Commit
•
b7619ec
1
Parent(s):
9aaa510
Evaluation on the test set completed on 2024_09_10.
Browse files- README.md +123 -0
- all_results.json +17 -0
- logs/events.out.tfevents.1725859043.datavisu2 +2 -2
- logs/events.out.tfevents.1725967888.datavisu2 +3 -0
- model.safetensors +1 -1
- test_results.json +12 -0
- train_results.json +9 -0
- trainer_state.json +1043 -0
README.md
ADDED
|
@@ -0,0 +1,123 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/dinov2-base
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: dinov2-base-2024_09_09-batch-size32_epochs150_freeze
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# dinov2-base-2024_09_09-batch-size32_epochs150_freeze
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [facebook/dinov2-base](https://huggingface.co/facebook/dinov2-base) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1321
|
| 21 |
+
- F1 Micro: 0.8069
|
| 22 |
+
- F1 Macro: 0.7121
|
| 23 |
+
- Roc Auc: 0.8742
|
| 24 |
+
- Accuracy: 0.2869
|
| 25 |
+
- Learning Rate: 0.0000
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 0.001
|
| 45 |
+
- train_batch_size: 32
|
| 46 |
+
- eval_batch_size: 32
|
| 47 |
+
- seed: 42
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 150
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Roc Auc | Accuracy | Rate |
|
| 56 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-------:|:--------:|:------:|
|
| 57 |
+
| No log | 1.0 | 273 | 0.1601 | 0.7634 | 0.6251 | 0.8453 | 0.2328 | 0.001 |
|
| 58 |
+
| 0.1759 | 2.0 | 546 | 0.1504 | 0.7780 | 0.6462 | 0.8546 | 0.2498 | 0.001 |
|
| 59 |
+
| 0.1759 | 3.0 | 819 | 0.1483 | 0.7817 | 0.6644 | 0.8583 | 0.2564 | 0.001 |
|
| 60 |
+
| 0.1474 | 4.0 | 1092 | 0.1464 | 0.7863 | 0.6809 | 0.8634 | 0.2554 | 0.001 |
|
| 61 |
+
| 0.1474 | 5.0 | 1365 | 0.1423 | 0.7891 | 0.6919 | 0.8572 | 0.2682 | 0.001 |
|
| 62 |
+
| 0.1397 | 6.0 | 1638 | 0.1440 | 0.7902 | 0.6988 | 0.8629 | 0.2651 | 0.001 |
|
| 63 |
+
| 0.1397 | 7.0 | 1911 | 0.1425 | 0.7938 | 0.6850 | 0.8647 | 0.2682 | 0.001 |
|
| 64 |
+
| 0.1356 | 8.0 | 2184 | 0.1429 | 0.7931 | 0.6880 | 0.8700 | 0.2637 | 0.001 |
|
| 65 |
+
| 0.1356 | 9.0 | 2457 | 0.1463 | 0.7927 | 0.6885 | 0.8704 | 0.2557 | 0.001 |
|
| 66 |
+
| 0.1315 | 10.0 | 2730 | 0.1392 | 0.8009 | 0.7050 | 0.8729 | 0.2744 | 0.001 |
|
| 67 |
+
| 0.1308 | 11.0 | 3003 | 0.1443 | 0.7853 | 0.6892 | 0.8519 | 0.2699 | 0.001 |
|
| 68 |
+
| 0.1308 | 12.0 | 3276 | 0.1452 | 0.7888 | 0.6976 | 0.8670 | 0.2713 | 0.001 |
|
| 69 |
+
| 0.1277 | 13.0 | 3549 | 0.1370 | 0.8007 | 0.7032 | 0.8680 | 0.2765 | 0.001 |
|
| 70 |
+
| 0.1277 | 14.0 | 3822 | 0.1401 | 0.7984 | 0.6875 | 0.8694 | 0.2730 | 0.001 |
|
| 71 |
+
| 0.1257 | 15.0 | 4095 | 0.1379 | 0.8049 | 0.7001 | 0.8748 | 0.2817 | 0.001 |
|
| 72 |
+
| 0.1257 | 16.0 | 4368 | 0.1429 | 0.7969 | 0.7063 | 0.8675 | 0.2682 | 0.001 |
|
| 73 |
+
| 0.1257 | 17.0 | 4641 | 0.1451 | 0.7956 | 0.6861 | 0.8728 | 0.2613 | 0.001 |
|
| 74 |
+
| 0.1257 | 18.0 | 4914 | 0.1418 | 0.7906 | 0.6849 | 0.8574 | 0.2713 | 0.001 |
|
| 75 |
+
| 0.1251 | 19.0 | 5187 | 0.1438 | 0.7900 | 0.6794 | 0.8556 | 0.2654 | 0.001 |
|
| 76 |
+
| 0.1251 | 20.0 | 5460 | 0.1319 | 0.8068 | 0.7202 | 0.8705 | 0.2866 | 0.0001 |
|
| 77 |
+
| 0.1161 | 21.0 | 5733 | 0.1312 | 0.8081 | 0.7237 | 0.8715 | 0.2876 | 0.0001 |
|
| 78 |
+
| 0.1109 | 22.0 | 6006 | 0.1310 | 0.8101 | 0.7222 | 0.8788 | 0.2935 | 0.0001 |
|
| 79 |
+
| 0.1109 | 23.0 | 6279 | 0.1305 | 0.8120 | 0.7226 | 0.8776 | 0.2935 | 0.0001 |
|
| 80 |
+
| 0.1103 | 24.0 | 6552 | 0.1309 | 0.8096 | 0.7238 | 0.8769 | 0.2952 | 0.0001 |
|
| 81 |
+
| 0.1103 | 25.0 | 6825 | 0.1308 | 0.8093 | 0.7171 | 0.8735 | 0.2949 | 0.0001 |
|
| 82 |
+
| 0.1099 | 26.0 | 7098 | 0.1301 | 0.8100 | 0.7200 | 0.8745 | 0.2911 | 0.0001 |
|
| 83 |
+
| 0.1099 | 27.0 | 7371 | 0.1303 | 0.8082 | 0.7208 | 0.8727 | 0.2924 | 0.0001 |
|
| 84 |
+
| 0.1107 | 28.0 | 7644 | 0.1302 | 0.8103 | 0.7218 | 0.8752 | 0.2970 | 0.0001 |
|
| 85 |
+
| 0.1107 | 29.0 | 7917 | 0.1302 | 0.8104 | 0.7237 | 0.8766 | 0.2963 | 0.0001 |
|
| 86 |
+
| 0.1103 | 30.0 | 8190 | 0.1303 | 0.8097 | 0.7181 | 0.8745 | 0.2956 | 0.0001 |
|
| 87 |
+
| 0.1103 | 31.0 | 8463 | 0.1301 | 0.8092 | 0.7190 | 0.8739 | 0.2959 | 0.0001 |
|
| 88 |
+
| 0.1104 | 32.0 | 8736 | 0.1301 | 0.8098 | 0.7210 | 0.8740 | 0.2928 | 0.0001 |
|
| 89 |
+
| 0.1093 | 33.0 | 9009 | 0.1296 | 0.8100 | 0.7204 | 0.8738 | 0.2963 | 1e-05 |
|
| 90 |
+
| 0.1093 | 34.0 | 9282 | 0.1296 | 0.8101 | 0.7222 | 0.8745 | 0.2956 | 1e-05 |
|
| 91 |
+
| 0.1084 | 35.0 | 9555 | 0.1295 | 0.8109 | 0.7220 | 0.8758 | 0.2956 | 1e-05 |
|
| 92 |
+
| 0.1084 | 36.0 | 9828 | 0.1295 | 0.8105 | 0.7212 | 0.8746 | 0.2931 | 1e-05 |
|
| 93 |
+
| 0.1091 | 37.0 | 10101 | 0.1295 | 0.8119 | 0.7239 | 0.8757 | 0.2963 | 1e-05 |
|
| 94 |
+
| 0.1091 | 38.0 | 10374 | 0.1295 | 0.8104 | 0.7213 | 0.8744 | 0.2959 | 1e-05 |
|
| 95 |
+
| 0.1075 | 39.0 | 10647 | 0.1295 | 0.8106 | 0.7222 | 0.8752 | 0.2966 | 1e-05 |
|
| 96 |
+
| 0.1075 | 40.0 | 10920 | 0.1295 | 0.8113 | 0.7233 | 0.8768 | 0.2956 | 1e-05 |
|
| 97 |
+
| 0.1088 | 41.0 | 11193 | 0.1295 | 0.8100 | 0.7223 | 0.8739 | 0.2945 | 1e-05 |
|
| 98 |
+
| 0.1088 | 42.0 | 11466 | 0.1295 | 0.8111 | 0.7219 | 0.8750 | 0.2973 | 1e-05 |
|
| 99 |
+
| 0.1085 | 43.0 | 11739 | 0.1294 | 0.8098 | 0.7212 | 0.8738 | 0.2931 | 1e-05 |
|
| 100 |
+
| 0.1084 | 44.0 | 12012 | 0.1295 | 0.8108 | 0.7212 | 0.8746 | 0.2970 | 1e-05 |
|
| 101 |
+
| 0.1084 | 45.0 | 12285 | 0.1294 | 0.8104 | 0.7218 | 0.8749 | 0.2945 | 1e-05 |
|
| 102 |
+
| 0.1083 | 46.0 | 12558 | 0.1294 | 0.8113 | 0.7233 | 0.8759 | 0.2976 | 1e-05 |
|
| 103 |
+
| 0.1083 | 47.0 | 12831 | 0.1294 | 0.8107 | 0.7229 | 0.8753 | 0.2945 | 1e-05 |
|
| 104 |
+
| 0.109 | 48.0 | 13104 | 0.1294 | 0.8103 | 0.7209 | 0.8742 | 0.2956 | 1e-05 |
|
| 105 |
+
| 0.109 | 49.0 | 13377 | 0.1293 | 0.8111 | 0.7215 | 0.8755 | 0.2959 | 1e-05 |
