|
| 787 |
"step": 17958
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 41.0958904109589,
|
| 791 |
+
"grad_norm": 0.28402578830718994,
|
| 792 |
+
"learning_rate": 0.0001,
|
| 793 |
+
"loss": 0.3907,
|
| 794 |
"step": 18000
|
| 795 |
},
|
| 796 |
{
|
| 797 |
"epoch": 42.0,
|
| 798 |
+
"eval_explained_variance": 0.37971171736717224,
|
| 799 |
+
"eval_kl_divergence": 1.0616570711135864,
|
| 800 |
+
"eval_loss": 0.4068816602230072,
|
| 801 |
+
"eval_mae": 0.14634381234645844,
|
| 802 |
+
"eval_rmse": 0.20491831004619598,
|
| 803 |
+
"eval_runtime": 63.1884,
|
| 804 |
+
"eval_samples_per_second": 37.254,
|
| 805 |
+
"eval_steps_per_second": 2.342,
|
| 806 |
+
"learning_rate": 0.0001,
|
| 807 |
"step": 18396
|
| 808 |
},
|
| 809 |
{
|
| 810 |
"epoch": 42.23744292237443,
|
| 811 |
+
"grad_norm": 0.24103382229804993,
|
| 812 |
+
"learning_rate": 0.0001,
|
| 813 |
+
"loss": 0.3919,
|
| 814 |
"step": 18500
|
| 815 |
},
|
| 816 |
{
|
| 817 |
"epoch": 43.0,
|
| 818 |
+
"eval_explained_variance": 0.3829738199710846,
|
| 819 |
+
"eval_kl_divergence": 1.0520097017288208,
|
| 820 |
+
"eval_loss": 0.40578988194465637,
|
| 821 |
+
"eval_mae": 0.14498426020145416,
|
| 822 |
+
"eval_rmse": 0.2040938138961792,
|
| 823 |
+
"eval_runtime": 64.2301,
|
| 824 |
+
"eval_samples_per_second": 36.649,
|
| 825 |
+
"eval_steps_per_second": 2.304,
|
| 826 |
+
"learning_rate": 0.0001,
|
| 827 |
"step": 18834
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 43.37899543378995,
|
| 831 |
+
"grad_norm": 0.3461155891418457,
|
| 832 |
+
"learning_rate": 0.0001,
|
| 833 |
+
"loss": 0.3902,
|
| 834 |
"step": 19000
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 44.0,
|
| 838 |
+
"eval_explained_variance": 0.3809111416339874,
|
| 839 |
+
"eval_kl_divergence": 1.0053679943084717,
|
| 840 |
+
"eval_loss": 0.4070681035518646,
|
| 841 |
+
"eval_mae": 0.14748047292232513,
|
| 842 |
+
"eval_rmse": 0.20503848791122437,
|
| 843 |
+
"eval_runtime": 63.682,
|
| 844 |
+
"eval_samples_per_second": 36.965,
|
| 845 |
+
"eval_steps_per_second": 2.324,
|
| 846 |
+
"learning_rate": 0.0001,
|
| 847 |
"step": 19272
|
| 848 |
},
|
| 849 |
{
|
| 850 |
"epoch": 44.52054794520548,
|
| 851 |
+
"grad_norm": 0.21600213646888733,
|
| 852 |
+
"learning_rate": 0.0001,
|
| 853 |
+
"loss": 0.3896,
|
| 854 |
"step": 19500
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 45.0,
|
| 858 |
+
"eval_explained_variance": 0.38130107522010803,
|
| 859 |
+
"eval_kl_divergence": 1.13860285282135,
|
| 860 |
+
"eval_loss": 0.40669572353363037,
|
| 861 |
+
"eval_mae": 0.14402073621749878,
|
| 862 |
+
"eval_rmse": 0.2047145813703537,
|
| 863 |
+
"eval_runtime": 61.9143,
|
| 864 |
+
"eval_samples_per_second": 38.02,
|
| 865 |
+
"eval_steps_per_second": 2.39,
|
| 866 |
+
"learning_rate": 0.0001,
|
| 867 |
"step": 19710
|
| 868 |
},
|
| 869 |
{
|
| 870 |
"epoch": 45.662100456621005,
|
| 871 |
+
"grad_norm": 0.2100251168012619,
|
| 872 |
+
"learning_rate": 0.0001,
|
| 873 |
+
"loss": 0.3925,
|
| 874 |
"step": 20000
|
