Evaluation on the test set completed on 2025_02_03.
Browse files- README.md +97 -1
- all_results.json +17 -0
- logs/events.out.tfevents.1738569064.datavisu4 +2 -2
- logs/events.out.tfevents.1738573356.datavisu4 +3 -0
- model.safetensors +1 -1
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +568 -0
README.md
CHANGED
|
@@ -1,4 +1,100 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
tags:
|
| 3 |
-
-
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: facebook/dinov2-large
|
| 5 |
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: DinoVdrone-large-2025_02_03_31850-bs32_freeze_probs
|
| 9 |
+
results: []
|
| 10 |
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# DinoVdrone-large-2025_02_03_31850-bs32_freeze_probs
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/dinov2-large](https://huggingface.co/facebook/dinov2-large) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.4512
|
| 20 |
+
- Rmse: 0.1689
|
| 21 |
+
- Mae: 0.1261
|
| 22 |
+
- Kl Divergence: 0.5558
|
| 23 |
+
- Explained Variance: 0.3655
|
| 24 |
+
- Learning Rate: 1e-05
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.001
|
| 44 |
+
- train_batch_size: 32
|
| 45 |
+
- eval_batch_size: 32
|
| 46 |
+
- seed: 42
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 150
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rmse | Mae | Kl Divergence | Explained Variance | Rate |
|
| 55 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:-------------:|:------------------:|:------:|
|
| 56 |
+
| No log | 1.0 | 76 | 0.5544 | 0.2605 | 0.2278 | 1.7912 | 0.0699 | 0.001 |
|
| 57 |
+
| No log | 2.0 | 152 | 0.4817 | 0.2007 | 0.1602 | 1.0345 | 0.0726 | 0.001 |
|
| 58 |
+
| No log | 3.0 | 228 | 0.4615 | 0.1801 | 0.1370 | 0.6064 | 0.2707 | 0.001 |
|
| 59 |
+
| No log | 4.0 | 304 | 0.4632 | 0.1837 | 0.1391 | 0.6577 | 0.0892 | 0.001 |
|
| 60 |
+
| No log | 5.0 | 380 | 0.4579 | 0.1769 | 0.1363 | 0.6678 | 0.2999 | 0.001 |
|
| 61 |
+
| No log | 6.0 | 456 | 0.4571 | 0.1766 | 0.1330 | 0.7896 | 0.3050 | 0.001 |
|
| 62 |
+
| 0.4966 | 7.0 | 532 | 0.4586 | 0.1773 | 0.1307 | 0.6493 | 0.3103 | 0.001 |
|
| 63 |
+
| 0.4966 | 8.0 | 608 | 0.4579 | 0.1772 | 0.1319 | 0.9475 | 0.3085 | 0.001 |
|
| 64 |
+
| 0.4966 | 9.0 | 684 | 0.4551 | 0.1746 | 0.1306 | 0.7271 | 0.3136 | 0.001 |
|
| 65 |
+
| 0.4966 | 10.0 | 760 | 0.4582 | 0.1774 | 0.1316 | 0.6882 | 0.2918 | 0.001 |
|
| 66 |
+
| 0.4966 | 11.0 | 836 | 0.4683 | 0.1842 | 0.1372 | 0.3715 | 0.2586 | 0.001 |
|
| 67 |
+
| 0.4966 | 12.0 | 912 | 0.4579 | 0.1764 | 0.1316 | 0.5271 | 0.3086 | 0.001 |
|
| 68 |
+
| 0.4966 | 13.0 | 988 | 0.4559 | 0.1756 | 0.1301 | 0.9168 | 0.3100 | 0.001 |
|
| 69 |
+
| 0.4448 | 14.0 | 1064 | 0.4556 | 0.1749 | 0.1292 | 0.8827 | 0.3229 | 0.001 |
|
| 70 |
+
| 0.4448 | 15.0 | 1140 | 0.4522 | 0.1717 | 0.1262 | 0.7009 | 0.3416 | 0.001 |
|
| 71 |
+
| 0.4448 | 16.0 | 1216 | 0.4556 | 0.1753 | 0.1286 | 1.0038 | 0.3163 | 0.001 |
|
| 72 |
+
| 0.4448 | 17.0 | 1292 | 0.4586 | 0.1775 | 0.1343 | 0.2600 | 0.3205 | 0.001 |
|
| 73 |
+
| 0.4448 | 18.0 | 1368 | 0.5672 | 0.2369 | 0.1638 | 2.0548 | -4.7788 | 0.001 |
|
| 74 |
+
| 0.4448 | 19.0 | 1444 | 0.4529 | 0.1727 | 0.1287 | 0.7115 | 0.3279 | 0.001 |
|
| 75 |
+
| 0.4406 | 20.0 | 1520 | 0.4552 | 0.1746 | 0.1285 | 0.9694 | 0.3204 | 0.001 |
|
| 76 |
+
| 0.4406 | 21.0 | 1596 | 0.4530 | 0.1724 | 0.1282 | 0.7789 | 0.3300 | 0.001 |
|
| 77 |
+
| 0.4406 | 22.0 | 1672 | 0.4503 | 0.1700 | 0.1261 | 0.7369 | 0.3473 | 0.0001 |
|
| 78 |
+
| 0.4406 | 23.0 | 1748 | 0.4535 | 0.1716 | 0.1280 | 0.5027 | 0.3403 | 0.0001 |