|
| 106 |
+
| 0.108 | 50.0 | 13650 | 0.1294 | 0.8107 | 0.7211 | 0.8750 | 0.2966 | 1e-05 |
|
| 107 |
+
| 0.108 | 51.0 | 13923 | 0.1294 | 0.8099 | 0.7224 | 0.8742 | 0.2924 | 1e-05 |
|
| 108 |
+
| 0.1084 | 52.0 | 14196 | 0.1294 | 0.8110 | 0.7224 | 0.8755 | 0.2973 | 1e-05 |
|
| 109 |
+
| 0.1084 | 53.0 | 14469 | 0.1295 | 0.8111 | 0.7225 | 0.8757 | 0.2980 | 1e-05 |
|
| 110 |
+
| 0.1086 | 54.0 | 14742 | 0.1294 | 0.8105 | 0.7222 | 0.8752 | 0.2963 | 1e-05 |
|
| 111 |
+
| 0.1083 | 55.0 | 15015 | 0.1293 | 0.8107 | 0.7231 | 0.8754 | 0.2956 | 1e-05 |
|
| 112 |
+
| 0.1083 | 56.0 | 15288 | 0.1294 | 0.8107 | 0.7227 | 0.8753 | 0.2959 | 0.0000 |
|
| 113 |
+
| 0.108 | 57.0 | 15561 | 0.1293 | 0.8111 | 0.7231 | 0.8754 | 0.2956 | 0.0000 |
|
| 114 |
+
| 0.108 | 58.0 | 15834 | 0.1294 | 0.8112 | 0.7230 | 0.8755 | 0.2966 | 0.0000 |
|
| 115 |
+
| 0.1089 | 59.0 | 16107 | 0.1294 | 0.8110 | 0.7227 | 0.8753 | 0.2966 | 0.0000 |
|
| 116 |
+
|
| 117 |
+
|
| 118 |
+
### Framework versions
|
| 119 |
+
|
| 120 |
+
- Transformers 4.41.1
|
| 121 |
+
- Pytorch 2.3.0+cu121
|
| 122 |
+
- Datasets 2.19.1
|
| 123 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 59.0,
|
| 3 |
+
"eval_accuracy": 0.28685121107266437,
|
| 4 |
+
"eval_f1_macro": 0.7121206032252584,
|
| 5 |
+
"eval_f1_micro": 0.8069197820934004,
|
| 6 |
+
"eval_loss": 0.13205093145370483,
|
| 7 |
+
"eval_roc_auc": 0.874152531963206,
|
| 8 |
+
"eval_runtime": 445.2138,
|
| 9 |
+
"eval_samples_per_second": 6.491,
|
| 10 |
+
"eval_steps_per_second": 0.204,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 12 |
+
"total_flos": 2.151593295698903e+20,
|
| 13 |
+
"train_loss": 0.11777938241923686,
|
| 14 |
+
"train_runtime": 108362.28,
|
| 15 |
+
"train_samples_per_second": 12.065,
|
| 16 |
+
"train_steps_per_second": 0.378
|
| 17 |
+
}
|
logs/events.out.tfevents.1725859043.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:ed78969fc172629185bbd0d12d933445325207acf164f92dbcd5f4cd20abe8b7
|
| 3 |
+
size 45828
|
logs/events.out.tfevents.1725967888.datavisu2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e86a994d18dfb9c6af1ce27f74b500329062e5be0e16f43ab231104b68b0028
|
| 3 |
+
size 40
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 346538228
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09e94bfc07f1f2cd594e8b888632c2d8f81041d757cf35ada9aa6911fdc928a6
|
| 3 |
size 346538228
|
test_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 59.0,
|
| 3 |
+
"eval_accuracy": 0.28685121107266437,
|
| 4 |
+
"eval_f1_macro": 0.7121206032252584,
|
| 5 |
+
"eval_f1_micro": 0.8069197820934004,
|
| 6 |
+
"eval_loss": 0.13205093145370483,
|
| 7 |
+
"eval_roc_auc": 0.874152531963206,
|
| 8 |
+
"eval_runtime": 445.2138,
|
| 9 |
+
"eval_samples_per_second": 6.491,
|
| 10 |
+
"eval_steps_per_second": 0.204,
|
| 11 |
+
"learning_rate": 1.0000000000000002e-06
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 59.0,
|
| 3 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 4 |
+
"total_flos": 2.151593295698903e+20,
|
| 5 |
+
"train_loss": 0.11777938241923686,
|
| 6 |
+
"train_runtime": 108362.28,
|
| 7 |
+
"train_samples_per_second": 12.065,
|
| 8 |
+
"train_steps_per_second": 0.378
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1043 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.12932655215263367,
|
| 3 |
+
"best_model_checkpoint": "/home/datawork-iot-nos/Seatizen/models/multilabel/fine_scale/dinov2-base-2024_09_09-batch-size32_epochs150_freeze/checkpoint-13377",
|
| 4 |
+
"epoch": 59.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 16107,
|
| 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_accuracy": 0.23284823284823286,
|
| 14 |
+
"eval_f1_macro": 0.6250897780499145,
|
| 15 |
+
"eval_f1_micro": 0.7633800438966739,
|
| 16 |
+
"eval_loss": 0.16006726026535034,
|
| 17 |
+
"eval_roc_auc": 0.8452995641064989,
|
| 18 |
+
"eval_runtime": 455.8596,
|
| 19 |
+
"eval_samples_per_second": 6.331,
|
| 20 |
+
"eval_steps_per_second": 0.2,
|
| 21 |
+
"learning_rate": 0.001,
|
| 22 |
+
"step": 273
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 1.8315018315018317,
|
| 26 |
+
"grad_norm": 0.4072045385837555,
|
| 27 |
+
"learning_rate": 0.001,
|
| 28 |
+
"loss": 0.1759,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_accuracy": 0.24982674982674982,
|
| 34 |
+
"eval_f1_macro": 0.646165211379598,
|
| 35 |
+
"eval_f1_micro": 0.7780064686856808,
|
| 36 |
+
"eval_loss": 0.150440976023674,
|
| 37 |
+
"eval_roc_auc": 0.8546135818062216,
|
| 38 |
+
"eval_runtime": 451.8319,
|
| 39 |
+
"eval_samples_per_second": 6.387,
|
| 40 |
+
"eval_steps_per_second": 0.201,
|
| 41 |
+
"learning_rate": 0.001,
|
| 42 |
+
"step": 546
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.0,
|
| 46 |
+
"eval_accuracy": 0.2564102564102564,
|
| 47 |
+
"eval_f1_macro": 0.6644318154557648,
|
| 48 |
+
"eval_f1_micro": 0.7816936696175046,
|
| 49 |
+
"eval_loss": 0.14829224348068237,
|
| 50 |
+
"eval_roc_auc": 0.8582657995297673,
|
| 51 |
+
"eval_runtime": 444.7156,
|
| 52 |
+
"eval_samples_per_second": 6.49,
|
| 53 |
+
"eval_steps_per_second": 0.205,
|
| 54 |
+
"learning_rate": 0.001,
|
| 55 |
+
"step": 819
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 3.663003663003663,
|
| 59 |
+
"grad_norm": 0.4122166037559509,
|
| 60 |
+
"learning_rate": 0.001,
|
| 61 |
+
"loss": 0.1474,
|
| 62 |
+
"step": 1000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.2553707553707554,
|
| 67 |
+
"eval_f1_macro": 0.680888104485521,
|
| 68 |
+
"eval_f1_micro": 0.7862639635912287,
|
| 69 |
+
"eval_loss": 0.14641565084457397,
|
| 70 |
+
"eval_roc_auc": 0.8633757977162271,
|
| 71 |
+
"eval_runtime": 456.1173,
|
| 72 |
+
"eval_samples_per_second": 6.327,
|
| 73 |
+
"eval_steps_per_second": 0.2,
|
| 74 |
+
"learning_rate": 0.001,
|
| 75 |
+
"step": 1092
