Commit
•
c0efc49
1
Parent(s):
eda9015
Training in progress, epoch 1
Browse files- README.md +172 -0
- all_results.json +17 -0
- config.json +89 -0
- logs/events.out.tfevents.1731560400.datavisu2 +3 -0
- logs/events.out.tfevents.1731577798.datavisu2 +3 -0
- logs/events.out.tfevents.1731607061.datavisu2 +3 -0
- model.safetensors +3 -0
- preprocessor_config.json +45 -0
- runs/events.out.tfevents.1731560383.datavisu2 +3 -0
- runs/events.out.tfevents.1731607045.datavisu2 +0 -0
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +1236 -0
- training_args.bin +3 -0
- transforms.json +44 -0
README.md
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
language:
|
| 4 |
+
- eng
|
| 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 |
+
drone-DinoVdeau-from-binary is a fine-tuned version of [drone-DinoVdeau-from-binary-large-2024_11_14-batch-size16_freeze_probs](https://huggingface.co/drone-DinoVdeau-from-binary-large-2024_11_14-batch-size16_freeze_probs). It achieves the following results on the test set:
|
| 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 |
+
# Model description
|
| 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 |
+
The source code for training the model can be found in this [Git repository](https://github.com/SeatizenDOI/DinoVdeau).
|
| 33 |
+
|
| 34 |
+
- **Developed by:** [lombardata](https://huggingface.co/lombardata), credits to [César Leblanc](https://huggingface.co/CesarLeblanc) and [Victor Illien](https://huggingface.co/groderg)
|
| 35 |
+
|
| 36 |
+
---
|
| 37 |
+
|
| 38 |
+
# Intended uses & limitations
|
| 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 |
+
# Training and evaluation data
|
| 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 |
+
# Training procedure
|
| 63 |
+
|
| 64 |
+
## Training hyperparameters
|
| 65 |
+
|
| 66 |
+
The following hyperparameters were used during training:
|
| 67 |
+
|
| 68 |
+
- **Number of Epochs**: 62.0
|
| 69 |
+
- **Learning Rate**: 0.001
|
| 70 |
+
- **Train Batch Size**: 16
|
| 71 |
+
- **Eval Batch Size**: 16
|
| 72 |
+
- **Optimizer**: Adam
|
| 73 |
+
- **LR Scheduler Type**: ReduceLROnPlateau with a patience of 5 epochs and a factor of 0.1
|
| 74 |
+
- **Freeze Encoder**: Yes
|
| 75 |
+
- **Data Augmentation**: Yes
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
## Data Augmentation
|
| 79 |
+
Data were augmented using the following transformations :
|
| 80 |
+
|
| 81 |
+
Train Transforms
|
| 82 |
+
- **PreProcess**: No additional parameters
|
| 83 |
+
- **Resize**: probability=1.00
|
| 84 |
+
- **RandomHorizontalFlip**: probability=0.25
|
| 85 |
+
- **RandomVerticalFlip**: probability=0.25
|
| 86 |
+
- **ColorJiggle**: probability=0.25
|
| 87 |
+
- **RandomPerspective**: probability=0.25
|
| 88 |
+
- **Normalize**: probability=1.00
|
| 89 |
+
|
| 90 |
+
Val Transforms
|
| 91 |
+
- **PreProcess**: No additional parameters
|
| 92 |
+
- **Resize**: probability=1.00
|
| 93 |
+
- **Normalize**: probability=1.00
|
| 94 |
+
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
## Training results
|
| 98 |
+
Epoch | Validation Loss | MAE | RMSE | KL div | Learning Rate
|
| 99 |
+
--- | --- | --- | --- | --- | ---
|
| 100 |
+
1 | 0.4821413457393646 | 0.1308 | 0.1731 | 0.4219 | 0.001
|
| 101 |
+
2 | 0.4784533977508545 | 0.1263 | 0.1710 | 0.6148 | 0.001
|
| 102 |
+
3 | 0.47776785492897034 | 0.1273 | 0.1699 | 0.4880 | 0.001
|
| 103 |
+
4 | 0.4793245792388916 | 0.1290 | 0.1710 | 0.3418 | 0.001
|
| 104 |
+
5 | 0.47521594166755676 | 0.1280 | 0.1674 | 0.3456 | 0.001
|
| 105 |
+
6 | 0.478865385055542 | 0.1254 | 0.1707 | 0.6403 | 0.001
|
| 106 |
+
7 | 0.4779475927352905 | 0.1288 | 0.1709 | 0.5492 | 0.001
|
| 107 |
+
8 | 0.4756968021392822 | 0.1270 | 0.1678 | 0.3383 | 0.001
|
| 108 |
+
9 | 0.4731782376766205 | 0.1231 | 0.1657 | 0.5418 | 0.001
|
| 109 |
+
10 | 0.4799855649471283 | 0.1321 | 0.1723 | 0.1547 | 0.001
|
| 110 |
+
11 | 0.4731641411781311 | 0.1256 | 0.1656 | 0.3437 | 0.001
|
| 111 |
+
12 | 0.47767141461372375 | 0.1293 | 0.1701 | 0.2947 | 0.001
|
| 112 |
+
13 | 0.48009705543518066 | 0.1248 | 0.1677 | 0.6136 | 0.001
|
| 113 |
+
14 | 0.4954195022583008 | 0.1253 | 0.1669 | inf | 0.001
|
| 114 |
+
15 | 0.4812238812446594 | 0.1254 | 0.1662 | inf | 0.001
|
| 115 |
+
16 | 0.4858487546443939 | 0.1243 | 0.1656 | inf | 0.0001
|
| 116 |
+
17 | 0.47084349393844604 | 0.1223 | 0.1628 | 0.4165 | 0.0001
|
| 117 |
+
18 | 0.4707622528076172 | 0.1216 | 0.1626 | 0.4066 | 0.0001
|
| 118 |
+
19 | 0.47095733880996704 | 0.1227 | 0.1632 | 0.3185 | 0.0001
|
| 119 |
+
20 | 0.4696938395500183 | 0.1205 | 0.1620 | 0.4651 | 0.0001
|
| 120 |
+
21 | 0.46922874450683594 | 0.1216 | 0.1614 | 0.3773 | 0.0001
|
| 121 |
+
22 | 0.4685634672641754 | 0.1203 | 0.1609 | 0.4611 | 0.0001
|
| 122 |
+
23 | 0.47018975019454956 | 0.1226 | 0.1621 | 0.2499 | 0.0001
|
| 123 |
+
24 | 0.4705464243888855 | 0.1213 | 0.1628 | 0.3702 | 0.0001
|
| 124 |
+
25 | 0.4678299129009247 | 0.1188 | 0.1601 | 0.5133 | 0.0001
|
| 125 |
+
26 | 0.46802961826324463 | 0.1179 | 0.1604 | 0.5665 | 0.0001
|
| 126 |
+
27 | 0.4680938124656677 | 0.1200 | 0.1604 | 0.4242 | 0.0001
|
| 127 |
+
28 | 0.4693257212638855 | 0.1215 | 0.1616 | 0.2968 | 0.0001
|
| 128 |
+
29 | 0.46847742795944214 | 0.1197 | 0.1607 | 0.3925 | 0.0001
|
| 129 |
+
30 | 0.46944141387939453 | 0.1221 | 0.1614 | 0.2495 | 0.0001
|
| 130 |
+
31 | 0.4678958058357239 | 0.1185 | 0.1601 | 0.4510 | 0.0001
|
| 131 |
+
32 | 0.46778997778892517 | 0.1193 | 0.1601 | 0.3886 | 1e-05
|
| 132 |
+
33 | 0.4686955511569977 | 0.1202 | 0.1606 | 0.3132 | 1e-05
|
| 133 |
+
34 | 0.46784329414367676 | 0.1195 | 0.1601 | 0.3958 | 1e-05
|
| 134 |
+
35 | 0.4671097695827484 | 0.1180 | 0.1595 | 0.4579 | 1e-05
|
| 135 |
+
36 | 0.46735426783561707 | 0.1184 | 0.1595 | 0.4391 | 1e-05
|
| 136 |
+
37 | 0.468018501996994 | 0.1191 | 0.1600 | 0.3633 | 1e-05
|
| 137 |
+
38 | 0.46701580286026 | 0.1186 | 0.1592 | 0.4303 | 1e-05
|
| 138 |
+
39 | 0.4673251509666443 | 0.1187 | 0.1596 | 0.4562 | 1e-05
|
| 139 |
+
40 | 0.4673212468624115 | 0.1189 | 0.1594 | 0.4065 | 1e-05
|
| 140 |
+
41 | 0.4677547216415405 | 0.1206 | 0.1599 | 0.3336 | 1e-05
|
| 141 |
+
42 | 0.4671882390975952 | 0.1178 | 0.1597 | 0.5312 | 1e-05
|
| 142 |
+
43 | 0.46716412901878357 | 0.1185 | 0.1592 | 0.3924 | 1e-05
|
| 143 |
+
44 | 0.4678168296813965 | 0.1194 | 0.1602 | 0.4259 | 1e-05
|
| 144 |
+
45 | 0.46699702739715576 | 0.1172 | 0.1594 | 0.5214 | 1.0000000000000002e-06
|
| 145 |
+
46 | 0.46712958812713623 | 0.1188 | 0.1594 | 0.4175 | 1.0000000000000002e-06
|
| 146 |
+
47 | 0.4666382074356079 | 0.1188 | 0.1589 | 0.4446 | 1.0000000000000002e-06
|
| 147 |
+
48 | 0.46714723110198975 | 0.1180 | 0.1597 | 0.5755 | 1.0000000000000002e-06
|
| 148 |
+
49 | 0.46758702397346497 | 0.1192 | 0.1600 | 0.4304 | 1.0000000000000002e-06
|
| 149 |
+
50 | 0.46752068400382996 | 0.1204 | 0.1595 | 0.3337 | 1.0000000000000002e-06
|
| 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 |
+
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 62.0,
|
| 3 |
+
"eval_explained_variance": 0.44826042652130127,
|
| 4 |
+
"eval_kl_divergence": 0.41849657893180847,
|
| 5 |
+
"eval_loss": 0.4693068563938141,
|
| 6 |
+
"eval_mae": 0.11716800183057785,
|
| 7 |
+
"eval_rmse": 0.15763415396213531,
|
| 8 |
+
"eval_runtime": 70.8809,
|
| 9 |
+
"eval_samples_per_second": 33.253,
|
| 10 |
+
