End of training
Browse files- README.md +44 -44
- all_results.json +9 -9
- eval_results.json +5 -5
- model.safetensors +1 -1
- runs/Dec01_19-11-43_DESKTOP-SKBE9FB/events.out.tfevents.1733101904.DESKTOP-SKBE9FB.5632.0 +3 -0
- runs/Dec01_19-11-43_DESKTOP-SKBE9FB/events.out.tfevents.1733102475.DESKTOP-SKBE9FB.5632.1 +3 -0
- train_results.json +4 -4
- trainer_state.json +254 -254
- 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: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -52,7 +52,7 @@ More information needed
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
-
- learning_rate:
|
| 56 |
- train_batch_size: 16
|
| 57 |
- eval_batch_size: 16
|
| 58 |
- seed: 42
|
|
@@ -67,46 +67,46 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
| No log | 1.0 | 8 | 4.
|
| 71 |
-
| 4.
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
|
|
| 75 |
-
|
|
| 76 |
-
|
|
| 77 |
-
|
|
| 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 |
|
| 111 |
|
| 112 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.6822429906542056
|
| 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: 0.6396
|
| 36 |
+
- Accuracy: 0.6822
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 4e-05
|
| 56 |
- train_batch_size: 16
|
| 57 |
- eval_batch_size: 16
|
| 58 |
- seed: 42
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 8 | 4.6265 | 0.4112 |
|
| 71 |
+
| 4.5369 | 2.0 | 16 | 4.5295 | 0.4112 |
|
| 72 |
+
| 4.6305 | 3.0 | 24 | 4.1439 | 0.4112 |
|
| 73 |
+
| 4.0918 | 4.0 | 32 | 3.3693 | 0.4112 |
|
| 74 |
+
| 3.1767 | 5.0 | 40 | 2.4325 | 0.4112 |
|
| 75 |
+
| 3.1767 | 6.0 | 48 | 1.5422 | 0.4112 |
|
| 76 |
+
| 2.0113 | 7.0 | 56 | 0.8834 | 0.4112 |
|
| 77 |
+
| 1.0593 | 8.0 | 64 | 0.6790 | 0.5888 |
|
| 78 |
+
| 0.696 | 9.0 | 72 | 0.7044 | 0.5888 |
|
| 79 |
+
| 0.6893 | 10.0 | 80 | 0.6778 | 0.5888 |
|
| 80 |
+
| 0.6893 | 11.0 | 88 | 0.6866 | 0.5888 |
|
| 81 |
+
| 0.6961 | 12.0 | 96 | 0.6934 | 0.5888 |
|
| 82 |
+
| 0.7329 | 13.0 | 104 | 0.6915 | 0.5888 |
|
| 83 |
+
| 0.6948 | 14.0 | 112 | 0.6762 | 0.5888 |
|
| 84 |
+
| 0.6771 | 15.0 | 120 | 0.6795 | 0.5888 |
|
| 85 |
+
| 0.6771 | 16.0 | 128 | 0.6801 | 0.5888 |
|
| 86 |
+
| 0.6763 | 17.0 | 136 | 0.6820 | 0.5888 |
|
| 87 |
+
| 0.6822 | 18.0 | 144 | 0.6800 | 0.5888 |
|
| 88 |
+
| 0.6723 | 19.0 | 152 | 0.6741 | 0.5888 |
|
| 89 |
+
| 0.6757 | 20.0 | 160 | 0.6815 | 0.5888 |
|
| 90 |
+
| 0.6757 | 21.0 | 168 | 0.6729 | 0.5888 |
|
| 91 |
+
| 0.6711 | 22.0 | 176 | 0.6812 | 0.5888 |
|
| 92 |
+
| 0.6784 | 23.0 | 184 | 0.6781 | 0.5794 |
|
| 93 |
+
| 0.6665 | 24.0 | 192 | 0.6698 | 0.5794 |
|
| 94 |
+
| 0.6723 | 25.0 | 200 | 0.6647 | 0.5981 |
|
| 95 |
+
| 0.6723 | 26.0 | 208 | 0.6762 | 0.5794 |
|
| 96 |
+
| 0.6675 | 27.0 | 216 | 0.6597 | 0.5701 |
|
| 97 |
+
| 0.6628 | 28.0 | 224 | 0.6563 | 0.6355 |
|
| 98 |
+
| 0.6478 | 29.0 | 232 | 0.6791 | 0.5794 |
|
| 99 |
+
| 0.6642 | 30.0 | 240 | 0.6574 | 0.5888 |
|
| 100 |
+
| 0.6642 | 31.0 | 248 | 0.6556 | 0.5607 |
|
| 101 |
+