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"eval_accuracy": 0.2681912681912682,
|
| 80 |
+
"eval_f1_macro": 0.6919100708566497,
|
| 81 |
+
"eval_f1_micro": 0.7891243298442687,
|
| 82 |
+
"eval_loss": 0.14226503670215607,
|
| 83 |
+
"eval_roc_auc": 0.8571516929773072,
|
| 84 |
+
"eval_runtime": 446.9545,
|
| 85 |
+
"eval_samples_per_second": 6.457,
|
| 86 |
+
"eval_steps_per_second": 0.204,
|
| 87 |
+
"learning_rate": 0.001,
|
| 88 |
+
"step": 1365
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 5.4945054945054945,
|
| 92 |
+
"grad_norm": 0.4282256066799164,
|
| 93 |
+
"learning_rate": 0.001,
|
| 94 |
+
"loss": 0.1397,
|
| 95 |
+
"step": 1500
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 6.0,
|
| 99 |
+
"eval_accuracy": 0.26507276507276506,
|
| 100 |
+
"eval_f1_macro": 0.6987715680115144,
|
| 101 |
+
"eval_f1_micro": 0.7901946045268521,
|
| 102 |
+
"eval_loss": 0.1439608633518219,
|
| 103 |
+
"eval_roc_auc": 0.8629406419717581,
|
| 104 |
+
"eval_runtime": 465.0998,
|
| 105 |
+
"eval_samples_per_second": 6.205,
|
| 106 |
+
"eval_steps_per_second": 0.196,
|
| 107 |
+
"learning_rate": 0.001,
|
| 108 |
+
"step": 1638
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 7.0,
|
| 112 |
+
"eval_accuracy": 0.2681912681912682,
|
| 113 |
+
"eval_f1_macro": 0.6849790066180481,
|
| 114 |
+
"eval_f1_micro": 0.7937821236053655,
|
| 115 |
+
"eval_loss": 0.1425073742866516,
|
| 116 |
+
"eval_roc_auc": 0.8647460265764118,
|
| 117 |
+
"eval_runtime": 459.0682,
|
| 118 |
+
"eval_samples_per_second": 6.287,
|
| 119 |
+
"eval_steps_per_second": 0.198,
|
| 120 |
+
"learning_rate": 0.001,
|
| 121 |
+
"step": 1911
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 7.326007326007326,
|
| 125 |
+
"grad_norm": 0.4099022448062897,
|
| 126 |
+
"learning_rate": 0.001,
|
| 127 |
+
"loss": 0.1356,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.2636867636867637,
|
| 133 |
+
"eval_f1_macro": 0.6880365824342907,
|
| 134 |
+
"eval_f1_micro": 0.793083667950504,
|
| 135 |
+
"eval_loss": 0.14294348657131195,
|
| 136 |
+
"eval_roc_auc": 0.8699640457613058,
|
| 137 |
+
"eval_runtime": 467.5382,
|
| 138 |
+
"eval_samples_per_second": 6.173,
|
| 139 |
+
"eval_steps_per_second": 0.195,
|
| 140 |
+
"learning_rate": 0.001,
|
| 141 |
+
"step": 2184
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 9.0,
|
| 145 |
+
"eval_accuracy": 0.25571725571725573,
|
| 146 |
+
"eval_f1_macro": 0.6884565577441364,
|
| 147 |
+
"eval_f1_micro": 0.7926595005517636,
|
| 148 |
+
"eval_loss": 0.14630228281021118,
|
| 149 |
+
"eval_roc_auc": 0.8704441778385391,
|
| 150 |
+
"eval_runtime": 469.2736,
|
| 151 |
+
"eval_samples_per_second": 6.15,
|
| 152 |
+
"eval_steps_per_second": 0.194,
|
| 153 |
+
"learning_rate": 0.001,
|
| 154 |
+
"step": 2457
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 9.157509157509157,
|
| 158 |
+
"grad_norm": 0.35209059715270996,
|
| 159 |
+
"learning_rate": 0.001,
|
| 160 |
+
"loss": 0.1315,
|
| 161 |
+
"step": 2500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 10.0,
|
| 165 |
+
"eval_accuracy": 0.27442827442827444,
|
| 166 |
+
"eval_f1_macro": 0.7049759390767861,
|
| 167 |
+
"eval_f1_micro": 0.8009224940284985,
|
| 168 |
+
"eval_loss": 0.13922064006328583,
|
| 169 |
+
"eval_roc_auc": 0.8728939594088932,
|
| 170 |
+
"eval_runtime": 446.1349,
|
| 171 |
+
"eval_samples_per_second": 6.469,
|
| 172 |
+
"eval_steps_per_second": 0.204,
|
| 173 |
+
"learning_rate": 0.001,
|
| 174 |
+
"step": 2730
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 10.989010989010989,
|
| 178 |
+
"grad_norm": 0.47372138500213623,
|
| 179 |
+
"learning_rate": 0.001,
|
| 180 |
+
"loss": 0.1308,
|
| 181 |
+
"step": 3000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 11.0,
|
| 185 |
+
"eval_accuracy": 0.26992376992376993,
|
| 186 |
+
"eval_f1_macro": 0.6892328865834217,
|
| 187 |
+
"eval_f1_micro": 0.785345272946444,
|
| 188 |
+
"eval_loss": 0.14429208636283875,
|
| 189 |
+
"eval_roc_auc": 0.8519184223488243,
|
| 190 |
+
"eval_runtime": 447.1698,
|
| 191 |
+
"eval_samples_per_second": 6.454,
|
| 192 |
+
"eval_steps_per_second": 0.204,
|
| 193 |
+
"learning_rate": 0.001,
|
| 194 |
+
"step": 3003
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.0,
|
| 198 |
+
"eval_accuracy": 0.2713097713097713,
|
| 199 |
+
"eval_f1_macro": 0.6976448599197044,
|
| 200 |
+
"eval_f1_micro": 0.7888341543513957,
|
| 201 |
+
"eval_loss": 0.14520499110221863,
|
| 202 |
+
"eval_roc_auc": 0.867032334670059,
|
| 203 |
+
"eval_runtime": 443.567,
|
| 204 |
+
"eval_samples_per_second": 6.506,
|
| 205 |
+
"eval_steps_per_second": 0.205,
|
| 206 |
+
"learning_rate": 0.001,
|
| 207 |
+
"step": 3276
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 12.820512820512821,
|
| 211 |
+
"grad_norm": 0.40755951404571533,
|
| 212 |
+
"learning_rate": 0.001,
|
| 213 |
+
"loss": 0.1277,
|
| 214 |
+
"step": 3500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 13.0,
|
| 218 |
+
"eval_accuracy": 0.2765072765072765,
|
| 219 |
+
"eval_f1_macro": 0.7032121010324246,
|
| 220 |
+
"eval_f1_micro": 0.8007200870802982,
|
| 221 |
+
"eval_loss": 0.13695523142814636,
|
| 222 |
+
"eval_roc_auc": 0.8680389701881897,
|
| 223 |
+
"eval_runtime": 444.0658,
|
| 224 |
+
"eval_samples_per_second": 6.499,
|
| 225 |
+
"eval_steps_per_second": 0.205,
|
| 226 |
+
"learning_rate": 0.001,
|
| 227 |
+
"step": 3549
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 14.0,
|
| 231 |
+
"eval_accuracy": 0.273042273042273,
|
| 232 |
+
"eval_f1_macro": 0.6875097222118577,
|
| 233 |
+
"eval_f1_micro": 0.7983576642335767,
|
| 234 |
+
"eval_loss": 0.14012356102466583,
|
| 235 |
+
"eval_roc_auc": 0.869430406200805,
|
| 236 |
+
"eval_runtime": 440.0286,
|
| 237 |
+
"eval_samples_per_second": 6.559,
|
| 238 |
+
"eval_steps_per_second": 0.207,
|
| 239 |