|
| 79 |
+
| 0.4406 | 24.0 | 1824 | 0.4502 | 0.1697 | 0.1264 | 0.5968 | 0.3511 | 0.0001 |
|
| 80 |
+
| 0.4406 | 25.0 | 1900 | 0.4504 | 0.1699 | 0.1267 | 0.6215 | 0.3504 | 0.0001 |
|
| 81 |
+
| 0.4406 | 26.0 | 1976 | 0.4510 | 0.1704 | 0.1260 | 0.6568 | 0.3460 | 0.0001 |
|
| 82 |
+
| 0.4334 | 27.0 | 2052 | 0.4498 | 0.1693 | 0.1262 | 0.5748 | 0.3546 | 0.0001 |
|
| 83 |
+
| 0.4334 | 28.0 | 2128 | 0.4506 | 0.1701 | 0.1256 | 0.7001 | 0.3467 | 0.0001 |
|
| 84 |
+
| 0.4334 | 29.0 | 2204 | 0.4505 | 0.1699 | 0.1263 | 0.5840 | 0.3531 | 0.0001 |
|
| 85 |
+
| 0.4334 | 30.0 | 2280 | 0.4506 | 0.1703 | 0.1252 | 0.8101 | 0.3486 | 0.0001 |
|
| 86 |
+
| 0.4334 | 31.0 | 2356 | 0.4508 | 0.1701 | 0.1249 | 0.7416 | 0.3489 | 0.0001 |
|
| 87 |
+
| 0.4334 | 32.0 | 2432 | 0.4502 | 0.1697 | 0.1254 | 0.6402 | 0.3524 | 0.0001 |
|
| 88 |
+
| 0.4289 | 33.0 | 2508 | 0.4511 | 0.1710 | 0.1250 | 0.8411 | 0.3392 | 0.0001 |
|
| 89 |
+
| 0.4289 | 34.0 | 2584 | 0.4515 | 0.1711 | 0.1259 | 0.7204 | 0.3383 | 1e-05 |
|
| 90 |
+
| 0.4289 | 35.0 | 2660 | 0.4502 | 0.1698 | 0.1247 | 0.7355 | 0.3498 | 1e-05 |
|
| 91 |
+
| 0.4289 | 36.0 | 2736 | 0.4509 | 0.1703 | 0.1261 | 0.4990 | 0.3486 | 1e-05 |
|
| 92 |
+
| 0.4289 | 37.0 | 2812 | 0.4500 | 0.1696 | 0.1260 | 0.5451 | 0.3536 | 1e-05 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.48.0
|
| 98 |
+
- Pytorch 2.5.1+cu124
|
| 99 |
+
- Datasets 3.0.2
|
| 100 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.0,
|
| 3 |
+
"eval_explained_variance": 0.3655208349227905,
|
| 4 |
+
"eval_kl_divergence": 0.5558046698570251,
|
| 5 |
+
"eval_loss": 0.451246976852417,
|
| 6 |
+
"eval_mae": 0.12609094381332397,
|
| 7 |
+
"eval_rmse": 0.1689337193965912,
|
| 8 |
+
"eval_runtime": 33.8846,
|
| 9 |
+
"eval_samples_per_second": 23.669,
|
| 10 |
+
"eval_steps_per_second": 0.767,
|
| 11 |
+
"learning_rate": 1e-05,
|
| 12 |
+
"total_flos": 1.318896404308369e+20,
|
| 13 |
+
"train_loss": 0.4464974437295797,
|
| 14 |
+
"train_runtime": 4164.1679,
|
| 15 |
+
"train_samples_per_second": 86.596,
|
| 16 |
+
"train_steps_per_second": 2.738
|
| 17 |
+
}
|
logs/events.out.tfevents.1738569064.datavisu4
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:e35403578608b95100241e4a10fca05474c8b45953e6c056aa6aa497d12c9d73
|
| 3 |
+
size 28123
|
logs/events.out.tfevents.1738573356.datavisu4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:760aeafae17ddec88dc492d7630cf29b3783355af6c6fc4b56d18fb05e395fb8
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1228076728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71bbb7679db9b4309c6556dbad7dddb03732bcacba355dedc979d8d082cda9bd
|
| 3 |
size 1228076728
|
test_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.0,
|
| 3 |
+
"eval_explained_variance": 0.3655208349227905,
|
| 4 |
+
"eval_kl_divergence": 0.5558046698570251,
|
| 5 |
+
"eval_loss": 0.451246976852417,
|
| 6 |
+
"eval_mae": 0.12609094381332397,
|
| 7 |
+
"eval_rmse": 0.1689337193965912,
|
| 8 |
+
"eval_runtime": 33.8846,
|
| 9 |
+
"eval_samples_per_second": 23.669,
|
| 10 |
+
"eval_steps_per_second": 0.767,
|
| 11 |
+
"learning_rate": 1e-05
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.0,
|
| 3 |
+
"learning_rate": 1e-05,
|
| 4 |
+
"total_flos": 1.318896404308369e+20,
|
| 5 |
+
"train_loss": 0.4464974437295797,
|
| 6 |
+
"train_runtime": 4164.1679,
|
| 7 |
+
"train_samples_per_second": 86.596,
|
| 8 |
+
"train_steps_per_second": 2.738
