lombardata
commited on
Commit
•
2e3f7df
1
Parent(s):
185dce1
Evaluation on the test set completed on 2024_11_15.
Browse files- README.md +141 -0
- all_results.json +17 -0
- logs/events.out.tfevents.1731665663.datavisu2 +2 -2
- logs/events.out.tfevents.1731685574.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +1198 -0
README.md
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/dinov2-large
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: drone-DinoVdeau-from-probs-large-2024_11_15-batch-size64_freeze_probs
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# drone-DinoVdeau-from-probs-large-2024_11_15-batch-size64_freeze_probs
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.4672
|
19 |
+
- Rmse: 0.1553
|
20 |
+
- Mae: 0.1147
|
21 |
+
- Kl Divergence: 0.3577
|
22 |
+
- Explained Variance: 0.4654
|
23 |
+
- Learning Rate: 0.0000
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.001
|
43 |
+
- train_batch_size: 64
|
44 |
+
- eval_batch_size: 64
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 150
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Rmse | Mae | Kl Divergence | Explained Variance | Rate |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:-------------:|:------------------:|:------:|
|
55 |
+
| No log | 1.0 | 110 | 0.5006 | 0.1904 | 0.1552 | 0.1025 | 0.3284 | 0.001 |
|
56 |
+
| No log | 2.0 | 220 | 0.4755 | 0.1681 | 0.1245 | 0.5180 | 0.3932 | 0.001 |
|
57 |
+
| No log | 3.0 | 330 | 0.4745 | 0.1675 | 0.1227 | 0.6862 | 0.3975 | 0.001 |
|
58 |
+
| No log | 4.0 | 440 | 0.4742 | 0.1672 | 0.1255 | 0.3212 | 0.4024 | 0.001 |
|
59 |
+
| 0.5081 | 5.0 | 550 | 0.4725 | 0.1653 | 0.1224 | 0.5072 | 0.4118 | 0.001 |
|
60 |
+
| 0.5081 | 6.0 | 660 | 0.4726 | 0.1657 | 0.1216 | 0.6710 | 0.4101 | 0.001 |
|
61 |
+
| 0.5081 | 7.0 | 770 | 0.4732 | 0.1655 | 0.1255 | 0.3162 | 0.4183 | 0.001 |
|
62 |
+
| 0.5081 | 8.0 | 880 | 0.4728 | 0.1651 | 0.1260 | 0.2719 | 0.4234 | 0.001 |
|
63 |
+
| 0.5081 | 9.0 | 990 | 0.4708 | 0.1639 | 0.1206 | 0.6393 | 0.4237 | 0.001 |
|
64 |
+
| 0.4668 | 10.0 | 1100 | 0.4733 | 0.1654 | 0.1230 | 0.5359 | 0.4151 | 0.001 |
|
65 |
+
| 0.4668 | 11.0 | 1210 | 0.4716 | 0.1647 | 0.1253 | 0.2479 | 0.4305 | 0.001 |
|
66 |
+
| 0.4668 | 12.0 | 1320 | 0.4708 | 0.1631 | 0.1244 | 0.3119 | 0.4358 | 0.001 |
|
67 |
+
| 0.4668 | 13.0 | 1430 | 0.4715 | 0.1635 | 0.1230 | 0.3694 | 0.4274 | 0.001 |
|
68 |
+
| 0.4641 | 14.0 | 1540 | 0.4721 | 0.1653 | 0.1216 | 0.5592 | 0.4134 | 0.001 |
|
69 |
+
| 0.4641 | 15.0 | 1650 | 0.4701 | 0.1628 | 0.1213 | 0.4936 | 0.4314 | 0.001 |
|
70 |
+
| 0.4641 | 16.0 | 1760 | 0.4719 | 0.1646 | 0.1229 | 0.2820 | 0.4328 | 0.001 |
|
71 |
+
| 0.4641 | 17.0 | 1870 | 0.4693 | 0.1621 | 0.1200 | 0.5294 | 0.4332 | 0.001 |
|
72 |
+
| 0.4641 | 18.0 | 1980 | 0.4710 | 0.1635 | 0.1216 | 0.4093 | 0.4294 | 0.001 |
|
73 |
+
| 0.4618 | 19.0 | 2090 | 0.4698 | 0.1622 | 0.1219 | 0.2918 | 0.4388 | 0.001 |
|
74 |
+
| 0.4618 | 20.0 | 2200 | 0.4692 | 0.1617 | 0.1190 | 0.4772 | 0.4355 | 0.001 |
|
75 |
+
| 0.4618 | 21.0 | 2310 | 0.4683 | 0.1606 | 0.1204 | 0.4336 | 0.4424 | 0.001 |
|
76 |
+
| 0.4618 | 22.0 | 2420 | 0.4724 | 0.1650 | 0.1183 | 0.7962 | 0.4233 | 0.001 |
|
77 |
+
| 0.4613 | 23.0 | 2530 | 0.4714 | 0.1641 | 0.1223 | 0.2854 | 0.4354 | 0.001 |
|
78 |
+
| 0.4613 | 24.0 | 2640 | 0.4707 | 0.1633 | 0.1207 | 0.4206 | 0.4280 | 0.001 |
|
79 |
+
| 0.4613 | 25.0 | 2750 | 0.4679 | 0.1606 | 0.1185 | 0.5436 | 0.4416 | 0.001 |
|
80 |
+
| 0.4613 | 26.0 | 2860 | 0.4708 | 0.1634 | 0.1192 | 0.4964 | 0.4268 | 0.001 |
|
81 |
+
| 0.4613 | 27.0 | 2970 | 0.4695 | 0.1625 | 0.1185 | 0.6399 | 0.4301 | 0.001 |
|
82 |
+
| 0.4607 | 28.0 | 3080 | 0.4701 | 0.1624 | 0.1184 | 0.5737 | 0.4324 | 0.001 |
|
83 |
+
| 0.4607 | 29.0 | 3190 | 0.4699 | 0.1624 | 0.1200 | 0.4459 | 0.4324 | 0.001 |
|
84 |
+
| 0.4607 | 30.0 | 3300 | 0.4723 | 0.1643 | 0.1254 | 0.2726 | 0.4308 | 0.001 |
|
85 |
+
| 0.4607 | 31.0 | 3410 | 0.4696 | 0.1622 | 0.1184 | 0.5308 | 0.4313 | 0.001 |
|
86 |
+
| 0.4604 | 32.0 | 3520 | 0.4668 | 0.1593 | 0.1175 | 0.4200 | 0.4508 | 0.0001 |
|
87 |
+
| 0.4604 | 33.0 | 3630 | 0.4663 | 0.1587 | 0.1177 | 0.3529 | 0.4565 | 0.0001 |
|
88 |
+
| 0.4604 | 34.0 | 3740 | 0.4667 | 0.1592 | 0.1181 | 0.3588 | 0.4542 | 0.0001 |
|
89 |
+
| 0.4604 | 35.0 | 3850 | 0.4659 | 0.1584 | 0.1160 | 0.4813 | 0.4545 | 0.0001 |
|
90 |
+
| 0.4604 | 36.0 | 3960 | 0.4658 | 0.1581 | 0.1173 | 0.3504 | 0.4594 | 0.0001 |
|
91 |
+
| 0.4565 | 37.0 | 4070 | 0.4654 | 0.1578 | 0.1158 | 0.3919 | 0.4608 | 0.0001 |
|
92 |
+
| 0.4565 | 38.0 | 4180 | 0.4655 | 0.1580 | 0.1166 | 0.4058 | 0.4583 | 0.0001 |
|
93 |
+
| 0.4565 | 39.0 | 4290 | 0.4658 | 0.1585 | 0.1174 | 0.4118 | 0.4567 | 0.0001 |
|
94 |
+
| 0.4565 | 40.0 | 4400 | 0.4656 | 0.1579 | 0.1170 | 0.3564 | 0.4607 | 0.0001 |
|
95 |
+
| 0.4552 | 41.0 | 4510 | 0.4657 | 0.1582 | 0.1171 | 0.3573 | 0.4598 | 0.0001 |
|
96 |
+
| 0.4552 | 42.0 | 4620 | 0.4652 | 0.1579 | 0.1155 | 0.5042 | 0.4587 | 0.0001 |
|
97 |
+
| 0.4552 | 43.0 | 4730 | 0.4651 | 0.1575 | 0.1157 | 0.4462 | 0.4613 | 0.0001 |
|
98 |
+
| 0.4552 | 44.0 | 4840 | 0.4654 | 0.1579 | 0.1166 | 0.4236 | 0.4604 | 0.0001 |
|
99 |
+
| 0.4552 | 45.0 | 4950 | 0.4649 | 0.1574 | 0.1151 | 0.4510 | 0.4625 | 0.0001 |
|
100 |
+
| 0.4538 | 46.0 | 5060 | 0.4648 | 0.1575 | 0.1157 | 0.4490 | 0.4619 | 0.0001 |
|
101 |
+
| 0.4538 | 47.0 | 5170 | 0.4649 | 0.1574 | 0.1152 | 0.4751 | 0.4615 | 0.0001 |
|
102 |
+
| 0.4538 | 48.0 | 5280 | 0.4648 | 0.1575 | 0.1151 | 0.5305 | 0.4631 | 0.0001 |
|
103 |
+
| 0.4538 | 49.0 | 5390 | 0.4648 | 0.1574 | 0.1154 | 0.4799 | 0.4630 | 0.0001 |
|
104 |
+
| 0.4532 | 50.0 | 5500 | 0.4650 | 0.1572 | 0.1172 | 0.2825 | 0.4694 | 0.0001 |
|
105 |
+
| 0.4532 | 51.0 | 5610 | 0.4656 | 0.1582 | 0.1151 | 0.4879 | 0.4573 | 0.0001 |
|
106 |
+
| 0.4532 | 52.0 | 5720 | 0.4643 | 0.1566 | 0.1155 | 0.4199 | 0.4674 | 0.0001 |
|
107 |
+
| 0.4532 | 53.0 | 5830 | 0.4644 | 0.1569 | 0.1156 | 0.3880 | 0.4673 | 0.0001 |
|
108 |
+
| 0.4532 | 54.0 | 5940 | 0.4646 | 0.1569 | 0.1148 | 0.4229 | 0.4654 | 0.0001 |
|
109 |
+
| 0.4526 | 55.0 | 6050 | 0.4644 | 0.1569 | 0.1159 | 0.4009 | 0.4659 | 0.0001 |
|
110 |
+
| 0.4526 | 56.0 | 6160 | 0.4647 | 0.1572 | 0.1164 | 0.3405 | 0.4660 | 0.0001 |
|
111 |
+
| 0.4526 | 57.0 | 6270 | 0.4645 | 0.1569 | 0.1152 | 0.4188 | 0.4661 | 0.0001 |
|
112 |
+
| 0.4526 | 58.0 | 6380 | 0.4651 | 0.1576 | 0.1164 | 0.3079 | 0.4659 | 0.0001 |
|
113 |
+
| 0.4526 | 59.0 | 6490 | 0.4645 | 0.1570 | 0.1150 | 0.4339 | 0.4654 | 1e-05 |
|
114 |
+
| 0.4514 | 60.0 | 6600 | 0.4642 | 0.1566 | 0.1150 | 0.3894 | 0.4679 | 1e-05 |
|
115 |
+
| 0.4514 | 61.0 | 6710 | 0.4639 | 0.1563 | 0.1146 | 0.4145 | 0.4693 | 1e-05 |
|
116 |
+
| 0.4514 | 62.0 | 6820 | 0.4641 | 0.1565 | 0.1148 | 0.4064 | 0.4686 | 1e-05 |