| 0.654 | 32.0 | 256 | 0.6523 | 0.5888 |
|
| 102 |
+
| 0.6602 | 33.0 | 264 | 0.6464 | 0.6262 |
|
| 103 |
+
| 0.6535 | 34.0 | 272 | 0.6450 | 0.6168 |
|
| 104 |
+
| 0.6506 | 35.0 | 280 | 0.6550 | 0.5794 |
|
| 105 |
+
| 0.6506 | 36.0 | 288 | 0.6438 | 0.6075 |
|
| 106 |
+
| 0.6533 | 37.0 | 296 | 0.6396 | 0.6822 |
|
| 107 |
+
| 0.6443 | 38.0 | 304 | 0.6383 | 0.6636 |
|
| 108 |
+
| 0.6263 | 39.0 | 312 | 0.6378 | 0.6449 |
|
| 109 |
+
| 0.6283 | 40.0 | 320 | 0.6379 | 0.6449 |
|
| 110 |
|
| 111 |
|
| 112 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 40.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
-
"train_loss":
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.6822429906542056,
|
| 4 |
+
"eval_loss": 0.6395505666732788,
|
| 5 |
+
"eval_runtime": 1.971,
|
| 6 |
+
"eval_samples_per_second": 54.288,
|
| 7 |
+
"eval_steps_per_second": 3.552,
|
| 8 |
+
"train_loss": 1.1531404286623002,
|
| 9 |
+
"train_runtime": 569.0029,
|
| 10 |
+
"train_samples_per_second": 35.009,
|
| 11 |
+
"train_steps_per_second": 0.562
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 40.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 3.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.6822429906542056,
|
| 4 |
+
"eval_loss": 0.6395505666732788,
|
| 5 |
+
"eval_runtime": 1.971,
|
| 6 |
+
"eval_samples_per_second": 54.288,
|
| 7 |
+
"eval_steps_per_second": 3.552
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110350128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65de1007e53d84849bf77cba6491b1b90ffc48c80769e0d3eac6bb172d6e6d23
|
| 3 |
size 110350128
|
runs/Dec01_19-11-43_DESKTOP-SKBE9FB/events.out.tfevents.1733101904.DESKTOP-SKBE9FB.5632.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ca5bb44bf6d5dac75e7187e391c40ab012431b2530c30f26e747fcdf8733c5e
|
| 3 |
+
size 22870
|
runs/Dec01_19-11-43_DESKTOP-SKBE9FB/events.out.tfevents.1733102475.DESKTOP-SKBE9FB.5632.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:77d00c1cc2cd9dfe2fe50adad5e853ad9b511e866d1ef303e5e4e5a7261df6b0
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 40.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 40.0,
|
| 3 |
+
"train_loss": 1.1531404286623002,
|
| 4 |
+
"train_runtime": 569.0029,
|
| 5 |
+
"train_samples_per_second": 35.009,
|
| 6 |
+
"train_steps_per_second": 0.562
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RH\\checkpoint-
|
| 4 |
"epoch": 40.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 320,
|
|
@@ -11,563 +11,563 @@
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_accuracy": 0.411214953271028,
|
| 14 |
-
"eval_loss": 4.
|
| 15 |
-
"eval_runtime": 1.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second": 3.
|
| 18 |
"step": 8
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.25,
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 4.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
"eval_accuracy": 0.411214953271028,
|
| 29 |
-
"eval_loss":
|
| 30 |
-
"eval_runtime": 1.