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,568 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4497845768928528,
|
| 3 |
+
"best_model_checkpoint": "/home1/datahome/villien/project_hub/DinoVdeau/models/DinoVdrone-large-2025_02_03_31850-bs32_freeze_probs/checkpoint-2052",
|
| 4 |
+
"epoch": 37.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2812,
|
| 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": 0.0698663592338562,
|
| 14 |
+
"eval_kl_divergence": 1.791170597076416,
|
| 15 |
+
"eval_loss": 0.5543646216392517,
|
| 16 |
+
"eval_mae": 0.22781437635421753,
|
| 17 |
+
"eval_rmse": 0.26052138209342957,
|
| 18 |
+
"eval_runtime": 36.0517,
|
| 19 |
+
"eval_samples_per_second": 22.218,
|
| 20 |
+
"eval_steps_per_second": 0.721,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"step": 76
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 2.0,
|
| 26 |
+
"eval_explained_variance": 0.07257537543773651,
|
| 27 |
+
"eval_kl_divergence": 1.0344740152359009,
|
| 28 |
+
"eval_loss": 0.48171326518058777,
|
| 29 |
+
"eval_mae": 0.16019925475120544,
|
| 30 |
+
"eval_rmse": 0.20066045224666595,
|
| 31 |
+
"eval_runtime": 32.1858,
|
| 32 |
+
"eval_samples_per_second": 24.887,
|
| 33 |
+
"eval_steps_per_second": 0.808,
|
| 34 |
+
"learning_rate": 0.001,
|
| 35 |
+
"step": 152
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 3.0,
|
| 39 |
+
"eval_explained_variance": 0.27069091796875,
|
| 40 |
+
"eval_kl_divergence": 0.6063743233680725,
|
| 41 |
+
"eval_loss": 0.4615386724472046,
|
| 42 |
+
"eval_mae": 0.1370290368795395,
|
| 43 |
+
"eval_rmse": 0.18013149499893188,
|
| 44 |
+
"eval_runtime": 22.3828,
|
| 45 |
+
"eval_samples_per_second": 35.786,
|
| 46 |
+
"eval_steps_per_second": 1.162,
|
| 47 |
+
"learning_rate": 0.001,
|
| 48 |
+
"step": 228
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_explained_variance": 0.08923790603876114,
|
| 53 |
+
"eval_kl_divergence": 0.6576936841011047,
|
| 54 |
+
"eval_loss": 0.4632064700126648,
|
| 55 |
+
"eval_mae": 0.1390942633152008,
|
| 56 |
+
"eval_rmse": 0.18370357155799866,
|
| 57 |
+
"eval_runtime": 22.4997,
|
| 58 |
+
"eval_samples_per_second": 35.601,
|
| 59 |
+
"eval_steps_per_second": 1.156,
|
| 60 |
+
"learning_rate": 0.001,
|
| 61 |
+
"step": 304
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 5.0,
|
| 65 |
+
"eval_explained_variance": 0.2999000549316406,
|
| 66 |
+
"eval_kl_divergence": 0.6677561402320862,
|
| 67 |
+
"eval_loss": 0.4579373300075531,
|
| 68 |
+
"eval_mae": 0.13632091879844666,
|
| 69 |
+
"eval_rmse": 0.17685972154140472,
|
| 70 |
+
"eval_runtime": 22.4993,
|
| 71 |
+
"eval_samples_per_second": 35.601,
|
| 72 |
+
"eval_steps_per_second": 1.156,
|
| 73 |
+
"learning_rate": 0.001,
|
| 74 |
+
"step": 380
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 6.0,
|
| 78 |
+
"eval_explained_variance": 0.30495360493659973,
|
| 79 |
+
"eval_kl_divergence": 0.7895806431770325,
|
| 80 |
+
"eval_loss": 0.4571229815483093,
|
| 81 |
+
"eval_mae": 0.13304883241653442,
|
| 82 |
+
"eval_rmse": 0.176561176776886,
|
| 83 |
+
"eval_runtime": 22.7,
|
| 84 |
+
"eval_samples_per_second": 35.286,
|
| 85 |
+
"eval_steps_per_second": 1.145,
|
| 86 |
+
"learning_rate": 0.001,
|
| 87 |
+
"step": 456
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.578947368421053,
|
| 91 |
+
"grad_norm": 0.27282145619392395,
|
| 92 |
+
"learning_rate": 0.001,
|
| 93 |
+
"loss": 0.4966,
|
| 94 |
+
"step": 500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 7.0,
|
| 98 |
+
"eval_explained_variance": 0.3103345036506653,
|
| 99 |
