End of training
Browse files- README.md +81 -83
- all_results.json +10 -10
- eval_results.json +6 -6
- model.safetensors +1 -1
- runs/Feb04_10-06-24_DESKTOP-SKBE9FB/events.out.tfevents.1738685186.DESKTOP-SKBE9FB.14636.0 +3 -0
- runs/Feb04_10-06-24_DESKTOP-SKBE9FB/events.out.tfevents.1738687878.DESKTOP-SKBE9FB.14636.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +966 -1224
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 1.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -67,86 +67,84 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| 1.
|
| 71 |
-
| 1.
|
| 72 |
-
| 1.
|
| 73 |
-
| 1.
|
| 74 |
-
| 1.
|
| 75 |
-
| 1.
|
| 76 |
-
|
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.0942 | 78.96 | 1599 | 1.6474 | 0.7059 |
|
| 149 |
-
| 0.1172 | 79.01 | 1600 | 1.6474 | 0.7059 |
|
| 150 |
|
| 151 |
|
| 152 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8068181818181818
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.0322
|
| 36 |
+
- Accuracy: 0.8068
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| 1.6093 | 0.97 | 15 | 1.6090 | 0.2045 |
|
| 71 |
+
| 1.6042 | 2.0 | 31 | 1.6055 | 0.2045 |
|
| 72 |
+
| 1.586 | 2.97 | 46 | 1.5730 | 0.1932 |
|
| 73 |
+
| 1.4855 | 4.0 | 62 | 1.4935 | 0.2614 |
|
| 74 |
+
| 1.3738 | 4.97 | 77 | 1.3273 | 0.5 |
|
| 75 |
+
| 1.1557 | 6.0 | 93 | 1.0828 | 0.625 |
|
| 76 |
+
| 1.0441 | 6.97 | 108 | 0.8971 | 0.6023 |
|
| 77 |
+
| 0.9358 | 8.0 | 124 | 0.7635 | 0.6818 |
|
| 78 |
+
| 0.7707 | 8.97 | 139 | 0.8718 | 0.6477 |
|
| 79 |
+
| 0.7161 | 10.0 | 155 | 0.6903 | 0.7727 |
|
| 80 |
+
| 0.6799 | 10.97 | 170 | 0.8108 | 0.7273 |
|
| 81 |
+
| 0.6402 | 12.0 | 186 | 0.7147 | 0.7273 |
|
| 82 |
+
| 0.5131 | 12.97 | 201 | 0.7521 | 0.75 |
|
| 83 |
+
| 0.5262 | 14.0 | 217 | 0.7967 | 0.7273 |
|
| 84 |
+
| 0.4757 | 14.97 | 232 | 0.7084 | 0.7614 |
|
| 85 |
+
| 0.4758 | 16.0 | 248 | 0.7529 | 0.7727 |
|
| 86 |
+
| 0.4184 | 16.97 | 263 | 0.7769 | 0.7727 |
|
| 87 |
+
| 0.398 | 18.0 | 279 | 0.8496 | 0.7386 |
|
| 88 |
+
| 0.3591 | 18.97 | 294 | 0.8204 | 0.7273 |
|
| 89 |
+
| 0.3536 | 20.0 | 310 | 0.8589 | 0.7614 |
|
| 90 |
+
| 0.2589 | 20.97 | 325 | 0.9754 | 0.7045 |
|
| 91 |
+
| 0.3218 | 22.0 | 341 | 1.0231 | 0.7159 |
|
| 92 |
+
| 0.3151 | 22.97 | 356 | 0.9173 | 0.7386 |
|
| 93 |
+
| 0.2708 | 24.0 | 372 | 0.9598 | 0.7273 |
|
| 94 |
+
| 0.2802 | 24.97 | 387 | 0.9050 | 0.7386 |
|
| 95 |
+
| 0.3114 | 26.0 | 403 | 0.8725 | 0.7727 |
|
| 96 |
+
| 0.2794 | 26.97 | 418 | 0.9579 | 0.7386 |
|
| 97 |
+
| 0.26 | 28.0 | 434 | 1.0064 | 0.7273 |
|
| 98 |
+
| 0.2961 | 28.97 | 449 | 1.1056 | 0.75 |
|
| 99 |
+
| 0.297 | 30.0 | 465 | 0.8761 | 0.7727 |
|
| 100 |
+
| 0.2044 | 30.97 | 480 | 1.0461 | 0.7614 |
|
| 101 |
+
| 0.1884 | 32.0 | 496 | 0.9889 | 0.75 |
|
| 102 |
+
| 0.2156 | 32.97 | 511 | 1.0186 | 0.7727 |
|
| 103 |
+
| 0.194 | 34.0 | 527 | 1.0900 | 0.7727 |
|
| 104 |
+
| 0.2085 | 34.97 | 542 | 1.0762 | 0.75 |
|
| 105 |
+
| 0.1909 | 36.0 | 558 | 1.0325 | 0.7841 |
|
| 106 |
+
| 0.1551 | 36.97 | 573 | 1.1497 | 0.7045 |
|
| 107 |
+
| 0.2106 | 38.0 | 589 | 1.0304 | 0.7727 |
|
| 108 |
+
| 0.1771 | 38.97 | 604 | 1.0794 | 0.7841 |
|
| 109 |
+
| 0.1567 | 40.0 | 620 | 1.0634 | 0.7955 |
|
| 110 |
+
| 0.1856 | 40.97 | 635 | 1.0716 | 0.7614 |
|
| 111 |
+
| 0.185 | 42.0 | 651 | 1.0322 | 0.8068 |
|
| 112 |
+
| 0.1239 | 42.97 | 666 | 1.1516 | 0.7614 |
|
| 113 |
+
| 0.1617 | 44.0 | 682 | 1.0322 | 0.7841 |
|
| 114 |
+
| 0.1221 | 44.97 | 697 | 1.0553 | 0.8068 |
|
| 115 |
+
| 0.1433 | 46.0 | 713 | 1.0597 | 0.7727 |
|
| 116 |
+
| 0.216 | 46.97 | 728 | 1.1586 | 0.75 |
|
| 117 |
+
| 0.1807 | 48.0 | 744 | 1.0873 | 0.7727 |
|
| 118 |
+
| 0.185 | 48.97 | 759 | 1.2490 | 0.7727 |
|
| 119 |
+
| 0.1554 | 50.0 | 775 | 1.2223 | 0.7614 |
|
| 120 |
+
| 0.1359 | 50.97 | 790 | 1.2345 | 0.75 |
|
| 121 |
+
| 0.0929 | 52.0 | 806 | 1.1833 | 0.7614 |
|
| 122 |
+
| 0.1379 | 52.97 | 821 | 1.2581 | 0.7386 |
|
| 123 |
+
| 0.145 | 54.0 | 837 | 1.3023 | 0.75 |
|
| 124 |
+
| 0.134 | 54.97 | 852 | 1.2469 | 0.75 |
|
| 125 |
+
| 0.1974 | 56.0 | 868 | 1.2671 | 0.7386 |
|
| 126 |
+
| 0.122 | 56.97 | 883 | 1.2676 | 0.7273 |
|
| 127 |
+
| 0.1487 | 58.0 | 899 | 1.2846 | 0.7273 |
|
| 128 |
+
| 0.1282 | 58.97 | 914 | 1.1780 | 0.75 |
|
| 129 |
+
| 0.0989 | 60.0 | 930 | 1.2320 | 0.75 |
|
| 130 |
+
| 0.0997 | 60.97 | 945 | 1.2792 | 0.7386 |
|
| 131 |
+
| 0.1058 | 62.0 | 961 | 1.2126 | 0.7614 |
|
| 132 |
+
| 0.1105 | 62.97 | 976 | 1.2561 | 0.7386 |
|
| 133 |
+
| 0.0957 | 64.0 | 992 | 1.1702 | 0.7614 |
|
| 134 |
+
| 0.1326 | 64.97 | 1007 | 1.1839 | 0.75 |
|
| 135 |
+
| 0.0838 | 66.0 | 1023 | 1.2728 | 0.7386 |
|
| 136 |
+
| 0.1163 | 66.97 | 1038 | 1.2736 | 0.75 |
|
| 137 |
+
| 0.0926 | 68.0 | 1054 | 1.2641 | 0.75 |
|
| 138 |
+
| 0.102 | 68.97 | 1069 | 1.3310 | 0.75 |
|
| 139 |
+
| 0.0996 | 70.0 | 1085 | 1.3120 | 0.7273 |
|
| 140 |
+
| 0.081 | 70.97 | 1100 | 1.3358 | 0.7273 |
|
| 141 |
+
| 0.1305 | 72.0 | 1116 | 1.3440 | 0.7273 |
|
| 142 |
+
| 0.1131 | 72.97 | 1131 | 1.3126 | 0.7273 |
|
| 143 |
+
| 0.0883 | 74.0 | 1147 | 1.2848 | 0.7386 |
|
| 144 |
+
| 0.0873 | 74.97 | 1162 | 1.2802 | 0.7386 |
|
| 145 |
+
| 0.0991 | 76.0 | 1178 | 1.2711 | 0.75 |
|
| 146 |
+
| 0.0881 | 76.97 | 1193 | 1.2746 | 0.75 |
|
| 147 |
+
| 0.0895 | 77.42 | 1200 | 1.2752 | 0.75 |
|
|
|
|
|
|
|
| 148 |
|
| 149 |
|
| 150 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 1.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 77.42,
|
| 3 |
+
"eval_accuracy": 0.8068181818181818,
|
| 4 |
+
"eval_loss": 1.0321924686431885,
|
| 5 |
+
"eval_runtime": 1.2083,
|
| 6 |
+
"eval_samples_per_second": 72.831,
|
| 7 |
+
"eval_steps_per_second": 4.966,
|
| 8 |
+
"train_loss": 0.34467112536231675,
|
| 9 |
+
"train_runtime": 2690.4819,
|
| 10 |
+
"train_samples_per_second": 29.14,
|
| 11 |
+
"train_steps_per_second": 0.446
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 1.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 77.42,
|
| 3 |
+
"eval_accuracy": 0.8068181818181818,
|
| 4 |
+
"eval_loss": 1.0321924686431885,
|
| 5 |
+
"eval_runtime": 1.2083,
|
| 6 |
+
"eval_samples_per_second": 72.831,
|
| 7 |
+
"eval_steps_per_second": 4.966
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110359372
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bae448fc19dc668baef35b6daa0e185c54f7072d9c1559745215cb0a98c90f4d
|
| 3 |
size 110359372
|
runs/Feb04_10-06-24_DESKTOP-SKBE9FB/events.out.tfevents.1738685186.DESKTOP-SKBE9FB.14636.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cb5df47b1b3abc627ba6041f137781309aba3ab74c99c197c2d4d25a6bc130e
|
| 3 |
+
size 49138
|
runs/Feb04_10-06-24_DESKTOP-SKBE9FB/events.out.tfevents.1738687878.DESKTOP-SKBE9FB.14636.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6d844049c71ea4c8cc8a010e882ce8ac192ff2bed9c8b1ecd23241a3f46c230
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 77.42,
|
| 3 |
+
"train_loss": 0.34467112536231675,
|
| 4 |
+
"train_runtime": 2690.4819,
|
| 5 |
+
"train_samples_per_second": 29.14,
|
| 6 |
+
"train_steps_per_second": 0.446
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1709 +1,1451 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/Modelos/Swin-DA2-final-AMD-Wet\\checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"learning_rate":
|
| 14 |
"loss": 1.6093,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
|
|
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch":
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"eval_runtime": 0.4261,
|
| 28 |
-
"eval_samples_per_second": 199.486,
|
| 29 |
-
"eval_steps_per_second": 14.081,
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 1.
|
| 34 |
-
"learning_rate":
|
| 35 |
-
"loss": 1.
|
| 36 |
"step": 30
|
| 37 |
},
|
| 38 |
{
|
| 39 |
-
"epoch":
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
|
|
|
|
|
|
|
|
|
| 43 |
},
|
| 44 |
{
|
| 45 |
-
"epoch":
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"eval_runtime": 0.4061,
|
| 49 |
-
"eval_samples_per_second": 209.312,
|
| 50 |
-
"eval_steps_per_second": 14.775,
|
| 51 |
"step": 40
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 2.
|
| 55 |
-
"
|
| 56 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
"step": 50
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch":
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 60
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch":
|
| 67 |
-
"eval_accuracy": 0.
|
| 68 |
-
"eval_loss": 1.
|
| 69 |
-
"eval_runtime":
|
| 70 |
-
"eval_samples_per_second":
|
| 71 |
-
"eval_steps_per_second":
|
| 72 |
-
"step":
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"learning_rate": 2.
|
| 77 |
-
"loss": 1.
|
| 78 |
"step": 70
|
| 79 |
},
|
| 80 |
{
|
| 81 |
-
"epoch":
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
|
|
|
|
|
|
|
|
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"epoch":
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"eval_samples_per_second": 197.171,
|
| 92 |
-
"eval_steps_per_second": 13.918,
|
| 93 |
-
"step": 81
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch":
|
| 97 |
-
"learning_rate":
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 90
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"
|
| 104 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
"step": 100
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"eval_accuracy": 0.
|
| 110 |
-
"eval_loss": 0.
|
| 111 |
-
"eval_runtime":
|
| 112 |
-
"eval_samples_per_second":
|
| 113 |
-
"eval_steps_per_second":
|
| 114 |
-
"step":
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch":
|
| 118 |
-
"learning_rate":
|
| 119 |
-
"loss":
|
| 120 |
"step": 110
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"epoch":
|
| 124 |
-
"learning_rate":
|
| 125 |
-
"loss":
|
| 126 |
"step": 120
|
| 127 |
},
|
| 128 |
{
|
| 129 |
-
"epoch":
|
| 130 |
-
"eval_accuracy": 0.
|
| 131 |
-
"eval_loss": 0.
|
| 132 |
-
"eval_runtime":
|
| 133 |
-
"eval_samples_per_second":
|
| 134 |
-
"eval_steps_per_second":
|
| 135 |
-
"step":
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"learning_rate": 4.
|
| 140 |
-
"loss":
|
| 141 |
"step": 130
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"
|
| 146 |
-
"
|
| 147 |
-
"
|
|
|
|
|
|
|
|
|
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"eval_samples_per_second": 202.818,
|
| 155 |
-
"eval_steps_per_second": 14.317,
|
| 156 |
-
"step": 141
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"learning_rate": 4.
|
| 161 |
-
"loss": 0.
|
| 162 |
"step": 150
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch":
|
| 166 |
-
"
|
| 167 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
"step": 160
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"epoch":
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
"
|
| 175 |
-
"eval_samples_per_second": 200.9,
|
| 176 |
-
"eval_steps_per_second": 14.181,
|
| 177 |
-
"step": 162
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch":
|
| 181 |
-
"
|
| 182 |
-
"
|
|
|
|
|
|
|
|
|
|
| 183 |
"step": 170
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch":
|
| 187 |
-
"learning_rate": 4.
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 180
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"eval_accuracy": 0.
|
| 194 |
-
"eval_loss": 0.
|
| 195 |
-
"eval_runtime":
|
| 196 |
-
"eval_samples_per_second":
|
| 197 |
-
"eval_steps_per_second":
|
| 198 |
-
"step":
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"learning_rate": 4.
|
| 203 |
-
"loss": 0.
|
| 204 |
"step": 190
|
| 205 |
},
|
| 206 |
{
|
| 207 |
-
"epoch": 9
|
| 208 |
-
"learning_rate": 4.
|
| 209 |
-
"loss": 0.
|
| 210 |
"step": 200
|
| 211 |
},
|
| 212 |
{
|
| 213 |
-
"epoch":
|
| 214 |
-
"eval_accuracy": 0.
|
| 215 |
-
"eval_loss": 0.
|
| 216 |
-
"eval_runtime":
|
| 217 |
-
"eval_samples_per_second":
|
| 218 |
-
"eval_steps_per_second":
|
| 219 |
-
"step":
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate": 4.
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 210
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"
|
| 230 |
-
"
|
| 231 |
-
"
|
|
|
|
|
|
|
|
|
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
"eval_samples_per_second": 199.485,
|
| 239 |
-
"eval_steps_per_second": 14.081,
|
| 240 |
-
"step": 222
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"learning_rate": 4.