| 875 |
},
|
| 876 |
{
|
| 877 |
"epoch": 46.0,
|
| 878 |
+
"eval_explained_variance": 0.3830677270889282,
|
| 879 |
+
"eval_kl_divergence": 1.0252840518951416,
|
| 880 |
+
"eval_loss": 0.40670666098594666,
|
| 881 |
+
"eval_mae": 0.14572028815746307,
|
| 882 |
+
"eval_rmse": 0.20469875633716583,
|
| 883 |
+
"eval_runtime": 61.3533,
|
| 884 |
+
"eval_samples_per_second": 38.368,
|
| 885 |
+
"eval_steps_per_second": 2.412,
|
| 886 |
+
"learning_rate": 0.0001,
|
| 887 |
"step": 20148
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 46.80365296803653,
|
| 891 |
+
"grad_norm": 0.16854612529277802,
|
| 892 |
+
"learning_rate": 0.0001,
|
| 893 |
+
"loss": 0.3896,
|
| 894 |
"step": 20500
|
| 895 |
},
|
| 896 |
{
|
| 897 |
"epoch": 47.0,
|
| 898 |
+
"eval_explained_variance": 0.3834179639816284,
|
| 899 |
+
"eval_kl_divergence": 1.0430312156677246,
|
| 900 |
+
"eval_loss": 0.4062415659427643,
|
| 901 |
+
"eval_mae": 0.14726205170154572,
|
| 902 |
+
"eval_rmse": 0.20429861545562744,
|
| 903 |
+
"eval_runtime": 62.7532,
|
| 904 |
+
"eval_samples_per_second": 37.512,
|
| 905 |
+
"eval_steps_per_second": 2.358,
|
| 906 |
+
"learning_rate": 0.0001,
|
| 907 |
"step": 20586
|
| 908 |
},
|
| 909 |
{
|
| 910 |
"epoch": 47.945205479452056,
|
| 911 |
+
"grad_norm": 0.2040056735277176,
|
| 912 |
+
"learning_rate": 0.0001,
|
| 913 |
+
"loss": 0.3902,
|
| 914 |
"step": 21000
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 48.0,
|
| 918 |
+
"eval_explained_variance": 0.38119378685951233,
|
| 919 |
+
"eval_kl_divergence": 1.104145884513855,
|
| 920 |
+
"eval_loss": 0.4064981937408447,
|
| 921 |
+
"eval_mae": 0.14571230113506317,
|
| 922 |
+
"eval_rmse": 0.20479492843151093,
|
| 923 |
+
"eval_runtime": 66.5743,
|
| 924 |
+
"eval_samples_per_second": 35.359,
|
| 925 |
+
"eval_steps_per_second": 2.223,
|
| 926 |
+
"learning_rate": 0.0001,
|
| 927 |
"step": 21024
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 49.0,
|
| 931 |
+
"eval_explained_variance": 0.37976840138435364,
|
| 932 |
+
"eval_kl_divergence": 1.0702213048934937,
|
| 933 |
+
"eval_loss": 0.40709760785102844,
|
| 934 |
+
"eval_mae": 0.14625640213489532,
|
| 935 |
+
"eval_rmse": 0.20520327985286713,
|
| 936 |
+
"eval_runtime": 62.1191,
|
| 937 |
+
"eval_samples_per_second": 37.895,
|
| 938 |
+
"eval_steps_per_second": 2.383,
|
| 939 |
+
"learning_rate": 0.0001,
|
| 940 |
"step": 21462
|
| 941 |
},
|
| 942 |
{
|
| 943 |
"epoch": 49.08675799086758,
|
| 944 |
+
"grad_norm": 0.2242765724658966,
|
| 945 |
+
"learning_rate": 1e-05,
|
| 946 |
+
"loss": 0.3897,
|
| 947 |
"step": 21500
|
| 948 |
},
|
| 949 |
{
|
| 950 |
"epoch": 50.0,
|
| 951 |
+
"eval_explained_variance": 0.38569536805152893,
|
| 952 |
+
"eval_kl_divergence": 0.8917386531829834,
|
| 953 |
+
"eval_loss": 0.40644556283950806,
|
| 954 |
+
"eval_mae": 0.1479080468416214,
|
| 955 |
+
"eval_rmse": 0.2042473703622818,
|
| 956 |
+
"eval_runtime": 62.3011,
|
| 957 |
+
"eval_samples_per_second": 37.784,
|
| 958 |
+
"eval_steps_per_second": 2.376,
|
| 959 |