+
"learning_rate": 0.001,
|
| 240 |
+
"step": 3822
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.652014652014651,
|
| 244 |
+
"grad_norm": 0.3442566990852356,
|
| 245 |
+
"learning_rate": 0.001,
|
| 246 |
+
"loss": 0.1257,
|
| 247 |
+
"step": 4000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 15.0,
|
| 251 |
+
"eval_accuracy": 0.2817047817047817,
|
| 252 |
+
"eval_f1_macro": 0.7001361694791496,
|
| 253 |
+
"eval_f1_micro": 0.8048810652595126,
|
| 254 |
+
"eval_loss": 0.13785772025585175,
|
| 255 |
+
"eval_roc_auc": 0.8748105574865406,
|
| 256 |
+
"eval_runtime": 441.6171,
|
| 257 |
+
"eval_samples_per_second": 6.535,
|
| 258 |
+
"eval_steps_per_second": 0.206,
|
| 259 |
+
"learning_rate": 0.001,
|
| 260 |
+
"step": 4095
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 16.0,
|
| 264 |
+
"eval_accuracy": 0.2681912681912682,
|
| 265 |
+
"eval_f1_macro": 0.7063273106998997,
|
| 266 |
+
"eval_f1_micro": 0.7968854097268487,
|
| 267 |
+
"eval_loss": 0.1429404616355896,
|
| 268 |
+
"eval_roc_auc": 0.8674701731662587,
|
| 269 |
+
"eval_runtime": 440.4364,
|
| 270 |
+
"eval_samples_per_second": 6.553,
|
| 271 |
+
"eval_steps_per_second": 0.207,
|
| 272 |
+
"learning_rate": 0.001,
|
| 273 |
+
"step": 4368
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 16.483516483516482,
|
| 277 |
+
"grad_norm": 0.44264066219329834,
|
| 278 |
+
"learning_rate": 0.001,
|
| 279 |
+
"loss": 0.1257,
|
| 280 |
+
"step": 4500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 17.0,
|
| 284 |
+
"eval_accuracy": 0.26126126126126126,
|
| 285 |
+
"eval_f1_macro": 0.6860743816280108,
|
| 286 |
+
"eval_f1_micro": 0.7956287718153646,
|
| 287 |
+
"eval_loss": 0.1451471894979477,
|
| 288 |
+
"eval_roc_auc": 0.8727966023485881,
|
| 289 |
+
"eval_runtime": 445.5579,
|
| 290 |
+
"eval_samples_per_second": 6.477,
|
| 291 |
+
"eval_steps_per_second": 0.204,
|
| 292 |
+
"learning_rate": 0.001,
|
| 293 |
+
"step": 4641
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 18.0,
|
| 297 |
+
"eval_accuracy": 0.2713097713097713,
|
| 298 |
+
"eval_f1_macro": 0.6849355289660601,
|
| 299 |
+
"eval_f1_micro": 0.7906203368151778,
|
| 300 |
+
"eval_loss": 0.141770601272583,
|
| 301 |
+
"eval_roc_auc": 0.8574113028622815,
|
| 302 |
+
"eval_runtime": 440.4062,
|
| 303 |
+
"eval_samples_per_second": 6.553,
|
| 304 |
+
"eval_steps_per_second": 0.207,
|
| 305 |
+
"learning_rate": 0.001,
|
| 306 |
+
"step": 4914
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 18.315018315018314,
|
| 310 |
+
"grad_norm": 0.38295412063598633,
|
| 311 |
+
"learning_rate": 0.001,
|
| 312 |
+
"loss": 0.1251,
|
| 313 |
+
"step": 5000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 19.0,
|
| 317 |
+
"eval_accuracy": 0.2654192654192654,
|
| 318 |
+
"eval_f1_macro": 0.6794374521554336,
|
| 319 |
+
"eval_f1_micro": 0.7899699957136733,
|
| 320 |
+
"eval_loss": 0.14384245872497559,
|
| 321 |
+
"eval_roc_auc": 0.8555935775996669,
|
| 322 |
+
"eval_runtime": 441.9996,
|
| 323 |
+
"eval_samples_per_second": 6.529,
|
| 324 |
+
"eval_steps_per_second": 0.206,
|
| 325 |
+
"learning_rate": 0.001,
|
| 326 |
+
"step": 5187
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 20.0,
|
| 330 |
+
"eval_accuracy": 0.28655578655578656,
|
| 331 |
+
"eval_f1_macro": 0.7201978132992005,
|
| 332 |
+
"eval_f1_micro": 0.8068363147728227,
|
| 333 |
+
"eval_loss": 0.13193023204803467,
|
| 334 |
+
"eval_roc_auc": 0.8705382753554913,
|
| 335 |
+
"eval_runtime": 445.6167,
|
| 336 |
+
"eval_samples_per_second": 6.476,
|
| 337 |
+
"eval_steps_per_second": 0.204,
|
| 338 |
+
"learning_rate": 0.0001,
|
| 339 |
+
"step": 5460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 20.146520146520146,
|
| 343 |
+
"grad_norm": 0.34160131216049194,
|
| 344 |
+
"learning_rate": 0.0001,
|
| 345 |
+
"loss": 0.1161,
|
| 346 |
+
"step": 5500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 21.0,
|
| 350 |
+
"eval_accuracy": 0.2875952875952876,
|
| 351 |
+
"eval_f1_macro": 0.7236910659256566,
|
| 352 |
+
"eval_f1_micro": 0.8080536912751679,
|
| 353 |
+
"eval_loss": 0.13121400773525238,
|
| 354 |
+
"eval_roc_auc": 0.8715230464470173,
|
| 355 |
+
"eval_runtime": 442.006,
|
| 356 |
+
"eval_samples_per_second": 6.529,
|
| 357 |
+
"eval_steps_per_second": 0.206,
|
| 358 |
+
"learning_rate": 0.0001,
|
| 359 |
+
"step": 5733
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 21.978021978021978,
|
| 363 |
+
"grad_norm": 0.25530439615249634,
|
| 364 |
+
"learning_rate": 0.0001,
|
| 365 |
+
"loss": 0.1109,
|
| 366 |
+
"step": 6000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 22.0,
|
| 370 |
+
"eval_accuracy": 0.2934857934857935,
|
| 371 |
+
"eval_f1_macro": 0.7222147145142929,
|
| 372 |
+
"eval_f1_micro": 0.810120343368793,
|
| 373 |
+
"eval_loss": 0.1310088187456131,
|
| 374 |
+
"eval_roc_auc": 0.8788407212738992,
|
| 375 |
+
"eval_runtime": 442.6084,
|
| 376 |
+
"eval_samples_per_second": 6.52,
|
| 377 |
+
"eval_steps_per_second": 0.206,
|
| 378 |
+
"learning_rate": 0.0001,
|
| 379 |
+
"step": 6006
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 23.0,
|
| 383 |
+
"eval_accuracy": 0.2934857934857935,
|
| 384 |
+
"eval_f1_macro": 0.7226400439644629,
|
| 385 |
+
"eval_f1_micro": 0.8120394137616957,
|
| 386 |
+
"eval_loss": 0.1304517388343811,
|
| 387 |
+
"eval_roc_auc": 0.8775576952587192,
|
| 388 |
+
"eval_runtime": 443.2768,
|
| 389 |
+
"eval_samples_per_second": 6.511,
|
| 390 |
+
"eval_steps_per_second": 0.205,
|
| 391 |
+
"learning_rate": 0.0001,
|
| 392 |
+
"step": 6279
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 23.80952380952381,
|
| 396 |
+
"grad_norm": 0.31216299533843994,
|
| 397 |
+
"learning_rate": 0.0001,
|
| 398 |
+
"loss": 0.1103,
|
| 399 |
+
"step": 6500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 24.0,
|