|
117 |
+
| 0.4514 | 63.0 | 6930 | 0.4643 | 0.1565 | 0.1149 | 0.3542 | 0.4698 | 1e-05 |
|
118 |
+
| 0.4511 | 64.0 | 7040 | 0.4640 | 0.1564 | 0.1150 | 0.3718 | 0.4702 | 1e-05 |
|
119 |
+
| 0.4511 | 65.0 | 7150 | 0.4641 | 0.1565 | 0.1152 | 0.4128 | 0.4680 | 1e-05 |
|
120 |
+
| 0.4511 | 66.0 | 7260 | 0.4644 | 0.1570 | 0.1145 | 0.4988 | 0.4658 | 1e-05 |
|
121 |
+
| 0.4511 | 67.0 | 7370 | 0.4638 | 0.1562 | 0.1151 | 0.4122 | 0.4697 | 1e-05 |
|
122 |
+
| 0.4511 | 68.0 | 7480 | 0.4640 | 0.1565 | 0.1144 | 0.4579 | 0.4674 | 1e-05 |
|
123 |
+
| 0.4508 | 69.0 | 7590 | 0.4638 | 0.1561 | 0.1143 | 0.4197 | 0.4702 | 1e-05 |
|
124 |
+
| 0.4508 | 70.0 | 7700 | 0.4639 | 0.1563 | 0.1145 | 0.4286 | 0.4695 | 1e-05 |
|
125 |
+
| 0.4508 | 71.0 | 7810 | 0.4641 | 0.1563 | 0.1153 | 0.3542 | 0.4708 | 1e-05 |
|
126 |
+
| 0.4508 | 72.0 | 7920 | 0.4642 | 0.1566 | 0.1147 | 0.4250 | 0.4681 | 1e-05 |
|
127 |
+
| 0.4505 | 73.0 | 8030 | 0.4638 | 0.1561 | 0.1140 | 0.4397 | 0.4700 | 1e-05 |
|
128 |
+
| 0.4505 | 74.0 | 8140 | 0.4638 | 0.1563 | 0.1145 | 0.4437 | 0.4689 | 1e-05 |
|
129 |
+
| 0.4505 | 75.0 | 8250 | 0.4638 | 0.1561 | 0.1145 | 0.4049 | 0.4705 | 1e-05 |
|
130 |
+
| 0.4505 | 76.0 | 8360 | 0.4640 | 0.1565 | 0.1141 | 0.4926 | 0.4675 | 0.0000 |
|
131 |
+
| 0.4505 | 77.0 | 8470 | 0.4639 | 0.1562 | 0.1142 | 0.4427 | 0.4695 | 0.0000 |
|
132 |
+
| 0.4505 | 78.0 | 8580 | 0.4639 | 0.1563 | 0.1145 | 0.4293 | 0.4692 | 0.0000 |
|
133 |
+
| 0.4505 | 79.0 | 8690 | 0.4641 | 0.1564 | 0.1147 | 0.3765 | 0.4700 | 0.0000 |
|
134 |
+
|
135 |
+
|
136 |
+
### Framework versions
|
137 |
+
|
138 |
+
- Transformers 4.41.0
|
139 |
+
- Pytorch 2.5.0+cu124
|
140 |
+
- Datasets 3.0.2
|
141 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 79.0,
|
3 |
+
"eval_explained_variance": 0.46537885069847107,
|
4 |
+
"eval_kl_divergence": 0.35774946212768555,
|
5 |
+
"eval_loss": 0.46723154187202454,
|
6 |
+
"eval_mae": 0.11465383321046829,
|
7 |
+
"eval_rmse": 0.15526758134365082,
|
8 |
+
"eval_runtime": 55.2715,
|
9 |
+
"eval_samples_per_second": 42.644,
|
10 |
+
"eval_steps_per_second": 0.669,
|
11 |
+
"learning_rate": 1.0000000000000002e-06,
|
12 |
+
"total_flos": 8.188406191467658e+19,
|
13 |
+
"train_loss": 0.4591466036709872,
|
14 |
+
"train_runtime": 19731.8487,
|
15 |
+
"train_samples_per_second": 53.236,
|
16 |
+
"train_steps_per_second": 0.836
|
17 |
+
}
|
logs/events.out.tfevents.1731665663.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 sha256:2b9787c9faf824d22538efe608b24007520f5dca2eb1efccafa39476d057b2df
|
3 |
+
size 53097
|
logs/events.out.tfevents.1731685574.datavisu2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbfda6d0ad1fc5f8b4bdf95291947b1a81413fd40d2aee987af1023541160de6
|
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 sha256:197459fbab5389ddd81caf8961bb524a564af1913bf5aec15a3fcccb6e30208d
|
3 |
size 1222956704
|
test_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 79.0,
|
3 |
+
"eval_explained_variance": 0.46537885069847107,
|
4 |
+
"eval_kl_divergence": 0.35774946212768555,
|
5 |
+
"eval_loss": 0.46723154187202454,
|
6 |
+
"eval_mae": 0.11465383321046829,
|
7 |
+
"eval_rmse": 0.15526758134365082,
|
8 |
+
"eval_runtime": 55.2715,
|
9 |
+
"eval_samples_per_second": 42.644,
|
10 |
+
"eval_steps_per_second": 0.669,
|
11 |
+
"learning_rate": 1.0000000000000002e-06
|
12 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 79.0,
|
3 |
+
"learning_rate": 1.0000000000000002e-06,
|
4 |
+
"total_flos": 8.188406191467658e+19,
|
5 |
+
"train_loss": 0.4591466036709872,
|
6 |
+
"train_runtime": 19731.8487,
|
7 |
+
"train_samples_per_second": 53.236,
|
8 |
+
"train_steps_per_second": 0.836
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4637599587440491,
|
3 |
+
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/drone/drone-DinoVdeau-from-probs-large-2024_11_15-batch-size64_freeze_probs/checkpoint-7590",
|
4 |
+
"epoch": 79.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8690,
|
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": 0.32841917872428894,
|
14 |
+
"eval_kl_divergence": 0.10252656042575836,
|
15 |
+
"eval_loss": 0.5005590319633484,
|
16 |
+
"eval_mae": 0.15520869195461273,
|
17 |
+
"eval_rmse": 0.19042611122131348,
|
18 |
+
"eval_runtime": 60.5528,
|
19 |
+
"eval_samples_per_second": 38.875,
|
20 |
+
"eval_steps_per_second": 0.611,
|
21 |
+
"learning_rate": 0.001,
|
22 |
+
"step": 110
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"eval_explained_variance": 0.3932196795940399,
|
27 |
+
"eval_kl_divergence": 0.5180067420005798,
|
28 |
+
"eval_loss": 0.47547808289527893,
|
29 |
+
"eval_mae": 0.12452296167612076,
|
30 |
+
"eval_rmse": 0.16812847554683685,
|
31 |
+
"eval_runtime": 57.4976,
|
32 |
+
"eval_samples_per_second": 40.941,
|
33 |
+
"eval_steps_per_second": 0.644,
|
34 |
+
"learning_rate": 0.001,
|
35 |
+
"step": 220
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 3.0,
|
39 |
+
"eval_explained_variance": 0.3974684476852417,
|
40 |
+
"eval_kl_divergence": 0.6862403154373169,
|
41 |
+
"eval_loss": 0.47452571988105774,
|
42 |
+
"eval_mae": 0.1226513460278511,
|
43 |
+
"eval_rmse": 0.16751675307750702,
|
44 |
+
"eval_runtime": 57.6506,
|
45 |
+
"eval_samples_per_second": 40.832,
|
46 |
+
"eval_steps_per_second": 0.642,
|
47 |
+
"learning_rate": 0.001,
|
48 |
+
"step": 330
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 4.0,
|
52 |
+
"eval_explained_variance": 0.40236756205558777,
|
53 |
+
"eval_kl_divergence": 0.3211989104747772,
|
54 |
+
"eval_loss": 0.47420722246170044,
|
55 |
+
"eval_mae": 0.1255439817905426,
|
56 |
+
"eval_rmse": 0.16721709072589874,
|
57 |
+
"eval_runtime": 58.0216,
|
58 |
+
"eval_samples_per_second": 40.571,
|
59 |
+
"eval_steps_per_second": 0.638,
|
60 |
+
"learning_rate": 0.001,
|
61 |
+
"step": 440
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 4.545454545454545,
|
65 |
+
"grad_norm": 0.20816726982593536,
|
66 |
+
"learning_rate": 0.001,
|
67 |
+
"loss": 0.5081,
|
68 |
+
"step": 500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 5.0,
|
72 |
+
"eval_explained_variance": 0.4118477404117584,
|
73 |
+
"eval_kl_divergence": 0.5071600079536438,
|
74 |
+
"eval_loss": 0.47245556116104126,
|
75 |
+
"eval_mae": 0.12236347794532776,
|
76 |
+
"eval_rmse": 0.16526558995246887,
|
77 |
+
"eval_runtime": 60.9082,
|
78 |
+
"eval_samples_per_second": 38.648,
|
79 |
+
"eval_steps_per_second": 0.607,
|
80 |
+
"learning_rate": 0.001,
|
81 |
+
"step": 550
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 6.0,
|
85 |
+
"eval_explained_variance": 0.4100535213947296,
|
86 |
+
"eval_kl_divergence": 0.6710320115089417,
|
87 |
+
"eval_loss": 0.4725925624370575,