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 230
|
| 247 |
},
|
| 248 |
{
|
| 249 |
-
"epoch":
|
| 250 |
-
"
|
| 251 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
"step": 240
|
| 253 |
},
|
| 254 |
{
|
| 255 |
-
"epoch":
|
| 256 |
-
"eval_accuracy": 0.
|
| 257 |
-
"eval_loss": 0.
|
| 258 |
-
"eval_runtime":
|
| 259 |
-
"eval_samples_per_second":
|
| 260 |
-
"eval_steps_per_second":
|
| 261 |
-
"step":
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"learning_rate": 4.
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 250
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"learning_rate": 4.
|
| 272 |
-
"loss": 0.
|
| 273 |
"step": 260
|
| 274 |
},
|
| 275 |
{
|
| 276 |
-
"epoch":
|
| 277 |
-
"eval_accuracy": 0.
|
| 278 |
-
"eval_loss": 0.
|
| 279 |
-
"eval_runtime":
|
| 280 |
-
"eval_samples_per_second":
|
| 281 |
-
"eval_steps_per_second":
|
| 282 |
"step": 263
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch":
|
| 286 |
-
"learning_rate": 4.
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 270
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch":
|
| 292 |
-
"
|
| 293 |
-
"
|
| 294 |
-
"
|
|
|
|
|
|
|
|
|
|
| 295 |
},
|
| 296 |
{
|
| 297 |
-
"epoch":
|
| 298 |
-
"
|
| 299 |
-
"
|
| 300 |
-
"
|
| 301 |
-
"eval_samples_per_second": 203.791,
|
| 302 |
-
"eval_steps_per_second": 14.385,
|
| 303 |
-
"step": 283
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch":
|
| 307 |
-
"learning_rate": 4.
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 290
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch":
|
| 313 |
-
"
|
| 314 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 315 |
"step": 300
|
| 316 |
},
|
| 317 |
{
|
| 318 |
-
"epoch":
|
| 319 |
-
"
|
| 320 |
-
"
|
| 321 |
-
"
|
| 322 |
-
"eval_samples_per_second": 199.486,
|
| 323 |
-
"eval_steps_per_second": 14.081,
|
| 324 |
-
"step": 303
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch":
|
| 328 |
-
"
|
| 329 |
-
"
|
|
|
|
|
|
|
|
|
|
| 330 |
"step": 310
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"epoch":
|
| 334 |
-
"learning_rate": 4.
|
| 335 |
-
"loss": 0.
|
| 336 |
"step": 320
|
| 337 |
},
|
| 338 |
{
|
| 339 |
-
"epoch":
|
| 340 |
-
"eval_accuracy": 0.
|
| 341 |
-
"eval_loss": 0.
|
| 342 |
-
"eval_runtime":
|
| 343 |
-
"eval_samples_per_second":
|
| 344 |
-
"eval_steps_per_second":
|
| 345 |
-
"step":
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch":
|
| 349 |
-
"learning_rate": 4.
|
| 350 |
-
"loss": 0.
|
| 351 |
"step": 330
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch":
|
| 355 |
-
"learning_rate":
|
| 356 |
-
"loss": 0.
|
| 357 |
"step": 340
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch":
|
| 361 |
-
"eval_accuracy": 0.
|
| 362 |
-
"eval_loss":
|
| 363 |
-
"eval_runtime":
|
| 364 |
-
"eval_samples_per_second":
|
| 365 |
-
"eval_steps_per_second":
|
| 366 |
-
"step":
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch":
|
| 370 |
-
"learning_rate":
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 350
|
| 373 |
},
|
| 374 |
{
|
| 375 |
-
"epoch":
|
| 376 |
-
"
|
| 377 |
-
"
|
| 378 |
-
"
|
|
|
|
|
|
|
|
|
|
| 379 |
},
|
| 380 |
{
|
| 381 |
-
"epoch":
|
| 382 |
-
"
|
| 383 |
-
"
|
| 384 |
-
"
|
| 385 |
-
"eval_samples_per_second": 201.855,
|
| 386 |
-
"eval_steps_per_second": 14.249,
|
| 387 |
-
"step": 364
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch":
|
| 391 |
-
"learning_rate":
|
| 392 |
-
"loss": 0.
|
| 393 |
"step": 370
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch":
|
| 397 |
-
"
|
| 398 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 399 |
"step": 380
|
| 400 |
},
|
| 401 |
{
|
| 402 |
-
"epoch":
|
| 403 |
-
"eval_accuracy": 0.
|
| 404 |
-
"eval_loss":
|
| 405 |
-
"eval_runtime":
|
| 406 |
-
"eval_samples_per_second":
|
| 407 |
-
"eval_steps_per_second":
|
| 408 |
-
"step":
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch":
|
| 412 |
-
"learning_rate":
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 390
|
| 415 |
},
|
| 416 |
{
|
| 417 |
-
"epoch":
|
| 418 |
-
"learning_rate":
|
| 419 |
-
"loss": 0.
|
| 420 |
"step": 400
|
| 421 |
},
|
| 422 |
{
|
| 423 |
-
"epoch":
|
| 424 |
-
"eval_accuracy": 0.
|
| 425 |
-
"eval_loss":
|
| 426 |
-
"eval_runtime":
|
| 427 |
-
"eval_samples_per_second":
|
| 428 |
-
"eval_steps_per_second":
|
| 429 |
-
"step":
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch":
|
| 433 |
-
"learning_rate":
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 410
|
| 436 |
},
|
| 437 |
{
|
| 438 |
-
"epoch":
|
| 439 |
-
"
|
| 440 |
-
"
|
| 441 |
-
"
|
|
|
|
|
|
|
|
|
|
| 442 |
},
|
| 443 |
{
|
| 444 |
-
"epoch":
|
| 445 |
-
"
|
| 446 |
-
"
|
| 447 |
-
"
|
| 448 |
-
"eval_samples_per_second": 185.144,
|
| 449 |
-
"eval_steps_per_second": 13.069,
|
| 450 |
-
"step": 425
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch":
|
| 454 |
-
"learning_rate":
|
| 455 |
-
"loss": 0.
|
| 456 |
"step": 430
|
| 457 |
},
|
| 458 |
{
|
| 459 |
-
"epoch":
|
| 460 |
-
"
|
| 461 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 462 |
"step": 440
|
| 463 |
},
|
| 464 |
{
|
| 465 |
-
"epoch":
|
| 466 |
-
"eval_accuracy": 0.
|
| 467 |
-
"eval_loss": 1.
|
| 468 |
-
"eval_runtime":
|
| 469 |
-
"eval_samples_per_second":
|
| 470 |
-
"eval_steps_per_second":
|
| 471 |
-
"step":
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch":
|
| 475 |
-
"learning_rate": 3.
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 450
|
| 478 |
},
|
| 479 |
{
|
| 480 |
-
"epoch":
|
| 481 |
-
"learning_rate": 3.
|
| 482 |
-
"loss": 0.
|
| 483 |
"step": 460
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch":
|
| 487 |
-
"eval_accuracy": 0.
|
| 488 |
-
"eval_loss": 0.
|
| 489 |
-
"eval_runtime":
|
| 490 |
-
"eval_samples_per_second":
|
| 491 |
-
"eval_steps_per_second":
|
| 492 |
"step": 465
|
| 493 |
},
|
| 494 |
{
|
| 495 |
-
"epoch":
|
| 496 |
-
"learning_rate": 3.
|
| 497 |
-
"loss": 0.
|
| 498 |
"step": 470
|
| 499 |
},
|
| 500 |
{
|
| 501 |
-
"epoch":
|
| 502 |
-
"learning_rate": 3.
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 480
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"epoch":
|
| 508 |
-
"eval_accuracy": 0.
|
| 509 |
-
"eval_loss": 1.
|
| 510 |
-
"eval_runtime":
|
| 511 |
-
"eval_samples_per_second":
|
| 512 |
-
"eval_steps_per_second":
|
| 513 |
-
"step":
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch":
|
| 517 |
-
"learning_rate": 3.
|
| 518 |
-
"loss": 0.
|
| 519 |
"step": 490
|
| 520 |
},
|
| 521 |
{
|
| 522 |
-
"epoch":
|
| 523 |
-
"
|
| 524 |
-
"
|
| 525 |
-
"
|
|
|
|
|
|
|
|
|
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch":
|
| 529 |
-
"
|
| 530 |
-
"
|
| 531 |
-
"
|
| 532 |
-
"eval_samples_per_second": 202.818,
|
| 533 |
-
"eval_steps_per_second": 14.317,
|
| 534 |
-
"step": 506
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"epoch":
|
| 538 |
-
"learning_rate": 3.
|
| 539 |
-
"loss": 0.
|
| 540 |
"step": 510
|
| 541 |
},
|
| 542 |
{
|
| 543 |
-
"epoch":
|
| 544 |
-
"
|
| 545 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 546 |
"step": 520
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"epoch":
|
| 550 |
-
"eval_accuracy": 0.
|
| 551 |
-
"eval_loss": 1.
|
| 552 |
-
"eval_runtime":
|
| 553 |
-
"eval_samples_per_second":
|
| 554 |
-
"eval_steps_per_second":
|
| 555 |
-
"step":
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch":
|
| 559 |
-
"learning_rate": 3.
|
| 560 |
-
"loss": 0.
|
| 561 |
"step": 530
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"epoch":
|
| 565 |
-
"learning_rate": 3.
|
| 566 |
-
"loss": 0.
|
| 567 |
"step": 540
|
| 568 |
},
|
| 569 |
{
|
| 570 |
-
"epoch":
|
| 571 |
-
"eval_accuracy": 0.
|
| 572 |
-
"eval_loss": 1.
|
| 573 |
-
"eval_runtime":
|
| 574 |
-
"eval_samples_per_second":
|
| 575 |
-
"eval_steps_per_second":
|
| 576 |
-
"step":
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch":
|
| 580 |
-
"learning_rate": 3.
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 550
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch":
|
| 586 |
-
"
|
| 587 |
-
"
|
| 588 |
-
"
|
|
|
|
|
|
|
|
|
|
| 589 |
},
|
| 590 |
{
|
| 591 |
-
"epoch":
|
| 592 |
-
"
|
| 593 |
-
"
|
| 594 |
-
"
|
| 595 |
-
"eval_samples_per_second": 187.595,
|
| 596 |
-
"eval_steps_per_second": 13.242,
|
| 597 |
-
"step": 567
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
-
"learning_rate":
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 570
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch":
|
| 607 |
-
"
|
| 608 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 609 |
"step": 580
|
| 610 |
},
|
| 611 |
{
|
| 612 |
-
"epoch":
|
| 613 |
-
"eval_accuracy": 0.
|
| 614 |
-
"eval_loss": 1.
|
| 615 |
-
"eval_runtime":
|
| 616 |
-
"eval_samples_per_second":
|
| 617 |
-
"eval_steps_per_second":
|
| 618 |
-
"step":
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch":
|
| 622 |
-
"learning_rate":
|
| 623 |
-
"loss": 0.
|
| 624 |
"step": 590
|
| 625 |
},
|
| 626 |
{
|
| 627 |
-
"epoch":
|
| 628 |
-
"learning_rate":
|
| 629 |
-
"loss": 0.
|
| 630 |
"step": 600
|
| 631 |
},
|
| 632 |
{
|
| 633 |
-
"epoch":
|
| 634 |
-
"eval_accuracy": 0.
|
| 635 |
-
"eval_loss": 1.
|
| 636 |
-
"eval_runtime":
|
| 637 |
-
"eval_samples_per_second":
|
| 638 |
-
"eval_steps_per_second":
|
| 639 |
-
"step":
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"learning_rate":
|
| 644 |
-
"loss": 0.
|
| 645 |
"step": 610
|
| 646 |
},
|
| 647 |
{
|
| 648 |
-
"epoch":
|
| 649 |
-
"learning_rate":
|
| 650 |
-
"loss": 0.
|
| 651 |
"step": 620
|
| 652 |
},
|
| 653 |
{
|
| 654 |
-
"epoch":
|
| 655 |
-
"eval_accuracy": 0.
|
| 656 |
-
"eval_loss": 1.
|
| 657 |
-
"eval_runtime":
|
| 658 |
-
"eval_samples_per_second":
|
| 659 |
-
"eval_steps_per_second":
|
| 660 |
-
"step":
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch":
|
| 664 |
-
"learning_rate":
|
| 665 |
-
"loss": 0.
|
| 666 |
"step": 630
|
| 667 |
},
|
| 668 |
{
|
| 669 |
-
"epoch":
|
| 670 |
-
"
|
| 671 |
-
"
|
| 672 |
-
"
|
|
|
|
|
|
|
|
|
|
| 673 |
},
|
| 674 |
{
|
| 675 |
-
"epoch":
|
| 676 |
-
"
|
| 677 |
-
"
|
| 678 |
-
"
|
| 679 |
-
"eval_samples_per_second": 182.755,
|
| 680 |
-
"eval_steps_per_second": 12.9,
|
| 681 |
-
"step": 648
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch":
|
| 685 |
-
"learning_rate":
|
| 686 |
-
"loss": 0.
|
| 687 |
"step": 650
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"epoch":
|
| 691 |
-
"
|
| 692 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 693 |
"step": 660
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch":
|
| 697 |
-
"eval_accuracy": 0.
|
| 698 |
-
"eval_loss": 1.
|
| 699 |
-
"eval_runtime":
|
| 700 |
-
"eval_samples_per_second":
|
| 701 |
-
"eval_steps_per_second":
|
| 702 |
-
"step":
|
| 703 |
},
|
| 704 |
{
|
| 705 |
-
"epoch":
|
| 706 |
-
"learning_rate":
|
| 707 |
-
"loss": 0.
|
| 708 |
"step": 670
|
| 709 |
},
|
| 710 |
{
|
| 711 |
-
"epoch":
|
| 712 |
-
"learning_rate":
|
| 713 |
-
"loss": 0.
|
| 714 |
"step": 680
|
| 715 |
},
|
| 716 |
{
|
| 717 |
-
"epoch":
|
| 718 |
-
"eval_accuracy": 0.
|
| 719 |
-
"eval_loss": 1.
|
| 720 |
-
"eval_runtime":
|
| 721 |
-
"eval_samples_per_second":
|
| 722 |
-
"eval_steps_per_second":
|
| 723 |
-
"step":
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"epoch":
|
| 727 |
-
"learning_rate":
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 690
|
| 730 |
},
|
| 731 |
{
|
| 732 |
-
"epoch":
|
| 733 |
-
"
|
| 734 |
-
"
|
| 735 |
-
"
|
|
|
|
|
|
|
|
|
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch":
|
| 739 |
-
"
|
| 740 |
-
"
|
| 741 |
-
"
|
| 742 |
-
"eval_samples_per_second": 202.335,
|
| 743 |
-
"eval_steps_per_second": 14.283,
|
| 744 |
-
"step": 708
|
| 745 |
},
|
| 746 |
{
|
| 747 |
-
"epoch":
|
| 748 |
-
"learning_rate":
|
| 749 |
-
"loss": 0.
|
| 750 |
"step": 710
|
| 751 |
},
|
| 752 |
{
|
| 753 |
-
"epoch":
|
| 754 |
-
"
|
| 755 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 756 |
"step": 720
|
| 757 |
},
|
| 758 |
{
|
| 759 |
-
"epoch":
|
| 760 |
-
"eval_accuracy": 0.
|
| 761 |
-
"eval_loss": 1.
|
| 762 |
-
"eval_runtime":
|
| 763 |
-
"eval_samples_per_second":
|
| 764 |
-
"eval_steps_per_second":
|
| 765 |
-
"step":
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch":
|
| 769 |
-
"learning_rate":
|
| 770 |
-
"loss": 0.
|
| 771 |
"step": 730
|
| 772 |
},
|
| 773 |
{
|
| 774 |
-
"epoch":
|
| 775 |
-
"learning_rate": 2.
|
| 776 |
-
"loss": 0.
|
| 777 |
"step": 740
|
| 778 |
},
|
| 779 |
{
|
| 780 |
-
"epoch":
|
| 781 |
-
"eval_accuracy": 0.