"eval_steps_per_second": 2.088,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 12 |
+
"total_flos": 6.42634409963284e+19,
|
| 13 |
+
"train_loss": 0.466335079458891,
|
| 14 |
+
"train_runtime": 17194.6751,
|
| 15 |
+
"train_samples_per_second": 61.092,
|
| 16 |
+
"train_steps_per_second": 3.821
|
| 17 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/dinov2-large",
|
| 3 |
+
"apply_layernorm": true,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Dinov2ForImageClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_probs_dropout_prob": 0.0,
|
| 8 |
+
"drop_path_rate": 0.0,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.0,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "Acropore_branched",
|
| 14 |
+
"1": "Acropore_digitised",
|
| 15 |
+
"2": "Acropore_tabular",
|
| 16 |
+
"3": "Algae",
|
| 17 |
+
"4": "Dead_coral",
|
| 18 |
+
"5": "Millepore",
|
| 19 |
+
"6": "No_acropore_encrusting",
|
| 20 |
+
"7": "No_acropore_massive",
|
| 21 |
+
"8": "No_acropore_sub_massive",
|
| 22 |
+
"9": "Rock",
|
| 23 |
+
"10": "Rubble",
|
| 24 |
+
"11": "Sand"
|
| 25 |
+
},
|
| 26 |
+
"image_size": 164,
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"label2id": {
|
| 29 |
+
"Acropore_branched": 0,
|
| 30 |
+
"Acropore_digitised": 1,
|
| 31 |
+
"Acropore_tabular": 2,
|
| 32 |
+
"Algae": 3,
|
| 33 |
+
"Dead_coral": 4,
|
| 34 |
+
"Millepore": 5,
|
| 35 |
+
"No_acropore_encrusting": 6,
|
| 36 |
+
"No_acropore_massive": 7,
|
| 37 |
+
"No_acropore_sub_massive": 8,
|
| 38 |
+
"Rock": 9,
|
| 39 |
+
"Rubble": 10,
|
| 40 |
+
"Sand": 11
|
| 41 |
+
},
|
| 42 |
+
"layer_norm_eps": 1e-06,
|
| 43 |
+
"layerscale_value": 1.0,
|
| 44 |
+
"mlp_ratio": 4,
|
| 45 |
+
"model_type": "dinov2",
|
| 46 |
+
"num_attention_heads": 16,
|
| 47 |
+
"num_channels": 3,
|
| 48 |
+
"num_hidden_layers": 24,
|
| 49 |
+
"out_features": [
|
| 50 |
+
"stage24"
|
| 51 |
+
],
|
| 52 |
+
"out_indices": [
|
| 53 |
+
24
|
| 54 |
+
],
|
| 55 |
+
"patch_size": 14,
|
| 56 |
+
"problem_type": "multi_label_classification",
|
| 57 |
+
"qkv_bias": true,
|
| 58 |
+
"reshape_hidden_states": true,
|
| 59 |
+
"stage_names": [
|
| 60 |
+
"stem",
|
| 61 |
+
"stage1",
|
| 62 |
+
"stage2",
|
| 63 |
+
"stage3",
|
| 64 |
+
"stage4",
|
| 65 |
+
"stage5",
|
| 66 |
+
"stage6",
|
| 67 |
+
"stage7",
|
| 68 |
+
"stage8",
|
| 69 |
+
"stage9",
|
| 70 |
+
"stage10",
|
| 71 |
+
"stage11",
|
| 72 |
+
"stage12",
|
| 73 |
+
"stage13",
|
| 74 |
+
"stage14",
|
| 75 |
+
"stage15",
|
| 76 |
+
"stage16",
|
| 77 |
+
"stage17",
|
| 78 |
+
"stage18",
|
| 79 |
+
"stage19",
|
| 80 |
+
"stage20",
|
| 81 |
+
"stage21",
|
| 82 |
+
"stage22",
|
| 83 |
+
"stage23",
|
| 84 |
+
"stage24"
|
| 85 |
+
],
|
| 86 |
+
"torch_dtype": "float32",
|
| 87 |
+
"transformers_version": "4.41.0",
|
| 88 |
+
"use_swiglu_ffn": false
|
| 89 |
+
}
|
logs/events.out.tfevents.1731560400.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fdc7ba52b14864d7c78b132f832294a8dcf8c0a37960f6aad3a72e55e9e693
|
| 3 |
+
size 52031
|
logs/events.out.tfevents.1731577798.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a5cd31e320be7b4d7c1d59352e2bb65d4ad723b15133e6fbc69205969198d68c
|
| 3 |
+
size 593
|
logs/events.out.tfevents.1731607061.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8983be708225f95b0195f1bd6b52ba33032cb21cb2d24ac833f876ff6451325
|
| 3 |
+
size 6214
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8656b6e7b091757f3d36e6e1ef5ba34a52c9657f272178c6b5f32f82bad7f8e3
|
| 3 |
+
size 1222956704
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_center_crop",
|
| 8 |
+
"crop_size",
|
| 9 |
+
"do_rescale",
|
| 10 |
+
"rescale_factor",
|
| 11 |
+
"do_normalize",
|
| 12 |
+
"image_mean",
|
| 13 |
+
"image_std",
|
| 14 |
+
"do_convert_rgb",
|
| 15 |
+
"return_tensors",
|
| 16 |
+
"data_format",
|
| 17 |
+
"input_data_format"
|
| 18 |
+
],
|
| 19 |
+
"crop_size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
},
|
| 23 |
+
"do_center_crop": false,
|
| 24 |
+
"do_convert_rgb": true,
|
| 25 |
+
"do_normalize": true,
|
| 26 |
+
"do_rescale": true,
|
| 27 |
+
"do_resize": true,
|
| 28 |
+
"image_mean": [
|
| 29 |
+
0.485,
|
| 30 |
+
0.456,
|
| 31 |
+
0.406
|
| 32 |
+
],
|
| 33 |
+
"image_processor_type": "BitImageProcessor",
|
| 34 |
+
"image_std": [
|
| 35 |
+
0.229,
|
| 36 |
+
0.224,
|
| 37 |
+
0.225
|
| 38 |
+
],
|
| 39 |
+
"resample": 3,
|
| 40 |
+
"rescale_factor": 0.00392156862745098,
|
| 41 |
+
"size": {
|
| 42 |
+
"height": 164,
|
| 43 |
+
"width": 164
|
| 44 |
+
}
|
| 45 |
+
}
|
runs/events.out.tfevents.1731560383.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00425745a3a22ae5f550088ec56895bfe16144e3347e42b718c3f2c287394a56
|
| 3 |
+
size 40
|
runs/events.out.tfevents.1731607045.datavisu2
ADDED
|
File without changes
|
test_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 62.0,
|
| 3 |
+
"eval_explained_variance": 0.44826042652130127,
|
| 4 |
+
"eval_kl_divergence": 0.41849657893180847,
|
| 5 |
+
"eval_loss": 0.4693068563938141,
|
| 6 |
+
"eval_mae": 0.11716800183057785,
|
| 7 |
+
"eval_rmse": 0.15763415396213531,
|
| 8 |
+
"eval_runtime": 70.8809,
|
| 9 |
+
"eval_samples_per_second": 33.253,
|
| 10 |
+
"eval_steps_per_second": 2.088,
|
| 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": 6.42634409963284e+19,
|
| 5 |
+
"train_loss": 0.466335079458891,
|
| 6 |
+
"train_runtime": 17194.6751,
|
| 7 |
+
"train_samples_per_second": 61.092,
|
| 8 |
+
"train_steps_per_second": 3.821
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1236 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.466439425945282,
|
| 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,
|
| 6 |
+
"global_step": 27156,
|
| 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": 0.3631434440612793,
|
| 14 |
+
"eval_kl_divergence": 0.421912282705307,
|
| 15 |
+
"eval_loss": 0.4821413457393646,
|
| 16 |
+
"eval_mae": 0.13084472715854645,
|
| 17 |
+
"eval_rmse": 0.173090398311615,
|
| 18 |
+
"eval_runtime": 64.2475,
|
| 19 |
+
"eval_samples_per_second": 36.64,
|
| 20 |
+
"eval_steps_per_second": 2.304,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"step": 438
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.1415525114155252,
|
| 26 |
+
"grad_norm": 0.4757365882396698,
|
| 27 |
+
"learning_rate": 0.001,
|
| 28 |
+
"loss": 0.5317,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_explained_variance": 0.3752269744873047,
|
| 34 |
+
"eval_kl_divergence": 0.6148446202278137,
|
| 35 |
+
"eval_loss": 0.4784533977508545,
|
| 36 |
+
"eval_mae": 0.12629373371601105,
|
| 37 |
+
"eval_rmse": 0.17098082602024078,
|
| 38 |
+
"eval_runtime": 63.6833,
|
| 39 |
+
"eval_samples_per_second": 36.964,
|
| 40 |
+
"eval_steps_per_second": 2.324,
|
| 41 |
+
"learning_rate": 0.001,
|
| 42 |
+
"step": 876
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 2.2831050228310503,
|
| 46 |
+
"grad_norm": 0.4254082143306732,
|
| 47 |
+
"learning_rate": 0.001,
|
| 48 |
+
"loss": 0.4832,
|
| 49 |
+
"step": 1000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"eval_explained_variance": 0.3838556706905365,
|
| 54 |
+
"eval_kl_divergence": 0.48802560567855835,
|
| 55 |
+
"eval_loss": 0.47776785492897034,
|
| 56 |
+
"eval_mae": 0.12731628119945526,
|
| 57 |
+
"eval_rmse": 0.16985835134983063,
|
| 58 |
+
"eval_runtime": 62.637,
|
| 59 |
+
"eval_samples_per_second": 37.582,
|
| 60 |
+