|
88 |
+
"eval_mae": 0.12164705991744995,
|
89 |
+
"eval_rmse": 0.16568797826766968,
|
90 |
+
"eval_runtime": 60.266,
|
91 |
+
"eval_samples_per_second": 39.06,
|
92 |
+
"eval_steps_per_second": 0.614,
|
93 |
+
"learning_rate": 0.001,
|
94 |
+
"step": 660
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 7.0,
|
98 |
+
"eval_explained_variance": 0.4183339774608612,
|
99 |
+
"eval_kl_divergence": 0.3161657452583313,
|
100 |
+
"eval_loss": 0.4731809198856354,
|
101 |
+
"eval_mae": 0.12548527121543884,
|
102 |
+
"eval_rmse": 0.16550247371196747,
|
103 |
+
"eval_runtime": 59.012,
|
104 |
+
"eval_samples_per_second": 39.89,
|
105 |
+
"eval_steps_per_second": 0.627,
|
106 |
+
"learning_rate": 0.001,
|
107 |
+
"step": 770
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 8.0,
|
111 |
+
"eval_explained_variance": 0.4233661890029907,
|
112 |
+
"eval_kl_divergence": 0.27189013361930847,
|
113 |
+
"eval_loss": 0.47284314036369324,
|
114 |
+
"eval_mae": 0.12600405514240265,
|
115 |
+
"eval_rmse": 0.16514724493026733,
|
116 |
+
"eval_runtime": 60.8246,
|
117 |
+
"eval_samples_per_second": 38.701,
|
118 |
+
"eval_steps_per_second": 0.608,
|
119 |
+
"learning_rate": 0.001,
|
120 |
+
"step": 880
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 9.0,
|
124 |
+
"eval_explained_variance": 0.42370346188545227,
|
125 |
+
"eval_kl_divergence": 0.6392844319343567,
|
126 |
+
"eval_loss": 0.4707973003387451,
|
127 |
+
"eval_mae": 0.12056442350149155,
|
128 |
+
"eval_rmse": 0.16385647654533386,
|
129 |
+
"eval_runtime": 57.5192,
|
130 |
+
"eval_samples_per_second": 40.925,
|
131 |
+
"eval_steps_per_second": 0.643,
|
132 |
+
"learning_rate": 0.001,
|
133 |
+
"step": 990
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 9.090909090909092,
|
137 |
+
"grad_norm": 0.15108729898929596,
|
138 |
+
"learning_rate": 0.001,
|
139 |
+
"loss": 0.4668,
|
140 |
+
"step": 1000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.0,
|
144 |
+
"eval_explained_variance": 0.41512250900268555,
|
145 |
+
"eval_kl_divergence": 0.5359246134757996,
|
146 |
+
"eval_loss": 0.4732784628868103,
|
147 |
+
"eval_mae": 0.12296172976493835,
|
148 |
+
"eval_rmse": 0.16544467210769653,
|
149 |
+
"eval_runtime": 60.8049,
|
150 |
+
"eval_samples_per_second": 38.714,
|
151 |
+
"eval_steps_per_second": 0.609,
|
152 |
+
"learning_rate": 0.001,
|
153 |
+
"step": 1100
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 11.0,
|
157 |
+
"eval_explained_variance": 0.43050625920295715,
|
158 |
+
"eval_kl_divergence": 0.24788798391819,
|
159 |
+
"eval_loss": 0.47162503004074097,
|
160 |
+
"eval_mae": 0.12532271444797516,
|
161 |
+
"eval_rmse": 0.1646868884563446,
|
162 |
+
"eval_runtime": 59.6353,
|
163 |
+
"eval_samples_per_second": 39.473,
|
164 |
+
"eval_steps_per_second": 0.62,
|
165 |
+
"learning_rate": 0.001,
|
166 |
+
"step": 1210
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 12.0,
|
170 |
+
"eval_explained_variance": 0.43575945496559143,
|
171 |
+
"eval_kl_divergence": 0.3118789792060852,
|
172 |
+
"eval_loss": 0.47083696722984314,
|
173 |
+
"eval_mae": 0.12438095360994339,
|
174 |
+
"eval_rmse": 0.16306261718273163,
|
175 |
+
"eval_runtime": 59.6011,
|
176 |
+
"eval_samples_per_second": 39.496,
|
177 |
+
"eval_steps_per_second": 0.621,
|
178 |
+
"learning_rate": 0.001,
|
179 |
+
"step": 1320
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 13.0,
|
183 |
+
"eval_explained_variance": 0.42740270495414734,
|
184 |
+
"eval_kl_divergence": 0.36944085359573364,
|
185 |
+
"eval_loss": 0.47152063250541687,
|
186 |
+
"eval_mae": 0.1230199933052063,
|
187 |
+
"eval_rmse": 0.16350014507770538,
|
188 |
+
"eval_runtime": 60.519,
|
189 |
+
"eval_samples_per_second": 38.897,
|
190 |
+
"eval_steps_per_second": 0.611,
|
191 |
+
"learning_rate": 0.001,
|
192 |
+
"step": 1430
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 13.636363636363637,
|
196 |
+
"grad_norm": 0.1494702696800232,
|
197 |
+
"learning_rate": 0.001,
|
198 |
+
"loss": 0.4641,
|
199 |
+
"step": 1500
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 14.0,
|
203 |
+
"eval_explained_variance": 0.41340962052345276,
|
204 |
+
"eval_kl_divergence": 0.5592221617698669,
|
205 |
+
"eval_loss": 0.47212228178977966,
|
206 |
+
"eval_mae": 0.12158066779375076,
|
207 |
+
"eval_rmse": 0.16525773704051971,
|
208 |
+
"eval_runtime": 59.2288,
|
209 |
+
"eval_samples_per_second": 39.744,
|
210 |
+
"eval_steps_per_second": 0.625,
|
211 |
+
"learning_rate": 0.001,
|
212 |
+
"step": 1540
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 15.0,
|
216 |
+
"eval_explained_variance": 0.43138065934181213,
|
217 |
+
"eval_kl_divergence": 0.49361512064933777,
|
218 |
+
"eval_loss": 0.47012239694595337,
|
219 |
+
"eval_mae": 0.12126541882753372,
|
220 |
+
"eval_rmse": 0.16284985840320587,
|
221 |
+
"eval_runtime": 61.7909,
|
222 |
+
"eval_samples_per_second": 38.096,
|
223 |
+
"eval_steps_per_second": 0.599,
|
224 |
+
"learning_rate": 0.001,
|
225 |
+
"step": 1650
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 16.0,
|
229 |
+
"eval_explained_variance": 0.43279382586479187,
|
230 |
+
"eval_kl_divergence": 0.2819983661174774,
|
231 |
+
"eval_loss": 0.4718552827835083,
|
232 |
+
"eval_mae": 0.12293669581413269,
|
233 |
+
"eval_rmse": 0.16459016501903534,
|
234 |
+
"eval_runtime": 59.5152,
|
235 |
+
"eval_samples_per_second": 39.553,
|
236 |
+
"eval_steps_per_second": 0.622,
|
237 |
+
"learning_rate": 0.001,
|
238 |
+
"step": 1760
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 17.0,
|
242 |
+
"eval_explained_variance": 0.43319597840309143,
|
243 |
+
"eval_kl_divergence": 0.5294199585914612,
|
244 |
+
"eval_loss": 0.46933484077453613,
|
245 |
+
"eval_mae": 0.12004240602254868,
|
246 |
+
"eval_rmse": 0.16205951571464539,
|
247 |
+
"eval_runtime": 59.464,
|
248 |
+
"eval_samples_per_second": 39.587,
|
249 |
+
"eval_steps_per_second": 0.622,
|
250 |
+
"learning_rate": 0.001,
|
251 |
+
"step": 1870
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 18.0,
|
255 |
+
"eval_explained_variance": 0.42939844727516174,
|
256 |
+
"eval_kl_divergence": 0.4093473255634308,
|
257 |
+
"eval_loss": 0.4710436165332794,
|
258 |
+
"eval_mae": 0.12161851674318314,
|
259 |
+
"eval_rmse": 0.16353638470172882,
|
260 |
+
"eval_runtime": 60.82,
|
261 |
+
"eval_samples_per_second": 38.704,
|
262 |
+
"eval_steps_per_second": 0.608,
|
263 |
+
"learning_rate": 0.001,
|
264 |
+
"step": 1980
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 18.181818181818183,
|
268 |
+
"grad_norm": 0.11152761429548264,
|
269 |
+
"learning_rate": 0.001,
|
270 |
+
"loss": 0.4618,
|
271 |
+
"step": 2000
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 19.0,