+
"eval_kl_divergence": 0.6492787599563599,
|
| 100 |
+
"eval_loss": 0.4586440622806549,
|
| 101 |
+
"eval_mae": 0.13074660301208496,
|
| 102 |
+
"eval_rmse": 0.17730861902236938,
|
| 103 |
+
"eval_runtime": 22.4946,
|
| 104 |
+
"eval_samples_per_second": 35.608,
|
| 105 |
+
"eval_steps_per_second": 1.156,
|
| 106 |
+
"learning_rate": 0.001,
|
| 107 |
+
"step": 532
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_explained_variance": 0.30848240852355957,
|
| 112 |
+
"eval_kl_divergence": 0.9475247263908386,
|
| 113 |
+
"eval_loss": 0.45786425471305847,
|
| 114 |
+
"eval_mae": 0.13187319040298462,
|
| 115 |
+
"eval_rmse": 0.17719128727912903,
|
| 116 |
+
"eval_runtime": 22.513,
|
| 117 |
+
"eval_samples_per_second": 35.579,
|
| 118 |
+
"eval_steps_per_second": 1.155,
|
| 119 |
+
"learning_rate": 0.001,
|
| 120 |
+
"step": 608
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.0,
|
| 124 |
+
"eval_explained_variance": 0.3135569095611572,
|
| 125 |
+
"eval_kl_divergence": 0.7270792126655579,
|
| 126 |
+
"eval_loss": 0.4551210105419159,
|
| 127 |
+
"eval_mae": 0.13063107430934906,
|
| 128 |
+
"eval_rmse": 0.17461702227592468,
|
| 129 |
+
"eval_runtime": 22.4949,
|
| 130 |
+
"eval_samples_per_second": 35.608,
|
| 131 |
+
"eval_steps_per_second": 1.156,
|
| 132 |
+
"learning_rate": 0.001,
|
| 133 |
+
"step": 684
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 10.0,
|
| 137 |
+
"eval_explained_variance": 0.29183268547058105,
|
| 138 |
+
"eval_kl_divergence": 0.6882225275039673,
|
| 139 |
+
"eval_loss": 0.45817646384239197,
|
| 140 |
+
"eval_mae": 0.13160471618175507,
|
| 141 |
+
"eval_rmse": 0.17741131782531738,
|
| 142 |
+
"eval_runtime": 22.508,
|
| 143 |
+
"eval_samples_per_second": 35.587,
|
| 144 |
+
"eval_steps_per_second": 1.155,
|
| 145 |
+
"learning_rate": 0.001,
|
| 146 |
+
"step": 760
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 11.0,
|
| 150 |
+
"eval_explained_variance": 0.25859755277633667,
|
| 151 |
+
"eval_kl_divergence": 0.371459424495697,
|
| 152 |
+
"eval_loss": 0.46834859251976013,
|
| 153 |
+
"eval_mae": 0.13717466592788696,
|
| 154 |
+
"eval_rmse": 0.18415462970733643,
|
| 155 |
+
"eval_runtime": 22.4535,
|
| 156 |
+
"eval_samples_per_second": 35.674,
|
| 157 |
+
"eval_steps_per_second": 1.158,
|
| 158 |
+
"learning_rate": 0.001,
|
| 159 |
+
"step": 836
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.0,
|
| 163 |
+
"eval_explained_variance": 0.308597594499588,
|
| 164 |
+
"eval_kl_divergence": 0.5270651578903198,
|
| 165 |
+
"eval_loss": 0.4578668475151062,
|
| 166 |
+
"eval_mae": 0.13155478239059448,
|
| 167 |
+
"eval_rmse": 0.17636829614639282,
|
| 168 |
+
"eval_runtime": 22.5868,
|
| 169 |
+
"eval_samples_per_second": 35.463,
|
| 170 |
+
"eval_steps_per_second": 1.151,
|
| 171 |
+
"learning_rate": 0.001,
|
| 172 |
+
"step": 912
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 13.0,
|
| 176 |
+
"eval_explained_variance": 0.3100161552429199,
|
| 177 |
+
"eval_kl_divergence": 0.9167731404304504,
|
| 178 |
+
"eval_loss": 0.4558842182159424,
|
| 179 |
+
"eval_mae": 0.1300584226846695,
|
| 180 |
+
"eval_rmse": 0.1756095588207245,
|
| 181 |
+
"eval_runtime": 22.7991,
|
| 182 |
+
"eval_samples_per_second": 35.133,
|
| 183 |
+
"eval_steps_per_second": 1.14,
|
| 184 |
+
"learning_rate": 0.001,
|
| 185 |
+
"step": 988
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 13.157894736842104,
|
| 189 |
+
"grad_norm": 0.26468560099601746,
|
| 190 |
+
"learning_rate": 0.001,
|
| 191 |
+