|
| 782 |
-
"eval_loss": 1.
|
| 783 |
-
"eval_runtime":
|
| 784 |
-
"eval_samples_per_second":
|
| 785 |
-
"eval_steps_per_second":
|
| 786 |
-
"step":
|
| 787 |
},
|
| 788 |
{
|
| 789 |
-
"epoch":
|
| 790 |
-
"learning_rate": 2.
|
| 791 |
-
"loss": 0.
|
| 792 |
"step": 750
|
| 793 |
},
|
| 794 |
{
|
| 795 |
-
"epoch":
|
| 796 |
-
"
|
| 797 |
-
"
|
| 798 |
-
"
|
|
|
|
|
|
|
|
|
|
| 799 |
},
|
| 800 |
{
|
| 801 |
-
"epoch":
|
| 802 |
-
"
|
| 803 |
-
"
|
| 804 |
-
"
|
| 805 |
-
"eval_samples_per_second": 182.755,
|
| 806 |
-
"eval_steps_per_second": 12.9,
|
| 807 |
-
"step": 769
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch":
|
| 811 |
-
"learning_rate":
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 770
|
| 814 |
},
|
| 815 |
{
|
| 816 |
-
"epoch":
|
| 817 |
-
"
|
| 818 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 819 |
"step": 780
|
| 820 |
},
|
| 821 |
{
|
| 822 |
-
"epoch":
|
| 823 |
-
"
|
| 824 |
-
"
|
| 825 |
-
"
|
| 826 |
-
"eval_samples_per_second": 199.955,
|
| 827 |
-
"eval_steps_per_second": 14.114,
|
| 828 |
-
"step": 789
|
| 829 |
},
|
| 830 |
{
|
| 831 |
-
"epoch":
|
| 832 |
-
"
|
| 833 |
-
"
|
|
|
|
|
|
|
|
|
|
| 834 |
"step": 790
|
| 835 |
},
|
| 836 |
{
|
| 837 |
-
"epoch":
|
| 838 |
-
"learning_rate":
|
| 839 |
-
"loss": 0.
|
| 840 |
"step": 800
|
| 841 |
},
|
| 842 |
{
|
| 843 |
-
"epoch":
|
| 844 |
-
"
|
| 845 |
-
"
|
| 846 |
-
"
|
|
|
|
|
|
|
|
|
|
| 847 |
},
|
| 848 |
{
|
| 849 |
-
"epoch":
|
| 850 |
-
"
|
| 851 |
-
"
|
| 852 |
-
"eval_runtime": 0.4701,
|
| 853 |
-
"eval_samples_per_second": 180.81,
|
| 854 |
-
"eval_steps_per_second": 12.763,
|
| 855 |
"step": 810
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch":
|
| 859 |
-
"learning_rate":
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 820
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch":
|
| 865 |
-
"
|
| 866 |
-
"
|
| 867 |
-
"
|
|
|
|
|
|
|
|
|
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch":
|
| 871 |
-
"
|
| 872 |
-
"
|
| 873 |
-
"eval_runtime": 0.4201,
|
| 874 |
-
"eval_samples_per_second": 202.335,
|
| 875 |
-
"eval_steps_per_second": 14.282,
|
| 876 |
"step": 830
|
| 877 |
},
|
| 878 |
{
|
| 879 |
-
"epoch":
|
| 880 |
-
"
|
| 881 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 882 |
"step": 840
|
| 883 |
},
|
| 884 |
{
|
| 885 |
-
"epoch":
|
| 886 |
-
"learning_rate":
|
| 887 |
-
"loss": 0.
|
| 888 |
"step": 850
|
| 889 |
},
|
| 890 |
{
|
| 891 |
-
"epoch":
|
| 892 |
-
"eval_accuracy": 0.
|
| 893 |
-
"eval_loss": 1.
|
| 894 |
-
"eval_runtime":
|
| 895 |
-
"eval_samples_per_second":
|
| 896 |
-
"eval_steps_per_second":
|
| 897 |
-
"step":
|
| 898 |
},
|
| 899 |
{
|
| 900 |
-
"epoch":
|
| 901 |
-
"learning_rate":
|
| 902 |
-
"loss": 0.
|
| 903 |
"step": 860
|
| 904 |
},
|
| 905 |
{
|
| 906 |
-
"epoch":
|
| 907 |
-
"
|
| 908 |
-
"
|
| 909 |
-
"
|
|
|
|
|
|
|
|
|
|
| 910 |
},
|
| 911 |
{
|
| 912 |
-
"epoch":
|
| 913 |
-
"
|
| 914 |
-
"
|
| 915 |
-
"eval_runtime": 0.4591,
|
| 916 |
-
"eval_samples_per_second": 185.143,
|
| 917 |
-
"eval_steps_per_second": 13.069,
|
| 918 |
"step": 870
|
| 919 |
},
|
| 920 |
{
|
| 921 |
-
"epoch":
|
| 922 |
-
"learning_rate":
|
| 923 |
-
"loss": 0.
|
| 924 |
"step": 880
|
| 925 |
},
|
| 926 |
{
|
| 927 |
-
"epoch":
|
| 928 |
-
"
|
| 929 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 930 |
"step": 890
|
| 931 |
},
|
| 932 |
{
|
| 933 |
-
"epoch":
|
| 934 |
-
"eval_accuracy": 0.
|
| 935 |
-
"eval_loss": 1.
|
| 936 |
-
"eval_runtime":
|
| 937 |
-
"eval_samples_per_second":
|
| 938 |
-
"eval_steps_per_second":
|
| 939 |
-
"step":
|
| 940 |
},
|
| 941 |
{
|
| 942 |
-
"epoch":
|
| 943 |
-
"learning_rate":
|
| 944 |
-
"loss": 0.
|
| 945 |
"step": 900
|
| 946 |
},
|
| 947 |
{
|
| 948 |
-
"epoch":
|
| 949 |
-
"learning_rate":
|
| 950 |
-
"loss": 0.
|
| 951 |
"step": 910
|
| 952 |
},
|
| 953 |
{
|
| 954 |
-
"epoch":
|
| 955 |
-
"eval_accuracy": 0.
|
| 956 |
-
"eval_loss": 1.
|
| 957 |
-
"eval_runtime":
|
| 958 |
-
"eval_samples_per_second":
|
| 959 |
-
"eval_steps_per_second":
|
| 960 |
-
"step":
|
| 961 |
},
|
| 962 |
{
|
| 963 |
-
"epoch":
|
| 964 |
-
"learning_rate":
|
| 965 |
-
"loss": 0.
|
| 966 |
"step": 920
|
| 967 |
},
|
| 968 |
{
|
| 969 |
-
"epoch":
|
| 970 |
-
"learning_rate":
|
| 971 |
-
"loss": 0.
|
| 972 |
"step": 930
|
| 973 |
},
|
| 974 |
{
|
| 975 |
-
"epoch":
|
| 976 |
-
"eval_accuracy": 0.
|
| 977 |
-
"eval_loss": 1.
|
| 978 |
-
"eval_runtime":
|
| 979 |
-
"eval_samples_per_second":
|
| 980 |
-
"eval_steps_per_second":
|
| 981 |
-
"step":
|
| 982 |
},
|
| 983 |
{
|
| 984 |
-
"epoch":
|
| 985 |
-
"learning_rate":
|
| 986 |
-
"loss": 0.
|
| 987 |
"step": 940
|
| 988 |
},
|
| 989 |
{
|
| 990 |
-
"epoch":
|
| 991 |
-
"
|
| 992 |
-
"
|
| 993 |
-
"
|
|
|
|
|
|
|
|
|
|
| 994 |
},
|
| 995 |
{
|
| 996 |
-
"epoch":
|
| 997 |
-
"
|
| 998 |
-
"
|
| 999 |
-
"
|
| 1000 |
-
"eval_samples_per_second": 179.285,
|
| 1001 |
-
"eval_steps_per_second": 12.655,
|
| 1002 |
-
"step": 951
|
| 1003 |
},
|
| 1004 |
{
|
| 1005 |
-
"epoch":
|
| 1006 |
-
"learning_rate":
|
| 1007 |
-
"loss": 0.
|
| 1008 |
"step": 960
|
| 1009 |
},
|
| 1010 |
{
|
| 1011 |
-
"epoch":
|
| 1012 |
-
"
|
| 1013 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1014 |
"step": 970
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
-
"epoch":
|
| 1018 |
-
"eval_accuracy": 0.
|
| 1019 |
-
"eval_loss": 1.
|
| 1020 |
-
"eval_runtime":
|
| 1021 |
-
"eval_samples_per_second":
|
| 1022 |
-
"eval_steps_per_second":
|
| 1023 |
-
"step":
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
-
"epoch":
|
| 1027 |
-
"learning_rate":
|
| 1028 |
-
"loss": 0.
|
| 1029 |
"step": 980
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
-
"epoch":
|
| 1033 |
-
"learning_rate":
|
| 1034 |
-
"loss": 0.
|
| 1035 |
"step": 990
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
-
"epoch":
|
| 1039 |
-
"eval_accuracy": 0.
|
| 1040 |
-
"eval_loss": 1.
|
| 1041 |
-
"eval_runtime":
|
| 1042 |
-
"eval_samples_per_second":
|
| 1043 |
-
"eval_steps_per_second":
|
| 1044 |
"step": 992
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
-
"epoch":
|
| 1048 |
-
"learning_rate":
|
| 1049 |
-
"loss": 0.
|
| 1050 |
"step": 1000
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
-
"epoch":
|
| 1054 |
-
"
|
| 1055 |
-
"
|
| 1056 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
-
"epoch":
|
| 1060 |
-
"
|
| 1061 |
-
"
|
| 1062 |
-
"
|
| 1063 |
-
"eval_samples_per_second": 203.791,
|
| 1064 |
-
"eval_steps_per_second": 14.385,
|
| 1065 |
-
"step": 1012
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch":
|
| 1069 |
-
"learning_rate":
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 1020
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch":
|
| 1075 |
-
"
|
| 1076 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1077 |
"step": 1030
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch":
|
| 1081 |
-
"eval_accuracy": 0.
|
| 1082 |
-
"eval_loss": 1.
|
| 1083 |
-
"eval_runtime":
|
| 1084 |
-
"eval_samples_per_second":
|
| 1085 |
-
"eval_steps_per_second":
|
| 1086 |
-
"step":
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
-
"epoch":
|
| 1090 |
-
"learning_rate":
|
| 1091 |
-
"loss": 0.
|
| 1092 |
"step": 1040
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
-
"epoch":
|
| 1096 |
-
"learning_rate":
|
| 1097 |
-
"loss": 0.
|
| 1098 |
"step": 1050
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
-
"epoch":
|
| 1102 |
-
"eval_accuracy": 0.
|
| 1103 |
-
"eval_loss": 1.
|
| 1104 |
-
"eval_runtime":
|
| 1105 |
-
"eval_samples_per_second":
|
| 1106 |
-
"eval_steps_per_second":
|
| 1107 |
-
"step":
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
-
"epoch":
|
| 1111 |
-
"learning_rate":
|
| 1112 |
-
"loss": 0.
|
| 1113 |
"step": 1060
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch":
|
| 1117 |
-
"
|
| 1118 |
-
"
|
| 1119 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
-
"epoch":
|
| 1123 |
-
"
|
| 1124 |
-
"
|
| 1125 |
-
"
|
| 1126 |
-
"eval_samples_per_second": 202.336,
|
| 1127 |
-
"eval_steps_per_second": 14.283,
|
| 1128 |
-
"step": 1073
|
| 1129 |
},
|
| 1130 |
{
|
| 1131 |
-
"epoch":
|
| 1132 |
-
"learning_rate":
|
| 1133 |
-
"loss": 0.
|
| 1134 |
"step": 1080
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
-
"epoch":
|
| 1138 |
-
"
|
| 1139 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1140 |
"step": 1090
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
-
"epoch":
|
| 1144 |
-
"
|
| 1145 |
-
"
|
| 1146 |
-
"
|
| 1147 |
-
"eval_samples_per_second": 184.34,
|
| 1148 |
-
"eval_steps_per_second": 13.012,
|
| 1149 |
-
"step": 1093
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
-
"epoch":
|
| 1153 |
-
"
|
| 1154 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1155 |
"step": 1100
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
-
"epoch":
|
| 1159 |
-
"learning_rate":
|
| 1160 |
-
"loss": 0.
|
| 1161 |
"step": 1110
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
-
"epoch":
|
| 1165 |
-
"eval_accuracy": 0.
|
| 1166 |
-
"eval_loss": 1.
|
| 1167 |
-
"eval_runtime":
|
| 1168 |
-
"eval_samples_per_second":
|
| 1169 |
-
"eval_steps_per_second":
|
| 1170 |
-
"step":
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
-
"epoch":
|
| 1174 |
-
"learning_rate":
|
| 1175 |
-
"loss": 0.
|
| 1176 |
"step": 1120
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
-
"epoch":
|
| 1180 |
-
"learning_rate":
|
| 1181 |
-
"loss": 0.
|
| 1182 |
"step": 1130
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
-
"epoch":
|
| 1186 |
-
"eval_accuracy": 0.
|
| 1187 |
-
"eval_loss": 1.
|
| 1188 |
-
"eval_runtime":
|
| 1189 |
-
"eval_samples_per_second":
|
| 1190 |
-
"eval_steps_per_second":
|
| 1191 |
-
"step":
|
| 1192 |
},
|
| 1193 |
{
|
| 1194 |
-
"epoch":
|
| 1195 |
-
"learning_rate":
|
| 1196 |
-
"loss": 0.
|
| 1197 |
"step": 1140
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
-
"epoch":
|
| 1201 |
-
"
|
| 1202 |
-
"
|
| 1203 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1204 |
},
|
| 1205 |
{
|
| 1206 |
-
"epoch":
|
| 1207 |
-
"
|
| 1208 |
-
"
|
| 1209 |
-
"
|
| 1210 |
-
"eval_samples_per_second": 177.784,
|
| 1211 |
-
"eval_steps_per_second": 12.549,
|
| 1212 |
-
"step": 1154
|
| 1213 |
},
|
| 1214 |
{
|
| 1215 |
-
"epoch":
|
| 1216 |
-
"learning_rate": 1.
|
| 1217 |
-
"loss": 0.
|
| 1218 |
"step": 1160
|
| 1219 |
},
|
| 1220 |
{
|
| 1221 |
-
"epoch":
|
| 1222 |
-
"
|
| 1223 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1224 |
"step": 1170
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
-
"epoch":
|
| 1228 |
-
"eval_accuracy": 0.
|
| 1229 |
-
"eval_loss": 1.
|
| 1230 |
-
"eval_runtime":
|
| 1231 |
-
"eval_samples_per_second":
|
| 1232 |
-
"eval_steps_per_second":
|
| 1233 |
-
"step":
|
| 1234 |
},
|
| 1235 |
{
|
| 1236 |
-
"epoch":
|
| 1237 |
-
"learning_rate":
|
| 1238 |
-
"loss": 0.
|
| 1239 |
"step": 1180
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
-
"epoch":
|
| 1243 |
-
"learning_rate":
|
| 1244 |
-
"loss": 0.
|
| 1245 |
"step": 1190
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
-
"epoch":
|
| 1249 |
-
"eval_accuracy": 0.
|
| 1250 |
-
"eval_loss": 1.
|
| 1251 |
-
"eval_runtime":
|
| 1252 |
-
"eval_samples_per_second":
|
| 1253 |
-
"eval_steps_per_second":
|
| 1254 |
-
"step":
|
| 1255 |
},
|
| 1256 |
{
|
| 1257 |
-
"epoch":
|
| 1258 |
-
"learning_rate":
|
| 1259 |
-
"loss": 0.