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second": 3.
|
| 33 |
"step": 16
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 2.5,
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss":
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 3.0,
|
| 43 |
"eval_accuracy": 0.411214953271028,
|
| 44 |
-
"eval_loss":
|
| 45 |
-
"eval_runtime": 1.
|
| 46 |
-
"eval_samples_per_second":
|
| 47 |
-
"eval_steps_per_second": 3.
|
| 48 |
"step": 24
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 3.75,
|
| 52 |
-
"learning_rate":
|
| 53 |
-
"loss":
|
| 54 |
"step": 30
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 4.0,
|
| 58 |
"eval_accuracy": 0.411214953271028,
|
| 59 |
-
"eval_loss":
|
| 60 |
-
"eval_runtime": 1.
|
| 61 |
-
"eval_samples_per_second": 57.
|
| 62 |
-
"eval_steps_per_second": 3.
|
| 63 |
"step": 32
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 5.0,
|
| 67 |
-
"learning_rate":
|
| 68 |
-
"loss":
|
| 69 |
"step": 40
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 5.0,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_loss":
|
| 75 |
-
"eval_runtime": 1.
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second": 3.
|
| 78 |
"step": 40
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 6.0,
|
| 82 |
-
"eval_accuracy": 0.
|
| 83 |
-
"eval_loss":
|
| 84 |
-
"eval_runtime": 1.
|
| 85 |
-
"eval_samples_per_second":
|
| 86 |
-
"eval_steps_per_second": 3.
|
| 87 |
"step": 48
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 6.25,
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss":
|
| 93 |
"step": 50
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 7.0,
|
| 97 |
-
"eval_accuracy": 0.
|
| 98 |
-
"eval_loss": 0.
|
| 99 |
-
"eval_runtime": 1.
|
| 100 |
-
"eval_samples_per_second":
|
| 101 |
-
"eval_steps_per_second": 3.
|
| 102 |
"step": 56
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 7.5,
|
| 106 |
-
"learning_rate":
|
| 107 |
-
"loss":
|
| 108 |
"step": 60
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 8.0,
|
| 112 |
"eval_accuracy": 0.5887850467289719,
|
| 113 |
-
"eval_loss": 0.
|
| 114 |
-
"eval_runtime": 1.
|
| 115 |
-
"eval_samples_per_second":
|
| 116 |
-
"eval_steps_per_second": 3.
|
| 117 |
"step": 64
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 8.75,
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 70
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 9.0,
|
| 127 |
"eval_accuracy": 0.5887850467289719,
|
| 128 |
-
"eval_loss": 0.
|
| 129 |
-
"eval_runtime": 1.
|
| 130 |
-
"eval_samples_per_second":
|
| 131 |
-
"eval_steps_per_second": 3.
|
| 132 |
"step": 72
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 10.0,
|
| 136 |
-
"learning_rate":
|
| 137 |
-
"loss": 0.
|
| 138 |
"step": 80
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 10.0,
|
| 142 |
-
"eval_accuracy": 0.
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
-
"eval_runtime": 1.
|
| 145 |
-
"eval_samples_per_second":
|
| 146 |
-
"eval_steps_per_second": 3.
|
| 147 |
"step": 80
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 11.0,
|
| 151 |
"eval_accuracy": 0.5887850467289719,
|
| 152 |
-
"eval_loss": 0.
|
| 153 |
-
"eval_runtime": 1.
|
| 154 |
-
"eval_samples_per_second":
|
| 155 |
-
"eval_steps_per_second": 3.
|
| 156 |
"step": 88
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 11.25,
|
| 160 |
-
"learning_rate":
|
| 161 |
-
"loss": 0.
|
| 162 |
"step": 90
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 12.0,
|
| 166 |
"eval_accuracy": 0.5887850467289719,
|
| 167 |
-
"eval_loss": 0.
|
| 168 |
-
"eval_runtime": 1.
|
| 169 |
-
"eval_samples_per_second":
|
| 170 |
-
"eval_steps_per_second": 3.