| 403 |
+
"eval_accuracy": 0.29521829521829523,
|
| 404 |
+
"eval_f1_macro": 0.7237916982943077,
|
| 405 |
+
"eval_f1_micro": 0.8096162584162916,
|
| 406 |
+
"eval_loss": 0.13093852996826172,
|
| 407 |
+
"eval_roc_auc": 0.8768767860419646,
|
| 408 |
+
"eval_runtime": 445.0523,
|
| 409 |
+
"eval_samples_per_second": 6.485,
|
| 410 |
+
"eval_steps_per_second": 0.204,
|
| 411 |
+
"learning_rate": 0.0001,
|
| 412 |
+
"step": 6552
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 25.0,
|
| 416 |
+
"eval_accuracy": 0.2948717948717949,
|
| 417 |
+
"eval_f1_macro": 0.7170657451815683,
|
| 418 |
+
"eval_f1_micro": 0.8093388464269307,
|
| 419 |
+
"eval_loss": 0.13081994652748108,
|
| 420 |
+
"eval_roc_auc": 0.8734838965144617,
|
| 421 |
+
"eval_runtime": 438.7401,
|
| 422 |
+
"eval_samples_per_second": 6.578,
|
| 423 |
+
"eval_steps_per_second": 0.207,
|
| 424 |
+
"learning_rate": 0.0001,
|
| 425 |
+
"step": 6825
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 25.641025641025642,
|
| 429 |
+
"grad_norm": 0.38898253440856934,
|
| 430 |
+
"learning_rate": 0.0001,
|
| 431 |
+
"loss": 0.1099,
|
| 432 |
+
"step": 7000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 26.0,
|
| 436 |
+
"eval_accuracy": 0.2910602910602911,
|
| 437 |
+
"eval_f1_macro": 0.7200172245050901,
|
| 438 |
+
"eval_f1_micro": 0.8099862459884133,
|
| 439 |
+
"eval_loss": 0.13007444143295288,
|
| 440 |
+
"eval_roc_auc": 0.8744510016858411,
|
| 441 |
+
"eval_runtime": 440.3465,
|
| 442 |
+
"eval_samples_per_second": 6.554,
|
| 443 |
+
"eval_steps_per_second": 0.207,
|
| 444 |
+
"learning_rate": 0.0001,
|
| 445 |
+
"step": 7098
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 27.0,
|
| 449 |
+
"eval_accuracy": 0.29244629244629244,
|
| 450 |
+
"eval_f1_macro": 0.7207907434740295,
|
| 451 |
+
"eval_f1_micro": 0.8082065853250877,
|
| 452 |
+
"eval_loss": 0.13034380972385406,
|
| 453 |
+
"eval_roc_auc": 0.8727246375334137,
|
| 454 |
+
"eval_runtime": 441.8582,
|
| 455 |
+
"eval_samples_per_second": 6.532,
|
| 456 |
+
"eval_steps_per_second": 0.206,
|
| 457 |
+
"learning_rate": 0.0001,
|
| 458 |
+
"step": 7371
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 27.47252747252747,
|
| 462 |
+
"grad_norm": 0.23454292118549347,
|
| 463 |
+
"learning_rate": 0.0001,
|
| 464 |
+
"loss": 0.1107,
|
| 465 |
+
"step": 7500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 28.0,
|
| 469 |
+
"eval_accuracy": 0.29695079695079696,
|
| 470 |
+
"eval_f1_macro": 0.7217805682073449,
|
| 471 |
+
"eval_f1_micro": 0.810349848163401,
|
| 472 |
+
"eval_loss": 0.13018907606601715,
|
| 473 |
+
"eval_roc_auc": 0.8752133458313793,
|
| 474 |
+
"eval_runtime": 442.3473,
|
| 475 |
+
"eval_samples_per_second": 6.524,
|
| 476 |
+
"eval_steps_per_second": 0.206,
|
| 477 |
+
"learning_rate": 0.0001,
|
| 478 |
+
"step": 7644
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 29.0,
|
| 482 |
+
"eval_accuracy": 0.29625779625779625,
|
| 483 |
+
"eval_f1_macro": 0.723719101965087,
|
| 484 |
+
"eval_f1_micro": 0.8104190823256585,
|
| 485 |
+
"eval_loss": 0.13019531965255737,
|
| 486 |
+
"eval_roc_auc": 0.8765812809388343,
|
| 487 |
+
"eval_runtime": 443.3045,
|
| 488 |
+
"eval_samples_per_second": 6.51,
|
| 489 |
+
"eval_steps_per_second": 0.205,
|
| 490 |
+
"learning_rate": 0.0001,
|
| 491 |
+
"step": 7917
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 29.304029304029303,
|
| 495 |
+
"grad_norm": 0.30432701110839844,
|
| 496 |
+
"learning_rate": 0.0001,
|
| 497 |
+
"loss": 0.1103,
|
| 498 |
+
"step": 8000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 30.0,
|
| 502 |
+
"eval_accuracy": 0.2955647955647956,
|
| 503 |
+
"eval_f1_macro": 0.718144679800513,
|
| 504 |
+
"eval_f1_micro": 0.8096606287736832,
|
| 505 |
+
"eval_loss": 0.13030356168746948,
|
| 506 |
+
"eval_roc_auc": 0.87453866059864,
|
| 507 |
+
"eval_runtime": 441.0327,
|
| 508 |
+
"eval_samples_per_second": 6.544,
|
| 509 |
+
"eval_steps_per_second": 0.206,
|
| 510 |
+
"learning_rate": 0.0001,
|
| 511 |
+
"step": 8190
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 31.0,
|
| 515 |
+
"eval_accuracy": 0.2959112959112959,
|
| 516 |
+
"eval_f1_macro": 0.7189603352791966,
|
| 517 |
+
"eval_f1_micro": 0.8092418049879057,
|
| 518 |
+
"eval_loss": 0.1301266849040985,
|
| 519 |
+
"eval_roc_auc": 0.8738562356271575,
|
| 520 |
+
"eval_runtime": 443.1469,
|
| 521 |
+
"eval_samples_per_second": 6.513,
|
| 522 |
+
"eval_steps_per_second": 0.205,
|
| 523 |
+
"learning_rate": 0.0001,
|
| 524 |
+
"step": 8463
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 31.135531135531135,
|
| 528 |
+
"grad_norm": 0.3088095188140869,
|
| 529 |
+
"learning_rate": 0.0001,
|
| 530 |
+
"loss": 0.1104,
|
| 531 |
+
"step": 8500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 32.0,
|
| 535 |
+
"eval_accuracy": 0.2927927927927928,
|
| 536 |
+
"eval_f1_macro": 0.7210148516296496,
|
| 537 |
+
"eval_f1_micro": 0.8097980303789017,
|
| 538 |
+
"eval_loss": 0.1301257312297821,
|
| 539 |
+
"eval_roc_auc": 0.8739934717919385,
|
| 540 |
+
"eval_runtime": 440.0353,
|
| 541 |
+
"eval_samples_per_second": 6.559,
|
| 542 |
+
"eval_steps_per_second": 0.207,
|
| 543 |
+
"learning_rate": 0.0001,
|
| 544 |
+
"step": 8736
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 32.967032967032964,
|
| 548 |
+
"grad_norm": 0.3049701750278473,
|
| 549 |
+
"learning_rate": 1e-05,
|
| 550 |
+
"loss": 0.1093,
|
| 551 |
+
"step": 9000
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 33.0,
|
| 555 |
+
"eval_accuracy": 0.29625779625779625,
|
| 556 |
+
"eval_f1_macro": 0.7204264964359948,
|
| 557 |
+
"eval_f1_micro": 0.8099594769603543,
|
| 558 |
+
"eval_loss": 0.12959885597229004,
|
| 559 |
+
"eval_roc_auc": 0.8737537142697711,
|
| 560 |
+
"eval_runtime": 441.033,
|
| 561 |
+
"eval_samples_per_second": 6.544,