|
| 1260 |
"step": 1200
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
-
"epoch":
|
| 1264 |
-
"
|
| 1265 |
-
"
|
| 1266 |
-
"
|
| 1267 |
-
|
| 1268 |
-
|
| 1269 |
-
"
|
| 1270 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1271 |
-
"eval_loss": 1.5555047988891602,
|
| 1272 |
-
"eval_runtime": 0.4201,
|
| 1273 |
-
"eval_samples_per_second": 202.335,
|
| 1274 |
-
"eval_steps_per_second": 14.282,
|
| 1275 |
-
"step": 1215
|
| 1276 |
-
},
|
| 1277 |
-
{
|
| 1278 |
-
"epoch": 60.25,
|
| 1279 |
-
"learning_rate": 1.3194444444444446e-05,
|
| 1280 |
-
"loss": 0.1239,
|
| 1281 |
-
"step": 1220
|
| 1282 |
-
},
|
| 1283 |
-
{
|
| 1284 |
-
"epoch": 60.74,
|
| 1285 |
-
"learning_rate": 1.2847222222222222e-05,
|
| 1286 |
-
"loss": 0.1199,
|
| 1287 |
-
"step": 1230
|
| 1288 |
-
},
|
| 1289 |
-
{
|
| 1290 |
-
"epoch": 60.99,
|
| 1291 |
-
"eval_accuracy": 0.7058823529411765,
|
| 1292 |
-
"eval_loss": 1.5170692205429077,
|
| 1293 |
-
"eval_runtime": 0.4581,
|
| 1294 |
-
"eval_samples_per_second": 185.548,
|
| 1295 |
-
"eval_steps_per_second": 13.097,
|
| 1296 |
-
"step": 1235
|
| 1297 |
-
},
|
| 1298 |
-
{
|
| 1299 |
-
"epoch": 61.23,
|
| 1300 |
-
"learning_rate": 1.25e-05,
|
| 1301 |
-
"loss": 0.1142,
|
| 1302 |
-
"step": 1240
|
| 1303 |
-
},
|
| 1304 |
-
{
|
| 1305 |
-
"epoch": 61.73,
|
| 1306 |
-
"learning_rate": 1.2152777777777779e-05,
|
| 1307 |
-
"loss": 0.1235,
|
| 1308 |
-
"step": 1250
|
| 1309 |
-
},
|
| 1310 |
-
{
|
| 1311 |
-
"epoch": 61.98,
|
| 1312 |
-
"eval_accuracy": 0.6823529411764706,
|
| 1313 |
-
"eval_loss": 1.609281301498413,
|
| 1314 |
-
"eval_runtime": 0.4211,
|
| 1315 |
-
"eval_samples_per_second": 201.855,
|
| 1316 |
-
"eval_steps_per_second": 14.249,
|
| 1317 |
-
"step": 1255
|
| 1318 |
-
},
|
| 1319 |
-
{
|
| 1320 |
-
"epoch": 62.22,
|
| 1321 |
-
"learning_rate": 1.1805555555555555e-05,
|
| 1322 |
-
"loss": 0.1353,
|
| 1323 |
-
"step": 1260
|
| 1324 |
-
},
|
| 1325 |
-
{
|
| 1326 |
-
"epoch": 62.72,
|
| 1327 |
-
"learning_rate": 1.1458333333333333e-05,
|
| 1328 |
-
"loss": 0.0917,
|
| 1329 |
-
"step": 1270
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 62.96,
|
| 1333 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1334 |
-
"eval_loss": 1.5284392833709717,
|
| 1335 |
-
"eval_runtime": 0.4501,
|
| 1336 |
-
"eval_samples_per_second": 188.846,
|
| 1337 |
-
"eval_steps_per_second": 13.33,
|
| 1338 |
-
"step": 1275
|
| 1339 |
-
},
|
| 1340 |
-
{
|
| 1341 |
-
"epoch": 63.21,
|
| 1342 |
-
"learning_rate": 1.1111111111111112e-05,
|
| 1343 |
-
"loss": 0.1338,
|
| 1344 |
-
"step": 1280
|
| 1345 |
-
},
|
| 1346 |
-
{
|
| 1347 |
-
"epoch": 63.7,
|
| 1348 |
-
"learning_rate": 1.076388888888889e-05,
|
| 1349 |
-
"loss": 0.1397,
|
| 1350 |
-
"step": 1290
|
| 1351 |
-
},
|
| 1352 |
-
{
|
| 1353 |
-
"epoch": 64.0,
|
| 1354 |
-
"eval_accuracy": 0.7411764705882353,
|
| 1355 |
-
"eval_loss": 1.5438880920410156,
|
| 1356 |
-
"eval_runtime": 0.4211,
|
| 1357 |
-
"eval_samples_per_second": 201.855,
|
| 1358 |
-
"eval_steps_per_second": 14.249,
|
| 1359 |
-
"step": 1296
|
| 1360 |
-
},
|
| 1361 |
-
{
|
| 1362 |
-
"epoch": 64.2,
|
| 1363 |
-
"learning_rate": 1.0416666666666668e-05,
|
| 1364 |
-
"loss": 0.1037,
|
| 1365 |
-
"step": 1300
|
| 1366 |
-
},
|
| 1367 |
-
{
|
| 1368 |
-
"epoch": 64.69,
|
| 1369 |
-
"learning_rate": 1.0069444444444445e-05,
|
| 1370 |
-
"loss": 0.1116,
|
| 1371 |
-
"step": 1310
|
| 1372 |
-
},
|
| 1373 |
-
{
|
| 1374 |
-
"epoch": 64.99,
|
| 1375 |
-
"eval_accuracy": 0.7176470588235294,
|
| 1376 |
-
"eval_loss": 1.4917408227920532,
|
| 1377 |
-
"eval_runtime": 0.4671,
|
| 1378 |
-
"eval_samples_per_second": 181.972,
|
| 1379 |
-
"eval_steps_per_second": 12.845,
|
| 1380 |
-
"step": 1316
|
| 1381 |
-
},
|
| 1382 |
-
{
|
| 1383 |
-
"epoch": 65.19,
|
| 1384 |
-
"learning_rate": 9.722222222222223e-06,
|
| 1385 |
-
"loss": 0.084,
|
| 1386 |
-
"step": 1320
|
| 1387 |
-
},
|
| 1388 |
-
{
|
| 1389 |
-
"epoch": 65.68,
|
| 1390 |
-
"learning_rate": 9.375000000000001e-06,
|
| 1391 |
-
"loss": 0.154,
|
| 1392 |
-
"step": 1330
|
| 1393 |
-
},
|
| 1394 |
-
{
|
| 1395 |
-
"epoch": 65.98,
|
| 1396 |
-
"eval_accuracy": 0.7176470588235294,
|
| 1397 |
-
"eval_loss": 1.4917773008346558,
|
| 1398 |
-
"eval_runtime": 0.4221,
|
| 1399 |
-
"eval_samples_per_second": 201.376,
|
| 1400 |
-
"eval_steps_per_second": 14.215,
|
| 1401 |
-
"step": 1336
|
| 1402 |
-
},
|
| 1403 |
-
{
|
| 1404 |
-
"epoch": 66.17,
|
| 1405 |
-
"learning_rate": 9.027777777777777e-06,
|
| 1406 |
-
"loss": 0.1385,
|
| 1407 |
-
"step": 1340
|
| 1408 |
-
},
|
| 1409 |
-
{
|
| 1410 |
-
"epoch": 66.67,
|
| 1411 |
-
"learning_rate": 8.680555555555556e-06,
|
| 1412 |
-
"loss": 0.1165,
|
| 1413 |
-
"step": 1350
|
| 1414 |
-
},
|
| 1415 |
-
{
|
| 1416 |
-
"epoch": 66.96,
|
| 1417 |
-
"eval_accuracy": 0.7176470588235294,
|
| 1418 |
-
"eval_loss": 1.567964792251587,
|
| 1419 |
-
"eval_runtime": 0.4221,
|
| 1420 |
-
"eval_samples_per_second": 201.376,
|
| 1421 |
-
"eval_steps_per_second": 14.215,
|
| 1422 |
-
"step": 1356
|
| 1423 |
-
},
|
| 1424 |
-
{
|
| 1425 |
-
"epoch": 67.16,
|
| 1426 |
-
"learning_rate": 8.333333333333334e-06,
|
| 1427 |
-
"loss": 0.1235,
|
| 1428 |
-
"step": 1360
|
| 1429 |
-
},
|
| 1430 |
-
{
|
| 1431 |
-
"epoch": 67.65,
|
| 1432 |
-
"learning_rate": 7.98611111111111e-06,
|
| 1433 |
-
"loss": 0.0803,
|
| 1434 |
-
"step": 1370
|
| 1435 |
-
},
|
| 1436 |
-
{
|
| 1437 |
-
"epoch": 68.0,
|
| 1438 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1439 |
-
"eval_loss": 1.6100775003433228,
|
| 1440 |
-
"eval_runtime": 0.4591,
|
| 1441 |
-
"eval_samples_per_second": 185.143,
|
| 1442 |
-
"eval_steps_per_second": 13.069,
|
| 1443 |
-
"step": 1377
|
| 1444 |
-
},
|
| 1445 |
-
{
|
| 1446 |
-
"epoch": 68.15,
|
| 1447 |
-
"learning_rate": 7.63888888888889e-06,
|
| 1448 |
-
"loss": 0.1418,
|
| 1449 |
-
"step": 1380
|
| 1450 |
-
},
|
| 1451 |
-
{
|
| 1452 |
-
"epoch": 68.64,
|
| 1453 |
-
"learning_rate": 7.2916666666666674e-06,
|
| 1454 |
-
"loss": 0.1155,
|
| 1455 |
-
"step": 1390
|
| 1456 |
-
},
|
| 1457 |
-
{
|
| 1458 |
-
"epoch": 68.99,
|
| 1459 |
-
"eval_accuracy": 0.7058823529411765,
|
| 1460 |
-
"eval_loss": 1.5571577548980713,
|
| 1461 |
-
"eval_runtime": 0.4471,
|
| 1462 |
-
"eval_samples_per_second": 190.114,
|
| 1463 |
-
"eval_steps_per_second": 13.42,
|
| 1464 |
-
"step": 1397
|
| 1465 |
-
},
|
| 1466 |
-
{
|
| 1467 |
-
"epoch": 69.14,
|
| 1468 |
-
"learning_rate": 6.944444444444445e-06,
|
| 1469 |
-
"loss": 0.1345,
|
| 1470 |
-
"step": 1400
|
| 1471 |
-
},
|
| 1472 |
-
{
|
| 1473 |
-
"epoch": 69.63,
|
| 1474 |
-
"learning_rate": 6.597222222222223e-06,
|
| 1475 |
-
"loss": 0.1177,
|
| 1476 |
-
"step": 1410
|
| 1477 |
-
},
|
| 1478 |
-
{
|
| 1479 |
-
"epoch": 69.98,
|
| 1480 |
-
"eval_accuracy": 0.7176470588235294,
|
| 1481 |
-
"eval_loss": 1.540352702140808,
|
| 1482 |
-
"eval_runtime": 0.4261,
|
| 1483 |
-
"eval_samples_per_second": 199.485,
|
| 1484 |
-
"eval_steps_per_second": 14.081,
|
| 1485 |
-
"step": 1417
|
| 1486 |
-
},
|
| 1487 |
-
{
|
| 1488 |
-
"epoch": 70.12,
|
| 1489 |
-
"learning_rate": 6.25e-06,
|
| 1490 |
-
"loss": 0.0858,
|
| 1491 |
-
"step": 1420
|
| 1492 |
-
},
|
| 1493 |
-
{
|
| 1494 |
-
"epoch": 70.62,
|
| 1495 |
-
"learning_rate": 5.902777777777778e-06,
|
| 1496 |
-
"loss": 0.0948,
|
| 1497 |
-
"step": 1430
|
| 1498 |
-
},
|
| 1499 |
-
{
|
| 1500 |
-
"epoch": 70.96,
|
| 1501 |
-
"eval_accuracy": 0.7058823529411765,
|
| 1502 |
-
"eval_loss": 1.5666162967681885,
|
| 1503 |
-
"eval_runtime": 0.4211,
|
| 1504 |
-
"eval_samples_per_second": 201.854,
|
| 1505 |
-
"eval_steps_per_second": 14.249,
|
| 1506 |
-
"step": 1437
|
| 1507 |
-
},
|
| 1508 |
-
{
|
| 1509 |
-
"epoch": 71.11,
|
| 1510 |
-
"learning_rate": 5.555555555555556e-06,
|
| 1511 |
-
"loss": 0.1391,
|
| 1512 |
-
"step": 1440
|
| 1513 |
-
},
|
| 1514 |
-
{
|
| 1515 |
-
"epoch": 71.6,
|
| 1516 |
-
"learning_rate": 5.208333333333334e-06,
|
| 1517 |
-
"loss": 0.1262,
|
| 1518 |
-
"step": 1450
|
| 1519 |
-
},
|
| 1520 |
-
{
|
| 1521 |
-
"epoch": 72.0,
|
| 1522 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1523 |
-
"eval_loss": 1.6309505701065063,
|
| 1524 |
-
"eval_runtime": 0.4821,
|
| 1525 |
-
"eval_samples_per_second": 176.309,
|
| 1526 |
-
"eval_steps_per_second": 12.445,
|
| 1527 |
-
"step": 1458
|
| 1528 |
-
},
|
| 1529 |
-
{
|
| 1530 |
-
"epoch": 72.1,
|
| 1531 |
-
"learning_rate": 4.861111111111111e-06,
|
| 1532 |
-
"loss": 0.0788,
|
| 1533 |
-
"step": 1460
|
| 1534 |
-
},
|
| 1535 |
-
{
|
| 1536 |
-
"epoch": 72.59,
|
| 1537 |
-
"learning_rate": 4.513888888888889e-06,
|
| 1538 |
-
"loss": 0.0985,
|
| 1539 |
-
"step": 1470
|
| 1540 |
-
},
|
| 1541 |
-
{
|
| 1542 |
-
"epoch": 72.99,
|
| 1543 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1544 |
-
"eval_loss": 1.6212233304977417,
|
| 1545 |
-
"eval_runtime": 0.4181,
|
| 1546 |
-
"eval_samples_per_second": 203.303,
|
| 1547 |
-
"eval_steps_per_second": 14.351,
|
| 1548 |
-
"step": 1478
|
| 1549 |
-
},
|
| 1550 |
-
{
|
| 1551 |
-
"epoch": 73.09,
|
| 1552 |
-
"learning_rate": 4.166666666666667e-06,
|
| 1553 |
-
"loss": 0.1069,
|
| 1554 |
-
"step": 1480
|
| 1555 |
-
},
|
| 1556 |
-
{
|
| 1557 |
-
"epoch": 73.58,
|
| 1558 |
-
"learning_rate": 3.819444444444445e-06,
|
| 1559 |
-
"loss": 0.106,
|
| 1560 |
-
"step": 1490
|
| 1561 |
-
},
|
| 1562 |
-
{
|
| 1563 |
-
"epoch": 73.98,
|
| 1564 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1565 |
-
"eval_loss": 1.6286240816116333,
|
| 1566 |
-
"eval_runtime": 0.4121,
|
| 1567 |
-
"eval_samples_per_second": 206.264,
|
| 1568 |
-
"eval_steps_per_second": 14.56,
|
| 1569 |
-
"step": 1498
|
| 1570 |
-
},
|
| 1571 |
-
{
|
| 1572 |
-
"epoch": 74.07,
|
| 1573 |
-
"learning_rate": 3.4722222222222224e-06,
|
| 1574 |
-
"loss": 0.1089,
|
| 1575 |
-
"step": 1500
|
| 1576 |
-
},
|
| 1577 |
-
{
|
| 1578 |
-
"epoch": 74.57,
|
| 1579 |
-
"learning_rate": 3.125e-06,
|
| 1580 |
-
"loss": 0.1292,
|
| 1581 |
-
"step": 1510
|
| 1582 |
-
},
|
| 1583 |
-
{
|
| 1584 |
-
"epoch": 74.96,
|
| 1585 |
-
"eval_accuracy": 0.7058823529411765,
|
| 1586 |
-
"eval_loss": 1.6158820390701294,
|
| 1587 |
-
"eval_runtime": 0.4141,
|
| 1588 |
-
"eval_samples_per_second": 205.268,
|
| 1589 |
-
"eval_steps_per_second": 14.489,
|
| 1590 |
-
"step": 1518
|
| 1591 |
-
},
|
| 1592 |
-
{
|
| 1593 |
-
"epoch": 75.06,
|
| 1594 |
-
"learning_rate": 2.777777777777778e-06,
|
| 1595 |
-
"loss": 0.0942,
|
| 1596 |
-
"step": 1520
|
| 1597 |
-
},
|
| 1598 |
-
{
|
| 1599 |
-
"epoch": 75.56,
|
| 1600 |
-
"learning_rate": 2.4305555555555557e-06,
|
| 1601 |
-
"loss": 0.0927,
|
| 1602 |
-
"step": 1530
|
| 1603 |
-
},
|
| 1604 |
-
{
|
| 1605 |
-
"epoch": 76.0,
|
| 1606 |
-
"eval_accuracy": 0.7058823529411765,
|
| 1607 |
-
"eval_loss": 1.6224379539489746,
|
| 1608 |
-
"eval_runtime": 0.4171,
|
| 1609 |
-
"eval_samples_per_second": 203.791,
|
| 1610 |
-
"eval_steps_per_second": 14.385,
|
| 1611 |
-
"step": 1539
|
| 1612 |
-
},
|
| 1613 |
-
{
|
| 1614 |
-
"epoch": 76.05,
|
| 1615 |
-
"learning_rate": 2.0833333333333334e-06,
|
| 1616 |
-
"loss": 0.107,
|
| 1617 |
-
"step": 1540
|
| 1618 |
-
},
|
| 1619 |
-
{
|
| 1620 |
-
"epoch": 76.54,
|
| 1621 |
-
"learning_rate": 1.7361111111111112e-06,
|
| 1622 |
-
"loss": 0.0908,
|
| 1623 |
-
"step": 1550
|
| 1624 |
-
},
|
| 1625 |
-
{
|
| 1626 |
-
"epoch": 76.99,
|
| 1627 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1628 |
-
"eval_loss": 1.6388969421386719,
|
| 1629 |
-
"eval_runtime": 0.4151,
|
| 1630 |
-
"eval_samples_per_second": 204.773,
|
| 1631 |
-
"eval_steps_per_second": 14.455,
|
| 1632 |
-
"step": 1559
|
| 1633 |
-
},
|
| 1634 |
-
{
|
| 1635 |
-
"epoch": 77.04,
|
| 1636 |
-
"learning_rate": 1.388888888888889e-06,
|
| 1637 |
-
"loss": 0.1139,
|
| 1638 |
-
"step": 1560
|
| 1639 |
-
},
|
| 1640 |
-
{
|
| 1641 |