"eval_steps_per_second": 2.363,
|
| 61 |
+
"learning_rate": 0.001,
|
| 62 |
+
"step": 1314
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.4246575342465753,
|
| 66 |
+
"grad_norm": 0.2670271098613739,
|
| 67 |
+
"learning_rate": 0.001,
|
| 68 |
+
"loss": 0.4791,
|
| 69 |
+
"step": 1500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"eval_explained_variance": 0.38376739621162415,
|
| 74 |
+
"eval_kl_divergence": 0.3418101370334625,
|
| 75 |
+
"eval_loss": 0.4793245792388916,
|
| 76 |
+
"eval_mae": 0.12901858985424042,
|
| 77 |
+
"eval_rmse": 0.171015664935112,
|
| 78 |
+
"eval_runtime": 62.2828,
|
| 79 |
+
"eval_samples_per_second": 37.795,
|
| 80 |
+
"eval_steps_per_second": 2.376,
|
| 81 |
+
"learning_rate": 0.001,
|
| 82 |
+
"step": 1752
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 4.566210045662101,
|
| 86 |
+
"grad_norm": 0.20498104393482208,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"loss": 0.4771,
|
| 89 |
+
"step": 2000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"eval_explained_variance": 0.40547776222229004,
|
| 94 |
+
"eval_kl_divergence": 0.34562820196151733,
|
| 95 |
+
"eval_loss": 0.47521594166755676,
|
| 96 |
+
"eval_mae": 0.12799377739429474,
|
| 97 |
+
"eval_rmse": 0.16736441850662231,
|
| 98 |
+
"eval_runtime": 62.7606,
|
| 99 |
+
"eval_samples_per_second": 37.508,
|
| 100 |
+
"eval_steps_per_second": 2.358,
|
| 101 |
+
"learning_rate": 0.001,
|
| 102 |
+
"step": 2190
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 5.707762557077626,
|
| 106 |
+
"grad_norm": 0.24335043132305145,
|
| 107 |
+
"learning_rate": 0.001,
|
| 108 |
+
"loss": 0.4752,
|
| 109 |
+
"step": 2500
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"eval_explained_variance": 0.3849389851093292,
|
| 114 |
+
"eval_kl_divergence": 0.6402714848518372,
|
| 115 |
+
"eval_loss": 0.478865385055542,
|
| 116 |
+
"eval_mae": 0.12540282309055328,
|
| 117 |
+
"eval_rmse": 0.17068879306316376,
|
| 118 |
+
"eval_runtime": 63.4836,
|
| 119 |
+
"eval_samples_per_second": 37.08,
|
| 120 |
+
"eval_steps_per_second": 2.331,
|
| 121 |
+
"learning_rate": 0.001,
|
| 122 |
+
"step": 2628
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 6.8493150684931505,
|
| 126 |
+
"grad_norm": 0.18768365681171417,
|
| 127 |
+
"learning_rate": 0.001,
|
| 128 |
+
"loss": 0.4752,
|
| 129 |
+
"step": 3000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"eval_explained_variance": 0.3788411617279053,
|
| 134 |
+
"eval_kl_divergence": 0.5491646528244019,
|
| 135 |
+
"eval_loss": 0.4779475927352905,
|
| 136 |
+
"eval_mae": 0.12878474593162537,
|
| 137 |
+
"eval_rmse": 0.17091502249240875,
|
| 138 |
+
"eval_runtime": 63.4904,
|
| 139 |
+
"eval_samples_per_second": 37.076,
|
| 140 |
+
"eval_steps_per_second": 2.331,
|
| 141 |
+
"learning_rate": 0.001,
|
| 142 |
+
"step": 3066
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 7.9908675799086755,
|
| 146 |
+
"grad_norm": 0.1587909311056137,
|
| 147 |
+
"learning_rate": 0.001,
|
| 148 |
+
"loss": 0.4735,
|
| 149 |
+
"step": 3500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_explained_variance": 0.40857037901878357,
|
| 154 |
+
"eval_kl_divergence": 0.33827269077301025,
|
| 155 |
+
"eval_loss": 0.4756968021392822,
|
| 156 |
+
"eval_mae": 0.12695902585983276,
|
| 157 |
+
"eval_rmse": 0.16784566640853882,
|
| 158 |
+
"eval_runtime": 64.8792,
|
| 159 |
+
"eval_samples_per_second": 36.283,
|
| 160 |
+
"eval_steps_per_second": 2.281,
|
| 161 |
+
"learning_rate": 0.001,
|
| 162 |
+
"step": 3504
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 9.0,
|
| 166 |
+
"eval_explained_variance": 0.4111548960208893,
|
| 167 |
+
"eval_kl_divergence": 0.5417521595954895,
|
| 168 |
+
"eval_loss": 0.4731782376766205,
|
| 169 |
+
"eval_mae": 0.12311580032110214,
|
| 170 |
+
"eval_rmse": 0.1657222956418991,
|
| 171 |
+
"eval_runtime": 61.0673,
|
| 172 |
+
"eval_samples_per_second": 38.548,
|
| 173 |
+
"eval_steps_per_second": 2.424,
|
| 174 |
+
"learning_rate": 0.001,
|
| 175 |
+
"step": 3942
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 9.132420091324201,
|
| 179 |
+
"grad_norm": 0.1892658919095993,
|
| 180 |
+
"learning_rate": 0.001,
|
| 181 |
+
"loss": 0.4719,
|
| 182 |
+
"step": 4000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 10.0,
|
| 186 |
+
"eval_explained_variance": 0.4006313979625702,
|
| 187 |
+
"eval_kl_divergence": 0.15472176671028137,
|
| 188 |
+
"eval_loss": 0.4799855649471283,
|
| 189 |
+
"eval_mae": 0.1320570707321167,
|
| 190 |
+
"eval_rmse": 0.1722680777311325,
|
| 191 |
+
"eval_runtime": 62.7974,
|
| 192 |
+
"eval_samples_per_second": 37.486,
|
| 193 |
+
"eval_steps_per_second": 2.357,
|
| 194 |
+
"learning_rate": 0.001,
|
| 195 |
+
"step": 4380
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 10.273972602739725,
|
| 199 |
+
"grad_norm": 0.20271532237529755,
|
| 200 |
+
"learning_rate": 0.001,
|
| 201 |
+
"loss": 0.4727,
|
| 202 |
+
"step": 4500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 11.0,
|
| 206 |
+
"eval_explained_variance": 0.41580215096473694,
|
| 207 |
+
"eval_kl_divergence": 0.3436921238899231,
|
| 208 |
+
"eval_loss": 0.4731641411781311,
|
| 209 |
+
"eval_mae": 0.12562014162540436,
|
| 210 |
+
"eval_rmse": 0.16564464569091797,
|
| 211 |
+
"eval_runtime": 62.757,
|
| 212 |
+
"eval_samples_per_second": 37.51,
|
| 213 |
+
"eval_steps_per_second": 2.358,
|
| 214 |
+
"learning_rate": 0.001,
|
| 215 |
+
"step": 4818
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 11.415525114155251,
|
| 219 |
+
"grad_norm": 0.15571434795856476,
|
| 220 |
+
"learning_rate": 0.001,
|
| 221 |
+
"loss": 0.4723,
|
| 222 |
+
"step": 5000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 12.0,
|
| 226 |
+
"eval_explained_variance": 0.401115745306015,
|
| 227 |
+
"eval_kl_divergence": 0.2946830093860626,
|
| 228 |
+
"eval_loss": 0.47767141461372375,
|
| 229 |
+
"eval_mae": 0.12927968800067902,
|
| 230 |
+
"eval_rmse": 0.17007046937942505,
|
| 231 |
+
"eval_runtime": 62.3684,
|
| 232 |
+
"eval_samples_per_second": 37.743,
|
| 233 |
+
"eval_steps_per_second": 2.373,
|
| 234 |
+
"learning_rate": 0.001,
|
| 235 |
+
"step": 5256
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 12.557077625570777,
|
| 239 |
+
"grad_norm": 0.16043365001678467,
|
| 240 |
+
"learning_rate": 0.001,
|
| 241 |
+
"loss": 0.4735,
|
| 242 |
+
"step": 5500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 13.0,
|
| 246 |
+
"eval_explained_variance": 0.39704158902168274,
|
| 247 |
+
"eval_kl_divergence": 0.6136478781700134,
|
| 248 |
+
"eval_loss": 0.48009705543518066,
|
| 249 |
+
"eval_mae": 0.12475714087486267,
|
| 250 |
+
"eval_rmse": 0.16773907840251923,
|
| 251 |
+
"eval_runtime": 64.7917,
|
| 252 |
+
"eval_samples_per_second": 36.332,
|
| 253 |
+
"eval_steps_per_second": 2.284,
|
| 254 |
+
"learning_rate": 0.001,
|
| 255 |
+
"step": 5694
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 13.698630136986301,
|
| 259 |
+
"grad_norm": 0.13616104423999786,
|
| 260 |
+
"learning_rate": 0.001,
|
| 261 |
+
"loss": 0.4728,
|
| 262 |
+
"step": 6000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 14.0,
|
| 266 |
+
"eval_explained_variance": 0.40355002880096436,
|
| 267 |
+
"eval_kl_divergence": Infinity,
|
| 268 |
+
"eval_loss": 0.4954195022583008,
|
| 269 |
+
"eval_mae": 0.12534154951572418,
|
| 270 |
+