"loss": 0.4448,
|
| 192 |
+
"step": 1000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 14.0,
|
| 196 |
+
"eval_explained_variance": 0.3228832185268402,
|
| 197 |
+
"eval_kl_divergence": 0.8826888799667358,
|
| 198 |
+
"eval_loss": 0.4555540680885315,
|
| 199 |
+
"eval_mae": 0.12918463349342346,
|
| 200 |
+
"eval_rmse": 0.17491525411605835,
|
| 201 |
+
"eval_runtime": 22.7093,
|
| 202 |
+
"eval_samples_per_second": 35.272,
|
| 203 |
+
"eval_steps_per_second": 1.145,
|
| 204 |
+
"learning_rate": 0.001,
|
| 205 |
+
"step": 1064
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 15.0,
|
| 209 |
+
"eval_explained_variance": 0.34160685539245605,
|
| 210 |
+
"eval_kl_divergence": 0.7008672952651978,
|
| 211 |
+
"eval_loss": 0.45217740535736084,
|
| 212 |
+
"eval_mae": 0.1262015700340271,
|
| 213 |
+
"eval_rmse": 0.17165420949459076,
|
| 214 |
+
"eval_runtime": 22.6104,
|
| 215 |
+
"eval_samples_per_second": 35.426,
|
| 216 |
+
"eval_steps_per_second": 1.15,
|
| 217 |
+
"learning_rate": 0.001,
|
| 218 |
+
"step": 1140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 16.0,
|
| 222 |
+
"eval_explained_variance": 0.31633102893829346,
|
| 223 |
+
"eval_kl_divergence": 1.0038130283355713,
|
| 224 |
+
"eval_loss": 0.45556434988975525,
|
| 225 |
+
"eval_mae": 0.12863175570964813,
|
| 226 |
+
"eval_rmse": 0.1752910166978836,
|
| 227 |
+
"eval_runtime": 22.5805,
|
| 228 |
+
"eval_samples_per_second": 35.473,
|
| 229 |
+
"eval_steps_per_second": 1.151,
|
| 230 |
+
"learning_rate": 0.001,
|
| 231 |
+
"step": 1216
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 17.0,
|
| 235 |
+
"eval_explained_variance": 0.3205307126045227,
|
| 236 |
+
"eval_kl_divergence": 0.2600082457065582,
|
| 237 |
+
"eval_loss": 0.458648681640625,
|
| 238 |
+
"eval_mae": 0.13426683843135834,
|
| 239 |
+
"eval_rmse": 0.17750133574008942,
|
| 240 |
+
"eval_runtime": 22.3997,
|
| 241 |
+
"eval_samples_per_second": 35.759,
|
| 242 |
+
"eval_steps_per_second": 1.161,
|
| 243 |
+
"learning_rate": 0.001,
|
| 244 |
+
"step": 1292
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 18.0,
|
| 248 |
+
"eval_explained_variance": -4.778772354125977,
|
| 249 |
+
"eval_kl_divergence": 2.054769277572632,
|
| 250 |
+
"eval_loss": 0.567169725894928,
|
| 251 |
+
"eval_mae": 0.16376179456710815,
|
| 252 |
+
"eval_rmse": 0.23688165843486786,
|
| 253 |
+
"eval_runtime": 22.2481,
|
| 254 |
+
"eval_samples_per_second": 36.003,
|
| 255 |
+
"eval_steps_per_second": 1.169,
|
| 256 |
+
"learning_rate": 0.001,
|
| 257 |
+
"step": 1368
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 19.0,
|
| 261 |
+
"eval_explained_variance": 0.32792216539382935,
|
| 262 |
+
"eval_kl_divergence": 0.7114961743354797,
|
| 263 |
+
"eval_loss": 0.45287612080574036,
|
| 264 |
+
"eval_mae": 0.12865176796913147,
|
| 265 |
+
"eval_rmse": 0.17274516820907593,
|
| 266 |
+
"eval_runtime": 22.3304,
|
| 267 |
+
"eval_samples_per_second": 35.87,
|
| 268 |
+
"eval_steps_per_second": 1.164,
|
| 269 |
+
"learning_rate": 0.001,
|
| 270 |
+
"step": 1444
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 19.736842105263158,
|
| 274 |
+
"grad_norm": 0.1475011706352234,
|
| 275 |
+
"learning_rate": 0.001,
|
| 276 |
+
"loss": 0.4406,
|
| 277 |
+
"step": 1500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 20.0,
|
| 281 |
+
"eval_explained_variance": 0.3204135596752167,
|
| 282 |
+
"eval_kl_divergence": 0.9694227576255798,
|
| 283 |
+
"eval_loss": 0.45518893003463745,
|
| 284 |
+
"eval_mae": 0.12852200865745544,