|
| 562 |
+
"eval_steps_per_second": 0.206,
|
| 563 |
+
"learning_rate": 1e-05,
|
| 564 |
+
"step": 9009
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 34.0,
|
| 568 |
+
"eval_accuracy": 0.2955647955647956,
|
| 569 |
+
"eval_f1_macro": 0.722168676552786,
|
| 570 |
+
"eval_f1_micro": 0.8100854344655136,
|
| 571 |
+
"eval_loss": 0.12959957122802734,
|
| 572 |
+
"eval_roc_auc": 0.874530303826999,
|
| 573 |
+
"eval_runtime": 444.1246,
|
| 574 |
+
"eval_samples_per_second": 6.498,
|
| 575 |
+
"eval_steps_per_second": 0.205,
|
| 576 |
+
"learning_rate": 1e-05,
|
| 577 |
+
"step": 9282
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 34.798534798534796,
|
| 581 |
+
"grad_norm": 0.3583316504955292,
|
| 582 |
+
"learning_rate": 1e-05,
|
| 583 |
+
"loss": 0.1084,
|
| 584 |
+
"step": 9500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 35.0,
|
| 588 |
+
"eval_accuracy": 0.2955647955647956,
|
| 589 |
+
"eval_f1_macro": 0.7220033007887567,
|
| 590 |
+
"eval_f1_micro": 0.8108894430590192,
|
| 591 |
+
"eval_loss": 0.12954092025756836,
|
| 592 |
+
"eval_roc_auc": 0.875769077852382,
|
| 593 |
+
"eval_runtime": 441.2982,
|
| 594 |
+
"eval_samples_per_second": 6.54,
|
| 595 |
+
"eval_steps_per_second": 0.206,
|
| 596 |
+
"learning_rate": 1e-05,
|
| 597 |
+
"step": 9555
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 36.0,
|
| 601 |
+
"eval_accuracy": 0.29313929313929316,
|
| 602 |
+
"eval_f1_macro": 0.7211650841899886,
|
| 603 |
+
"eval_f1_micro": 0.8104569713142095,
|
| 604 |
+
"eval_loss": 0.12953610718250275,
|
| 605 |
+
"eval_roc_auc": 0.8746018662294139,
|
| 606 |
+
"eval_runtime": 447.4449,
|
| 607 |
+
"eval_samples_per_second": 6.45,
|
| 608 |
+
"eval_steps_per_second": 0.203,
|
| 609 |
+
"learning_rate": 1e-05,
|
| 610 |
+
"step": 9828
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 36.63003663003663,
|
| 614 |
+
"grad_norm": 0.3639417588710785,
|
| 615 |
+
"learning_rate": 1e-05,
|
| 616 |
+
"loss": 0.1091,
|
| 617 |
+
"step": 10000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 37.0,
|
| 621 |
+
"eval_accuracy": 0.29625779625779625,
|
| 622 |
+
"eval_f1_macro": 0.7239071903959954,
|
| 623 |
+
"eval_f1_micro": 0.8118778893007372,
|
| 624 |
+
"eval_loss": 0.1295497566461563,
|
| 625 |
+
"eval_roc_auc": 0.8757186018785701,
|
| 626 |
+
"eval_runtime": 444.3576,
|
| 627 |
+
"eval_samples_per_second": 6.495,
|
| 628 |
+
"eval_steps_per_second": 0.205,
|
| 629 |
+
"learning_rate": 1e-05,
|
| 630 |
+
"step": 10101
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 38.0,
|
| 634 |
+
"eval_accuracy": 0.2959112959112959,
|
| 635 |
+
"eval_f1_macro": 0.7212977755433345,
|
| 636 |
+
"eval_f1_micro": 0.8104318798247445,
|
| 637 |
+
"eval_loss": 0.12949061393737793,
|
| 638 |
+
"eval_roc_auc": 0.8743562200671975,
|
| 639 |
+
"eval_runtime": 450.6653,
|
| 640 |
+
"eval_samples_per_second": 6.404,
|
| 641 |
+
"eval_steps_per_second": 0.202,
|
| 642 |
+
"learning_rate": 1e-05,
|
| 643 |
+
"step": 10374
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 38.46153846153846,
|
| 647 |
+
"grad_norm": 0.30328261852264404,
|
| 648 |
+
"learning_rate": 1e-05,
|
| 649 |
+
"loss": 0.1075,
|
| 650 |
+
"step": 10500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 39.0,
|
| 654 |
+
"eval_accuracy": 0.2966042966042966,
|
| 655 |
+
"eval_f1_macro": 0.7221707642640621,
|
| 656 |
+
"eval_f1_micro": 0.8106218263547823,
|
| 657 |
+
"eval_loss": 0.12945865094661713,
|
| 658 |
+
"eval_roc_auc": 0.8752056060926364,
|
| 659 |
+
"eval_runtime": 456.2278,
|
| 660 |
+
"eval_samples_per_second": 6.326,
|
| 661 |
+
"eval_steps_per_second": 0.199,
|
| 662 |
+
"learning_rate": 1e-05,
|
| 663 |
+
"step": 10647
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 40.0,
|
| 667 |
+
"eval_accuracy": 0.2955647955647956,
|
| 668 |
+
"eval_f1_macro": 0.7232749192333074,
|
| 669 |
+
"eval_f1_micro": 0.8113418729013804,
|
| 670 |
+
"eval_loss": 0.12946291267871857,
|
| 671 |
+
"eval_roc_auc": 0.8767900795060302,
|
| 672 |
+
"eval_runtime": 456.1604,
|
| 673 |
+
"eval_samples_per_second": 6.327,
|
| 674 |
+
"eval_steps_per_second": 0.199,
|
| 675 |
+
"learning_rate": 1e-05,
|
| 676 |
+
"step": 10920
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 40.29304029304029,
|
| 680 |
+
"grad_norm": 0.3177196681499481,
|
| 681 |
+
"learning_rate": 1e-05,
|
| 682 |
+
"loss": 0.1088,
|
| 683 |
+
"step": 11000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 41.0,
|
| 687 |
+
"eval_accuracy": 0.2945252945252945,
|
| 688 |
+
"eval_f1_macro": 0.722313917509489,
|
| 689 |
+
"eval_f1_micro": 0.8100071001962995,
|
| 690 |
+
"eval_loss": 0.1294611394405365,
|
| 691 |
+
"eval_roc_auc": 0.8738531504626673,
|
| 692 |
+
"eval_runtime": 455.3171,
|
| 693 |
+
"eval_samples_per_second": 6.338,
|
| 694 |
+
"eval_steps_per_second": 0.2,
|
| 695 |
+
"learning_rate": 1e-05,
|
| 696 |
+
"step": 11193
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 42.0,
|
| 700 |
+
"eval_accuracy": 0.2972972972972973,
|
| 701 |
+
"eval_f1_macro": 0.7219276596712088,
|
| 702 |
+
"eval_f1_micro": 0.8111398315684148,
|
| 703 |
+
"eval_loss": 0.12951640784740448,
|
| 704 |
+
"eval_roc_auc": 0.8750042655752517,
|
| 705 |
+
"eval_runtime": 453.9232,
|
| 706 |
+
"eval_samples_per_second": 6.358,
|
| 707 |
+
"eval_steps_per_second": 0.2,
|
| 708 |
+
"learning_rate": 1e-05,
|
| 709 |
+
"step": 11466
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 42.124542124542124,
|
| 713 |
+
"grad_norm": 0.3328670561313629,
|
| 714 |
+
"learning_rate": 1e-05,
|
| 715 |
+
"loss": 0.1085,
|
| 716 |
+
"step": 11500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 43.0,
|
| 720 |
+
"eval_accuracy": 0.29313929313929316,
|
| 721 |
+
"eval_f1_macro": 0.7212066160587719,
|
| 722 |
+
"eval_f1_micro": 0.8097862391449566,