|
275 |
+
"eval_explained_variance": 0.4387861490249634,
|
276 |
+
"eval_kl_divergence": 0.29183313250541687,
|
277 |
+
"eval_loss": 0.4698491394519806,
|
278 |
+
"eval_mae": 0.12186750769615173,
|
279 |
+
"eval_rmse": 0.16223199665546417,
|
280 |
+
"eval_runtime": 62.7122,
|
281 |
+
"eval_samples_per_second": 37.537,
|
282 |
+
"eval_steps_per_second": 0.59,
|
283 |
+
"learning_rate": 0.001,
|
284 |
+
"step": 2090
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 20.0,
|
288 |
+
"eval_explained_variance": 0.4355180561542511,
|
289 |
+
"eval_kl_divergence": 0.47719886898994446,
|
290 |
+
"eval_loss": 0.4691685736179352,
|
291 |
+
"eval_mae": 0.11899092048406601,
|
292 |
+
"eval_rmse": 0.16173695027828217,
|
293 |
+
"eval_runtime": 60.1867,
|
294 |
+
"eval_samples_per_second": 39.112,
|
295 |
+
"eval_steps_per_second": 0.615,
|
296 |
+
"learning_rate": 0.001,
|
297 |
+
"step": 2200
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 21.0,
|
301 |
+
"eval_explained_variance": 0.44244399666786194,
|
302 |
+
"eval_kl_divergence": 0.4335584044456482,
|
303 |
+
"eval_loss": 0.46830564737319946,
|
304 |
+
"eval_mae": 0.12040043622255325,
|
305 |
+
"eval_rmse": 0.16058459877967834,
|
306 |
+
"eval_runtime": 59.7866,
|
307 |
+
"eval_samples_per_second": 39.373,
|
308 |
+
"eval_steps_per_second": 0.619,
|
309 |
+
"learning_rate": 0.001,
|
310 |
+
"step": 2310
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 22.0,
|
314 |
+
"eval_explained_variance": 0.4233216345310211,
|
315 |
+
"eval_kl_divergence": 0.7962150573730469,
|
316 |
+
"eval_loss": 0.47239789366722107,
|
317 |
+
"eval_mae": 0.11830935627222061,
|
318 |
+
"eval_rmse": 0.16501490771770477,
|
319 |
+
"eval_runtime": 62.1424,
|
320 |
+
"eval_samples_per_second": 37.881,
|
321 |
+
"eval_steps_per_second": 0.595,
|
322 |
+
"learning_rate": 0.001,
|
323 |
+
"step": 2420
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 22.727272727272727,
|
327 |
+
"grad_norm": 0.10114327073097229,
|
328 |
+
"learning_rate": 0.001,
|
329 |
+
"loss": 0.4613,
|
330 |
+
"step": 2500
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 23.0,
|
334 |
+
"eval_explained_variance": 0.43542811274528503,
|
335 |
+
"eval_kl_divergence": 0.2854216396808624,
|
336 |
+
"eval_loss": 0.47136834263801575,
|
337 |
+
"eval_mae": 0.12230511754751205,
|
338 |
+
"eval_rmse": 0.16408009827136993,
|
339 |
+
"eval_runtime": 61.631,
|
340 |
+
"eval_samples_per_second": 38.195,
|
341 |
+
"eval_steps_per_second": 0.6,
|
342 |
+
"learning_rate": 0.001,
|
343 |
+
"step": 2530
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 24.0,
|
347 |
+
"eval_explained_variance": 0.42795756459236145,
|
348 |
+
"eval_kl_divergence": 0.42056405544281006,
|
349 |
+
"eval_loss": 0.4706868529319763,
|
350 |
+
"eval_mae": 0.12066368013620377,
|
351 |
+
"eval_rmse": 0.16326285898685455,
|
352 |
+
"eval_runtime": 61.2844,
|
353 |
+
"eval_samples_per_second": 38.411,
|
354 |
+
"eval_steps_per_second": 0.604,
|
355 |
+
"learning_rate": 0.001,
|
356 |
+
"step": 2640
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 25.0,
|
360 |
+
"eval_explained_variance": 0.44159284234046936,
|
361 |
+
"eval_kl_divergence": 0.5435640811920166,
|
362 |
+
"eval_loss": 0.46786901354789734,
|
363 |
+
"eval_mae": 0.11850475519895554,
|
364 |
+
"eval_rmse": 0.16058622300624847,
|
365 |
+
"eval_runtime": 61.9284,
|
366 |
+
"eval_samples_per_second": 38.012,
|
367 |
+
"eval_steps_per_second": 0.597,
|
368 |
+
"learning_rate": 0.001,
|
369 |
+
"step": 2750
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 26.0,
|
373 |
+
"eval_explained_variance": 0.4267805814743042,
|
374 |
+
"eval_kl_divergence": 0.4964081943035126,
|
375 |
+
"eval_loss": 0.47084224224090576,
|
376 |
+
"eval_mae": 0.11923620104789734,
|
377 |
+
"eval_rmse": 0.16337566077709198,
|
378 |
+
"eval_runtime": 66.0163,
|
379 |
+
"eval_samples_per_second": 35.658,
|
380 |
+
"eval_steps_per_second": 0.56,
|
381 |
+
"learning_rate": 0.001,
|
382 |
+
"step": 2860
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 27.0,
|
386 |
+
"eval_explained_variance": 0.43011048436164856,
|
387 |
+
"eval_kl_divergence": 0.6398861408233643,
|
388 |
+
"eval_loss": 0.4695045053958893,
|
389 |
+
"eval_mae": 0.11852020025253296,
|
390 |
+
"eval_rmse": 0.16250041127204895,
|
391 |
+
"eval_runtime": 60.9743,
|
392 |
+
"eval_samples_per_second": 38.606,
|
393 |
+
"eval_steps_per_second": 0.607,
|
394 |
+
"learning_rate": 0.001,
|
395 |
+
"step": 2970
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 27.272727272727273,
|
399 |
+
"grad_norm": 0.12341216951608658,
|
400 |
+
"learning_rate": 0.001,
|
401 |
+
"loss": 0.4607,
|
402 |
+
"step": 3000
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 28.0,
|
406 |
+
"eval_explained_variance": 0.43241068720817566,
|
407 |
+
"eval_kl_divergence": 0.5736985206604004,
|
408 |
+
"eval_loss": 0.4700873792171478,
|
409 |
+
"eval_mae": 0.11835578829050064,
|
410 |
+
"eval_rmse": 0.16237075626850128,
|
411 |
+
"eval_runtime": 60.2395,
|
412 |
+
"eval_samples_per_second": 39.077,
|
413 |
+
"eval_steps_per_second": 0.614,
|
414 |
+
"learning_rate": 0.001,
|
415 |
+
"step": 3080
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 29.0,
|
419 |
+
"eval_explained_variance": 0.43240413069725037,
|
420 |
+
"eval_kl_divergence": 0.4459187090396881,
|
421 |
+
"eval_loss": 0.4698559045791626,
|
422 |
+
"eval_mae": 0.1200462281703949,
|
423 |
+
"eval_rmse": 0.16241396963596344,
|
424 |
+
"eval_runtime": 59.6241,
|
425 |
+
"eval_samples_per_second": 39.481,
|
426 |
+
"eval_steps_per_second": 0.621,
|
427 |
+
"learning_rate": 0.001,
|
428 |
+
"step": 3190
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 30.0,
|
432 |
+
"eval_explained_variance": 0.4308302402496338,
|
433 |
+
"eval_kl_divergence": 0.27262812852859497,
|
434 |
+
"eval_loss": 0.4722815454006195,
|
435 |
+
"eval_mae": 0.12538868188858032,
|
436 |
+
"eval_rmse": 0.1643446981906891,
|
437 |
+
"eval_runtime": 60.4817,
|
438 |
+
"eval_samples_per_second": 38.921,
|
439 |
+
"eval_steps_per_second": 0.612,
|
440 |
+
"learning_rate": 0.001,
|
441 |
+
"step": 3300
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 31.0,
|
445 |
+
"eval_explained_variance": 0.431255966424942,
|
446 |
+
"eval_kl_divergence": 0.5307573080062866,
|
447 |
+
"eval_loss": 0.46958214044570923,
|
448 |
+
"eval_mae": 0.11837340146303177,
|
449 |
+
"eval_rmse": 0.16221857070922852,
|
450 |
+
"eval_runtime": 59.6158,
|
451 |
+
"eval_samples_per_second": 39.486,
|
452 |
+
"eval_steps_per_second": 0.621,
|
453 |
+
"learning_rate": 0.001,
|
454 |
+
"step": 3410
|
455 |
+
},
|
456 |
+
{
|
457 |
+
"epoch": 31.818181818181817,