-
"epoch": 77.53,
|
| 1642 |
-
"learning_rate": 1.0416666666666667e-06,
|
| 1643 |
-
"loss": 0.1324,
|
| 1644 |
-
"step": 1570
|
| 1645 |
-
},
|
| 1646 |
-
{
|
| 1647 |
-
"epoch": 77.98,
|
| 1648 |
-
"eval_accuracy": 0.6941176470588235,
|
| 1649 |
-
"eval_loss": 1.6460027694702148,
|
| 1650 |
-
"eval_runtime": 0.4141,
|
| 1651 |
-
"eval_samples_per_second": 205.268,
|
| 1652 |
-
"eval_steps_per_second": 14.489,
|
| 1653 |
-
"step": 1579
|
| 1654 |
-
},
|
| 1655 |
-
{
|
| 1656 |
-
"epoch": 78.02,
|
| 1657 |
-
"learning_rate": 6.944444444444445e-07,
|
| 1658 |
-
"loss": 0.1232,
|
| 1659 |
-
"step": 1580
|
| 1660 |
-
},
|
| 1661 |
-
{
|
| 1662 |
-
"epoch": 78.52,
|
| 1663 |
-
"learning_rate": 3.4722222222222224e-07,
|
| 1664 |
-
"loss": 0.0942,
|
| 1665 |
-
"step": 1590
|
| 1666 |
-
},
|
| 1667 |
-
{
|
| 1668 |
-
"epoch": 78.96,
|
| 1669 |
-
"eval_accuracy": 0.7058823529411765,
|
| 1670 |
-
"eval_loss": 1.6473891735076904,
|
| 1671 |
-
"eval_runtime": 0.4291,
|
| 1672 |
-
"eval_samples_per_second": 198.09,
|
| 1673 |
-
"eval_steps_per_second": 13.983,
|
| 1674 |
-
"step": 1599
|
| 1675 |
},
|
| 1676 |
{
|
| 1677 |
-
"epoch":
|
| 1678 |
-
"
|
| 1679 |
-
"
|
| 1680 |
-
"
|
| 1681 |
-
|
| 1682 |
-
|
| 1683 |
-
"
|
| 1684 |
-
"eval_accuracy": 0.7058823529411765,
|
| 1685 |
-
"eval_loss": 1.6473920345306396,
|
| 1686 |
-
"eval_runtime": 0.4161,
|
| 1687 |
-
"eval_samples_per_second": 204.281,
|
| 1688 |
-
"eval_steps_per_second": 14.42,
|
| 1689 |
-
"step": 1600
|
| 1690 |
-
},
|
| 1691 |
-
{
|
| 1692 |
-
"epoch": 79.01,
|
| 1693 |
-
"step": 1600,
|
| 1694 |
-
"total_flos": 3.3112304999580303e+18,
|
| 1695 |
-
"train_loss": 0.33946088805794716,
|
| 1696 |
-
"train_runtime": 1321.034,
|
| 1697 |
-
"train_samples_per_second": 78.0,
|
| 1698 |
-
"train_steps_per_second": 1.211
|
| 1699 |
}
|
| 1700 |
],
|
| 1701 |
"logging_steps": 10,
|
| 1702 |
-
"max_steps":
|
| 1703 |
"num_input_tokens_seen": 0,
|
| 1704 |
"num_train_epochs": 80,
|
| 1705 |
"save_steps": 500,
|
| 1706 |
-
"total_flos":
|
| 1707 |
"train_batch_size": 16,
|
| 1708 |
"trial_name": null,
|
| 1709 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8068181818181818,
|
| 3 |
+
"best_model_checkpoint": "/Modelos/Swin-DA2-final-AMD-Wet\\checkpoint-651",
|
| 4 |
+
"epoch": 77.41935483870968,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.65,
|
| 13 |
+
"learning_rate": 4.166666666666667e-06,
|
| 14 |
"loss": 1.6093,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.97,
|
| 19 |
+
"eval_accuracy": 0.20454545454545456,
|
| 20 |
+
"eval_loss": 1.6090493202209473,
|
| 21 |
+
"eval_runtime": 1.6312,
|
| 22 |
+
"eval_samples_per_second": 53.948,
|
| 23 |
+
"eval_steps_per_second": 3.678,
|
| 24 |
+
"step": 15
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 1.29,
|
| 28 |
+
"learning_rate": 8.333333333333334e-06,
|
| 29 |
+
"loss": 1.6084,
|
|
|
|
|
|
|
|
|
|
| 30 |
"step": 20
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 1.94,
|
| 34 |
+
"learning_rate": 1.25e-05,
|
| 35 |
+
"loss": 1.6042,
|
| 36 |
"step": 30
|
| 37 |
},
|
| 38 |
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.20454545454545456,
|
| 41 |
+
"eval_loss": 1.605498194694519,
|
| 42 |
+
"eval_runtime": 1.0762,
|
| 43 |
+
"eval_samples_per_second": 81.766,
|
| 44 |
+
"eval_steps_per_second": 5.575,
|
| 45 |
+
"step": 31
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 2.58,
|
| 49 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 50 |
+
"loss": 1.586,
|
|
|
|
|
|
|
|
|
|
| 51 |
"step": 40
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 2.97,
|
| 55 |
+
"eval_accuracy": 0.19318181818181818,
|
| 56 |
+
"eval_loss": 1.5730183124542236,
|
| 57 |
+
"eval_runtime": 1.0502,
|
| 58 |
+
"eval_samples_per_second": 83.791,
|
| 59 |
+
"eval_steps_per_second": 5.713,
|
| 60 |
+
"step": 46
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.23,
|
| 64 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 65 |
+
"loss": 1.5425,
|
| 66 |
"step": 50
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 3.87,
|
| 70 |
+
"learning_rate": 2.5e-05,
|
| 71 |
+
"loss": 1.4855,
|
| 72 |
"step": 60
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 4.0,
|
| 76 |
+
"eval_accuracy": 0.26136363636363635,
|
| 77 |
+
"eval_loss": 1.4935040473937988,
|
| 78 |
+
"eval_runtime": 1.0352,
|
| 79 |
+
"eval_samples_per_second": 85.005,
|
| 80 |
+
"eval_steps_per_second": 5.796,
|
| 81 |
+
"step": 62
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 4.52,
|
| 85 |
+
"learning_rate": 2.916666666666667e-05,
|
| 86 |
+
"loss": 1.3738,
|
| 87 |
"step": 70
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 4.97,
|
| 91 |
+
"eval_accuracy": 0.5,
|
| 92 |
+
"eval_loss": 1.3272513151168823,
|
| 93 |
+
"eval_runtime": 1.0512,
|
| 94 |
+
"eval_samples_per_second": 83.711,
|
| 95 |
+
"eval_steps_per_second": 5.708,
|
| 96 |
+
"step": 77
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 5.16,
|
| 100 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 101 |
+
"loss": 1.2795,
|
| 102 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 5.81,
|
| 106 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 107 |
+
"loss": 1.1557,
|
| 108 |
"step": 90
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 6.0,
|
| 112 |
+
"eval_accuracy": 0.625,
|
| 113 |
+
"eval_loss": 1.0827698707580566,
|
| 114 |
+
"eval_runtime": 1.0852,
|
| 115 |
+
"eval_samples_per_second": 81.088,
|
| 116 |
+
"eval_steps_per_second": 5.529,
|
| 117 |
+
"step": 93
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 6.45,
|
| 121 |
+
"learning_rate": 4.166666666666667e-05,
|
| 122 |
+
"loss": 1.0441,
|
| 123 |
"step": 100
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 6.97,
|
| 127 |
+
"eval_accuracy": 0.6022727272727273,
|
| 128 |
+
"eval_loss": 0.8971154689788818,
|
| 129 |
+
"eval_runtime": 1.0662,
|
| 130 |
+
"eval_samples_per_second": 82.533,
|
| 131 |
+
"eval_steps_per_second": 5.627,
|
| 132 |
+
"step": 108
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 7.1,
|
| 136 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 137 |
+
"loss": 0.9639,
|
| 138 |
"step": 110
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 7.74,
|
| 142 |
+
"learning_rate": 5e-05,
|
| 143 |
+
"loss": 0.9358,
|
| 144 |
"step": 120
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 8.0,
|
| 148 |
+
"eval_accuracy": 0.6818181818181818,
|
| 149 |
+
"eval_loss": 0.7635229229927063,
|
| 150 |
+
"eval_runtime": 1.0302,
|
| 151 |
+
"eval_samples_per_second": 85.418,
|
| 152 |
+
"eval_steps_per_second": 5.824,
|
| 153 |
+
"step": 124
|
| 154 |
},
|
| 155 |
{
|
| 156 |
+
"epoch": 8.39,
|
| 157 |
+
"learning_rate": 4.9537037037037035e-05,
|
| 158 |
+
"loss": 0.7707,
|
| 159 |
"step": 130
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 8.97,
|
| 163 |
+
"eval_accuracy": 0.6477272727272727,
|
| 164 |
+
"eval_loss": 0.8717986941337585,
|
| 165 |
+
"eval_runtime": 1.0472,
|
| 166 |
+
"eval_samples_per_second": 84.031,
|
| 167 |
+
"eval_steps_per_second": 5.729,
|
| 168 |
+
"step": 139
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"epoch": 9.03,
|
| 172 |
+
"learning_rate": 4.9074074074074075e-05,
|
| 173 |
+
"loss": 0.8861,
|
| 174 |
+
"step": 140
|
|
|
|
|
|
|
|
|
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 9.68,
|
| 178 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 179 |
+
"loss": 0.7161,
|
| 180 |
"step": 150
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"epoch": 10.0,
|
| 184 |
+
"eval_accuracy": 0.7727272727272727,
|
| 185 |
+
"eval_loss": 0.6902639269828796,
|
| 186 |
+
"eval_runtime": 1.0472,
|
| 187 |
+
"eval_samples_per_second": 84.031,
|
| 188 |
+
"eval_steps_per_second": 5.729,
|
| 189 |
+
"step": 155
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.32,
|
| 193 |
+
"learning_rate": 4.814814814814815e-05,
|
| 194 |
+
"loss": 0.7251,
|
| 195 |
"step": 160
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 10.97,
|
| 199 |
+
"learning_rate": 4.768518518518519e-05,
|
| 200 |
+
"loss": 0.6799,
|
| 201 |
+
"step": 170
|
|
|
|
|
|
|
|
|
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 10.97,
|
| 205 |
+
"eval_accuracy": 0.7272727272727273,
|
| 206 |
+
"eval_loss": 0.8108208179473877,
|
| 207 |
+
"eval_runtime": 1.0902,
|
| 208 |
+
"eval_samples_per_second": 80.716,
|
| 209 |
+
"eval_steps_per_second": 5.503,
|
| 210 |
"step": 170
|
| 211 |
},
|
| 212 |
{
|
| 213 |
+
"epoch": 11.61,
|
| 214 |
+
"learning_rate": 4.722222222222222e-05,
|
| 215 |
+
"loss": 0.6402,
|
| 216 |
"step": 180
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 12.0,
|
| 220 |
+
"eval_accuracy": 0.7272727272727273,
|
| 221 |
+
"eval_loss": 0.7146868109703064,
|
| 222 |
+
"eval_runtime": 1.0392,
|
| 223 |
+
"eval_samples_per_second": 84.678,
|
| 224 |
+
"eval_steps_per_second": 5.773,
|
| 225 |
+
"step": 186
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 12.26,
|
| 229 |
+
"learning_rate": 4.675925925925926e-05,
|
| 230 |
+
"loss": 0.5816,
|
| 231 |
"step": 190
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 12.9,
|
| 235 |
+
"learning_rate": 4.62962962962963e-05,
|
| 236 |
+
"loss": 0.5131,
|
| 237 |
"step": 200
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 12.97,
|
| 241 |
+
"eval_accuracy": 0.75,
|
| 242 |
+
"eval_loss": 0.7520684599876404,
|
| 243 |
+
"eval_runtime": 1.1293,
|
| 244 |
+
"eval_samples_per_second": 77.928,
|
| 245 |
+
"eval_steps_per_second": 5.313,
|
| 246 |
+
"step": 201
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 13.55,
|
| 250 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 251 |
+
"loss": 0.5262,
|
| 252 |
"step": 210
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 14.0,
|
| 256 |
+
"eval_accuracy": 0.7272727272727273,
|
| 257 |
+
"eval_loss": 0.7967298626899719,
|
| 258 |
+
"eval_runtime": 1.0822,
|
| 259 |
+
"eval_samples_per_second": 81.313,
|
| 260 |
+
"eval_steps_per_second": 5.544,
|
| 261 |
+
"step": 217
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 14.19,
|
| 265 |
+
"learning_rate": 4.5370370370370374e-05,
|
| 266 |
+
"loss": 0.5323,
|
| 267 |
+
"step": 220
|
|
|
|
|
|
|
|
|
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 14.84,
|
| 271 |
+
"learning_rate": 4.490740740740741e-05,
|
| 272 |
+
"loss": 0.4757,
|
| 273 |
"step": 230
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 14.97,
|
| 277 |
+
"eval_accuracy": 0.7613636363636364,
|
| 278 |
+
"eval_loss": 0.7084075808525085,
|
| 279 |
+
"eval_runtime": 1.0422,
|
| 280 |
+
"eval_samples_per_second": 84.434,
|
| 281 |
+
"eval_steps_per_second": 5.757,
|
| 282 |
+
"step": 232
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 15.48,
|
| 286 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 287 |
+
"loss": 0.4758,
|
| 288 |
"step": 240
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 16.0,
|
| 292 |
+
"eval_accuracy": 0.7727272727272727,
|
| 293 |
+
"eval_loss": 0.7528924345970154,
|
| 294 |
+
"eval_runtime": 1.0702,
|
| 295 |
+
"eval_samples_per_second": 82.224,
|
| 296 |
+
"eval_steps_per_second": 5.606,
|
| 297 |
+
"step": 248
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 16.13,
|
| 301 |
+
"learning_rate": 4.3981481481481486e-05,
|
| 302 |
+
"loss": 0.4203,
|
| 303 |
"step": 250
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 16.77,
|
| 307 |
+
"learning_rate": 4.351851851851852e-05,
|
| 308 |
+
"loss": 0.4184,
|
| 309 |
"step": 260
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 16.97,
|
| 313 |
+
"eval_accuracy": 0.7727272727272727,
|
| 314 |
+
"eval_loss": 0.7768625020980835,
|
| 315 |
+
"eval_runtime": 1.0432,
|
| 316 |
+
"eval_samples_per_second": 84.353,
|
| 317 |
+
"eval_steps_per_second": 5.751,
|
| 318 |
"step": 263
|
| 319 |
},
|
| 320 |
{
|
| 321 |
+
"epoch": 17.42,
|
| 322 |
+