+
"learning_rate": 1e-05,
|
| 960 |
"step": 21900
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 50.22831050228311,
|
| 964 |
+
"grad_norm": 0.21291576325893402,
|
| 965 |
+
"learning_rate": 1e-05,
|
| 966 |
+
"loss": 0.3875,
|
| 967 |
"step": 22000
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 51.0,
|
| 971 |
+
"eval_explained_variance": 0.3844810426235199,
|
| 972 |
+
"eval_kl_divergence": 0.9960101842880249,
|
| 973 |
+
"eval_loss": 0.40579161047935486,
|
| 974 |
+
"eval_mae": 0.14372152090072632,
|
| 975 |
+
"eval_rmse": 0.20405276119709015,
|
| 976 |
+
"eval_runtime": 61.2114,
|
| 977 |
+
"eval_samples_per_second": 38.457,
|
| 978 |
+
"eval_steps_per_second": 2.418,
|
| 979 |
+
"learning_rate": 1e-05,
|
| 980 |
"step": 22338
|
| 981 |
},
|
| 982 |
{
|
| 983 |
"epoch": 51.36986301369863,
|
| 984 |
+
"grad_norm": 0.24317112565040588,
|
| 985 |
+
"learning_rate": 1e-05,
|
| 986 |
+
"loss": 0.3874,
|
| 987 |
"step": 22500
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 52.0,
|
| 991 |
+
"eval_explained_variance": 0.385125994682312,
|
| 992 |
+
"eval_kl_divergence": 1.0567286014556885,
|
| 993 |
+
"eval_loss": 0.40528106689453125,
|
| 994 |
+
"eval_mae": 0.14458806812763214,
|
| 995 |
+
"eval_rmse": 0.20368923246860504,
|
| 996 |
+
"eval_runtime": 62.8042,
|
| 997 |
+
"eval_samples_per_second": 37.482,
|
| 998 |
+
"eval_steps_per_second": 2.357,
|
| 999 |
+
"learning_rate": 1e-05,
|
| 1000 |
"step": 22776
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 52.51141552511415,
|
| 1004 |
+
"grad_norm": 0.30417612195014954,
|
| 1005 |
+
"learning_rate": 1e-05,
|
| 1006 |
+
"loss": 0.3899,
|
| 1007 |
"step": 23000
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 53.0,
|
| 1011 |
+
"eval_explained_variance": 0.3858625590801239,
|
| 1012 |
+
"eval_kl_divergence": 1.0205212831497192,
|
| 1013 |
+
"eval_loss": 0.4056229293346405,
|
| 1014 |
+
"eval_mae": 0.14624176919460297,
|
| 1015 |
+
"eval_rmse": 0.20387189090251923,
|
| 1016 |
+
"eval_runtime": 62.9117,
|
| 1017 |
+
"eval_samples_per_second": 37.418,
|
| 1018 |
+
"eval_steps_per_second": 2.353,
|
| 1019 |
+
"learning_rate": 1e-05,
|
| 1020 |
"step": 23214
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 53.65296803652968,
|
| 1024 |
+
"grad_norm": 0.24982061982154846,
|
| 1025 |
+
"learning_rate": 1e-05,
|
| 1026 |
+
"loss": 0.3892,
|
| 1027 |
"step": 23500
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 54.0,
|
| 1031 |
+
"eval_explained_variance": 0.3853992521762848,
|
| 1032 |
+
"eval_kl_divergence": 0.9905322194099426,
|
| 1033 |
+
"eval_loss": 0.4058997631072998,
|
| 1034 |
+
"eval_mae": 0.14412301778793335,
|
| 1035 |
+
"eval_rmse": 0.20410750806331635,
|
| 1036 |
+
"eval_runtime": 63.4824,
|
| 1037 |
+
"eval_samples_per_second": 37.081,
|
| 1038 |
+
"eval_steps_per_second": 2.331,
|
| 1039 |
+
"learning_rate": 1e-05,
|
| 1040 |
"step": 23652
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 54.794520547945204,
|
| 1044 |
+
"grad_norm": 0.2903271019458771,