|
| 723 |
+
"eval_loss": 0.12940654158592224,
|
| 724 |
+
"eval_roc_auc": 0.8738407561496718,
|
| 725 |
+
"eval_runtime": 457.3356,
|
| 726 |
+
"eval_samples_per_second": 6.31,
|
| 727 |
+
"eval_steps_per_second": 0.199,
|
| 728 |
+
"learning_rate": 1e-05,
|
| 729 |
+
"step": 11739
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 43.956043956043956,
|
| 733 |
+
"grad_norm": 0.2574955224990845,
|
| 734 |
+
"learning_rate": 1e-05,
|
| 735 |
+
"loss": 0.1084,
|
| 736 |
+
"step": 12000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 44.0,
|
| 740 |
+
"eval_accuracy": 0.29695079695079696,
|
| 741 |
+
"eval_f1_macro": 0.7211905265653523,
|
| 742 |
+
"eval_f1_micro": 0.8108311081441923,
|
| 743 |
+
"eval_loss": 0.12948854267597198,
|
| 744 |
+
"eval_roc_auc": 0.8746136435095113,
|
| 745 |
+
"eval_runtime": 457.7561,
|
| 746 |
+
"eval_samples_per_second": 6.305,
|
| 747 |
+
"eval_steps_per_second": 0.199,
|
| 748 |
+
"learning_rate": 1e-05,
|
| 749 |
+
"step": 12012
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 45.0,
|
| 753 |
+
"eval_accuracy": 0.2945252945252945,
|
| 754 |
+
"eval_f1_macro": 0.7217673828508766,
|
| 755 |
+
"eval_f1_micro": 0.8103943697164036,
|
| 756 |
+
"eval_loss": 0.12943118810653687,
|
| 757 |
+
"eval_roc_auc": 0.8749209258927392,
|
| 758 |
+
"eval_runtime": 454.0903,
|
| 759 |
+
"eval_samples_per_second": 6.356,
|
| 760 |
+
"eval_steps_per_second": 0.2,
|
| 761 |
+
"learning_rate": 1e-05,
|
| 762 |
+
"step": 12285
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 45.78754578754579,
|
| 766 |
+
"grad_norm": 0.35246723890304565,
|
| 767 |
+
"learning_rate": 1e-05,
|
| 768 |
+
"loss": 0.1083,
|
| 769 |
+
"step": 12500
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 46.0,
|
| 773 |
+
"eval_accuracy": 0.29764379764379767,
|
| 774 |
+
"eval_f1_macro": 0.7232663108413819,
|
| 775 |
+
"eval_f1_micro": 0.8113435070065285,
|
| 776 |
+
"eval_loss": 0.12941767275333405,
|
| 777 |
+
"eval_roc_auc": 0.8758867969983227,
|
| 778 |
+
"eval_runtime": 464.2204,
|
| 779 |
+
"eval_samples_per_second": 6.217,
|
| 780 |
+
"eval_steps_per_second": 0.196,
|
| 781 |
+
"learning_rate": 1e-05,
|
| 782 |
+
"step": 12558
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 47.0,
|
| 786 |
+
"eval_accuracy": 0.2945252945252945,
|
| 787 |
+
"eval_f1_macro": 0.7229077354567445,
|
| 788 |
+
"eval_f1_micro": 0.8107185952648442,
|
| 789 |
+
"eval_loss": 0.12936843931674957,
|
| 790 |
+
"eval_roc_auc": 0.8753446933561116,
|
| 791 |
+
"eval_runtime": 462.6765,
|
| 792 |
+
"eval_samples_per_second": 6.238,
|
| 793 |
+
"eval_steps_per_second": 0.197,
|
| 794 |
+
"learning_rate": 1e-05,
|
| 795 |
+
"step": 12831
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 47.61904761904762,
|
| 799 |
+
"grad_norm": 0.23883384466171265,
|
| 800 |
+
"learning_rate": 1e-05,
|
| 801 |
+
"loss": 0.109,
|
| 802 |
+
"step": 13000
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 48.0,
|
| 806 |
+
"eval_accuracy": 0.2955647955647956,
|
| 807 |
+
"eval_f1_macro": 0.7208766406208041,
|
| 808 |
+
"eval_f1_micro": 0.8102512730611904,
|
| 809 |
+
"eval_loss": 0.12944123148918152,
|
| 810 |
+
"eval_roc_auc": 0.8741709760601966,
|
| 811 |
+
"eval_runtime": 461.7262,
|
| 812 |
+
"eval_samples_per_second": 6.25,
|
| 813 |
+
"eval_steps_per_second": 0.197,
|
| 814 |
+
"learning_rate": 1e-05,
|
| 815 |
+
"step": 13104
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 49.0,
|
| 819 |
+
"eval_accuracy": 0.2959112959112959,
|
| 820 |
+
"eval_f1_macro": 0.7215165769975259,
|
| 821 |
+
"eval_f1_micro": 0.8111032502392942,
|
| 822 |
+
"eval_loss": 0.12932655215263367,
|
| 823 |
+
"eval_roc_auc": 0.875509186278476,
|
| 824 |
+
"eval_runtime": 467.4634,
|
| 825 |
+
"eval_samples_per_second": 6.174,
|
| 826 |
+
"eval_steps_per_second": 0.195,
|
| 827 |
+
"learning_rate": 1e-05,
|
| 828 |
+
"step": 13377
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 49.45054945054945,
|
| 832 |
+
"grad_norm": 0.37183043360710144,
|
| 833 |
+
"learning_rate": 1e-05,
|
| 834 |
+
"loss": 0.108,
|
| 835 |
+
"step": 13500
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 50.0,
|
| 839 |
+
"eval_accuracy": 0.2966042966042966,
|
| 840 |
+
"eval_f1_macro": 0.7210862927892402,
|
| 841 |
+
"eval_f1_micro": 0.8106959890041235,
|
| 842 |
+
"eval_loss": 0.1294257938861847,
|
| 843 |
+
"eval_roc_auc": 0.8750392620715779,
|
| 844 |
+
"eval_runtime": 461.0793,
|
| 845 |
+
"eval_samples_per_second": 6.259,
|
| 846 |
+
"eval_steps_per_second": 0.197,
|
| 847 |
+
"learning_rate": 1e-05,
|
| 848 |
+
"step": 13650
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 51.0,
|
| 852 |
+
"eval_accuracy": 0.29244629244629244,
|
| 853 |
+
"eval_f1_macro": 0.7224236625273444,
|
| 854 |
+
"eval_f1_micro": 0.8098573930447837,
|
| 855 |
+
"eval_loss": 0.12937645614147186,
|
| 856 |
+
"eval_roc_auc": 0.8742456236271018,
|
| 857 |
+
"eval_runtime": 450.9312,
|
| 858 |
+
"eval_samples_per_second": 6.4,
|
| 859 |
+
"eval_steps_per_second": 0.202,
|
| 860 |
+
"learning_rate": 1e-05,
|
| 861 |
+
"step": 13923
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 51.282051282051285,
|
| 865 |
+
"grad_norm": 0.2766432762145996,
|
| 866 |
+
"learning_rate": 1e-05,
|
| 867 |
+
"loss": 0.1084,
|
| 868 |
+
"step": 14000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 52.0,
|
| 872 |
+
"eval_accuracy": 0.2972972972972973,
|
| 873 |
+
"eval_f1_macro": 0.7223932851056244,
|
| 874 |
+
"eval_f1_micro": 0.8110019973368842,
|
| 875 |
+
"eval_loss": 0.12941104173660278,
|
| 876 |
+
"eval_roc_auc": 0.8754896692596356,
|
| 877 |
+
"eval_runtime": 461.8073,
|
| 878 |
+
"eval_samples_per_second": 6.249,
|
| 879 |
+
"eval_steps_per_second": 0.197,
|
| 880 |
+
"learning_rate": 1e-05,
|
| 881 |
+
"step": 14196