"eval_rmse": 0.16692323982715607,
|
| 271 |
+
"eval_runtime": 62.1801,
|
| 272 |
+
"eval_samples_per_second": 37.858,
|
| 273 |
+
"eval_steps_per_second": 2.38,
|
| 274 |
+
"learning_rate": 0.001,
|
| 275 |
+
"step": 6132
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 14.840182648401827,
|
| 279 |
+
"grad_norm": 0.12133222818374634,
|
| 280 |
+
"learning_rate": 0.001,
|
| 281 |
+
"loss": 0.4713,
|
| 282 |
+
"step": 6500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.0,
|
| 286 |
+
"eval_explained_variance": 0.4051372706890106,
|
| 287 |
+
"eval_kl_divergence": Infinity,
|
| 288 |
+
"eval_loss": 0.4812238812446594,
|
| 289 |
+
"eval_mae": 0.12540575861930847,
|
| 290 |
+
"eval_rmse": 0.16624794900417328,
|
| 291 |
+
"eval_runtime": 61.3206,
|
| 292 |
+
"eval_samples_per_second": 38.388,
|
| 293 |
+
"eval_steps_per_second": 2.414,
|
| 294 |
+
"learning_rate": 0.001,
|
| 295 |
+
"step": 6570
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 15.981735159817351,
|
| 299 |
+
"grad_norm": 0.11760278791189194,
|
| 300 |
+
"learning_rate": 0.0001,
|
| 301 |
+
"loss": 0.4706,
|
| 302 |
+
"step": 7000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 16.0,
|
| 306 |
+
"eval_explained_variance": 0.41243478655815125,
|
| 307 |
+
"eval_kl_divergence": Infinity,
|
| 308 |
+
"eval_loss": 0.4858487546443939,
|
| 309 |
+
"eval_mae": 0.12432911992073059,
|
| 310 |
+
"eval_rmse": 0.16562338173389435,
|
| 311 |
+
"eval_runtime": 61.1501,
|
| 312 |
+
"eval_samples_per_second": 38.495,
|
| 313 |
+
"eval_steps_per_second": 2.42,
|
| 314 |
+
"learning_rate": 0.0001,
|
| 315 |
+
"step": 7008
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 17.0,
|
| 319 |
+
"eval_explained_variance": 0.4291960895061493,
|
| 320 |
+
"eval_kl_divergence": 0.41650328040122986,
|
| 321 |
+
"eval_loss": 0.47084349393844604,
|
| 322 |
+
"eval_mae": 0.12233477830886841,
|
| 323 |
+
"eval_rmse": 0.162751242518425,
|
| 324 |
+
"eval_runtime": 60.5736,
|
| 325 |
+
"eval_samples_per_second": 38.862,
|
| 326 |
+
"eval_steps_per_second": 2.443,
|
| 327 |
+
"learning_rate": 0.0001,
|
| 328 |
+
"step": 7446
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 17.123287671232877,
|
| 332 |
+
"grad_norm": 0.13284093141555786,
|
| 333 |
+
"learning_rate": 0.0001,
|
| 334 |
+
"loss": 0.4672,
|
| 335 |
+
"step": 7500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 18.0,
|
| 339 |
+
"eval_explained_variance": 0.43114474415779114,
|
| 340 |
+
"eval_kl_divergence": 0.4066373407840729,
|
| 341 |
+
"eval_loss": 0.4707622528076172,
|
| 342 |
+
"eval_mae": 0.12164173275232315,
|
| 343 |
+
"eval_rmse": 0.16261519491672516,
|
| 344 |
+
"eval_runtime": 63.1248,
|
| 345 |
+
"eval_samples_per_second": 37.291,
|
| 346 |
+
"eval_steps_per_second": 2.345,
|
| 347 |
+
"learning_rate": 0.0001,
|
| 348 |
+
"step": 7884
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 18.264840182648403,
|
| 352 |
+
"grad_norm": 0.11859569698572159,
|
| 353 |
+
"learning_rate": 0.0001,
|
| 354 |
+
"loss": 0.4659,
|
| 355 |
+
"step": 8000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 19.0,
|
| 359 |
+
"eval_explained_variance": 0.4342735707759857,
|
| 360 |
+
"eval_kl_divergence": 0.31854644417762756,
|
| 361 |
+
"eval_loss": 0.47095733880996704,
|
| 362 |
+
"eval_mae": 0.12272538989782333,
|
| 363 |
+
"eval_rmse": 0.16323107481002808,
|
| 364 |
+
"eval_runtime": 61.7089,
|
| 365 |
+
"eval_samples_per_second": 38.147,
|
| 366 |
+
"eval_steps_per_second": 2.398,
|
| 367 |
+
"learning_rate": 0.0001,
|
| 368 |
+
"step": 8322
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 19.40639269406393,
|
| 372 |
+
"grad_norm": 0.16951066255569458,
|
| 373 |
+
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 0.4653,
|
| 375 |
+
"step": 8500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 20.0,
|
| 379 |
+
"eval_explained_variance": 0.43487218022346497,
|
| 380 |
+
"eval_kl_divergence": 0.465139240026474,
|
| 381 |
+
"eval_loss": 0.4696938395500183,
|
| 382 |
+
"eval_mae": 0.12050192803144455,
|
| 383 |
+
"eval_rmse": 0.1620241105556488,
|
| 384 |
+
"eval_runtime": 61.0162,
|
| 385 |
+
"eval_samples_per_second": 38.58,
|
| 386 |
+
"eval_steps_per_second": 2.426,
|
| 387 |
+
"learning_rate": 0.0001,
|
| 388 |
+
"step": 8760
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 20.54794520547945,
|
| 392 |
+
"grad_norm": 0.167369082570076,
|
| 393 |
+
"learning_rate": 0.0001,
|
| 394 |
+
"loss": 0.4653,
|
| 395 |
+
"step": 9000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 21.0,
|
| 399 |
+
"eval_explained_variance": 0.4389828145503998,
|
| 400 |
+
"eval_kl_divergence": 0.3772728741168976,
|
| 401 |
+
"eval_loss": 0.46922874450683594,
|
| 402 |
+
"eval_mae": 0.12155676633119583,
|
| 403 |
+
"eval_rmse": 0.16139467060565948,
|
| 404 |
+
"eval_runtime": 62.17,
|
| 405 |
+
"eval_samples_per_second": 37.864,
|
| 406 |
+
"eval_steps_per_second": 2.381,
|
| 407 |
+
"learning_rate": 0.0001,
|
| 408 |
+
"step": 9198
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 21.689497716894977,
|
| 412 |
+
"grad_norm": 0.1247042864561081,
|
| 413 |
+
"learning_rate": 0.0001,
|
| 414 |
+
"loss": 0.4659,
|
| 415 |
+
"step": 9500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 22.0,
|
| 419 |
+
"eval_explained_variance": 0.43975934386253357,
|
| 420 |
+
"eval_kl_divergence": 0.4611187279224396,
|
| 421 |
+
"eval_loss": 0.4685634672641754,
|
| 422 |
+
"eval_mae": 0.1203194335103035,
|
| 423 |
+
"eval_rmse": 0.16088876128196716,
|
| 424 |
+
"eval_runtime": 62.0052,
|
| 425 |
+
"eval_samples_per_second": 37.965,
|
| 426 |
+
"eval_steps_per_second": 2.387,
|
| 427 |
+
"learning_rate": 0.0001,
|
| 428 |
+
"step": 9636
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 22.831050228310502,
|
| 432 |
+
"grad_norm": 0.16208066046237946,
|
| 433 |
+
"learning_rate": 0.0001,
|
| 434 |
+
"loss": 0.465,
|
| 435 |
+
"step": 10000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 23.0,
|
| 439 |
+
"eval_explained_variance": 0.44279029965400696,
|
| 440 |
+
"eval_kl_divergence": 0.24986685812473297,
|
| 441 |
+
"eval_loss": 0.47018975019454956,
|
| 442 |
+
"eval_mae": 0.12256480008363724,
|
| 443 |
+
"eval_rmse": 0.16208301484584808,
|
| 444 |
+
"eval_runtime": 61.6543,
|
| 445 |
+
"eval_samples_per_second": 38.181,
|
| 446 |
+
"eval_steps_per_second": 2.4,
|
| 447 |
+
"learning_rate": 0.0001,
|
| 448 |
+
"step": 10074
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 23.972602739726028,
|
| 452 |
+
"grad_norm": 0.17417912185192108,
|
| 453 |
+
"learning_rate": 0.0001,
|
| 454 |
+
"loss": 0.4633,
|
| 455 |
+
"step": 10500
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 24.0,
|
| 459 |
+
"eval_explained_variance": 0.4367590844631195,
|
| 460 |
+
"eval_kl_divergence": 0.3702172040939331,
|
| 461 |
+
"eval_loss": 0.4705464243888855,
|
| 462 |
+
"eval_mae": 0.12131566554307938,
|
| 463 |
+
"eval_rmse": 0.16277877986431122,
|
| 464 |
+
"eval_runtime": 62.8273,
|
| 465 |
+
"eval_samples_per_second": 37.468,
|
| 466 |
+
"eval_steps_per_second": 2.356,
|
| 467 |
+
"learning_rate": 0.0001,
|
| 468 |
+
"step": 10512
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 25.0,
|
| 472 |
+
"eval_explained_variance": 0.4433206617832184,
|
| 473 |
+
"eval_kl_divergence": 0.5132729411125183,
|
| 474 |
+
"eval_loss": 0.4678299129009247,
|