|
| 285 |
+
"eval_rmse": 0.17462262511253357,
|
| 286 |
+
"eval_runtime": 22.5552,
|
| 287 |
+
"eval_samples_per_second": 35.513,
|
| 288 |
+
"eval_steps_per_second": 1.153,
|
| 289 |
+
"learning_rate": 0.001,
|
| 290 |
+
"step": 1520
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 21.0,
|
| 294 |
+
"eval_explained_variance": 0.32996666431427,
|
| 295 |
+
"eval_kl_divergence": 0.778915524482727,
|
| 296 |
+
"eval_loss": 0.45299893617630005,
|
| 297 |
+
"eval_mae": 0.12820784747600555,
|
| 298 |
+
"eval_rmse": 0.17243456840515137,
|
| 299 |
+
"eval_runtime": 22.5861,
|
| 300 |
+
"eval_samples_per_second": 35.464,
|
| 301 |
+
"eval_steps_per_second": 1.151,
|
| 302 |
+
"learning_rate": 0.001,
|
| 303 |
+
"step": 1596
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 22.0,
|
| 307 |
+
"eval_explained_variance": 0.34726351499557495,
|
| 308 |
+
"eval_kl_divergence": 0.7368760704994202,
|
| 309 |
+
"eval_loss": 0.4502638280391693,
|
| 310 |
+
"eval_mae": 0.12613575160503387,
|
| 311 |
+
"eval_rmse": 0.17001575231552124,
|
| 312 |
+
"eval_runtime": 22.7271,
|
| 313 |
+
"eval_samples_per_second": 35.244,
|
| 314 |
+
"eval_steps_per_second": 1.144,
|
| 315 |
+
"learning_rate": 0.0001,
|
| 316 |
+
"step": 1672
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 23.0,
|
| 320 |
+
"eval_explained_variance": 0.34029728174209595,
|
| 321 |
+
"eval_kl_divergence": 0.5027008056640625,
|
| 322 |
+
"eval_loss": 0.453466534614563,
|
| 323 |
+
"eval_mae": 0.12802833318710327,
|
| 324 |
+
"eval_rmse": 0.17160943150520325,
|
| 325 |
+
"eval_runtime": 22.4563,
|
| 326 |
+
"eval_samples_per_second": 35.669,
|
| 327 |
+
"eval_steps_per_second": 1.158,
|
| 328 |
+
"learning_rate": 0.0001,
|
| 329 |
+
"step": 1748
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 24.0,
|
| 333 |
+
"eval_explained_variance": 0.3511368930339813,
|
| 334 |
+
"eval_kl_divergence": 0.5968054533004761,
|
| 335 |
+
"eval_loss": 0.4502425491809845,
|
| 336 |
+
"eval_mae": 0.12641073763370514,
|
| 337 |
+
"eval_rmse": 0.16971111297607422,
|
| 338 |
+
"eval_runtime": 22.592,
|
| 339 |
+
"eval_samples_per_second": 35.455,
|
| 340 |
+
"eval_steps_per_second": 1.151,
|
| 341 |
+
"learning_rate": 0.0001,
|
| 342 |
+
"step": 1824
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 25.0,
|
| 346 |
+
"eval_explained_variance": 0.3504308760166168,
|
| 347 |
+
"eval_kl_divergence": 0.621475100517273,
|
| 348 |
+
"eval_loss": 0.45040303468704224,
|
| 349 |
+
"eval_mae": 0.12673497200012207,
|
| 350 |
+
"eval_rmse": 0.1699284017086029,
|
| 351 |
+
"eval_runtime": 22.3202,
|
| 352 |
+
"eval_samples_per_second": 35.887,
|
| 353 |
+
"eval_steps_per_second": 1.165,
|
| 354 |
+
"learning_rate": 0.0001,
|
| 355 |
+
"step": 1900
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 26.0,
|
| 359 |
+
"eval_explained_variance": 0.34598857164382935,
|
| 360 |
+
"eval_kl_divergence": 0.6567814350128174,
|
| 361 |
+
"eval_loss": 0.4509589374065399,
|
| 362 |
+
"eval_mae": 0.12596669793128967,
|
| 363 |
+
"eval_rmse": 0.17043226957321167,
|
| 364 |
+
"eval_runtime": 22.4313,
|
| 365 |
+
"eval_samples_per_second": 35.709,
|
| 366 |
+
"eval_steps_per_second": 1.159,
|
| 367 |
+
"learning_rate": 0.0001,
|
| 368 |
+
"step": 1976
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 26.31578947368421,
|
| 372 |
+
"grad_norm": 0.16591614484786987,
|
| 373 |
+
"learning_rate": 0.0001,
|
| 374 |
+
"loss": 0.4334,
|
| 375 |
+
"step": 2000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 27.0,