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 53.0,
|
| 885 |
+
"eval_accuracy": 0.29799029799029797,
|
| 886 |
+
"eval_f1_macro": 0.7225026360610024,
|
| 887 |
+
"eval_f1_micro": 0.8110783049860689,
|
| 888 |
+
"eval_loss": 0.12947481870651245,
|
| 889 |
+
"eval_roc_auc": 0.8757151813701134,
|
| 890 |
+
"eval_runtime": 469.6848,
|
| 891 |
+
"eval_samples_per_second": 6.145,
|
| 892 |
+
"eval_steps_per_second": 0.194,
|
| 893 |
+
"learning_rate": 1e-05,
|
| 894 |
+
"step": 14469
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 53.11355311355312,
|
| 898 |
+
"grad_norm": 0.3167434334754944,
|
| 899 |
+
"learning_rate": 1e-05,
|
| 900 |
+
"loss": 0.1086,
|
| 901 |
+
"step": 14500
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 54.0,
|
| 905 |
+
"eval_accuracy": 0.29625779625779625,
|
| 906 |
+
"eval_f1_macro": 0.7221711249170111,
|
| 907 |
+
"eval_f1_micro": 0.8104531646623112,
|
| 908 |
+
"eval_loss": 0.12942463159561157,
|
| 909 |
+
"eval_roc_auc": 0.8751730777279024,
|
| 910 |
+
"eval_runtime": 467.6515,
|
| 911 |
+
"eval_samples_per_second": 6.171,
|
| 912 |
+
"eval_steps_per_second": 0.195,
|
| 913 |
+
"learning_rate": 1e-05,
|
| 914 |
+
"step": 14742
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 54.94505494505494,
|
| 918 |
+
"grad_norm": 0.39026910066604614,
|
| 919 |
+
"learning_rate": 1e-05,
|
| 920 |
+
"loss": 0.1083,
|
| 921 |
+
"step": 15000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 55.0,
|
| 925 |
+
"eval_accuracy": 0.2955647955647956,
|
| 926 |
+
"eval_f1_macro": 0.7231230527181782,
|
| 927 |
+
"eval_f1_micro": 0.8107163657542226,
|
| 928 |
+
"eval_loss": 0.12934881448745728,
|
| 929 |
+
"eval_roc_auc": 0.875404478478429,
|
| 930 |
+
"eval_runtime": 485.1549,
|
| 931 |
+
"eval_samples_per_second": 5.949,
|
| 932 |
+
"eval_steps_per_second": 0.188,
|
| 933 |
+
"learning_rate": 1e-05,
|
| 934 |
+
"step": 15015
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 56.0,
|
| 938 |
+
"eval_accuracy": 0.2959112959112959,
|
| 939 |
+
"eval_f1_macro": 0.7226955143721722,
|
| 940 |
+
"eval_f1_micro": 0.810738813735692,
|
| 941 |
+
"eval_loss": 0.12935101985931396,
|
| 942 |
+
"eval_roc_auc": 0.875258268509109,
|
| 943 |
+
"eval_runtime": 477.6234,
|
| 944 |
+
"eval_samples_per_second": 6.042,
|
| 945 |
+
"eval_steps_per_second": 0.191,
|
| 946 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 947 |
+
"step": 15288
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 56.776556776556774,
|
| 951 |
+
"grad_norm": 0.2914769947528839,
|
| 952 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 953 |
+
"loss": 0.108,
|
| 954 |
+
"step": 15500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 57.0,
|
| 958 |
+
"eval_accuracy": 0.2955647955647956,
|
| 959 |
+
"eval_f1_macro": 0.7230703100391168,
|
| 960 |
+
"eval_f1_micro": 0.8110560712650376,
|
| 961 |
+
"eval_loss": 0.12934598326683044,
|
| 962 |
+
"eval_roc_auc": 0.8754097500855798,
|
| 963 |
+
"eval_runtime": 449.1576,
|
| 964 |
+
"eval_samples_per_second": 6.425,
|
| 965 |
+
"eval_steps_per_second": 0.203,
|
| 966 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 967 |
+
"step": 15561
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 58.0,
|
| 971 |
+
"eval_accuracy": 0.2966042966042966,
|
| 972 |
+
"eval_f1_macro": 0.7230017316798248,
|
| 973 |
+
"eval_f1_micro": 0.8112406328059951,
|
| 974 |
+
"eval_loss": 0.1293543428182602,
|
| 975 |
+
"eval_roc_auc": 0.875475423847946,
|
| 976 |
+
"eval_runtime": 441.9495,
|
| 977 |
+
"eval_samples_per_second": 6.53,
|
| 978 |
+
"eval_steps_per_second": 0.206,
|
| 979 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 980 |
+
"step": 15834
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 58.608058608058606,
|
| 984 |
+
"grad_norm": 0.25508466362953186,
|
| 985 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 986 |
+
"loss": 0.1089,
|
| 987 |
+
"step": 16000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 59.0,
|
| 991 |
+
"eval_accuracy": 0.2966042966042966,
|
| 992 |
+
"eval_f1_macro": 0.7227156089091311,
|
| 993 |
+
"eval_f1_micro": 0.8110088687179914,
|
| 994 |
+
"eval_loss": 0.12936049699783325,
|
| 995 |
+
"eval_roc_auc": 0.8753103138926834,
|
| 996 |
+
"eval_runtime": 445.121,
|
| 997 |
+
"eval_samples_per_second": 6.484,
|
| 998 |
+
"eval_steps_per_second": 0.204,
|
| 999 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1000 |
+
"step": 16107
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 59.0,
|
| 1004 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1005 |
+
"step": 16107,
|
| 1006 |
+
"total_flos": 2.151593295698903e+20,
|
| 1007 |
+
"train_loss": 0.11777938241923686,
|
| 1008 |
+
"train_runtime": 108362.28,
|
| 1009 |
+
"train_samples_per_second": 12.065,
|
| 1010 |
+
"train_steps_per_second": 0.378
|
| 1011 |
+
}
|
| 1012 |
+
],
|
| 1013 |
+
"logging_steps": 500,
|
| 1014 |
+
"max_steps": 40950,
|
| 1015 |
+
"num_input_tokens_seen": 0,
|
| 1016 |
+
"num_train_epochs": 150,
|
| 1017 |
+
"save_steps": 500,
|
| 1018 |
+
"stateful_callbacks": {
|
| 1019 |
+
"EarlyStoppingCallback": {
|
| 1020 |
+
"args": {
|
| 1021 |
+
"early_stopping_patience": 10,
|
| 1022 |
+
"early_stopping_threshold": 0.0
|
| 1023 |
+
},
|
| 1024 |
+
"attributes": {
|
| 1025 |
+
"early_stopping_patience_counter": 0
|
| 1026 |
+
}
|
| 1027 |
+
},
|
| 1028 |
+
"TrainerControl": {
|
| 1029 |
+
"args": {
|
| 1030 |
+
"should_epoch_stop": false,
|
| 1031 |
+
"should_evaluate": false,
|
| 1032 |
+
"should_log": false,
|
| 1033 |
+
"should_save": true,
|
| 1034 |
+
"should_training_stop": true
|
| 1035 |
+
},
|
| 1036 |
+
"attributes": {}
|
| 1037 |
+
}
|
| 1038 |
+
},
|
| 1039 |
+
"total_flos": 2.151593295698903e+20,
|
| 1040 |
+
"train_batch_size": 32,
|
| 1041 |
+
"trial_name": null,
|
| 1042 |
+
"trial_params": null
|
| 1043 |
+
}
|