| 475 |
+
"eval_mae": 0.11875440925359726,
|
| 476 |
+
"eval_rmse": 0.16013289988040924,
|
| 477 |
+
"eval_runtime": 61.7077,
|
| 478 |
+
"eval_samples_per_second": 38.148,
|
| 479 |
+
"eval_steps_per_second": 2.398,
|
| 480 |
+
"learning_rate": 0.0001,
|
| 481 |
+
"step": 10950
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 25.114155251141554,
|
| 485 |
+
"grad_norm": 0.13617579638957977,
|
| 486 |
+
"learning_rate": 0.0001,
|
| 487 |
+
"loss": 0.4656,
|
| 488 |
+
"step": 11000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 26.0,
|
| 492 |
+
"eval_explained_variance": 0.4423791468143463,
|
| 493 |
+
"eval_kl_divergence": 0.5665323138237,
|
| 494 |
+
"eval_loss": 0.46802961826324463,
|
| 495 |
+
"eval_mae": 0.117874376475811,
|
| 496 |
+
"eval_rmse": 0.1604483276605606,
|
| 497 |
+
"eval_runtime": 61.9639,
|
| 498 |
+
"eval_samples_per_second": 37.99,
|
| 499 |
+
"eval_steps_per_second": 2.388,
|
| 500 |
+
"learning_rate": 0.0001,
|
| 501 |
+
"step": 11388
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 26.255707762557076,
|
| 505 |
+
"grad_norm": 0.15818916261196136,
|
| 506 |
+
"learning_rate": 0.0001,
|
| 507 |
+
"loss": 0.4629,
|
| 508 |
+
"step": 11500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 27.0,
|
| 512 |
+
"eval_explained_variance": 0.4434410333633423,
|
| 513 |
+
"eval_kl_divergence": 0.42424070835113525,
|
| 514 |
+
"eval_loss": 0.4680938124656677,
|
| 515 |
+
"eval_mae": 0.1199984923005104,
|
| 516 |
+
"eval_rmse": 0.16038183867931366,
|
| 517 |
+
"eval_runtime": 62.3144,
|
| 518 |
+
"eval_samples_per_second": 37.776,
|
| 519 |
+
"eval_steps_per_second": 2.375,
|
| 520 |
+
"learning_rate": 0.0001,
|
| 521 |
+
"step": 11826
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 27.397260273972602,
|
| 525 |
+
"grad_norm": 0.15971983969211578,
|
| 526 |
+
"learning_rate": 0.0001,
|
| 527 |
+
"loss": 0.4636,
|
| 528 |
+
"step": 12000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 28.0,
|
| 532 |
+
"eval_explained_variance": 0.44512465596199036,
|
| 533 |
+
"eval_kl_divergence": 0.2967982292175293,
|
| 534 |
+
"eval_loss": 0.4693257212638855,
|
| 535 |
+
"eval_mae": 0.12149528414011002,
|
| 536 |
+
"eval_rmse": 0.1616295725107193,
|
| 537 |
+
"eval_runtime": 66.789,
|
| 538 |
+
"eval_samples_per_second": 35.245,
|
| 539 |
+
"eval_steps_per_second": 2.216,
|
| 540 |
+
"learning_rate": 0.0001,
|
| 541 |
+
"step": 12264
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 28.538812785388128,
|
| 545 |
+
"grad_norm": 0.15448875725269318,
|
| 546 |
+
"learning_rate": 0.0001,
|
| 547 |
+
"loss": 0.4633,
|
| 548 |
+
"step": 12500
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 29.0,
|
| 552 |
+
"eval_explained_variance": 0.4442717730998993,
|
| 553 |
+
"eval_kl_divergence": 0.3924856185913086,
|
| 554 |
+
"eval_loss": 0.46847742795944214,
|
| 555 |
+
"eval_mae": 0.1196620985865593,
|
| 556 |
+
"eval_rmse": 0.16072382032871246,
|
| 557 |
+
"eval_runtime": 61.9086,
|
| 558 |
+
"eval_samples_per_second": 38.024,
|
| 559 |
+
"eval_steps_per_second": 2.391,
|
| 560 |
+
"learning_rate": 0.0001,
|
| 561 |
+
"step": 12702
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 29.680365296803654,
|
| 565 |
+
"grad_norm": 0.15532433986663818,
|
| 566 |
+
"learning_rate": 0.0001,
|
| 567 |
+
"loss": 0.4631,
|
| 568 |
+
"step": 13000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 30.0,
|
| 572 |
+
"eval_explained_variance": 0.4473068416118622,
|
| 573 |
+
"eval_kl_divergence": 0.2495478093624115,
|
| 574 |
+
"eval_loss": 0.46944141387939453,
|
| 575 |
+
"eval_mae": 0.12209376692771912,
|
| 576 |
+
"eval_rmse": 0.16142255067825317,
|
| 577 |
+
"eval_runtime": 62.4285,
|
| 578 |
+
"eval_samples_per_second": 37.707,
|
| 579 |
+
"eval_steps_per_second": 2.371,
|
| 580 |
+
"learning_rate": 0.0001,
|
| 581 |
+
"step": 13140
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 30.82191780821918,
|
| 585 |
+
"grad_norm": 0.1961052566766739,
|
| 586 |
+
"learning_rate": 0.0001,
|
| 587 |
+
"loss": 0.463,
|
| 588 |
+
"step": 13500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 31.0,
|
| 592 |
+
"eval_explained_variance": 0.4445982277393341,
|
| 593 |
+
"eval_kl_divergence": 0.45099732279777527,
|
| 594 |
+
"eval_loss": 0.4678958058357239,
|
| 595 |
+
"eval_mae": 0.11854251474142075,
|
| 596 |
+
"eval_rmse": 0.16011421382427216,
|
| 597 |
+
"eval_runtime": 61.3729,
|
| 598 |
+
"eval_samples_per_second": 38.356,
|
| 599 |
+
"eval_steps_per_second": 2.411,
|
| 600 |
+
"learning_rate": 0.0001,
|
| 601 |
+
"step": 13578
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 31.963470319634702,
|
| 605 |
+
"grad_norm": 0.3346303701400757,
|
| 606 |
+
"learning_rate": 1e-05,
|
| 607 |
+
"loss": 0.4623,
|
| 608 |
+
"step": 14000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 32.0,
|
| 612 |
+
"eval_explained_variance": 0.4478188455104828,
|
| 613 |
+
"eval_kl_divergence": 0.3885524570941925,
|
| 614 |
+
"eval_loss": 0.46778997778892517,
|
| 615 |
+
"eval_mae": 0.11933697015047073,
|
| 616 |
+
"eval_rmse": 0.16006481647491455,
|
| 617 |
+
"eval_runtime": 63.8544,
|
| 618 |
+
"eval_samples_per_second": 36.865,
|
| 619 |
+
"eval_steps_per_second": 2.318,
|
| 620 |
+
"learning_rate": 1e-05,
|
| 621 |
+
"step": 14016
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 33.0,
|
| 625 |
+
"eval_explained_variance": 0.44756200909614563,
|
| 626 |
+
"eval_kl_divergence": 0.31322383880615234,
|
| 627 |
+
"eval_loss": 0.4686955511569977,
|
| 628 |
+
"eval_mae": 0.1201881393790245,
|
| 629 |
+
"eval_rmse": 0.16055406630039215,
|
| 630 |
+
"eval_runtime": 62.7334,
|
| 631 |
+
"eval_samples_per_second": 37.524,
|
| 632 |
+
"eval_steps_per_second": 2.359,
|
| 633 |
+
"learning_rate": 1e-05,
|
| 634 |
+
"step": 14454
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 33.10502283105023,
|
| 638 |
+
"grad_norm": 0.21087272465229034,
|
| 639 |
+
"learning_rate": 1e-05,
|
| 640 |
+
"loss": 0.4621,
|
| 641 |
+
"step": 14500
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 34.0,
|
| 645 |
+
"eval_explained_variance": 0.4478868544101715,
|
| 646 |
+
"eval_kl_divergence": 0.3957745432853699,
|
| 647 |
+
"eval_loss": 0.46784329414367676,
|
| 648 |
+
"eval_mae": 0.11951460689306259,
|
| 649 |
+
"eval_rmse": 0.1600986272096634,
|
| 650 |
+
"eval_runtime": 60.6174,
|
| 651 |
+
"eval_samples_per_second": 38.834,
|
| 652 |
+
"eval_steps_per_second": 2.442,
|
| 653 |
+
"learning_rate": 1e-05,
|
| 654 |
+
"step": 14892
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 34.24657534246575,
|
| 658 |
+
"grad_norm": 0.1875353455543518,
|
| 659 |
+
"learning_rate": 1e-05,
|
| 660 |
+
"loss": 0.4607,
|
| 661 |
+
"step": 15000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 35.0,
|
| 665 |
+
"eval_explained_variance": 0.44849491119384766,
|
| 666 |
+
"eval_kl_divergence": 0.45786312222480774,
|
| 667 |
+
"eval_loss": 0.4671097695827484,
|
| 668 |
+
"eval_mae": 0.11800643056631088,
|
| 669 |
+
"eval_rmse": 0.15947793424129486,
|
| 670 |
+
"eval_runtime": 61.7609,
|
| 671 |
+
"eval_samples_per_second": 38.115,
|
| 672 |
+
"eval_steps_per_second": 2.396,
|
| 673 |
+
"learning_rate": 1e-05,
|
| 674 |
+
"step": 15330
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 35.38812785388128,
|
| 678 |
+
"grad_norm": 0.16752338409423828,
|
| 679 |
+