|
| 379 |
+
"eval_explained_variance": 0.35463404655456543,
|
| 380 |
+
"eval_kl_divergence": 0.5748001337051392,
|
| 381 |
+
"eval_loss": 0.4497845768928528,
|
| 382 |
+
"eval_mae": 0.1262420266866684,
|
| 383 |
+
"eval_rmse": 0.1693224012851715,
|
| 384 |
+
"eval_runtime": 22.3409,
|
| 385 |
+
"eval_samples_per_second": 35.854,
|
| 386 |
+
"eval_steps_per_second": 1.164,
|
| 387 |
+
"learning_rate": 0.0001,
|
| 388 |
+
"step": 2052
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 28.0,
|
| 392 |
+
"eval_explained_variance": 0.34665071964263916,
|
| 393 |
+
"eval_kl_divergence": 0.7001035809516907,
|
| 394 |
+
"eval_loss": 0.45060041546821594,
|
| 395 |
+
"eval_mae": 0.12559720873832703,
|
| 396 |
+
"eval_rmse": 0.17011338472366333,
|
| 397 |
+
"eval_runtime": 22.4894,
|
| 398 |
+
"eval_samples_per_second": 35.617,
|
| 399 |
+
"eval_steps_per_second": 1.156,
|
| 400 |
+
"learning_rate": 0.0001,
|
| 401 |
+
"step": 2128
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 29.0,
|
| 405 |
+
"eval_explained_variance": 0.3531297743320465,
|
| 406 |
+
"eval_kl_divergence": 0.5840001702308655,
|
| 407 |
+
"eval_loss": 0.4504892826080322,
|
| 408 |
+
"eval_mae": 0.12626922130584717,
|
| 409 |
+
"eval_rmse": 0.16992022097110748,
|
| 410 |
+
"eval_runtime": 22.4286,
|
| 411 |
+
"eval_samples_per_second": 35.713,
|
| 412 |
+
"eval_steps_per_second": 1.159,
|
| 413 |
+
"learning_rate": 0.0001,
|
| 414 |
+
"step": 2204
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 30.0,
|
| 418 |
+
"eval_explained_variance": 0.34863966703414917,
|
| 419 |
+
"eval_kl_divergence": 0.8101097345352173,
|
| 420 |
+
"eval_loss": 0.45060065388679504,
|
| 421 |
+
"eval_mae": 0.12516793608665466,
|
| 422 |
+
"eval_rmse": 0.1702672839164734,
|
| 423 |
+
"eval_runtime": 22.3007,
|
| 424 |
+
"eval_samples_per_second": 35.918,
|
| 425 |
+
"eval_steps_per_second": 1.166,
|
| 426 |
+
"learning_rate": 0.0001,
|
| 427 |
+
"step": 2280
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 31.0,
|
| 431 |
+
"eval_explained_variance": 0.3488965630531311,
|
| 432 |
+
"eval_kl_divergence": 0.7415657043457031,
|
| 433 |
+
"eval_loss": 0.45080825686454773,
|
| 434 |
+
"eval_mae": 0.12486829608678818,
|
| 435 |
+
"eval_rmse": 0.1701475977897644,
|
| 436 |
+
"eval_runtime": 22.3895,
|
| 437 |
+
"eval_samples_per_second": 35.776,
|
| 438 |
+
"eval_steps_per_second": 1.161,
|
| 439 |
+
"learning_rate": 0.0001,
|
| 440 |
+
"step": 2356
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 32.0,
|
| 444 |
+
"eval_explained_variance": 0.3523526191711426,
|
| 445 |
+
"eval_kl_divergence": 0.6401851177215576,
|
| 446 |
+
"eval_loss": 0.4501984417438507,
|
| 447 |
+
"eval_mae": 0.12540514767169952,
|
| 448 |
+
"eval_rmse": 0.16971096396446228,
|
| 449 |
+
"eval_runtime": 22.3438,
|
| 450 |
+
"eval_samples_per_second": 35.849,
|
| 451 |
+
"eval_steps_per_second": 1.164,
|
| 452 |
+
"learning_rate": 0.0001,
|
| 453 |
+
"step": 2432
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 32.89473684210526,
|
| 457 |
+
"grad_norm": 0.1912919282913208,
|
| 458 |
+
"learning_rate": 0.0001,
|
| 459 |
+
"loss": 0.4289,
|
| 460 |
+
"step": 2500
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 33.0,
|
| 464 |
+
"eval_explained_variance": 0.33917075395584106,
|
| 465 |
+
"eval_kl_divergence": 0.8411455154418945,
|
| 466 |
+
"eval_loss": 0.4510658085346222,
|
| 467 |
+
"eval_mae": 0.12500226497650146,
|
| 468 |
+
"eval_rmse": 0.1709534227848053,
|
| 469 |
+
"eval_runtime": 22.56,