"learning_rate": 4.305555555555556e-05,
|
| 323 |
+
"loss": 0.398,
|
| 324 |
"step": 270
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 18.0,
|
| 328 |
+
"eval_accuracy": 0.7386363636363636,
|
| 329 |
+
"eval_loss": 0.8496245741844177,
|
| 330 |
+
"eval_runtime": 1.0792,
|
| 331 |
+
"eval_samples_per_second": 81.539,
|
| 332 |
+
"eval_steps_per_second": 5.559,
|
| 333 |
+
"step": 279
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 18.06,
|
| 337 |
+
"learning_rate": 4.259259259259259e-05,
|
| 338 |
+
"loss": 0.3623,
|
| 339 |
+
"step": 280
|
|
|
|
|
|
|
|
|
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 18.71,
|
| 343 |
+
"learning_rate": 4.212962962962963e-05,
|
| 344 |
+
"loss": 0.3591,
|
| 345 |
"step": 290
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 18.97,
|
| 349 |
+
"eval_accuracy": 0.7272727272727273,
|
| 350 |
+
"eval_loss": 0.8204294443130493,
|
| 351 |
+
"eval_runtime": 1.0712,
|
| 352 |
+
"eval_samples_per_second": 82.148,
|
| 353 |
+
"eval_steps_per_second": 5.601,
|
| 354 |
+
"step": 294
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 19.35,
|
| 358 |
+
"learning_rate": 4.166666666666667e-05,
|
| 359 |
+
"loss": 0.3449,
|
| 360 |
"step": 300
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 20.0,
|
| 364 |
+
"learning_rate": 4.1203703703703705e-05,
|
| 365 |
+
"loss": 0.3536,
|
| 366 |
+
"step": 310
|
|
|
|
|
|
|
|
|
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 20.0,
|
| 370 |
+
"eval_accuracy": 0.7613636363636364,
|
| 371 |
+
"eval_loss": 0.8589130640029907,
|
| 372 |
+
"eval_runtime": 1.0792,
|
| 373 |
+
"eval_samples_per_second": 81.539,
|
| 374 |
+
"eval_steps_per_second": 5.559,
|
| 375 |
"step": 310
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 20.65,
|
| 379 |
+
"learning_rate": 4.074074074074074e-05,
|
| 380 |
+
"loss": 0.2589,
|
| 381 |
"step": 320
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 20.97,
|
| 385 |
+
"eval_accuracy": 0.7045454545454546,
|
| 386 |
+
"eval_loss": 0.9754377007484436,
|
| 387 |
+
"eval_runtime": 1.0472,
|
| 388 |
+
"eval_samples_per_second": 84.031,
|
| 389 |
+
"eval_steps_per_second": 5.729,
|
| 390 |
+
"step": 325
|
| 391 |
},
|
| 392 |
{
|
| 393 |
+
"epoch": 21.29,
|
| 394 |
+
"learning_rate": 4.027777777777778e-05,
|
| 395 |
+
"loss": 0.286,
|
| 396 |
"step": 330
|
| 397 |
},
|
| 398 |
{
|
| 399 |
+
"epoch": 21.94,
|
| 400 |
+
"learning_rate": 3.981481481481482e-05,
|
| 401 |
+
"loss": 0.3218,
|
| 402 |
"step": 340
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 22.0,
|
| 406 |
+
"eval_accuracy": 0.7159090909090909,
|
| 407 |
+
"eval_loss": 1.0231382846832275,
|
| 408 |
+
"eval_runtime": 1.0582,
|
| 409 |
+
"eval_samples_per_second": 83.157,
|
| 410 |
+
"eval_steps_per_second": 5.67,
|
| 411 |
+
"step": 341
|
| 412 |
},
|
| 413 |
{
|
| 414 |
+
"epoch": 22.58,
|
| 415 |
+
"learning_rate": 3.935185185185186e-05,
|
| 416 |
+
"loss": 0.3151,
|
| 417 |
"step": 350
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"epoch": 22.97,
|
| 421 |
+
"eval_accuracy": 0.7386363636363636,
|
| 422 |
+
"eval_loss": 0.9173128604888916,
|
| 423 |
+
"eval_runtime": 1.0472,
|
| 424 |
+
"eval_samples_per_second": 84.031,
|
| 425 |
+
"eval_steps_per_second": 5.729,
|
| 426 |
+
"step": 356
|
| 427 |
},
|
| 428 |
{
|
| 429 |
+
"epoch": 23.23,
|
| 430 |
+
"learning_rate": 3.888888888888889e-05,
|
| 431 |
+
"loss": 0.3135,
|
| 432 |
+
"step": 360
|
|
|
|
|
|
|
|
|
|
| 433 |
},
|
| 434 |
{
|
| 435 |
+
"epoch": 23.87,
|
| 436 |
+
"learning_rate": 3.8425925925925924e-05,
|
| 437 |
+
"loss": 0.2708,
|
| 438 |
"step": 370
|
| 439 |
},
|
| 440 |
{
|
| 441 |
+
"epoch": 24.0,
|
| 442 |
+
"eval_accuracy": 0.7272727272727273,
|
| 443 |
+
"eval_loss": 0.9598014950752258,
|
| 444 |
+
"eval_runtime": 1.0532,
|
| 445 |
+
"eval_samples_per_second": 83.552,
|
| 446 |
+
"eval_steps_per_second": 5.697,
|
| 447 |
+
"step": 372
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 24.52,
|
| 451 |
+
"learning_rate": 3.7962962962962964e-05,
|
| 452 |
+
"loss": 0.2802,
|
| 453 |
"step": 380
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 24.97,
|
| 457 |
+
"eval_accuracy": 0.7386363636363636,
|
| 458 |
+
"eval_loss": 0.904956579208374,
|
| 459 |
+
"eval_runtime": 1.0442,
|
| 460 |
+
"eval_samples_per_second": 84.272,
|
| 461 |
+
"eval_steps_per_second": 5.746,
|
| 462 |
+
"step": 387
|
| 463 |
},
|
| 464 |
{
|
| 465 |
+
"epoch": 25.16,
|
| 466 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 467 |
+
"loss": 0.2795,
|
| 468 |
"step": 390
|
| 469 |
},
|
| 470 |
{
|
| 471 |
+
"epoch": 25.81,
|
| 472 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 473 |
+
"loss": 0.3114,
|
| 474 |
"step": 400
|
| 475 |
},
|
| 476 |
{
|
| 477 |
+
"epoch": 26.0,
|
| 478 |
+
"eval_accuracy": 0.7727272727272727,
|
| 479 |
+
"eval_loss": 0.8725055456161499,
|
| 480 |
+
"eval_runtime": 1.0662,
|
| 481 |
+
"eval_samples_per_second": 82.533,
|
| 482 |
+
"eval_steps_per_second": 5.627,
|
| 483 |
+
"step": 403
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 26.45,
|
| 487 |
+
"learning_rate": 3.6574074074074076e-05,
|
| 488 |
+
"loss": 0.2794,
|
| 489 |
"step": 410
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 26.97,
|
| 493 |
+
"eval_accuracy": 0.7386363636363636,
|
| 494 |
+
"eval_loss": 0.9578754901885986,
|
| 495 |
+
"eval_runtime": 1.0662,
|
| 496 |
+
"eval_samples_per_second": 82.533,
|
| 497 |
+
"eval_steps_per_second": 5.627,
|
| 498 |
+
"step": 418
|
| 499 |
},
|
| 500 |
{
|
| 501 |
+
"epoch": 27.1,
|
| 502 |
+
"learning_rate": 3.611111111111111e-05,
|
| 503 |
+
"loss": 0.2289,
|
| 504 |
+
"step": 420
|
|
|
|
|
|
|
|
|
|
| 505 |
},
|
| 506 |
{
|
| 507 |
+
"epoch": 27.74,
|
| 508 |
+
"learning_rate": 3.564814814814815e-05,
|
| 509 |
+
"loss": 0.26,
|
| 510 |
"step": 430
|
| 511 |
},
|
| 512 |
{
|
| 513 |
+
"epoch": 28.0,
|
| 514 |
+
"eval_accuracy": 0.7272727272727273,
|
| 515 |
+
"eval_loss": 1.0064443349838257,
|
| 516 |
+
"eval_runtime": 1.0862,
|
| 517 |
+
"eval_samples_per_second": 81.013,
|
| 518 |
+
"eval_steps_per_second": 5.524,
|
| 519 |
+
"step": 434
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 28.39,
|
| 523 |
+
"learning_rate": 3.518518518518519e-05,
|
| 524 |
+
"loss": 0.2961,
|
| 525 |
"step": 440
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 28.97,
|
| 529 |
+
"eval_accuracy": 0.75,
|
| 530 |
+
"eval_loss": 1.1055842638015747,
|
| 531 |
+
"eval_runtime": 1.1363,
|
| 532 |
+
"eval_samples_per_second": 77.447,
|
| 533 |
+
"eval_steps_per_second": 5.281,
|
| 534 |
+
"step": 449
|
| 535 |
},
|
| 536 |
{
|
| 537 |
+
"epoch": 29.03,
|
| 538 |
+
"learning_rate": 3.472222222222222e-05,
|
| 539 |
+
"loss": 0.2547,
|
| 540 |
"step": 450
|
| 541 |
},
|
| 542 |
{
|
| 543 |
+
"epoch": 29.68,
|
| 544 |
+
"learning_rate": 3.425925925925926e-05,
|
| 545 |
+
"loss": 0.297,
|
| 546 |
"step": 460
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 30.0,
|
| 550 |
+
"eval_accuracy": 0.7727272727272727,
|
| 551 |
+
"eval_loss": 0.8761419653892517,
|
| 552 |
+
"eval_runtime": 1.1092,
|
| 553 |
+
"eval_samples_per_second": 79.333,
|
| 554 |
+
"eval_steps_per_second": 5.409,
|
| 555 |
"step": 465
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 30.32,
|
| 559 |
+
"learning_rate": 3.3796296296296295e-05,
|
| 560 |
+
"loss": 0.2583,
|
| 561 |
"step": 470
|
| 562 |
},
|
| 563 |
{
|
| 564 |
+
"epoch": 30.97,
|
| 565 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 566 |
+
"loss": 0.2044,
|
| 567 |
"step": 480
|
| 568 |
},
|
| 569 |
{
|
| 570 |
+
"epoch": 30.97,
|
| 571 |
+
"eval_accuracy": 0.7613636363636364,
|
| 572 |
+
"eval_loss": 1.0461256504058838,
|
| 573 |
+
"eval_runtime": 1.1173,
|
| 574 |
+
"eval_samples_per_second": 78.765,
|
| 575 |
+
"eval_steps_per_second": 5.37,
|
| 576 |
+
"step": 480
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 31.61,
|
| 580 |
+
"learning_rate": 3.2870370370370375e-05,
|
| 581 |
+
"loss": 0.1884,
|
| 582 |
"step": 490
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 32.0,
|
| 586 |
+
"eval_accuracy": 0.75,
|
| 587 |
+
"eval_loss": 0.9888725280761719,
|
| 588 |
+
"eval_runtime": 1.0972,
|
| 589 |
+
"eval_samples_per_second": 80.201,
|
| 590 |
+
"eval_steps_per_second": 5.468,
|
| 591 |
+
"step": 496
|
| 592 |
},
|
| 593 |
{
|
| 594 |
+
"epoch": 32.26,
|
| 595 |
+
"learning_rate": 3.240740740740741e-05,
|
| 596 |
+
"loss": 0.1857,
|
| 597 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 32.9,
|
| 601 |
+
"learning_rate": 3.194444444444444e-05,
|
| 602 |
+
"loss": 0.2156,
|
| 603 |
"step": 510
|
| 604 |
},
|
| 605 |
{
|
| 606 |
+
"epoch": 32.97,
|
| 607 |
+
"eval_accuracy": 0.7727272727272727,
|
| 608 |
+
"eval_loss": 1.0186409950256348,
|
| 609 |
+
"eval_runtime": 1.1423,
|
| 610 |
+
"eval_samples_per_second": 77.04,
|
| 611 |
+
"eval_steps_per_second": 5.253,
|
| 612 |
+
"step": 511
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 33.55,
|
| 616 |
+
"learning_rate": 3.148148148148148e-05,
|
| 617 |
+
"loss": 0.194,
|
| 618 |
"step": 520
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 34.0,
|
| 622 |
+
"eval_accuracy": 0.7727272727272727,
|
| 623 |
+
"eval_loss": 1.0899921655654907,
|
| 624 |
+
"eval_runtime": 1.1843,
|
| 625 |
+
"eval_samples_per_second": 74.308,
|
| 626 |
+
"eval_steps_per_second": 5.066,
|
| 627 |
+
"step": 527
|
| 628 |
},
|
| 629 |
{
|
| 630 |
+
"epoch": 34.19,
|
| 631 |
+
"learning_rate": 3.101851851851852e-05,
|
| 632 |
+
"loss": 0.181,
|
| 633 |
"step": 530
|
| 634 |
},
|
| 635 |
{
|
| 636 |
+
"epoch": 34.84,
|
| 637 |
+
"learning_rate": 3.055555555555556e-05,
|
| 638 |
+
"loss": 0.2085,
|
| 639 |
"step": 540
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 34.97,
|
| 643 |
+
"eval_accuracy": 0.75,
|
| 644 |
+
"eval_loss": 1.0762078762054443,
|
| 645 |
+
"eval_runtime": 1.1223,
|
| 646 |
+
"eval_samples_per_second": 78.414,
|
| 647 |
+
"eval_steps_per_second": 5.346,
|
| 648 |
+
"step": 542
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"epoch": 35.48,
|
| 652 |
+
"learning_rate": 3.0092592592592593e-05,
|
| 653 |
+
"loss": 0.1909,
|
| 654 |
"step": 550
|
| 655 |
},
|
| 656 |
{
|
| 657 |
+
"epoch": 36.0,
|
| 658 |
+
"eval_accuracy": 0.7840909090909091,
|
| 659 |
+
"eval_loss": 1.0324878692626953,
|
| 660 |
+
"eval_runtime": 1.1523,
|
| 661 |
+
"eval_samples_per_second": 76.372,
|
| 662 |
+
"eval_steps_per_second": 5.207,
|
| 663 |
+
"step": 558
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 36.13,
|
| 667 |
+
"learning_rate": 2.962962962962963e-05,
|
| 668 |
+
"loss": 0.1864,
|
| 669 |
+
"step": 560
|
|
|
|
|
|
|
|
|
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 36.77,
|
| 673 |
+
"learning_rate": 2.916666666666667e-05,
|
| 674 |
+
"loss": 0.1551,
|
| 675 |
"step": 570
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 36.97,
|
| 679 |
+
"eval_accuracy": 0.7045454545454546,
|
| 680 |
+
"eval_loss": 1.149728775024414,
|
| 681 |
+
"eval_runtime": 1.1653,
|
| 682 |
+
"eval_samples_per_second": 75.519,
|
| 683 |
+
"eval_steps_per_second": 5.149,
|
| 684 |
+
"step": 573
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 37.42,
|
| 688 |
+
"learning_rate": 2.8703703703703706e-05,
|
| 689 |
+
"loss": 0.2106,
|
| 690 |
"step": 580
|
| 691 |
},
|
| 692 |
{
|
| 693 |
+
"epoch": 38.0,
|
| 694 |
+
"eval_accuracy": 0.7727272727272727,
|
| 695 |
+
"eval_loss": 1.0304036140441895,
|
| 696 |
+
"eval_runtime": 1.1102,
|
| 697 |
+
"eval_samples_per_second": 79.261,
|
| 698 |
+
"eval_steps_per_second": 5.404,
|
| 699 |
+
"step": 589
|
| 700 |
},
|
| 701 |
{
|
| 702 |
+
"epoch": 38.06,
|
| 703 |
+
"learning_rate": 2.824074074074074e-05,
|
| 704 |
+
"loss": 0.1922,
|
| 705 |
"step": 590
|
| 706 |
},
|
| 707 |
{
|
| 708 |
+
"epoch": 38.71,
|
| 709 |
+
"learning_rate": 2.777777777777778e-05,