|
458 |
+
"grad_norm": 0.09215673804283142,
|
459 |
+
"learning_rate": 0.0001,
|
460 |
+
"loss": 0.4604,
|
461 |
+
"step": 3500
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 32.0,
|
465 |
+
"eval_explained_variance": 0.4507780075073242,
|
466 |
+
"eval_kl_divergence": 0.4200185239315033,
|
467 |
+
"eval_loss": 0.46677276492118835,
|
468 |
+
"eval_mae": 0.11745267361402512,
|
469 |
+
"eval_rmse": 0.1592676192522049,
|
470 |
+
"eval_runtime": 59.8038,
|
471 |
+
"eval_samples_per_second": 39.362,
|
472 |
+
"eval_steps_per_second": 0.619,
|
473 |
+
"learning_rate": 0.0001,
|
474 |
+
"step": 3520
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 33.0,
|
478 |
+
"eval_explained_variance": 0.4565463066101074,
|
479 |
+
"eval_kl_divergence": 0.35289108753204346,
|
480 |
+
"eval_loss": 0.46626824140548706,
|
481 |
+
"eval_mae": 0.11769836395978928,
|
482 |
+
"eval_rmse": 0.1586667150259018,
|
483 |
+
"eval_runtime": 63.0473,
|
484 |
+
"eval_samples_per_second": 37.337,
|
485 |
+
"eval_steps_per_second": 0.587,
|
486 |
+
"learning_rate": 0.0001,
|
487 |
+
"step": 3630
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 34.0,
|
491 |
+
"eval_explained_variance": 0.4541673958301544,
|
492 |
+
"eval_kl_divergence": 0.3587631583213806,
|
493 |
+
"eval_loss": 0.46665358543395996,
|
494 |
+
"eval_mae": 0.1181267499923706,
|
495 |
+
"eval_rmse": 0.15922589600086212,
|
496 |
+
"eval_runtime": 58.0806,
|
497 |
+
"eval_samples_per_second": 40.53,
|
498 |
+
"eval_steps_per_second": 0.637,
|
499 |
+
"learning_rate": 0.0001,
|
500 |
+
"step": 3740
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 35.0,
|
504 |
+
"eval_explained_variance": 0.4545403718948364,
|
505 |
+
"eval_kl_divergence": 0.4813242256641388,
|
506 |
+
"eval_loss": 0.46587392687797546,
|
507 |
+
"eval_mae": 0.11597732454538345,
|
508 |
+
"eval_rmse": 0.15844957530498505,
|
509 |
+
"eval_runtime": 59.5027,
|
510 |
+
"eval_samples_per_second": 39.561,
|
511 |
+
"eval_steps_per_second": 0.622,
|
512 |
+
"learning_rate": 0.0001,
|
513 |
+
"step": 3850
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 36.0,
|
517 |
+
"eval_explained_variance": 0.45941615104675293,
|
518 |
+
"eval_kl_divergence": 0.3503873348236084,
|
519 |
+
"eval_loss": 0.46578526496887207,
|
520 |
+
"eval_mae": 0.11725542694330215,
|
521 |
+
"eval_rmse": 0.15814347565174103,
|
522 |
+
"eval_runtime": 60.095,
|
523 |
+
"eval_samples_per_second": 39.171,
|
524 |
+
"eval_steps_per_second": 0.616,
|
525 |
+
"learning_rate": 0.0001,
|
526 |
+
"step": 3960
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 36.36363636363637,
|
530 |
+
"grad_norm": 0.08345460891723633,
|
531 |
+
"learning_rate": 0.0001,
|
532 |
+
"loss": 0.4565,
|
533 |
+
"step": 4000
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 37.0,
|
537 |
+
"eval_explained_variance": 0.4607694149017334,
|
538 |
+
"eval_kl_divergence": 0.39189669489860535,
|
539 |
+
"eval_loss": 0.4654408395290375,
|
540 |
+
"eval_mae": 0.11584330350160599,
|
541 |
+
"eval_rmse": 0.1577824205160141,
|
542 |
+
"eval_runtime": 58.734,
|
543 |
+
"eval_samples_per_second": 40.079,
|
544 |
+
"eval_steps_per_second": 0.63,
|
545 |
+
"learning_rate": 0.0001,
|
546 |
+
"step": 4070
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 38.0,
|
550 |
+
"eval_explained_variance": 0.45832768082618713,
|
551 |
+
"eval_kl_divergence": 0.40583303570747375,
|
552 |
+
"eval_loss": 0.46546319127082825,
|
553 |
+
"eval_mae": 0.1166045293211937,
|
554 |
+
"eval_rmse": 0.15796954929828644,
|
555 |
+
"eval_runtime": 58.3156,
|
556 |
+
"eval_samples_per_second": 40.367,
|
557 |
+
"eval_steps_per_second": 0.634,
|
558 |
+
"learning_rate": 0.0001,
|
559 |
+
"step": 4180
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 39.0,
|
563 |
+
"eval_explained_variance": 0.45672306418418884,
|
564 |
+
"eval_kl_divergence": 0.4117860198020935,
|
565 |
+
"eval_loss": 0.465843141078949,
|
566 |
+
"eval_mae": 0.11737682670354843,
|
567 |
+
"eval_rmse": 0.15845851600170135,
|
568 |
+
"eval_runtime": 59.8584,
|
569 |
+
"eval_samples_per_second": 39.326,
|
570 |
+
"eval_steps_per_second": 0.618,
|
571 |
+
"learning_rate": 0.0001,
|
572 |
+
"step": 4290
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 40.0,
|
576 |
+
"eval_explained_variance": 0.4607222080230713,
|
577 |
+
"eval_kl_divergence": 0.3563988506793976,
|
578 |
+
"eval_loss": 0.46561121940612793,
|
579 |
+
"eval_mae": 0.11697889119386673,
|
580 |
+
"eval_rmse": 0.15787295997142792,
|
581 |
+
"eval_runtime": 61.3479,
|
582 |
+
"eval_samples_per_second": 38.371,
|
583 |
+
"eval_steps_per_second": 0.603,
|
584 |
+
"learning_rate": 0.0001,
|
585 |
+
"step": 4400
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 40.90909090909091,
|
589 |
+
"grad_norm": 0.08773978799581528,
|
590 |
+
"learning_rate": 0.0001,
|
591 |
+
"loss": 0.4552,
|
592 |
+
"step": 4500
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 41.0,
|
596 |
+
"eval_explained_variance": 0.45979323983192444,
|
597 |
+
"eval_kl_divergence": 0.3572520911693573,
|
598 |
+
"eval_loss": 0.4657152593135834,
|
599 |
+
"eval_mae": 0.11711093783378601,
|
600 |
+
"eval_rmse": 0.15820421278476715,
|
601 |
+
"eval_runtime": 57.6839,
|
602 |
+
"eval_samples_per_second": 40.809,
|
603 |
+
"eval_steps_per_second": 0.641,
|
604 |
+
"learning_rate": 0.0001,
|
605 |
+
"step": 4510
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 42.0,
|
609 |
+
"eval_explained_variance": 0.45867350697517395,
|
610 |
+
"eval_kl_divergence": 0.5041557550430298,
|
611 |
+
"eval_loss": 0.4651602804660797,
|
612 |
+
"eval_mae": 0.11550069600343704,
|
613 |
+
"eval_rmse": 0.15786336362361908,
|
614 |
+
"eval_runtime": 56.8293,
|
615 |
+
"eval_samples_per_second": 41.422,
|
616 |
+
"eval_steps_per_second": 0.651,
|
617 |
+
"learning_rate": 0.0001,
|
618 |
+
"step": 4620
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 43.0,
|
622 |
+
"eval_explained_variance": 0.4612714946269989,
|
623 |
+
"eval_kl_divergence": 0.44621211290359497,
|
624 |
+
"eval_loss": 0.4651065468788147,
|
625 |
+
"eval_mae": 0.11574172228574753,
|
626 |
+
"eval_rmse": 0.15747833251953125,
|
627 |
+
"eval_runtime": 57.1474,
|
628 |
+
"eval_samples_per_second": 41.192,
|
629 |
+
"eval_steps_per_second": 0.647,
|
630 |
+
"learning_rate": 0.0001,
|
631 |
+
"step": 4730
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 44.0,
|
635 |
+
"eval_explained_variance": 0.4603614807128906,
|
636 |
+
"eval_kl_divergence": 0.4236082434654236,
|
637 |
+
"eval_loss": 0.46537330746650696,
|
638 |
+
"eval_mae": 0.11658215522766113,
|
639 |
+
"eval_rmse": 0.15792043507099152,
|
640 |
+
"eval_runtime": 55.8584,
|
641 |
+