|
| 470 |
+
"eval_samples_per_second": 35.505,
|
| 471 |
+
"eval_steps_per_second": 1.152,
|
| 472 |
+
"learning_rate": 0.0001,
|
| 473 |
+
"step": 2508
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 34.0,
|
| 477 |
+
"eval_explained_variance": 0.33831754326820374,
|
| 478 |
+
"eval_kl_divergence": 0.7203648686408997,
|
| 479 |
+
"eval_loss": 0.45148056745529175,
|
| 480 |
+
"eval_mae": 0.12593072652816772,
|
| 481 |
+
"eval_rmse": 0.17108403146266937,
|
| 482 |
+
"eval_runtime": 22.505,
|
| 483 |
+
"eval_samples_per_second": 35.592,
|
| 484 |
+
"eval_steps_per_second": 1.155,
|
| 485 |
+
"learning_rate": 1e-05,
|
| 486 |
+
"step": 2584
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 35.0,
|
| 490 |
+
"eval_explained_variance": 0.34977057576179504,
|
| 491 |
+
"eval_kl_divergence": 0.7354820966720581,
|
| 492 |
+
"eval_loss": 0.4502483904361725,
|
| 493 |
+
"eval_mae": 0.12473371624946594,
|
| 494 |
+
"eval_rmse": 0.16982755064964294,
|
| 495 |
+
"eval_runtime": 22.3912,
|
| 496 |
+
"eval_samples_per_second": 35.773,
|
| 497 |
+
"eval_steps_per_second": 1.161,
|
| 498 |
+
"learning_rate": 1e-05,
|
| 499 |
+
"step": 2660
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 36.0,
|
| 503 |
+
"eval_explained_variance": 0.3486325144767761,
|
| 504 |
+
"eval_kl_divergence": 0.49899470806121826,
|
| 505 |
+
"eval_loss": 0.4508889615535736,
|
| 506 |
+
"eval_mae": 0.1260843575000763,
|
| 507 |
+
"eval_rmse": 0.1702878773212433,
|
| 508 |
+
"eval_runtime": 22.8537,
|
| 509 |
+
"eval_samples_per_second": 35.049,
|
| 510 |
+
"eval_steps_per_second": 1.138,
|
| 511 |
+
"learning_rate": 1e-05,
|
| 512 |
+
"step": 2736
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 37.0,
|
| 516 |
+
"eval_explained_variance": 0.3535779118537903,
|
| 517 |
+
"eval_kl_divergence": 0.5451197624206543,
|
| 518 |
+
"eval_loss": 0.44998663663864136,
|
| 519 |
+
"eval_mae": 0.12602195143699646,
|
| 520 |
+
"eval_rmse": 0.16962522268295288,
|
| 521 |
+
"eval_runtime": 22.2216,
|
| 522 |
+
"eval_samples_per_second": 36.046,
|
| 523 |
+
"eval_steps_per_second": 1.17,
|
| 524 |
+
"learning_rate": 1e-05,
|
| 525 |
+
"step": 2812
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 37.0,
|
| 529 |
+
"learning_rate": 1e-05,
|
| 530 |
+
"step": 2812,
|
| 531 |
+
"total_flos": 1.318896404308369e+20,
|
| 532 |
+
"train_loss": 0.4464974437295797,
|
| 533 |
+
"train_runtime": 4164.1679,
|
| 534 |
+
"train_samples_per_second": 86.596,
|
| 535 |
+
"train_steps_per_second": 2.738
|
| 536 |
+
}
|
| 537 |
+
],
|
| 538 |
+
"logging_steps": 500,
|
| 539 |
+
"max_steps": 11400,
|
| 540 |
+
"num_input_tokens_seen": 0,
|
| 541 |
+
"num_train_epochs": 150,
|
| 542 |
+
"save_steps": 500,
|
| 543 |
+
"stateful_callbacks": {
|
| 544 |
+
"EarlyStoppingCallback": {
|
| 545 |
+
"args": {
|
| 546 |
+
"early_stopping_patience": 10,
|
| 547 |
+
"early_stopping_threshold": 0.0
|
| 548 |
+
},
|
| 549 |
+
"attributes": {
|
| 550 |
+
"early_stopping_patience_counter": 10
|
| 551 |
+
}
|
| 552 |
+
},
|
| 553 |
+
"TrainerControl": {
|
| 554 |
+
"args": {
|
| 555 |
+
"should_epoch_stop": false,
|
| 556 |
+
"should_evaluate": false,
|
| 557 |
+
"should_log": false,
|
| 558 |
+
"should_save": true,
|
| 559 |
+
"should_training_stop": true
|
| 560 |
+
},
|
| 561 |
+
"attributes": {}
|
| 562 |
+
}
|
| 563 |
+
},
|
| 564 |
+
"total_flos": 1.318896404308369e+20,
|
| 565 |
+
"train_batch_size": 32,
|
| 566 |
+
"trial_name": null,
|
| 567 |
+
"trial_params": null
|
| 568 |
+
}
|