|
| 1045 |
+
"learning_rate": 1e-05,
|
| 1046 |
+
"loss": 0.3892,
|
| 1047 |
"step": 24000
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 55.0,
|
| 1051 |
+
"eval_explained_variance": 0.38560736179351807,
|
| 1052 |
+
"eval_kl_divergence": 0.937917947769165,
|
| 1053 |
+
"eval_loss": 0.4060685932636261,
|
| 1054 |
+
"eval_mae": 0.1471087485551834,
|
| 1055 |
+
"eval_rmse": 0.20407529175281525,
|
| 1056 |
+
"eval_runtime": 64.4026,
|
| 1057 |
+
"eval_samples_per_second": 36.551,
|
| 1058 |
+
"eval_steps_per_second": 2.298,
|
| 1059 |
+
"learning_rate": 1e-05,
|
| 1060 |
"step": 24090
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
"epoch": 55.93607305936073,
|
| 1064 |
+
"grad_norm": 0.2701994776725769,
|
| 1065 |
+
"learning_rate": 1e-05,
|
| 1066 |
+
"loss": 0.3869,
|
| 1067 |
"step": 24500
|
| 1068 |
},
|
| 1069 |
{
|
| 1070 |
"epoch": 56.0,
|
| 1071 |
+
"eval_explained_variance": 0.3853694200515747,
|
| 1072 |
+
"eval_kl_divergence": 0.9695614576339722,
|
| 1073 |
+
"eval_loss": 0.40592971444129944,
|
| 1074 |
+
"eval_mae": 0.14540034532546997,
|
| 1075 |
+
"eval_rmse": 0.20410047471523285,
|
| 1076 |
+
"eval_runtime": 63.4818,
|
| 1077 |
+
"eval_samples_per_second": 37.081,
|
| 1078 |
+
"eval_steps_per_second": 2.331,
|
| 1079 |
+
"learning_rate": 1e-05,
|
| 1080 |
"step": 24528
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
"epoch": 57.0,
|
| 1084 |
+
"eval_explained_variance": 0.3842361867427826,
|
| 1085 |
+
"eval_kl_divergence": 1.0590680837631226,
|
| 1086 |
+
"eval_loss": 0.4058408737182617,
|
| 1087 |
+
"eval_mae": 0.1459987610578537,
|
| 1088 |
+
"eval_rmse": 0.20412230491638184,
|
| 1089 |
+
"eval_runtime": 62.5651,
|
| 1090 |
+
"eval_samples_per_second": 37.625,
|
| 1091 |
+
"eval_steps_per_second": 2.366,
|
| 1092 |
+
"learning_rate": 1e-05,
|
| 1093 |
"step": 24966
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 57.077625570776256,
|
| 1097 |
+
"grad_norm": 0.20055490732192993,
|
| 1098 |
+
"learning_rate": 1e-05,
|
| 1099 |
+
"loss": 0.3874,
|
| 1100 |
"step": 25000
|
| 1101 |
},
|
| 1102 |
{
|
| 1103 |
"epoch": 58.0,
|
| 1104 |
+
"eval_explained_variance": 0.38601794838905334,
|
| 1105 |
+
"eval_kl_divergence": 0.9275628328323364,
|
| 1106 |
+
"eval_loss": 0.4063320457935333,
|
| 1107 |
+
"eval_mae": 0.14603658020496368,
|
| 1108 |
+
"eval_rmse": 0.20428447425365448,
|
| 1109 |
+
"eval_runtime": 62.6353,
|
| 1110 |
+
"eval_samples_per_second": 37.583,
|
| 1111 |
+
"eval_steps_per_second": 2.363,
|
| 1112 |
+
"learning_rate": 1e-05,
|
| 1113 |
"step": 25404
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 58.21917808219178,
|
| 1117 |
+
"grad_norm": 0.24670056998729706,
|
| 1118 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1119 |
+
"loss": 0.3887,
|
| 1120 |
"step": 25500
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 59.0,
|
| 1124 |
+
"eval_explained_variance": 0.3867626488208771,
|
| 1125 |
+
"eval_kl_divergence": 0.9793874621391296,
|
| 1126 |
+
"eval_loss": 0.4056239724159241,
|