|
| 171 |
"step": 96
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 12.5,
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 100
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 13.0,
|
| 181 |
"eval_accuracy": 0.5887850467289719,
|
| 182 |
-
"eval_loss": 0.
|
| 183 |
-
"eval_runtime": 1.
|
| 184 |
-
"eval_samples_per_second": 57.
|
| 185 |
-
"eval_steps_per_second": 3.
|
| 186 |
"step": 104
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 13.75,
|
| 190 |
-
"learning_rate":
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 110
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 14.0,
|
| 196 |
"eval_accuracy": 0.5887850467289719,
|
| 197 |
-
"eval_loss": 0.
|
| 198 |
-
"eval_runtime": 1.
|
| 199 |
-
"eval_samples_per_second":
|
| 200 |
-
"eval_steps_per_second": 3.
|
| 201 |
"step": 112
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 15.0,
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 120
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 15.0,
|
| 211 |
"eval_accuracy": 0.5887850467289719,
|
| 212 |
-
"eval_loss": 0.
|
| 213 |
-
"eval_runtime":
|
| 214 |
-
"eval_samples_per_second":
|
| 215 |
-
"eval_steps_per_second": 3.
|
| 216 |
"step": 120
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 16.0,
|
| 220 |
"eval_accuracy": 0.5887850467289719,
|
| 221 |
-
"eval_loss": 0.
|
| 222 |
-
"eval_runtime":
|
| 223 |
-
"eval_samples_per_second":
|
| 224 |
-
"eval_steps_per_second": 3.
|
| 225 |
"step": 128
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 16.25,
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 130
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 17.0,
|
| 235 |
"eval_accuracy": 0.5887850467289719,
|
| 236 |
-
"eval_loss": 0.
|
| 237 |
-
"eval_runtime": 1.
|
| 238 |
-
"eval_samples_per_second": 57.
|
| 239 |
-
"eval_steps_per_second": 3.
|
| 240 |
"step": 136
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 17.5,
|
| 244 |
-
"learning_rate":
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 140
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 18.0,
|
| 250 |
-
"eval_accuracy": 0.
|
| 251 |
-
"eval_loss": 0.
|
| 252 |
-
"eval_runtime": 1.
|
| 253 |
-
"eval_samples_per_second":
|
| 254 |
-
"eval_steps_per_second": 3.
|
| 255 |
"step": 144
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 18.75,
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 150
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 19.0,
|
| 265 |
"eval_accuracy": 0.5887850467289719,
|
| 266 |
-
"eval_loss": 0.
|
| 267 |
-
"eval_runtime": 1.
|
| 268 |
-
"eval_samples_per_second":
|
| 269 |
-
"eval_steps_per_second": 3.
|
| 270 |
"step": 152
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 20.0,
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 160
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 20.0,
|
| 280 |
-
"eval_accuracy": 0.
|
| 281 |
-
"eval_loss": 0.
|
| 282 |
-
"eval_runtime": 1.
|
| 283 |
-
"eval_samples_per_second":
|
| 284 |
-
"eval_steps_per_second": 3.
|
| 285 |
"step": 160
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 21.0,
|
| 289 |
"eval_accuracy": 0.5887850467289719,
|
| 290 |
-
"eval_loss": 0.
|
| 291 |
-
"eval_runtime": 1.
|
| 292 |
-
"eval_samples_per_second":
|
| 293 |
-
"eval_steps_per_second": 3.
|
| 294 |
"step": 168
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 21.25,
|
| 298 |
-
"learning_rate":
|
| 299 |
-
"loss": 0.
|
| 300 |
"step": 170
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 22.0,
|
| 304 |
-
"eval_accuracy": 0.
|
| 305 |
-
"eval_loss": 0.
|
| 306 |
-
"eval_runtime": 1.
|
| 307 |
-
"eval_samples_per_second":
|
| 308 |
-
"eval_steps_per_second": 3.
|
| 309 |
"step": 176
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 22.5,
|
| 313 |
-
"learning_rate":
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 180
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 23.0,
|
| 319 |
-
"eval_accuracy": 0.