|
| 710 |
+
"loss": 0.1771,
|
| 711 |
"step": 600
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 38.97,
|
| 715 |
+
"eval_accuracy": 0.7840909090909091,
|
| 716 |
+
"eval_loss": 1.0794123411178589,
|
| 717 |
+
"eval_runtime": 1.1483,
|
| 718 |
+
"eval_samples_per_second": 76.638,
|
| 719 |
+
"eval_steps_per_second": 5.225,
|
| 720 |
+
"step": 604
|
| 721 |
},
|
| 722 |
{
|
| 723 |
+
"epoch": 39.35,
|
| 724 |
+
"learning_rate": 2.7314814814814816e-05,
|
| 725 |
+
"loss": 0.2051,
|
| 726 |
"step": 610
|
| 727 |
},
|
| 728 |
{
|
| 729 |
+
"epoch": 40.0,
|
| 730 |
+
"learning_rate": 2.6851851851851855e-05,
|
| 731 |
+
"loss": 0.1567,
|
| 732 |
"step": 620
|
| 733 |
},
|
| 734 |
{
|
| 735 |
+
"epoch": 40.0,
|
| 736 |
+
"eval_accuracy": 0.7954545454545454,
|
| 737 |
+
"eval_loss": 1.0634194612503052,
|
| 738 |
+
"eval_runtime": 1.1643,
|
| 739 |
+
"eval_samples_per_second": 75.584,
|
| 740 |
+
"eval_steps_per_second": 5.153,
|
| 741 |
+
"step": 620
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 40.65,
|
| 745 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 746 |
+
"loss": 0.1856,
|
| 747 |
"step": 630
|
| 748 |
},
|
| 749 |
{
|
| 750 |
+
"epoch": 40.97,
|
| 751 |
+
"eval_accuracy": 0.7613636363636364,
|
| 752 |
+
"eval_loss": 1.0716369152069092,
|
| 753 |
+
"eval_runtime": 1.1173,
|
| 754 |
+
"eval_samples_per_second": 78.765,
|
| 755 |
+
"eval_steps_per_second": 5.37,
|
| 756 |
+
"step": 635
|
| 757 |
},
|
| 758 |
{
|
| 759 |
+
"epoch": 41.29,
|
| 760 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 761 |
+
"loss": 0.1765,
|
| 762 |
+
"step": 640
|
|
|
|
|
|
|
|
|
|
| 763 |
},
|
| 764 |
{
|
| 765 |
+
"epoch": 41.94,
|
| 766 |
+
"learning_rate": 2.5462962962962965e-05,
|
| 767 |
+
"loss": 0.185,
|
| 768 |
"step": 650
|
| 769 |
},
|
| 770 |
{
|
| 771 |
+
"epoch": 42.0,
|
| 772 |
+
"eval_accuracy": 0.8068181818181818,
|
| 773 |
+
"eval_loss": 1.0321924686431885,
|
| 774 |
+
"eval_runtime": 1.1433,
|
| 775 |
+
"eval_samples_per_second": 76.973,
|
| 776 |
+
"eval_steps_per_second": 5.248,
|
| 777 |
+
"step": 651
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 42.58,
|
| 781 |
+
"learning_rate": 2.5e-05,
|
| 782 |
+
"loss": 0.1239,
|
| 783 |
"step": 660
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 42.97,
|
| 787 |
+
"eval_accuracy": 0.7613636363636364,
|
| 788 |
+
"eval_loss": 1.1515936851501465,
|
| 789 |
+
"eval_runtime": 1.1523,
|
| 790 |
+
"eval_samples_per_second": 76.372,
|
| 791 |
+
"eval_steps_per_second": 5.207,
|
| 792 |
+
"step": 666
|
| 793 |
},
|
| 794 |
{
|
| 795 |
+
"epoch": 43.23,
|
| 796 |
+
"learning_rate": 2.4537037037037038e-05,
|
| 797 |
+
"loss": 0.2364,
|
| 798 |
"step": 670
|
| 799 |
},
|
| 800 |
{
|
| 801 |
+
"epoch": 43.87,
|
| 802 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 803 |
+
"loss": 0.1617,
|
| 804 |
"step": 680
|
| 805 |
},
|
| 806 |
{
|
| 807 |
+
"epoch": 44.0,
|
| 808 |
+
"eval_accuracy": 0.7840909090909091,
|
| 809 |
+
"eval_loss": 1.0321751832962036,
|
| 810 |
+
"eval_runtime": 1.1253,
|
| 811 |
+
"eval_samples_per_second": 78.205,
|
| 812 |
+
"eval_steps_per_second": 5.332,
|
| 813 |
+
"step": 682
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 44.52,
|
| 817 |
+
"learning_rate": 2.361111111111111e-05,
|
| 818 |
+
"loss": 0.1221,
|
| 819 |
"step": 690
|
| 820 |
},
|
| 821 |
{
|
| 822 |
+
"epoch": 44.97,
|
| 823 |
+
"eval_accuracy": 0.8068181818181818,
|
| 824 |
+
"eval_loss": 1.0553076267242432,
|
| 825 |
+
"eval_runtime": 1.1333,
|
| 826 |
+
"eval_samples_per_second": 77.652,
|
| 827 |
+
"eval_steps_per_second": 5.294,
|
| 828 |
+
"step": 697
|
| 829 |
},
|
| 830 |
{
|
| 831 |
+
"epoch": 45.16,
|
| 832 |
+
"learning_rate": 2.314814814814815e-05,
|
| 833 |
+
"loss": 0.1953,
|
| 834 |
+
"step": 700
|
|
|
|
|
|
|
|
|
|
| 835 |
},
|
| 836 |
{
|
| 837 |
+
"epoch": 45.81,
|
| 838 |
+
"learning_rate": 2.2685185185185187e-05,
|
| 839 |
+
"loss": 0.1433,
|
| 840 |
"step": 710
|
| 841 |
},
|
| 842 |
{
|
| 843 |
+
"epoch": 46.0,
|
| 844 |
+
"eval_accuracy": 0.7727272727272727,
|
| 845 |
+
"eval_loss": 1.0596939325332642,
|
| 846 |
+
"eval_runtime": 1.1092,
|
| 847 |
+
"eval_samples_per_second": 79.333,
|
| 848 |
+
"eval_steps_per_second": 5.409,
|
| 849 |
+
"step": 713
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 46.45,
|
| 853 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 854 |
+
"loss": 0.216,
|
| 855 |
"step": 720
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 46.97,
|
| 859 |
+
"eval_accuracy": 0.75,
|
| 860 |
+
"eval_loss": 1.1585843563079834,
|
| 861 |
+
"eval_runtime": 1.1223,
|
| 862 |
+
"eval_samples_per_second": 78.414,
|
| 863 |
+
"eval_steps_per_second": 5.346,
|
| 864 |
+
"step": 728
|
| 865 |
},
|
| 866 |
{
|
| 867 |
+
"epoch": 47.1,
|
| 868 |
+
"learning_rate": 2.175925925925926e-05,
|
| 869 |
+
"loss": 0.17,
|
| 870 |
"step": 730
|
| 871 |
},
|
| 872 |
{
|
| 873 |
+
"epoch": 47.74,
|
| 874 |
+
"learning_rate": 2.1296296296296296e-05,
|
| 875 |
+
"loss": 0.1807,
|
| 876 |
"step": 740
|
| 877 |
},
|
| 878 |
{
|
| 879 |
+
"epoch": 48.0,
|
| 880 |
+
"eval_accuracy": 0.7727272727272727,
|
| 881 |
+
"eval_loss": 1.0872578620910645,
|
| 882 |
+
"eval_runtime": 1.1243,
|
| 883 |
+
"eval_samples_per_second": 78.274,
|
| 884 |
+
"eval_steps_per_second": 5.337,
|
| 885 |
+
"step": 744
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 48.39,
|
| 889 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 890 |
+
"loss": 0.185,
|
| 891 |
"step": 750
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 48.97,
|
| 895 |
+
"eval_accuracy": 0.7727272727272727,
|
| 896 |
+
"eval_loss": 1.2490220069885254,
|
| 897 |
+
"eval_runtime": 1.1133,
|
| 898 |
+
"eval_samples_per_second": 79.048,
|
| 899 |
+
"eval_steps_per_second": 5.39,
|
| 900 |
+
"step": 759
|
| 901 |
},
|
| 902 |
{
|
| 903 |
+
"epoch": 49.03,
|
| 904 |
+
"learning_rate": 2.037037037037037e-05,
|
| 905 |
+
"loss": 0.1114,
|
| 906 |
+
"step": 760
|
|
|
|
|
|
|
|
|
|
| 907 |
},
|
| 908 |
{
|
| 909 |
+
"epoch": 49.68,
|
| 910 |
+
"learning_rate": 1.990740740740741e-05,
|
| 911 |
+
"loss": 0.1554,
|
| 912 |
"step": 770
|
| 913 |
},
|
| 914 |
{
|
| 915 |
+
"epoch": 50.0,
|
| 916 |
+
"eval_accuracy": 0.7613636363636364,
|
| 917 |
+
"eval_loss": 1.222277045249939,
|
| 918 |
+
"eval_runtime": 1.2013,
|
| 919 |
+
"eval_samples_per_second": 73.256,
|
| 920 |
+
"eval_steps_per_second": 4.995,
|
| 921 |
+
"step": 775
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 50.32,
|
| 925 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 926 |
+
"loss": 0.1378,
|
| 927 |
"step": 780
|
| 928 |
},
|
| 929 |
{
|
| 930 |
+
"epoch": 50.97,
|
| 931 |
+
"learning_rate": 1.8981481481481482e-05,
|
| 932 |
+
"loss": 0.1359,
|
| 933 |
+
"step": 790
|
|
|
|
|
|
|
|
|
|
| 934 |
},
|
| 935 |
{
|
| 936 |
+
"epoch": 50.97,
|
| 937 |
+
"eval_accuracy": 0.75,
|
| 938 |
+
"eval_loss": 1.2345318794250488,
|
| 939 |
+
"eval_runtime": 1.1193,
|
| 940 |
+
"eval_samples_per_second": 78.624,
|
| 941 |
+
"eval_steps_per_second": 5.361,
|
| 942 |
"step": 790
|
| 943 |
},
|
| 944 |
{
|
| 945 |
+
"epoch": 51.61,
|
| 946 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 947 |
+
"loss": 0.0929,
|
| 948 |
"step": 800
|
| 949 |
},
|
| 950 |
{
|
| 951 |
+
"epoch": 52.0,
|
| 952 |
+
"eval_accuracy": 0.7613636363636364,
|
| 953 |
+
"eval_loss": 1.1833394765853882,
|
| 954 |
+
"eval_runtime": 1.1123,
|
| 955 |
+
"eval_samples_per_second": 79.119,
|
| 956 |
+
"eval_steps_per_second": 5.394,
|
| 957 |
+
"step": 806
|
| 958 |
},
|
| 959 |
{
|
| 960 |
+
"epoch": 52.26,
|
| 961 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 962 |
+
"loss": 0.1513,
|
|
|
|
|
|
|
|
|
|
| 963 |
"step": 810
|
| 964 |
},
|
| 965 |
{
|
| 966 |
+
"epoch": 52.9,
|
| 967 |
+
"learning_rate": 1.7592592592592595e-05,
|
| 968 |
+
"loss": 0.1379,
|
| 969 |
"step": 820
|
| 970 |
},
|
| 971 |
{
|
| 972 |
+
"epoch": 52.97,
|
| 973 |
+
"eval_accuracy": 0.7386363636363636,
|
| 974 |
+
"eval_loss": 1.2581446170806885,
|
| 975 |
+
"eval_runtime": 1.1193,
|
| 976 |
+
"eval_samples_per_second": 78.624,
|
| 977 |
+
"eval_steps_per_second": 5.361,
|
| 978 |
+
"step": 821
|
| 979 |
},
|
| 980 |
{
|
| 981 |
+
"epoch": 53.55,
|
| 982 |
+
"learning_rate": 1.712962962962963e-05,
|
| 983 |
+
"loss": 0.145,
|
|
|
|
|
|
|
|
|
|
| 984 |
"step": 830
|
| 985 |
},
|
| 986 |
{
|
| 987 |
+
"epoch": 54.0,
|
| 988 |
+
"eval_accuracy": 0.75,
|
| 989 |
+
"eval_loss": 1.3023442029953003,
|
| 990 |
+
"eval_runtime": 1.1203,
|
| 991 |
+
"eval_samples_per_second": 78.554,
|
| 992 |
+
"eval_steps_per_second": 5.356,
|
| 993 |
+
"step": 837
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 54.19,
|
| 997 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 998 |
+
"loss": 0.1646,
|
| 999 |
"step": 840
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 54.84,
|
| 1003 |
+
"learning_rate": 1.6203703703703704e-05,
|
| 1004 |
+
"loss": 0.134,
|
| 1005 |
"step": 850
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
+
"epoch": 54.97,
|
| 1009 |
+
"eval_accuracy": 0.75,
|
| 1010 |
+
"eval_loss": 1.2468658685684204,
|
| 1011 |
+
"eval_runtime": 1.1072,
|
| 1012 |
+
"eval_samples_per_second": 79.476,
|
| 1013 |
+
"eval_steps_per_second": 5.419,
|
| 1014 |
+
"step": 852
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
+
"epoch": 55.48,
|
| 1018 |
+
"learning_rate": 1.574074074074074e-05,
|
| 1019 |
+
"loss": 0.1974,
|
| 1020 |
"step": 860
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
+
"epoch": 56.0,
|
| 1024 |
+
"eval_accuracy": 0.7386363636363636,
|
| 1025 |
+
"eval_loss": 1.2670570611953735,
|
| 1026 |
+
"eval_runtime": 1.1002,
|
| 1027 |
+
"eval_samples_per_second": 79.982,
|
| 1028 |
+
"eval_steps_per_second": 5.453,
|
| 1029 |
+
"step": 868
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
+
"epoch": 56.13,
|
| 1033 |
+
"learning_rate": 1.527777777777778e-05,
|
| 1034 |
+
"loss": 0.1158,
|
|
|
|
|
|
|
|
|
|
| 1035 |
"step": 870
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
+
"epoch": 56.77,
|
| 1039 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1040 |
+
"loss": 0.122,
|
| 1041 |
"step": 880
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
+
"epoch": 56.97,
|
| 1045 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1046 |
+
"eval_loss": 1.267562747001648,
|
| 1047 |
+
"eval_runtime": 1.0852,
|
| 1048 |
+
"eval_samples_per_second": 81.088,
|
| 1049 |
+
"eval_steps_per_second": 5.529,
|
| 1050 |
+
"step": 883
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 57.42,
|
| 1054 |
+
"learning_rate": 1.4351851851851853e-05,
|
| 1055 |
+
"loss": 0.1487,
|
| 1056 |
"step": 890
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
+
"epoch": 58.0,
|
| 1060 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1061 |
+
"eval_loss": 1.2845935821533203,
|
| 1062 |
+
"eval_runtime": 1.1173,
|
| 1063 |
+
"eval_samples_per_second": 78.765,
|
| 1064 |
+
"eval_steps_per_second": 5.37,
|
| 1065 |
+
"step": 899
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
+
"epoch": 58.06,
|
| 1069 |
+
"learning_rate": 1.388888888888889e-05,
|
| 1070 |
+
"loss": 0.1473,
|
| 1071 |
"step": 900
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
+
"epoch": 58.71,
|
| 1075 |
+
"learning_rate": 1.3425925925925928e-05,
|
| 1076 |
+
"loss": 0.1282,
|
| 1077 |
"step": 910
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
+
"epoch": 58.97,
|
| 1081 |
+
"eval_accuracy": 0.75,
|
| 1082 |
+
"eval_loss": 1.1780353784561157,
|
| 1083 |
+
"eval_runtime": 1.0612,
|
| 1084 |
+
"eval_samples_per_second": 82.922,
|
| 1085 |
+
"eval_steps_per_second": 5.654,
|
| 1086 |
+
"step": 914
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
+
"epoch": 59.35,
|
| 1090 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 1091 |