"learning_rate": 1e-05,
|
| 680 |
+
"loss": 0.4619,
|
| 681 |
+
"step": 15500
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 36.0,
|
| 685 |
+
"eval_explained_variance": 0.44863569736480713,
|
| 686 |
+
"eval_kl_divergence": 0.43913933634757996,
|
| 687 |
+
"eval_loss": 0.46735426783561707,
|
| 688 |
+
"eval_mae": 0.11842861026525497,
|
| 689 |
+
"eval_rmse": 0.15950414538383484,
|
| 690 |
+
"eval_runtime": 64.5571,
|
| 691 |
+
"eval_samples_per_second": 36.464,
|
| 692 |
+
"eval_steps_per_second": 2.293,
|
| 693 |
+
"learning_rate": 1e-05,
|
| 694 |
+
"step": 15768
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 36.529680365296805,
|
| 698 |
+
"grad_norm": 0.15660376846790314,
|
| 699 |
+
"learning_rate": 1e-05,
|
| 700 |
+
"loss": 0.4612,
|
| 701 |
+
"step": 16000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 37.0,
|
| 705 |
+
"eval_explained_variance": 0.44943228363990784,
|
| 706 |
+
"eval_kl_divergence": 0.36332887411117554,
|
| 707 |
+
"eval_loss": 0.468018501996994,
|
| 708 |
+
"eval_mae": 0.11912700533866882,
|
| 709 |
+
"eval_rmse": 0.16002707183361053,
|
| 710 |
+
"eval_runtime": 63.2971,
|
| 711 |
+
"eval_samples_per_second": 37.19,
|
| 712 |
+
"eval_steps_per_second": 2.338,
|
| 713 |
+
"learning_rate": 1e-05,
|
| 714 |
+
"step": 16206
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 37.67123287671233,
|
| 718 |
+
"grad_norm": 0.15865331888198853,
|
| 719 |
+
"learning_rate": 1e-05,
|
| 720 |
+
"loss": 0.4625,
|
| 721 |
+
"step": 16500
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 38.0,
|
| 725 |
+
"eval_explained_variance": 0.45025742053985596,
|
| 726 |
+
"eval_kl_divergence": 0.43029093742370605,
|
| 727 |
+
"eval_loss": 0.46701580286026,
|
| 728 |
+
"eval_mae": 0.1186341941356659,
|
| 729 |
+
"eval_rmse": 0.15923398733139038,
|
| 730 |
+
"eval_runtime": 63.0229,
|
| 731 |
+
"eval_samples_per_second": 37.351,
|
| 732 |
+
"eval_steps_per_second": 2.348,
|
| 733 |
+
"learning_rate": 1e-05,
|
| 734 |
+
"step": 16644
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 38.81278538812786,
|
| 738 |
+
"grad_norm": 0.2913804352283478,
|
| 739 |
+
"learning_rate": 1e-05,
|
| 740 |
+
"loss": 0.4608,
|
| 741 |
+
"step": 17000
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 39.0,
|
| 745 |
+
"eval_explained_variance": 0.448851078748703,
|
| 746 |
+
"eval_kl_divergence": 0.4562166929244995,
|
| 747 |
+
"eval_loss": 0.4673251509666443,
|
| 748 |
+
"eval_mae": 0.11870113760232925,
|
| 749 |
+
"eval_rmse": 0.1596096307039261,
|
| 750 |
+
"eval_runtime": 63.132,
|
| 751 |
+
"eval_samples_per_second": 37.287,
|
| 752 |
+
"eval_steps_per_second": 2.344,
|
| 753 |
+
"learning_rate": 1e-05,
|
| 754 |
+
"step": 17082
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 39.954337899543376,
|
| 758 |
+
"grad_norm": 0.1813182234764099,
|
| 759 |
+
"learning_rate": 1e-05,
|
| 760 |
+
"loss": 0.4614,
|
| 761 |
+
"step": 17500
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 40.0,
|
| 765 |
+
"eval_explained_variance": 0.449774831533432,
|
| 766 |
+
"eval_kl_divergence": 0.40653547644615173,
|
| 767 |
+
"eval_loss": 0.4673212468624115,
|
| 768 |
+
"eval_mae": 0.1188703179359436,
|
| 769 |
+
"eval_rmse": 0.15939703583717346,
|
| 770 |
+
"eval_runtime": 65.2215,
|
| 771 |
+
"eval_samples_per_second": 36.092,
|
| 772 |
+
"eval_steps_per_second": 2.269,
|
| 773 |
+
"learning_rate": 1e-05,
|
| 774 |
+
"step": 17520
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 41.0,
|
| 778 |
+
"eval_explained_variance": 0.4507579803466797,
|
| 779 |
+
"eval_kl_divergence": 0.3335873782634735,
|
| 780 |
+
"eval_loss": 0.4677547216415405,
|
| 781 |
+
"eval_mae": 0.12059084326028824,
|
| 782 |
+
"eval_rmse": 0.159872904419899,
|
| 783 |
+
"eval_runtime": 65.9882,
|
| 784 |
+
"eval_samples_per_second": 35.673,
|
| 785 |
+
"eval_steps_per_second": 2.243,
|
| 786 |
+
"learning_rate": 1e-05,
|
| 787 |
+
"step": 17958
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 41.0958904109589,
|
| 791 |
+
"grad_norm": 0.1584874391555786,
|
| 792 |
+
"learning_rate": 1e-05,
|
| 793 |
+
"loss": 0.4608,
|
| 794 |
+
"step": 18000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 42.0,
|
| 798 |
+
"eval_explained_variance": 0.4486294686794281,
|
| 799 |
+
"eval_kl_divergence": 0.5311685800552368,
|
| 800 |
+
"eval_loss": 0.4671882390975952,
|
| 801 |
+
"eval_mae": 0.1177595853805542,
|
| 802 |
+
"eval_rmse": 0.15967120230197906,
|
| 803 |
+
"eval_runtime": 65.4501,
|
| 804 |
+
"eval_samples_per_second": 35.966,
|
| 805 |
+
"eval_steps_per_second": 2.261,
|
| 806 |
+
"learning_rate": 1e-05,
|
| 807 |
+
"step": 18396
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 42.23744292237443,
|
| 811 |
+
"grad_norm": 0.17140232026576996,
|
| 812 |
+
"learning_rate": 1e-05,
|
| 813 |
+
"loss": 0.4615,
|
| 814 |
+
"step": 18500
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 43.0,
|
| 818 |
+
"eval_explained_variance": 0.45157137513160706,
|
| 819 |
+
"eval_kl_divergence": 0.3923657536506653,
|
| 820 |
+
"eval_loss": 0.46716412901878357,
|
| 821 |
+
"eval_mae": 0.1185157299041748,
|
| 822 |
+
"eval_rmse": 0.1592295914888382,
|
| 823 |
+
"eval_runtime": 64.3671,
|
| 824 |
+
"eval_samples_per_second": 36.571,
|
| 825 |
+
"eval_steps_per_second": 2.299,
|
| 826 |
+
"learning_rate": 1e-05,
|
| 827 |
+
"step": 18834
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 43.37899543378995,
|
| 831 |
+
"grad_norm": 0.12803754210472107,
|
| 832 |
+
"learning_rate": 1e-05,
|
| 833 |
+
"loss": 0.4601,
|
| 834 |
+
"step": 19000
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 44.0,
|
| 838 |
+
"eval_explained_variance": 0.44912728667259216,
|
| 839 |
+
"eval_kl_divergence": 0.4258858561515808,
|
| 840 |
+
"eval_loss": 0.4678168296813965,
|
| 841 |
+
"eval_mae": 0.11944716423749924,
|
| 842 |
+
"eval_rmse": 0.16020986437797546,
|
| 843 |
+
"eval_runtime": 65.6519,
|
| 844 |
+
"eval_samples_per_second": 35.856,
|
| 845 |
+
"eval_steps_per_second": 2.254,
|
| 846 |
+
"learning_rate": 1e-05,
|
| 847 |
+
"step": 19272
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 44.52054794520548,
|
| 851 |
+
"grad_norm": 0.12536858022212982,
|
| 852 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 853 |
+
"loss": 0.4602,
|
| 854 |
+
"step": 19500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 45.0,
|
| 858 |
+
"eval_explained_variance": 0.4489940404891968,
|
| 859 |
+
"eval_kl_divergence": 0.5214298367500305,
|
| 860 |
+
"eval_loss": 0.46699702739715576,
|
| 861 |
+
"eval_mae": 0.11719372868537903,
|
| 862 |
+
"eval_rmse": 0.15936775505542755,
|
| 863 |
+
"eval_runtime": 64.8181,
|
| 864 |
+
"eval_samples_per_second": 36.317,
|
| 865 |
+
"eval_steps_per_second": 2.283,
|
| 866 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 867 |
+
"step": 19710
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 45.662100456621005,
|
| 871 |
+
"grad_norm": 0.12503549456596375,
|
| 872 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 873 |
+
"loss": 0.4616,
|
| 874 |
+
"step": 20000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 46.0,
|
| 878 |
+
"eval_explained_variance": 0.45176592469215393,
|
| 879 |
+
"eval_kl_divergence": 0.4174787700176239,
|
| 880 |
+
"eval_loss": 0.46712958812713623,
|
| 881 |
+
"eval_mae": 0.11880326271057129,
|
| 882 |
+
"eval_rmse": 0.1593877524137497,