|
| 320 |
-
"eval_loss": 0.
|
| 321 |
-
"eval_runtime": 1.
|
| 322 |
-
"eval_samples_per_second": 55.
|
| 323 |
-
"eval_steps_per_second": 3.
|
| 324 |
"step": 184
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 23.75,
|
| 328 |
-
"learning_rate":
|
| 329 |
-
"loss": 0.
|
| 330 |
"step": 190
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 24.0,
|
| 334 |
-
"eval_accuracy": 0.
|
| 335 |
-
"eval_loss": 0.
|
| 336 |
-
"eval_runtime": 1.
|
| 337 |
-
"eval_samples_per_second":
|
| 338 |
-
"eval_steps_per_second": 3.
|
| 339 |
"step": 192
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 25.0,
|
| 343 |
-
"learning_rate":
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 200
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 25.0,
|
| 349 |
-
"eval_accuracy": 0.
|
| 350 |
-
"eval_loss": 0.
|
| 351 |
-
"eval_runtime": 1.
|
| 352 |
-
"eval_samples_per_second": 57.
|
| 353 |
-
"eval_steps_per_second": 3.
|
| 354 |
"step": 200
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 26.0,
|
| 358 |
-
"eval_accuracy": 0.
|
| 359 |
-
"eval_loss": 0.
|
| 360 |
-
"eval_runtime": 1.
|
| 361 |
-
"eval_samples_per_second": 57.
|
| 362 |
-
"eval_steps_per_second": 3.
|
| 363 |
"step": 208
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 26.25,
|
| 367 |
-
"learning_rate":
|
| 368 |
-
"loss": 0.
|
| 369 |
"step": 210
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 27.0,
|
| 373 |
-
"eval_accuracy": 0.
|
| 374 |
-
"eval_loss": 0.
|
| 375 |
-
"eval_runtime": 1.
|
| 376 |
-
"eval_samples_per_second":
|
| 377 |
-
"eval_steps_per_second": 3.
|
| 378 |
"step": 216
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 27.5,
|
| 382 |
-
"learning_rate":
|
| 383 |
-
"loss": 0.
|
| 384 |
"step": 220
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 28.0,
|
| 388 |
-
"eval_accuracy": 0.
|
| 389 |
-
"eval_loss": 0.
|
| 390 |
-
"eval_runtime": 1.
|
| 391 |
-
"eval_samples_per_second":
|
| 392 |
-
"eval_steps_per_second": 3.
|
| 393 |
"step": 224
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 28.75,
|
| 397 |
-
"learning_rate":
|
| 398 |
-
"loss": 0.
|
| 399 |
"step": 230
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 29.0,
|
| 403 |
-
"eval_accuracy": 0.
|
| 404 |
-
"eval_loss": 0.
|
| 405 |
-
"eval_runtime": 1.
|
| 406 |
-
"eval_samples_per_second":
|
| 407 |
-
"eval_steps_per_second": 3.
|
| 408 |
"step": 232
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 30.0,
|
| 412 |
-
"learning_rate":
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 240
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 30.0,
|
| 418 |
-
"eval_accuracy": 0.
|
| 419 |
-
"eval_loss": 0.
|
| 420 |
-
"eval_runtime": 1.
|
| 421 |
-
"eval_samples_per_second":
|
| 422 |
-
"eval_steps_per_second": 3.
|
| 423 |
"step": 240
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 31.0,
|
| 427 |
-
"eval_accuracy": 0.
|
| 428 |
-
"eval_loss": 0.
|
| 429 |
-
"eval_runtime": 1.
|
| 430 |
-
"eval_samples_per_second": 57.
|
| 431 |
-
"eval_steps_per_second": 3.
|
| 432 |
"step": 248
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 31.25,
|
| 436 |
-
"learning_rate":
|
| 437 |
-
"loss": 0.
|
| 438 |
"step": 250
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 32.0,
|
| 442 |
-
"eval_accuracy": 0.
|
| 443 |
-
"eval_loss": 0.