"eval_samples_per_second": 42.142,
|
642 |
+
"eval_steps_per_second": 0.662,
|
643 |
+
"learning_rate": 0.0001,
|
644 |
+
"step": 4840
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 45.0,
|
648 |
+
"eval_explained_variance": 0.46250852942466736,
|
649 |
+
"eval_kl_divergence": 0.45096999406814575,
|
650 |
+
"eval_loss": 0.46489208936691284,
|
651 |
+
"eval_mae": 0.11505404114723206,
|
652 |
+
"eval_rmse": 0.15738531947135925,
|
653 |
+
"eval_runtime": 55.5313,
|
654 |
+
"eval_samples_per_second": 42.391,
|
655 |
+
"eval_steps_per_second": 0.666,
|
656 |
+
"learning_rate": 0.0001,
|
657 |
+
"step": 4950
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 45.45454545454545,
|
661 |
+
"grad_norm": 0.08461819589138031,
|
662 |
+
"learning_rate": 0.0001,
|
663 |
+
"loss": 0.4538,
|
664 |
+
"step": 5000
|
665 |
+
},
|
666 |
+
{
|
667 |
+
"epoch": 46.0,
|
668 |
+
"eval_explained_variance": 0.46191954612731934,
|
669 |
+
"eval_kl_divergence": 0.44900697469711304,
|
670 |
+
"eval_loss": 0.46484702825546265,
|
671 |
+
"eval_mae": 0.11566606909036636,
|
672 |
+
"eval_rmse": 0.15745492279529572,
|
673 |
+
"eval_runtime": 56.8805,
|
674 |
+
"eval_samples_per_second": 41.385,
|
675 |
+
"eval_steps_per_second": 0.65,
|
676 |
+
"learning_rate": 0.0001,
|
677 |
+
"step": 5060
|
678 |
+
},
|
679 |
+
{
|
680 |
+
"epoch": 47.0,
|
681 |
+
"eval_explained_variance": 0.46148741245269775,
|
682 |
+
"eval_kl_divergence": 0.47508490085601807,
|
683 |
+
"eval_loss": 0.4648602306842804,
|
684 |
+
"eval_mae": 0.11517279595136642,
|
685 |
+
"eval_rmse": 0.1574285626411438,
|
686 |
+
"eval_runtime": 56.4955,
|
687 |
+
"eval_samples_per_second": 41.667,
|
688 |
+
"eval_steps_per_second": 0.655,
|
689 |
+
"learning_rate": 0.0001,
|
690 |
+
"step": 5170
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 48.0,
|
694 |
+
"eval_explained_variance": 0.4631068706512451,
|
695 |
+
"eval_kl_divergence": 0.5305130481719971,
|
696 |
+
"eval_loss": 0.4647873342037201,
|
697 |
+
"eval_mae": 0.11513545364141464,
|
698 |
+
"eval_rmse": 0.15746952593326569,
|
699 |
+
"eval_runtime": 59.054,
|
700 |
+
"eval_samples_per_second": 39.862,
|
701 |
+
"eval_steps_per_second": 0.627,
|
702 |
+
"learning_rate": 0.0001,
|
703 |
+
"step": 5280
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 49.0,
|
707 |
+
"eval_explained_variance": 0.46304425597190857,
|
708 |
+
"eval_kl_divergence": 0.4798574149608612,
|
709 |
+
"eval_loss": 0.4647849500179291,
|
710 |
+
"eval_mae": 0.11539488285779953,
|
711 |
+
"eval_rmse": 0.1573745161294937,
|
712 |
+
"eval_runtime": 54.2646,
|
713 |
+
"eval_samples_per_second": 43.38,
|
714 |
+
"eval_steps_per_second": 0.682,
|
715 |
+
"learning_rate": 0.0001,
|
716 |
+
"step": 5390
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 50.0,
|
720 |
+
"grad_norm": 0.16299596428871155,
|
721 |
+
"learning_rate": 0.0001,
|
722 |
+
"loss": 0.4532,
|
723 |
+
"step": 5500
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 50.0,
|
727 |
+
"eval_explained_variance": 0.4693569839000702,
|
728 |
+
"eval_kl_divergence": 0.2825404107570648,
|
729 |
+
"eval_loss": 0.46499085426330566,
|
730 |
+
"eval_mae": 0.1172276958823204,
|
731 |
+
"eval_rmse": 0.15717318654060364,
|
732 |
+
"eval_runtime": 56.0282,
|
733 |
+
"eval_samples_per_second": 42.015,
|
734 |
+
"eval_steps_per_second": 0.66,
|
735 |
+
"learning_rate": 0.0001,
|
736 |
+
"step": 5500
|
737 |
+
},
|
738 |
+
{
|
739 |
+
"epoch": 51.0,
|
740 |
+
"eval_explained_variance": 0.4573368728160858,
|
741 |
+
"eval_kl_divergence": 0.48794299364089966,
|
742 |
+
"eval_loss": 0.465638667345047,
|
743 |
+
"eval_mae": 0.11509021371603012,
|
744 |
+
"eval_rmse": 0.15819959342479706,
|
745 |
+
"eval_runtime": 52.7895,
|
746 |
+
"eval_samples_per_second": 44.592,
|
747 |
+
"eval_steps_per_second": 0.701,
|
748 |
+
"learning_rate": 0.0001,
|
749 |
+
"step": 5610
|
750 |
+
},
|
751 |
+
{
|
752 |
+
"epoch": 52.0,
|
753 |
+
"eval_explained_variance": 0.4673852026462555,
|
754 |
+
"eval_kl_divergence": 0.41987907886505127,
|
755 |
+
"eval_loss": 0.46429532766342163,
|
756 |
+
"eval_mae": 0.11551753431558609,
|
757 |
+
"eval_rmse": 0.15662376582622528,
|
758 |
+
"eval_runtime": 54.5816,
|
759 |
+
"eval_samples_per_second": 43.128,
|
760 |
+
"eval_steps_per_second": 0.678,
|
761 |
+
"learning_rate": 0.0001,
|
762 |
+
"step": 5720
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 53.0,
|
766 |
+
"eval_explained_variance": 0.4672771692276001,
|
767 |
+
"eval_kl_divergence": 0.3879646956920624,
|
768 |
+
"eval_loss": 0.46441230177879333,
|
769 |
+
"eval_mae": 0.1155916228890419,
|
770 |
+
"eval_rmse": 0.1568875014781952,
|
771 |
+
"eval_runtime": 53.5146,
|
772 |
+
"eval_samples_per_second": 43.988,
|
773 |
+
"eval_steps_per_second": 0.691,
|
774 |
+
"learning_rate": 0.0001,
|
775 |
+
"step": 5830
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 54.0,
|
779 |
+
"eval_explained_variance": 0.4654136002063751,
|
780 |
+
"eval_kl_divergence": 0.42290592193603516,
|
781 |
+
"eval_loss": 0.4646008610725403,
|
782 |
+
"eval_mae": 0.11479470133781433,
|
783 |
+
"eval_rmse": 0.1569375991821289,
|
784 |
+
"eval_runtime": 53.8924,
|
785 |
+
"eval_samples_per_second": 43.68,
|
786 |
+
"eval_steps_per_second": 0.687,
|
787 |
+
"learning_rate": 0.0001,
|
788 |
+
"step": 5940
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 54.54545454545455,
|
792 |
+
"grad_norm": 0.08747697621583939,
|
793 |
+
"learning_rate": 0.0001,
|
794 |
+
"loss": 0.4526,
|
795 |
+
"step": 6000
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 55.0,
|
799 |
+
"eval_explained_variance": 0.4658801555633545,
|
800 |
+
"eval_kl_divergence": 0.40089842677116394,
|
801 |
+
"eval_loss": 0.4644174873828888,
|
802 |
+
"eval_mae": 0.11586496233940125,
|
803 |
+
"eval_rmse": 0.156887486577034,
|
804 |
+
"eval_runtime": 54.8967,
|
805 |
+
"eval_samples_per_second": 42.881,
|
806 |
+
"eval_steps_per_second": 0.674,
|
807 |
+
"learning_rate": 0.0001,
|
808 |
+
"step": 6050
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 56.0,
|
812 |
+
"eval_explained_variance": 0.46597158908843994,
|
813 |
+
"eval_kl_divergence": 0.34050217270851135,
|
814 |
+
"eval_loss": 0.464743047952652,
|
815 |
+
"eval_mae": 0.11636239290237427,
|
816 |
+
"eval_rmse": 0.15719135105609894,
|
817 |
+
"eval_runtime": 53.8695,
|
818 |
+
"eval_samples_per_second": 43.698,
|
819 |
+
"eval_steps_per_second": 0.687,
|
820 |
+
"learning_rate": 0.0001,
|
821 |
+
"step": 6160
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 57.0,
|
825 |
+
"eval_explained_variance": 0.4660731554031372,
|
826 |
+
"eval_kl_divergence": 0.4187561571598053,
|
827 |
+
"eval_loss": 0.4645179808139801,