| 1127 |
+
"eval_mae": 0.14530591666698456,
|
| 1128 |
+
"eval_rmse": 0.20382745563983917,
|
| 1129 |
+
"eval_runtime": 63.6318,
|
| 1130 |
+
"eval_samples_per_second": 36.994,
|
| 1131 |
+
"eval_steps_per_second": 2.326,
|
| 1132 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1133 |
"step": 25842
|
| 1134 |
},
|
| 1135 |
{
|
| 1136 |
"epoch": 59.36073059360731,
|
| 1137 |
+
"grad_norm": 0.27373573184013367,
|
| 1138 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1139 |
+
"loss": 0.3882,
|
| 1140 |
"step": 26000
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
"epoch": 60.0,
|
| 1144 |
+
"eval_explained_variance": 0.3851200044155121,
|
| 1145 |
+
"eval_kl_divergence": 1.0348856449127197,
|
| 1146 |
+
"eval_loss": 0.40571752190589905,
|
| 1147 |
+
"eval_mae": 0.1446085125207901,
|
| 1148 |
+
"eval_rmse": 0.20402370393276215,
|
| 1149 |
+
"eval_runtime": 63.8531,
|
| 1150 |
+
"eval_samples_per_second": 36.866,
|
| 1151 |
+
"eval_steps_per_second": 2.318,
|
| 1152 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1153 |
"step": 26280
|
| 1154 |
},
|
| 1155 |
{
|
| 1156 |
"epoch": 60.50228310502283,
|
| 1157 |
+
"grad_norm": 0.23867332935333252,
|
| 1158 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1159 |
+
"loss": 0.389,
|
| 1160 |
"step": 26500
|
| 1161 |
},
|
| 1162 |
{
|
| 1163 |
"epoch": 61.0,
|
| 1164 |
+
"eval_explained_variance": 0.38573384284973145,
|
| 1165 |
+
"eval_kl_divergence": 0.9859956502914429,
|
| 1166 |
+
"eval_loss": 0.4058452248573303,
|
| 1167 |
+
"eval_mae": 0.14494158327579498,
|
| 1168 |
+
"eval_rmse": 0.2040751427412033,
|
| 1169 |
+
"eval_runtime": 61.8751,
|
| 1170 |
+
"eval_samples_per_second": 38.044,
|
| 1171 |
+
"eval_steps_per_second": 2.392,
|
| 1172 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1173 |
"step": 26718
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
"epoch": 61.64383561643836,
|
| 1177 |
+
"grad_norm": 0.21306726336479187,
|
| 1178 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1179 |
+
"loss": 0.3882,
|
| 1180 |
"step": 27000
|
| 1181 |
},
|
| 1182 |
{
|
| 1183 |
"epoch": 62.0,
|
| 1184 |
+
"eval_explained_variance": 0.3864554166793823,
|
| 1185 |
+
"eval_kl_divergence": 0.9528394937515259,
|
| 1186 |
+
"eval_loss": 0.4054276943206787,
|
| 1187 |
+
"eval_mae": 0.14455263316631317,
|
| 1188 |
+
"eval_rmse": 0.20368416607379913,
|
| 1189 |
+
"eval_runtime": 61.7886,
|
| 1190 |
+
"eval_samples_per_second": 38.098,
|
| 1191 |
+
"eval_steps_per_second": 2.395,
|
| 1192 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1193 |
"step": 27156
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 62.0,
|
| 1197 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1198 |
"step": 27156,
|
| 1199 |
"total_flos": 6.42634409963284e+19,
|
| 1200 |
+
"train_loss": 0.3985773164651095,
|
| 1201 |
+
"train_runtime": 16834.9641,
|
| 1202 |
+
"train_samples_per_second": 62.397,
|
| 1203 |
+
"train_steps_per_second": 3.903
|
| 1204 |
}
|
| 1205 |
],
|
| 1206 |
"logging_steps": 500,
|