|
| 444 |
-
"eval_runtime": 1.
|
| 445 |
-
"eval_samples_per_second": 57.
|
| 446 |
-
"eval_steps_per_second": 3.
|
| 447 |
"step": 256
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 32.5,
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 260
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 33.0,
|
| 457 |
-
"eval_accuracy": 0.
|
| 458 |
-
"eval_loss": 0.
|
| 459 |
-
"eval_runtime":
|
| 460 |
-
"eval_samples_per_second":
|
| 461 |
-
"eval_steps_per_second": 3.
|
| 462 |
"step": 264
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 33.75,
|
| 466 |
-
"learning_rate":
|
| 467 |
-
"loss": 0.
|
| 468 |
"step": 270
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 34.0,
|
| 472 |
-
"eval_accuracy": 0.
|
| 473 |
-
"eval_loss": 0.
|
| 474 |
-
"eval_runtime":
|
| 475 |
-
"eval_samples_per_second":
|
| 476 |
-
"eval_steps_per_second": 3.
|
| 477 |
"step": 272
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 35.0,
|
| 481 |
-
"learning_rate":
|
| 482 |
-
"loss": 0.
|
| 483 |
"step": 280
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 35.0,
|
| 487 |
-
"eval_accuracy": 0.
|
| 488 |
-
"eval_loss": 0.
|
| 489 |
-
"eval_runtime": 1.
|
| 490 |
-
"eval_samples_per_second":
|
| 491 |
-
"eval_steps_per_second": 3.
|
| 492 |
"step": 280
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 36.0,
|
| 496 |
-
"eval_accuracy": 0.
|
| 497 |
-
"eval_loss": 0.
|
| 498 |
-
"eval_runtime": 1.
|
| 499 |
-
"eval_samples_per_second":
|
| 500 |
-
"eval_steps_per_second": 3.
|
| 501 |
"step": 288
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 36.25,
|
| 505 |
-
"learning_rate":
|
| 506 |
-
"loss": 0.
|
| 507 |
"step": 290
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 37.0,
|
| 511 |
-
"eval_accuracy": 0.
|
| 512 |
-
"eval_loss": 0.
|
| 513 |
-
"eval_runtime": 1.
|
| 514 |
-
"eval_samples_per_second":
|
| 515 |
-
"eval_steps_per_second": 3.
|
| 516 |
"step": 296
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 37.5,
|
| 520 |
-
"learning_rate":
|
| 521 |
-
"loss": 0.
|
| 522 |
"step": 300
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 38.0,
|
| 526 |
-
"eval_accuracy": 0.
|
| 527 |
-
"eval_loss": 0.
|
| 528 |
-
"eval_runtime": 1.
|
| 529 |
-
"eval_samples_per_second":
|
| 530 |
-
"eval_steps_per_second": 3.
|
| 531 |
"step": 304
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 38.75,
|
| 535 |
-
"learning_rate":
|
| 536 |
-
"loss": 0.
|
| 537 |
"step": 310
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 39.0,
|
| 541 |
-
"eval_accuracy": 0.
|
| 542 |
-
"eval_loss": 0.
|
| 543 |
-
"eval_runtime": 1.
|
| 544 |
-
"eval_samples_per_second":
|
| 545 |
-
"eval_steps_per_second": 3.
|
| 546 |
"step": 312
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 40.0,
|
| 550 |
"learning_rate": 0.0,
|
| 551 |
-
"loss": 0.
|
| 552 |
"step": 320
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 40.0,
|
| 556 |
-
"eval_accuracy": 0.
|
| 557 |
-
"eval_loss": 0.
|
| 558 |
-
"eval_runtime": 1.
|
| 559 |
-
"eval_samples_per_second": 58.
|
| 560 |
-
"eval_steps_per_second": 3.
|
| 561 |
"step": 320
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 40.0,
|
| 565 |
"step": 320,
|
| 566 |
"total_flos": 6.480838238876467e+17,
|
| 567 |
-
"train_loss":
|
| 568 |
-
"train_runtime":
|
| 569 |
-
"train_samples_per_second":
|
| 570 |
-
"train_steps_per_second": 0.