|
828 |
+
"eval_mae": 0.11523237824440002,
|
829 |
+
"eval_rmse": 0.1568503975868225,
|
830 |
+
"eval_runtime": 52.6832,
|
831 |
+
"eval_samples_per_second": 44.682,
|
832 |
+
"eval_steps_per_second": 0.702,
|
833 |
+
"learning_rate": 0.0001,
|
834 |
+
"step": 6270
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 58.0,
|
838 |
+
"eval_explained_variance": 0.4659406840801239,
|
839 |
+
"eval_kl_divergence": 0.3079023063182831,
|
840 |
+
"eval_loss": 0.465102881193161,
|
841 |
+
"eval_mae": 0.11637380719184875,
|
842 |
+
"eval_rmse": 0.15757356584072113,
|
843 |
+
"eval_runtime": 53.7708,
|
844 |
+
"eval_samples_per_second": 43.778,
|
845 |
+
"eval_steps_per_second": 0.688,
|
846 |
+
"learning_rate": 0.0001,
|
847 |
+
"step": 6380
|
848 |
+
},
|
849 |
+
{
|
850 |
+
"epoch": 59.0,
|
851 |
+
"eval_explained_variance": 0.46542713046073914,
|
852 |
+
"eval_kl_divergence": 0.43387478590011597,
|
853 |
+
"eval_loss": 0.4644688367843628,
|
854 |
+
"eval_mae": 0.11504218727350235,
|
855 |
+
"eval_rmse": 0.15699030458927155,
|
856 |
+
"eval_runtime": 54.251,
|
857 |
+
"eval_samples_per_second": 43.391,
|
858 |
+
"eval_steps_per_second": 0.682,
|
859 |
+
"learning_rate": 1e-05,
|
860 |
+
"step": 6490
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 59.09090909090909,
|
864 |
+
"grad_norm": 0.09869211912155151,
|
865 |
+
"learning_rate": 1e-05,
|
866 |
+
"loss": 0.4514,
|
867 |
+
"step": 6500
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 60.0,
|
871 |
+
"eval_explained_variance": 0.4679425060749054,
|
872 |
+
"eval_kl_divergence": 0.38936442136764526,
|
873 |
+
"eval_loss": 0.46417686343193054,
|
874 |
+
"eval_mae": 0.11504556983709335,
|
875 |
+
"eval_rmse": 0.1565857082605362,
|
876 |
+
"eval_runtime": 53.3994,
|
877 |
+
"eval_samples_per_second": 44.083,
|
878 |
+
"eval_steps_per_second": 0.693,
|
879 |
+
"learning_rate": 1e-05,
|
880 |
+
"step": 6600
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 61.0,
|
884 |
+
"eval_explained_variance": 0.4692780673503876,
|
885 |
+
"eval_kl_divergence": 0.4144607186317444,
|
886 |
+
"eval_loss": 0.4639436900615692,
|
887 |
+
"eval_mae": 0.11456633359193802,
|
888 |
+
"eval_rmse": 0.15632741153240204,
|
889 |
+
"eval_runtime": 53.948,
|
890 |
+
"eval_samples_per_second": 43.635,
|
891 |
+
"eval_steps_per_second": 0.686,
|
892 |
+
"learning_rate": 1e-05,
|
893 |
+
"step": 6710
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 62.0,
|
897 |
+
"eval_explained_variance": 0.46859118342399597,
|
898 |
+
"eval_kl_divergence": 0.4063835144042969,
|
899 |
+
"eval_loss": 0.4641311764717102,
|
900 |
+
"eval_mae": 0.11482342332601547,
|
901 |
+
"eval_rmse": 0.15648160874843597,
|
902 |
+
"eval_runtime": 53.1646,
|
903 |
+
"eval_samples_per_second": 44.278,
|
904 |
+
"eval_steps_per_second": 0.696,
|
905 |
+
"learning_rate": 1e-05,
|
906 |
+
"step": 6820
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 63.0,
|
910 |
+
"eval_explained_variance": 0.4698045253753662,
|
911 |
+
"eval_kl_divergence": 0.35424694418907166,
|
912 |
+
"eval_loss": 0.4643491506576538,
|
913 |
+
"eval_mae": 0.11492928117513657,
|
914 |
+
"eval_rmse": 0.15652996301651,
|
915 |
+
"eval_runtime": 61.9895,
|
916 |
+
"eval_samples_per_second": 37.974,
|
917 |
+
"eval_steps_per_second": 0.597,
|
918 |
+
"learning_rate": 1e-05,
|
919 |
+
"step": 6930
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 63.63636363636363,
|
923 |
+
"grad_norm": 0.12132851779460907,
|
924 |
+
"learning_rate": 1e-05,
|
925 |
+
"loss": 0.4511,
|
926 |
+
"step": 7000
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 64.0,
|
930 |
+
"eval_explained_variance": 0.4702436923980713,
|
931 |
+
"eval_kl_divergence": 0.37175947427749634,
|
932 |
+
"eval_loss": 0.46402981877326965,
|
933 |
+
"eval_mae": 0.11502394080162048,
|
934 |
+
"eval_rmse": 0.1563546359539032,
|
935 |
+
"eval_runtime": 55.6273,
|
936 |
+
"eval_samples_per_second": 42.317,
|
937 |
+
"eval_steps_per_second": 0.665,
|
938 |
+
"learning_rate": 1e-05,
|
939 |
+
"step": 7040
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 65.0,
|
943 |
+
"eval_explained_variance": 0.46799585223197937,
|
944 |
+
"eval_kl_divergence": 0.41278746724128723,
|
945 |
+
"eval_loss": 0.4640822410583496,
|
946 |
+
"eval_mae": 0.11517596989870071,
|
947 |
+
"eval_rmse": 0.1565382480621338,
|
948 |
+
"eval_runtime": 60.037,
|
949 |
+
"eval_samples_per_second": 39.209,
|
950 |
+
"eval_steps_per_second": 0.616,
|
951 |
+
"learning_rate": 1e-05,
|
952 |
+
"step": 7150
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 66.0,
|
956 |
+
"eval_explained_variance": 0.46580052375793457,
|
957 |
+
"eval_kl_divergence": 0.4987623989582062,
|
958 |
+
"eval_loss": 0.46441909670829773,
|
959 |
+
"eval_mae": 0.11446693539619446,
|
960 |
+
"eval_rmse": 0.15703582763671875,
|
961 |
+
"eval_runtime": 58.422,
|
962 |
+
"eval_samples_per_second": 40.293,
|
963 |
+
"eval_steps_per_second": 0.633,
|
964 |
+
"learning_rate": 1e-05,
|
965 |
+
"step": 7260
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 67.0,
|
969 |
+
"eval_explained_variance": 0.4696963131427765,
|
970 |
+
"eval_kl_divergence": 0.41221925616264343,
|
971 |
+
"eval_loss": 0.46383005380630493,
|
972 |
+
"eval_mae": 0.11511614173650742,
|
973 |
+
"eval_rmse": 0.15620578825473785,
|
974 |
+
"eval_runtime": 57.3857,
|
975 |
+
"eval_samples_per_second": 41.021,
|
976 |
+
"eval_steps_per_second": 0.645,
|
977 |
+
"learning_rate": 1e-05,
|
978 |
+
"step": 7370
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 68.0,
|
982 |
+
"eval_explained_variance": 0.4673812687397003,
|
983 |
+
"eval_kl_divergence": 0.4579189419746399,
|
984 |
+
"eval_loss": 0.4639807641506195,
|
985 |
+
"eval_mae": 0.11436697095632553,
|
986 |
+
"eval_rmse": 0.15645776689052582,
|
987 |
+
"eval_runtime": 58.7335,
|
988 |
+
"eval_samples_per_second": 40.079,
|
989 |
+
"eval_steps_per_second": 0.63,
|
990 |
+
"learning_rate": 1e-05,
|
991 |
+
"step": 7480
|
992 |
+
},
|
993 |
+
{
|
994 |
+
"epoch": 68.18181818181819,
|
995 |
+
"grad_norm": 0.15623362362384796,
|
996 |
+
"learning_rate": 1e-05,
|
997 |
+
"loss": 0.4508,
|
998 |
+
"step": 7500
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 69.0,
|
1002 |
+
"eval_explained_variance": 0.4701990783214569,
|
1003 |
+
"eval_kl_divergence": 0.4197009801864624,
|
1004 |
+
"eval_loss": 0.4637599587440491,
|
1005 |
+
"eval_mae": 0.11433341354131699,
|
1006 |
+
"eval_rmse": 0.15607893466949463,
|
1007 |
+
"eval_runtime": 56.4381,
|
1008 |
+
"eval_samples_per_second": 41.709,
|
1009 |
+
"eval_steps_per_second": 0.656,
|
1010 |
+
"learning_rate": 1e-05,
|
1011 |
+
"step": 7590
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 70.0,