+
"loss": 0.1006,
|
| 1092 |
"step": 920
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
+
"epoch": 60.0,
|
| 1096 |
+
"learning_rate": 1.25e-05,
|
| 1097 |
+
"loss": 0.0989,
|
| 1098 |
"step": 930
|
| 1099 |
},
|
| 1100 |
{
|
| 1101 |
+
"epoch": 60.0,
|
| 1102 |
+
"eval_accuracy": 0.75,
|
| 1103 |
+
"eval_loss": 1.231979489326477,
|
| 1104 |
+
"eval_runtime": 1.0982,
|
| 1105 |
+
"eval_samples_per_second": 80.128,
|
| 1106 |
+
"eval_steps_per_second": 5.463,
|
| 1107 |
+
"step": 930
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 60.65,
|
| 1111 |
+
"learning_rate": 1.2037037037037037e-05,
|
| 1112 |
+
"loss": 0.0997,
|
| 1113 |
"step": 940
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
+
"epoch": 60.97,
|
| 1117 |
+
"eval_accuracy": 0.7386363636363636,
|
| 1118 |
+
"eval_loss": 1.2791739702224731,
|
| 1119 |
+
"eval_runtime": 1.1663,
|
| 1120 |
+
"eval_samples_per_second": 75.455,
|
| 1121 |
+
"eval_steps_per_second": 5.145,
|
| 1122 |
+
"step": 945
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
+
"epoch": 61.29,
|
| 1126 |
+
"learning_rate": 1.1574074074074075e-05,
|
| 1127 |
+
"loss": 0.1234,
|
| 1128 |
+
"step": 950
|
|
|
|
|
|
|
|
|
|
| 1129 |
},
|
| 1130 |
{
|
| 1131 |
+
"epoch": 61.94,
|
| 1132 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 1133 |
+
"loss": 0.1058,
|
| 1134 |
"step": 960
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
+
"epoch": 62.0,
|
| 1138 |
+
"eval_accuracy": 0.7613636363636364,
|
| 1139 |
+
"eval_loss": 1.2126153707504272,
|
| 1140 |
+
"eval_runtime": 1.1072,
|
| 1141 |
+
"eval_samples_per_second": 79.476,
|
| 1142 |
+
"eval_steps_per_second": 5.419,
|
| 1143 |
+
"step": 961
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 62.58,
|
| 1147 |
+
"learning_rate": 1.0648148148148148e-05,
|
| 1148 |
+
"loss": 0.1105,
|
| 1149 |
"step": 970
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
+
"epoch": 62.97,
|
| 1153 |
+
"eval_accuracy": 0.7386363636363636,
|
| 1154 |
+
"eval_loss": 1.256054401397705,
|
| 1155 |
+
"eval_runtime": 1.0872,
|
| 1156 |
+
"eval_samples_per_second": 80.939,
|
| 1157 |
+
"eval_steps_per_second": 5.519,
|
| 1158 |
+
"step": 976
|
| 1159 |
},
|
| 1160 |
{
|
| 1161 |
+
"epoch": 63.23,
|
| 1162 |
+
"learning_rate": 1.0185185185185185e-05,
|
| 1163 |
+
"loss": 0.1254,
|
| 1164 |
"step": 980
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
+
"epoch": 63.87,
|
| 1168 |
+
"learning_rate": 9.722222222222223e-06,
|
| 1169 |
+
"loss": 0.0957,
|
| 1170 |
"step": 990
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
+
"epoch": 64.0,
|
| 1174 |
+
"eval_accuracy": 0.7613636363636364,
|
| 1175 |
+
"eval_loss": 1.1701573133468628,
|
| 1176 |
+
"eval_runtime": 1.1323,
|
| 1177 |
+
"eval_samples_per_second": 77.721,
|
| 1178 |
+
"eval_steps_per_second": 5.299,
|
| 1179 |
"step": 992
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
+
"epoch": 64.52,
|
| 1183 |
+
"learning_rate": 9.259259259259259e-06,
|
| 1184 |
+
"loss": 0.1326,
|
| 1185 |
"step": 1000
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
+
"epoch": 64.97,
|
| 1189 |
+
"eval_accuracy": 0.75,
|
| 1190 |
+
"eval_loss": 1.1838548183441162,
|
| 1191 |
+
"eval_runtime": 1.1042,
|
| 1192 |
+
"eval_samples_per_second": 79.692,
|
| 1193 |
+
"eval_steps_per_second": 5.434,
|
| 1194 |
+
"step": 1007
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
+
"epoch": 65.16,
|
| 1198 |
+
"learning_rate": 8.796296296296297e-06,
|
| 1199 |
+
"loss": 0.1424,
|
| 1200 |
+
"step": 1010
|
|
|
|
|
|
|
|
|
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
+
"epoch": 65.81,
|
| 1204 |
+
"learning_rate": 8.333333333333334e-06,
|
| 1205 |
+
"loss": 0.0838,
|
| 1206 |
"step": 1020
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
+
"epoch": 66.0,
|
| 1210 |
+
"eval_accuracy": 0.7386363636363636,
|
| 1211 |
+
"eval_loss": 1.2728073596954346,
|
| 1212 |
+
"eval_runtime": 1.1643,
|
| 1213 |
+
"eval_samples_per_second": 75.584,
|
| 1214 |
+
"eval_steps_per_second": 5.153,
|
| 1215 |
+
"step": 1023
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 66.45,
|
| 1219 |
+
"learning_rate": 7.87037037037037e-06,
|
| 1220 |
+
"loss": 0.1163,
|
| 1221 |
"step": 1030
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
+
"epoch": 66.97,
|
| 1225 |
+
"eval_accuracy": 0.75,
|
| 1226 |
+
"eval_loss": 1.2736155986785889,
|
| 1227 |
+
"eval_runtime": 1.1353,
|
| 1228 |
+
"eval_samples_per_second": 77.516,
|
| 1229 |
+
"eval_steps_per_second": 5.285,
|
| 1230 |
+
"step": 1038
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
+
"epoch": 67.1,
|
| 1234 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 1235 |
+
"loss": 0.1363,
|
| 1236 |
"step": 1040
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
+
"epoch": 67.74,
|
| 1240 |
+
"learning_rate": 6.944444444444445e-06,
|
| 1241 |
+
"loss": 0.0926,
|
| 1242 |
"step": 1050
|
| 1243 |
},
|
| 1244 |
{
|
| 1245 |
+
"epoch": 68.0,
|
| 1246 |
+
"eval_accuracy": 0.75,
|
| 1247 |
+
"eval_loss": 1.2641026973724365,
|
| 1248 |
+
"eval_runtime": 1.1493,
|
| 1249 |
+
"eval_samples_per_second": 76.571,
|
| 1250 |
+
"eval_steps_per_second": 5.221,
|
| 1251 |
+
"step": 1054
|
| 1252 |
},
|
| 1253 |
{
|
| 1254 |
+
"epoch": 68.39,
|
| 1255 |
+
"learning_rate": 6.481481481481481e-06,
|
| 1256 |
+
"loss": 0.102,
|
| 1257 |
"step": 1060
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
+
"epoch": 68.97,
|
| 1261 |
+
"eval_accuracy": 0.75,
|
| 1262 |
+
"eval_loss": 1.3310309648513794,
|
| 1263 |
+
"eval_runtime": 1.1102,
|
| 1264 |
+
"eval_samples_per_second": 79.261,
|
| 1265 |
+
"eval_steps_per_second": 5.404,
|
| 1266 |
+
"step": 1069
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
+
"epoch": 69.03,
|
| 1270 |
+
"learning_rate": 6.0185185185185185e-06,
|
| 1271 |
+
"loss": 0.1224,
|
| 1272 |
+
"step": 1070
|
|
|
|
|
|
|
|
|
|
| 1273 |
},
|
| 1274 |
{
|
| 1275 |
+
"epoch": 69.68,
|
| 1276 |
+
"learning_rate": 5.555555555555556e-06,
|
| 1277 |
+
"loss": 0.0996,
|
| 1278 |
"step": 1080
|
| 1279 |
},
|
| 1280 |
{
|
| 1281 |
+
"epoch": 70.0,
|
| 1282 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1283 |
+
"eval_loss": 1.3119887113571167,
|
| 1284 |
+
"eval_runtime": 1.1012,
|
| 1285 |
+
"eval_samples_per_second": 79.909,
|
| 1286 |
+
"eval_steps_per_second": 5.448,
|
| 1287 |
+
"step": 1085
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 70.32,
|
| 1291 |
+
"learning_rate": 5.092592592592592e-06,
|
| 1292 |
+
"loss": 0.1182,
|
| 1293 |
"step": 1090
|
| 1294 |
},
|
| 1295 |
{
|
| 1296 |
+
"epoch": 70.97,
|
| 1297 |
+
"learning_rate": 4.6296296296296296e-06,
|
| 1298 |
+
"loss": 0.081,
|
| 1299 |
+
"step": 1100
|
|
|
|
|
|
|
|
|
|
| 1300 |
},
|
| 1301 |
{
|
| 1302 |
+
"epoch": 70.97,
|
| 1303 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1304 |
+
"eval_loss": 1.3357912302017212,
|
| 1305 |
+
"eval_runtime": 1.1133,
|
| 1306 |
+
"eval_samples_per_second": 79.048,
|
| 1307 |
+
"eval_steps_per_second": 5.39,
|
| 1308 |
"step": 1100
|
| 1309 |
},
|
| 1310 |
{
|
| 1311 |
+
"epoch": 71.61,
|
| 1312 |
+
"learning_rate": 4.166666666666667e-06,
|
| 1313 |
+
"loss": 0.1305,
|
| 1314 |
"step": 1110
|
| 1315 |
},
|
| 1316 |
{
|
| 1317 |
+
"epoch": 72.0,
|
| 1318 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1319 |
+
"eval_loss": 1.3439818620681763,
|
| 1320 |
+
"eval_runtime": 1.1243,
|
| 1321 |
+
"eval_samples_per_second": 78.274,
|
| 1322 |
+
"eval_steps_per_second": 5.337,
|
| 1323 |
+
"step": 1116
|
| 1324 |
},
|
| 1325 |
{
|
| 1326 |
+
"epoch": 72.26,
|
| 1327 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 1328 |
+
"loss": 0.1309,
|
| 1329 |
"step": 1120
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
+
"epoch": 72.9,
|
| 1333 |
+
"learning_rate": 3.2407407407407406e-06,
|
| 1334 |
+
"loss": 0.1131,
|
| 1335 |
"step": 1130
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
+
"epoch": 72.97,
|
| 1339 |
+
"eval_accuracy": 0.7272727272727273,
|
| 1340 |
+
"eval_loss": 1.3126434087753296,
|
| 1341 |
+
"eval_runtime": 1.1203,
|
| 1342 |
+
"eval_samples_per_second": 78.554,
|
| 1343 |
+
"eval_steps_per_second": 5.356,
|
| 1344 |
+
"step": 1131
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
+
"epoch": 73.55,
|
| 1348 |
+
"learning_rate": 2.777777777777778e-06,
|
| 1349 |
+
"loss": 0.0883,
|
| 1350 |
"step": 1140
|
| 1351 |
},
|
| 1352 |
{
|
| 1353 |
+
"epoch": 74.0,
|
| 1354 |
+
"eval_accuracy": 0.7386363636363636,
|
| 1355 |
+
"eval_loss": 1.284845232963562,
|
| 1356 |
+
"eval_runtime": 1.0972,
|
| 1357 |
+
"eval_samples_per_second": 80.201,
|
| 1358 |
+
"eval_steps_per_second": 5.468,
|
| 1359 |
+
"step": 1147
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
+
"epoch": 74.19,
|
| 1363 |
+
"learning_rate": 2.3148148148148148e-06,
|
| 1364 |
+
"loss": 0.1135,
|
| 1365 |
+
"step": 1150
|
|
|
|
|
|
|
|
|
|
| 1366 |
},
|
| 1367 |
{
|
| 1368 |
+
"epoch": 74.84,
|
| 1369 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 1370 |
+
"loss": 0.0873,
|
| 1371 |
"step": 1160
|
| 1372 |
},
|
| 1373 |
{
|
| 1374 |
+
"epoch": 74.97,
|
| 1375 |
+
"eval_accuracy": 0.7386363636363636,
|
| 1376 |
+
"eval_loss": 1.2801809310913086,
|
| 1377 |
+
"eval_runtime": 1.1313,
|
| 1378 |
+
"eval_samples_per_second": 77.79,
|
| 1379 |
+
"eval_steps_per_second": 5.304,
|
| 1380 |
+
"step": 1162
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 75.48,
|
| 1384 |
+
"learning_rate": 1.388888888888889e-06,
|
| 1385 |
+
"loss": 0.0991,
|
| 1386 |
"step": 1170
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
+
"epoch": 76.0,
|
| 1390 |
+
"eval_accuracy": 0.75,
|
| 1391 |
+
"eval_loss": 1.2710990905761719,
|
| 1392 |
+
"eval_runtime": 1.1643,
|
| 1393 |
+
"eval_samples_per_second": 75.584,
|
| 1394 |
+
"eval_steps_per_second": 5.153,
|
| 1395 |
+
"step": 1178
|
| 1396 |
},
|
| 1397 |
{
|
| 1398 |
+
"epoch": 76.13,
|
| 1399 |
+
"learning_rate": 9.259259259259259e-07,
|
| 1400 |
+
"loss": 0.0946,
|
| 1401 |
"step": 1180
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
+
"epoch": 76.77,
|
| 1405 |
+
"learning_rate": 4.6296296296296297e-07,
|
| 1406 |
+
"loss": 0.0881,
|
| 1407 |
"step": 1190
|
| 1408 |
},
|
| 1409 |
{
|
| 1410 |
+
"epoch": 76.97,
|
| 1411 |
+
"eval_accuracy": 0.75,
|
| 1412 |
+
"eval_loss": 1.2746005058288574,
|
| 1413 |
+
"eval_runtime": 1.4135,
|
| 1414 |
+
"eval_samples_per_second": 62.256,
|
| 1415 |
+
"eval_steps_per_second": 4.245,
|
| 1416 |
+
"step": 1193
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
+
"epoch": 77.42,
|
| 1420 |
+
"learning_rate": 0.0,
|
| 1421 |
+
"loss": 0.0895,
|
| 1422 |
"step": 1200
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
+
"epoch": 77.42,
|
| 1426 |
+
"eval_accuracy": 0.75,
|
| 1427 |
+
"eval_loss": 1.275152325630188,
|
| 1428 |
+
"eval_runtime": 1.1543,
|
| 1429 |
+
"eval_samples_per_second": 76.239,
|
| 1430 |
+
"eval_steps_per_second": 5.198,
|
| 1431 |
+
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1432 |
},
|
| 1433 |
{
|
| 1434 |
+
"epoch": 77.42,
|
| 1435 |
+
"step": 1200,
|
| 1436 |
+
"total_flos": 2.4687812024881644e+18,
|
| 1437 |
+
"train_loss": 0.34467112536231675,
|
| 1438 |
+
"train_runtime": 2690.4819,
|
| 1439 |
+
"train_samples_per_second": 29.14,
|
| 1440 |
+
"train_steps_per_second": 0.446
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1441 |
}
|
| 1442 |
],
|
| 1443 |
"logging_steps": 10,
|
| 1444 |
+
"max_steps": 1200,
|
| 1445 |
"num_input_tokens_seen": 0,
|
| 1446 |
"num_train_epochs": 80,
|
| 1447 |
"save_steps": 500,
|
| 1448 |
+
"total_flos": 2.4687812024881644e+18,
|
| 1449 |
"train_batch_size": 16,
|
| 1450 |
"trial_name": null,
|
| 1451 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18090fdadccf48c9d95b1c06c7930e2bbf8d2ce2e91d373591632e49d3c84478
|
| 3 |
size 4728
|