|
| 883 |
+
"eval_runtime": 64.134,
|
| 884 |
+
"eval_samples_per_second": 36.704,
|
| 885 |
+
"eval_steps_per_second": 2.308,
|
| 886 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 887 |
+
"step": 20148
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 46.80365296803653,
|
| 891 |
+
"grad_norm": 0.1746779829263687,
|
| 892 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 893 |
+
"loss": 0.4602,
|
| 894 |
+
"step": 20500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 47.0,
|
| 898 |
+
"eval_explained_variance": 0.4524901807308197,
|
| 899 |
+
"eval_kl_divergence": 0.4446321427822113,
|
| 900 |
+
"eval_loss": 0.4666382074356079,
|
| 901 |
+
"eval_mae": 0.11884639412164688,
|
| 902 |
+
"eval_rmse": 0.15886224806308746,
|
| 903 |
+
"eval_runtime": 68.911,
|
| 904 |
+
"eval_samples_per_second": 34.16,
|
| 905 |
+
"eval_steps_per_second": 2.148,
|
| 906 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 907 |
+
"step": 20586
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 47.945205479452056,
|
| 911 |
+
"grad_norm": 0.18253998458385468,
|
| 912 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 913 |
+
"loss": 0.4604,
|
| 914 |
+
"step": 21000
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 48.0,
|
| 918 |
+
"eval_explained_variance": 0.44860827922821045,
|
| 919 |
+
"eval_kl_divergence": 0.5755118727684021,
|
| 920 |
+
"eval_loss": 0.46714723110198975,
|
| 921 |
+
"eval_mae": 0.11802936345338821,
|
| 922 |
+
"eval_rmse": 0.15972274541854858,
|
| 923 |
+
"eval_runtime": 68.5695,
|
| 924 |
+
"eval_samples_per_second": 34.33,
|
| 925 |
+
"eval_steps_per_second": 2.158,
|
| 926 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 927 |
+
"step": 21024
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 49.0,
|
| 931 |
+
"eval_explained_variance": 0.4494647979736328,
|
| 932 |
+
"eval_kl_divergence": 0.4303589463233948,
|
| 933 |
+
"eval_loss": 0.46758702397346497,
|
| 934 |
+
"eval_mae": 0.11922705173492432,
|
| 935 |
+
"eval_rmse": 0.15995512902736664,
|
| 936 |
+
"eval_runtime": 68.4997,
|
| 937 |
+
"eval_samples_per_second": 34.365,
|
| 938 |
+
"eval_steps_per_second": 2.161,
|
| 939 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 940 |
+
"step": 21462
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 49.08675799086758,
|
| 944 |
+
"grad_norm": 0.1836538463830948,
|
| 945 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 946 |
+
"loss": 0.4606,
|
| 947 |
+
"step": 21500
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 50.0,
|
| 951 |
+
"eval_explained_variance": 0.4534037411212921,
|
| 952 |
+
"eval_kl_divergence": 0.33374354243278503,
|
| 953 |
+
"eval_loss": 0.46752068400382996,
|
| 954 |
+
"eval_mae": 0.12040751427412033,
|
| 955 |
+
"eval_rmse": 0.15945331752300262,
|
| 956 |
+
"eval_runtime": 67.7842,
|
| 957 |
+
"eval_samples_per_second": 34.728,
|
| 958 |
+
"eval_steps_per_second": 2.183,
|
| 959 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 960 |
+
"step": 21900
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 50.22831050228311,
|
| 964 |
+
"grad_norm": 0.18452928960323334,
|
| 965 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 966 |
+
"loss": 0.4598,
|
| 967 |
+
"step": 22000
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 51.0,
|
| 971 |
+
"eval_explained_variance": 0.4523892402648926,
|
| 972 |
+
"eval_kl_divergence": 0.395465224981308,
|
| 973 |
+
"eval_loss": 0.46691644191741943,
|
| 974 |
+
"eval_mae": 0.11809410899877548,
|
| 975 |
+
"eval_rmse": 0.1590944528579712,
|
| 976 |
+
"eval_runtime": 68.2629,
|
| 977 |
+
"eval_samples_per_second": 34.484,
|
| 978 |
+
"eval_steps_per_second": 2.168,
|
| 979 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 980 |
+
"step": 22338
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 51.36986301369863,
|
| 984 |
+
"grad_norm": 0.1816985160112381,
|
| 985 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 986 |
+
"loss": 0.4602,
|
| 987 |
+
"step": 22500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 52.0,
|
| 991 |
+
"eval_explained_variance": 0.45300889015197754,
|
| 992 |
+
"eval_kl_divergence": 0.4761090576648712,
|
| 993 |
+
"eval_loss": 0.466439425945282,
|
| 994 |
+
"eval_mae": 0.1174706444144249,
|
| 995 |
+
"eval_rmse": 0.15875311195850372,
|
| 996 |
+
"eval_runtime": 68.2396,
|
| 997 |
+
"eval_samples_per_second": 34.496,
|
| 998 |
+
"eval_steps_per_second": 2.169,
|
| 999 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1000 |
+
"step": 22776
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 52.51141552511415,
|
| 1004 |
+
"grad_norm": 0.17806819081306458,
|
| 1005 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1006 |
+
"loss": 0.462,
|
| 1007 |
+
"step": 23000
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 53.0,
|
| 1011 |
+
"eval_explained_variance": 0.45259252190589905,
|
| 1012 |
+
"eval_kl_divergence": 0.43274176120758057,
|
| 1013 |
+
"eval_loss": 0.4667709469795227,
|
| 1014 |
+
"eval_mae": 0.11889918893575668,
|
| 1015 |
+
"eval_rmse": 0.15901200473308563,
|
| 1016 |
+
"eval_runtime": 66.8799,
|
| 1017 |
+
"eval_samples_per_second": 35.197,
|
| 1018 |
+
"eval_steps_per_second": 2.213,
|
| 1019 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1020 |
+
"step": 23214
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 53.65296803652968,
|
| 1024 |
+
"grad_norm": 0.18054644763469696,
|
| 1025 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1026 |
+
"loss": 0.4604,
|
| 1027 |
+
"step": 23500
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 54.0,
|
| 1031 |
+
"eval_explained_variance": 0.4532507658004761,
|
| 1032 |
+
"eval_kl_divergence": 0.3724806606769562,
|
| 1033 |
+
"eval_loss": 0.46701404452323914,
|
| 1034 |
+
"eval_mae": 0.11868719011545181,
|
| 1035 |
+
"eval_rmse": 0.15923155844211578,
|
| 1036 |
+
"eval_runtime": 73.556,
|
| 1037 |
+
"eval_samples_per_second": 32.003,
|
| 1038 |
+
"eval_steps_per_second": 2.012,
|
| 1039 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1040 |
+
"step": 23652
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 54.794520547945204,
|
| 1044 |
+
"grad_norm": 0.26471829414367676,
|
| 1045 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1046 |
+
"loss": 0.461,
|
| 1047 |
+
"step": 24000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 55.0,
|
| 1051 |
+
"eval_explained_variance": 0.45088374614715576,
|
| 1052 |
+
"eval_kl_divergence": 0.38409897685050964,
|
| 1053 |
+
"eval_loss": 0.467383474111557,
|
| 1054 |
+
"eval_mae": 0.11990005522966385,
|
| 1055 |
+
"eval_rmse": 0.1595049947500229,
|
| 1056 |
+
"eval_runtime": 70.451,
|
| 1057 |
+
"eval_samples_per_second": 33.413,
|
| 1058 |
+
"eval_steps_per_second": 2.101,
|
| 1059 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1060 |
+
"step": 24090
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 55.93607305936073,
|
| 1064 |
+
"grad_norm": 0.2783886194229126,
|
| 1065 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1066 |
+
"loss": 0.4599,
|
| 1067 |
+
"step": 24500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 56.0,
|
| 1071 |
+
"eval_explained_variance": 0.45115411281585693,
|
| 1072 |
+
"eval_kl_divergence": 0.3821828067302704,
|
| 1073 |
+
"eval_loss": 0.46739572286605835,
|
| 1074 |
+
"eval_mae": 0.11897724121809006,
|