|
1015 |
+
"eval_explained_variance": 0.46952661871910095,
|
1016 |
+
"eval_kl_divergence": 0.4285525679588318,
|
1017 |
+
"eval_loss": 0.46392253041267395,
|
1018 |
+
"eval_mae": 0.11449825018644333,
|
1019 |
+
"eval_rmse": 0.15625734627246857,
|
1020 |
+
"eval_runtime": 59.9257,
|
1021 |
+
"eval_samples_per_second": 39.282,
|
1022 |
+
"eval_steps_per_second": 0.617,
|
1023 |
+
"learning_rate": 1e-05,
|
1024 |
+
"step": 7700
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 71.0,
|
1028 |
+
"eval_explained_variance": 0.4707754850387573,
|
1029 |
+
"eval_kl_divergence": 0.3542197048664093,
|
1030 |
+
"eval_loss": 0.46406444907188416,
|
1031 |
+
"eval_mae": 0.11525753885507584,
|
1032 |
+
"eval_rmse": 0.1563321352005005,
|
1033 |
+
"eval_runtime": 56.6326,
|
1034 |
+
"eval_samples_per_second": 41.566,
|
1035 |
+
"eval_steps_per_second": 0.653,
|
1036 |
+
"learning_rate": 1e-05,
|
1037 |
+
"step": 7810
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 72.0,
|
1041 |
+
"eval_explained_variance": 0.4681284427642822,
|
1042 |
+
"eval_kl_divergence": 0.42497748136520386,
|
1043 |
+
"eval_loss": 0.46417826414108276,
|
1044 |
+
"eval_mae": 0.11474020034074783,
|
1045 |
+
"eval_rmse": 0.15662290155887604,
|
1046 |
+
"eval_runtime": 56.0497,
|
1047 |
+
"eval_samples_per_second": 41.998,
|
1048 |
+
"eval_steps_per_second": 0.66,
|
1049 |
+
"learning_rate": 1e-05,
|
1050 |
+
"step": 7920
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 72.72727272727273,
|
1054 |
+
"grad_norm": 0.12685681879520416,
|
1055 |
+
"learning_rate": 1e-05,
|
1056 |
+
"loss": 0.4505,
|
1057 |
+
"step": 8000
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 73.0,
|
1061 |
+
"eval_explained_variance": 0.47002461552619934,
|
1062 |
+
"eval_kl_divergence": 0.43972158432006836,
|
1063 |
+
"eval_loss": 0.4637835919857025,
|
1064 |
+
"eval_mae": 0.11403892189264297,
|
1065 |
+
"eval_rmse": 0.15611138939857483,
|
1066 |
+
"eval_runtime": 55.8354,
|
1067 |
+
"eval_samples_per_second": 42.16,
|
1068 |
+
"eval_steps_per_second": 0.663,
|
1069 |
+
"learning_rate": 1e-05,
|
1070 |
+
"step": 8030
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 74.0,
|
1074 |
+
"eval_explained_variance": 0.4689449369907379,
|
1075 |
+
"eval_kl_divergence": 0.443666011095047,
|
1076 |
+
"eval_loss": 0.463798850774765,
|
1077 |
+
"eval_mae": 0.1145407184958458,
|
1078 |
+
"eval_rmse": 0.15625973045825958,
|
1079 |
+
"eval_runtime": 56.7357,
|
1080 |
+
"eval_samples_per_second": 41.491,
|
1081 |
+
"eval_steps_per_second": 0.652,
|
1082 |
+
"learning_rate": 1e-05,
|
1083 |
+
"step": 8140
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 75.0,
|
1087 |
+
"eval_explained_variance": 0.4704826772212982,
|
1088 |
+
"eval_kl_divergence": 0.4049000144004822,
|
1089 |
+
"eval_loss": 0.46379053592681885,
|
1090 |
+
"eval_mae": 0.11447467654943466,
|
1091 |
+
"eval_rmse": 0.15613143146038055,
|
1092 |
+
"eval_runtime": 56.7932,
|
1093 |
+
"eval_samples_per_second": 41.449,
|
1094 |
+
"eval_steps_per_second": 0.651,
|
1095 |
+
"learning_rate": 1e-05,
|
1096 |
+
"step": 8250
|
1097 |
+
},
|
1098 |
+
{
|
1099 |
+
"epoch": 76.0,
|
1100 |
+
"eval_explained_variance": 0.4674541652202606,
|
1101 |
+
"eval_kl_divergence": 0.49260592460632324,
|
1102 |
+
"eval_loss": 0.4639701247215271,
|
1103 |
+
"eval_mae": 0.11414843797683716,
|
1104 |
+
"eval_rmse": 0.15647520124912262,
|
1105 |
+
"eval_runtime": 57.4638,
|
1106 |
+
"eval_samples_per_second": 40.965,
|
1107 |
+
"eval_steps_per_second": 0.644,
|
1108 |
+
"learning_rate": 1.0000000000000002e-06,
|
1109 |
+
"step": 8360
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 77.0,
|
1113 |
+
"eval_explained_variance": 0.469455748796463,
|
1114 |
+
"eval_kl_divergence": 0.44272491335868835,
|
1115 |
+
"eval_loss": 0.463869571685791,
|
1116 |
+
"eval_mae": 0.11419638991355896,
|
1117 |
+
"eval_rmse": 0.15622590482234955,
|
1118 |
+
"eval_runtime": 57.5968,
|
1119 |
+
"eval_samples_per_second": 40.87,
|
1120 |
+
"eval_steps_per_second": 0.642,
|
1121 |
+
"learning_rate": 1.0000000000000002e-06,
|
1122 |
+
"step": 8470
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 77.27272727272727,
|
1126 |
+
"grad_norm": 0.11736844480037689,
|
1127 |
+
"learning_rate": 1.0000000000000002e-06,
|
1128 |
+
"loss": 0.4505,
|
1129 |
+
"step": 8500
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 78.0,
|
1133 |
+
"eval_explained_variance": 0.4691663682460785,
|
1134 |
+
"eval_kl_divergence": 0.42925453186035156,
|
1135 |
+
"eval_loss": 0.46388140320777893,
|
1136 |
+
"eval_mae": 0.1144518032670021,
|
1137 |
+
"eval_rmse": 0.1562517285346985,
|
1138 |
+
"eval_runtime": 55.8876,
|
1139 |
+
"eval_samples_per_second": 42.12,
|
1140 |
+
"eval_steps_per_second": 0.662,
|
1141 |
+
"learning_rate": 1.0000000000000002e-06,
|
1142 |
+
"step": 8580
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 79.0,
|
1146 |
+
"eval_explained_variance": 0.4699589014053345,
|
1147 |
+
"eval_kl_divergence": 0.376490980386734,
|
1148 |
+
"eval_loss": 0.46412238478660583,
|
1149 |
+
"eval_mae": 0.11472050100564957,
|
1150 |
+
"eval_rmse": 0.15639875829219818,
|
1151 |
+
"eval_runtime": 55.4743,
|
1152 |
+
"eval_samples_per_second": 42.434,
|
1153 |
+
"eval_steps_per_second": 0.667,
|
1154 |
+
"learning_rate": 1.0000000000000002e-06,
|
1155 |
+
"step": 8690
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 79.0,
|
1159 |
+
"learning_rate": 1.0000000000000002e-06,
|
1160 |
+
"step": 8690,
|
1161 |
+
"total_flos": 8.188406191467658e+19,
|
1162 |
+
"train_loss": 0.4591466036709872,
|
1163 |
+
"train_runtime": 19731.8487,
|
1164 |
+
"train_samples_per_second": 53.236,
|
1165 |
+
"train_steps_per_second": 0.836
|
1166 |
+
}
|
1167 |
+
],
|
1168 |
+
"logging_steps": 500,
|
1169 |
+
"max_steps": 16500,
|
1170 |
+
"num_input_tokens_seen": 0,
|
1171 |
+
"num_train_epochs": 150,
|
1172 |
+
"save_steps": 500,
|
1173 |
+
"stateful_callbacks": {
|
1174 |
+
"EarlyStoppingCallback": {
|
1175 |
+
"args": {
|
1176 |
+
"early_stopping_patience": 10,
|
1177 |
+
"early_stopping_threshold": 0.0
|
1178 |
+
},
|
1179 |
+
"attributes": {
|
1180 |
+
"early_stopping_patience_counter": 0
|
1181 |
+
}
|
1182 |
+
},
|
1183 |
+
"TrainerControl": {
|
1184 |
+
"args": {
|
1185 |
+
"should_epoch_stop": false,
|
1186 |
+
"should_evaluate": false,
|
1187 |
+
"should_log": false,
|
1188 |
+
"should_save": true,
|
1189 |
+
"should_training_stop": true
|
1190 |
+
},
|
1191 |
+
"attributes": {}
|
1192 |
+
}
|
1193 |
+
},
|
1194 |
+
"total_flos": 8.188406191467658e+19,
|
1195 |
+
"train_batch_size": 64,
|
1196 |
+
"trial_name": null,
|
1197 |
+
"trial_params": null
|
1198 |
+
}
|