| 1075 |
+
"eval_rmse": 0.15964223444461823,
|
| 1076 |
+
"eval_runtime": 69.6578,
|
| 1077 |
+
"eval_samples_per_second": 33.794,
|
| 1078 |
+
"eval_steps_per_second": 2.125,
|
| 1079 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1080 |
+
"step": 24528
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 57.0,
|
| 1084 |
+
"eval_explained_variance": 0.4505263864994049,
|
| 1085 |
+
"eval_kl_divergence": 0.4674541652202606,
|
| 1086 |
+
"eval_loss": 0.46702033281326294,
|
| 1087 |
+
"eval_mae": 0.1185864806175232,
|
| 1088 |
+
"eval_rmse": 0.15932416915893555,
|
| 1089 |
+
"eval_runtime": 67.4689,
|
| 1090 |
+
"eval_samples_per_second": 34.89,
|
| 1091 |
+
"eval_steps_per_second": 2.194,
|
| 1092 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1093 |
+
"step": 24966
|
| 1094 |
+
},
|
| 1095 |
+
{
|
| 1096 |
+
"epoch": 57.077625570776256,
|
| 1097 |
+
"grad_norm": 0.16562320291996002,
|
| 1098 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1099 |
+
"loss": 0.4594,
|
| 1100 |
+
"step": 25000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 58.0,
|
| 1104 |
+
"eval_explained_variance": 0.4521506726741791,
|
| 1105 |
+
"eval_kl_divergence": 0.37376847863197327,
|
| 1106 |
+
"eval_loss": 0.46735846996307373,
|
| 1107 |
+
"eval_mae": 0.11891353130340576,
|
| 1108 |
+
"eval_rmse": 0.15956538915634155,
|
| 1109 |
+
"eval_runtime": 68.6492,
|
| 1110 |
+
"eval_samples_per_second": 34.29,
|
| 1111 |
+
"eval_steps_per_second": 2.156,
|
| 1112 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1113 |
+
"step": 25404
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 58.21917808219178,
|
| 1117 |
+
"grad_norm": 0.21171259880065918,
|
| 1118 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1119 |
+
"loss": 0.4613,
|
| 1120 |
+
"step": 25500
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 59.0,
|
| 1124 |
+
"eval_explained_variance": 0.45357391238212585,
|
| 1125 |
+
"eval_kl_divergence": 0.4204346239566803,
|
| 1126 |
+
"eval_loss": 0.46666717529296875,
|
| 1127 |
+
"eval_mae": 0.11845538765192032,
|
| 1128 |
+
"eval_rmse": 0.1589372605085373,
|
| 1129 |
+
"eval_runtime": 69.2012,
|
| 1130 |
+
"eval_samples_per_second": 34.017,
|
| 1131 |
+
"eval_steps_per_second": 2.139,
|
| 1132 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1133 |
+
"step": 25842
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 59.36073059360731,
|
| 1137 |
+
"grad_norm": 0.1960112601518631,
|
| 1138 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1139 |
+
"loss": 0.4607,
|
| 1140 |
+
"step": 26000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 60.0,
|
| 1144 |
+
"eval_explained_variance": 0.4513193368911743,
|
| 1145 |
+
"eval_kl_divergence": 0.45320600271224976,
|
| 1146 |
+
"eval_loss": 0.46685320138931274,
|
| 1147 |
+
"eval_mae": 0.11779770255088806,
|
| 1148 |
+
"eval_rmse": 0.15917657315731049,
|
| 1149 |
+
"eval_runtime": 71.4331,
|
| 1150 |
+
"eval_samples_per_second": 32.954,
|
| 1151 |
+
"eval_steps_per_second": 2.072,
|
| 1152 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1153 |
+
"step": 26280
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 60.50228310502283,
|
| 1157 |
+
"grad_norm": 0.2178792506456375,
|
| 1158 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1159 |
+
"loss": 0.4613,
|
| 1160 |
+
"step": 26500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 61.0,
|
| 1164 |
+
"eval_explained_variance": 0.45110437273979187,
|
| 1165 |
+
"eval_kl_divergence": 0.40322577953338623,
|
| 1166 |
+
"eval_loss": 0.46734780073165894,
|
| 1167 |
+
"eval_mae": 0.11893540620803833,
|
| 1168 |
+
"eval_rmse": 0.1595635712146759,
|
| 1169 |
+
"eval_runtime": 69.3534,
|
| 1170 |
+
"eval_samples_per_second": 33.942,
|
| 1171 |
+
"eval_steps_per_second": 2.134,
|
| 1172 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1173 |
+
"step": 26718
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 61.64383561643836,
|
| 1177 |
+
"grad_norm": 0.16740958392620087,
|
| 1178 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1179 |
+
"loss": 0.4598,
|
| 1180 |
+
"step": 27000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 62.0,
|
| 1184 |
+
"eval_explained_variance": 0.4526772201061249,
|
| 1185 |
+
"eval_kl_divergence": 0.3406714200973511,
|
| 1186 |
+
"eval_loss": 0.4673011302947998,
|
| 1187 |
+
"eval_mae": 0.11888447403907776,
|
| 1188 |
+
"eval_rmse": 0.1594574898481369,
|
| 1189 |
+
"eval_runtime": 70.4024,
|
| 1190 |
+
"eval_samples_per_second": 33.436,
|
| 1191 |
+
"eval_steps_per_second": 2.102,
|
| 1192 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1193 |
+
"step": 27156
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 62.0,
|
| 1197 |
+
"learning_rate": 1.0000000000000002e-07,
|
| 1198 |
+
"step": 27156,
|
| 1199 |
+
"total_flos": 6.42634409963284e+19,
|
| 1200 |
+
"train_loss": 0.466335079458891,
|
| 1201 |
+
"train_runtime": 17194.6751,
|
| 1202 |
+
"train_samples_per_second": 61.092,
|
| 1203 |
+
"train_steps_per_second": 3.821
|
| 1204 |
+
}
|
| 1205 |
+
],
|
| 1206 |
+
"logging_steps": 500,
|
| 1207 |
+
"max_steps": 65700,
|
| 1208 |
+
"num_input_tokens_seen": 0,
|
| 1209 |
+
"num_train_epochs": 150,
|
| 1210 |
+
"save_steps": 500,
|
| 1211 |
+
"stateful_callbacks": {
|
| 1212 |
+
"EarlyStoppingCallback": {
|
| 1213 |
+
"args": {
|
| 1214 |
+
"early_stopping_patience": 10,
|
| 1215 |
+
"early_stopping_threshold": 0.0
|
| 1216 |
+
},
|
| 1217 |
+
"attributes": {
|
| 1218 |
+
"early_stopping_patience_counter": 0
|
| 1219 |
+
}
|
| 1220 |
+
},
|
| 1221 |
+
"TrainerControl": {
|
| 1222 |
+
"args": {
|
| 1223 |
+
"should_epoch_stop": false,
|
| 1224 |
+
"should_evaluate": false,
|
| 1225 |
+
"should_log": false,
|
| 1226 |
+
"should_save": true,
|
| 1227 |
+
"should_training_stop": true
|
| 1228 |
+
},
|
| 1229 |
+
"attributes": {}
|
| 1230 |
+
}
|
| 1231 |
+
},
|
| 1232 |
+
"total_flos": 6.42634409963284e+19,
|
| 1233 |
+
"train_batch_size": 16,
|
| 1234 |
+
"trial_name": null,
|
| 1235 |
+
"trial_params": null
|
| 1236 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df0893f1b11b09450b828abdf0d7056789b1043a66f48a4972d055d5ddf5c12b
|
| 3 |
+
size 5304
|
transforms.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"train_transforms": [
|
| 3 |
+
{
|
| 4 |
+
"operation": "PreProcess"
|
| 5 |
+
},
|
| 6 |
+
{
|
| 7 |
+
"operation": "Resize",
|
| 8 |
+
"probability": 1.0
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"operation": "RandomHorizontalFlip",
|
| 12 |
+
"probability": 0.25
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"operation": "RandomVerticalFlip",
|
| 16 |
+
"probability": 0.25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"operation": "ColorJiggle",
|
| 20 |
+
"probability": 0.25
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"operation": "RandomPerspective",
|
| 24 |
+
"probability": 0.25
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"operation": "Normalize",
|
| 28 |
+
"probability": 1.0
|
| 29 |
+
}
|
| 30 |
+
],
|
| 31 |
+
"val_transforms": [
|
| 32 |
+
{
|
| 33 |
+
"operation": "PreProcess"
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"operation": "Resize",
|
| 37 |
+
"probability": 1.0
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"operation": "Normalize",
|
| 41 |
+
"probability": 1.0
|
| 42 |
+
}
|
| 43 |
+
]
|
| 44 |
+
}
|