|
| 571 |
}
|
| 572 |
],
|
| 573 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6822429906542056,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RH\\checkpoint-296",
|
| 4 |
"epoch": 40.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 320,
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
"eval_accuracy": 0.411214953271028,
|
| 14 |
+
"eval_loss": 4.626469612121582,
|
| 15 |
+
"eval_runtime": 1.941,
|
| 16 |
+
"eval_samples_per_second": 55.127,
|
| 17 |
+
"eval_steps_per_second": 3.606,
|
| 18 |
"step": 8
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.25,
|
| 22 |
+
"learning_rate": 1.25e-05,
|
| 23 |
+
"loss": 4.5369,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
"eval_accuracy": 0.411214953271028,
|
| 29 |
+
"eval_loss": 4.52950382232666,
|
| 30 |
+
"eval_runtime": 1.8274,
|
| 31 |
+
"eval_samples_per_second": 58.552,
|
| 32 |
+
"eval_steps_per_second": 3.831,
|
| 33 |
"step": 16
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 2.5,
|
| 37 |
+
"learning_rate": 2.5e-05,
|
| 38 |
+
"loss": 4.6305,
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 3.0,
|
| 43 |
"eval_accuracy": 0.411214953271028,
|
| 44 |
+
"eval_loss": 4.143911361694336,
|
| 45 |
+
"eval_runtime": 1.8444,
|
| 46 |
+
"eval_samples_per_second": 58.012,
|
| 47 |
+
"eval_steps_per_second": 3.795,
|
| 48 |
"step": 24
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 3.75,
|
| 52 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 53 |
+
"loss": 4.0918,
|
| 54 |
"step": 30
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 4.0,
|
| 58 |
"eval_accuracy": 0.411214953271028,
|
| 59 |
+
"eval_loss": 3.369269609451294,
|
| 60 |
+
"eval_runtime": 1.8599,
|
| 61 |
+
"eval_samples_per_second": 57.529,
|
| 62 |
+
"eval_steps_per_second": 3.764,
|
| 63 |
"step": 32
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 5.0,
|
| 67 |
+
"learning_rate": 3.888888888888889e-05,
|
| 68 |
+
"loss": 3.1767,
|
| 69 |
"step": 40
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 5.0,
|
| 73 |
+
"eval_accuracy": 0.411214953271028,
|
| 74 |
+
"eval_loss": 2.4324560165405273,
|
| 75 |
+
"eval_runtime": 1.894,
|
| 76 |
+
"eval_samples_per_second": 56.496,
|
| 77 |
+
"eval_steps_per_second": 3.696,
|
| 78 |
"step": 40
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.411214953271028,
|
| 83 |
+
"eval_loss": 1.5421515703201294,
|
| 84 |
+
"eval_runtime": 1.8605,
|
| 85 |
+
"eval_samples_per_second": 57.513,
|
| 86 |
+
"eval_steps_per_second": 3.763,
|
| 87 |
"step": 48
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 6.25,
|
| 91 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 92 |
+
"loss": 2.0113,
|
| 93 |
"step": 50
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 7.0,
|
| 97 |
+
"eval_accuracy": 0.411214953271028,
|
| 98 |
+
"eval_loss": 0.8834472894668579,
|
| 99 |
+
"eval_runtime": 1.8524,
|
| 100 |
+
"eval_samples_per_second": 57.762,
|
| 101 |
+
"eval_steps_per_second": 3.779,
|
| 102 |
"step": 56
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 7.5,
|
| 106 |
+
"learning_rate": 3.6111111111111116e-05,
|
| 107 |
+
"loss": 1.0593,
|
| 108 |
"step": 60
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 8.0,
|
| 112 |
"eval_accuracy": 0.5887850467289719,
|
| 113 |
+
"eval_loss": 0.6790158748626709,
|
| 114 |
+
"eval_runtime": 1.8709,
|
| 115 |
+
"eval_samples_per_second": 57.19,
|
| 116 |
+
"eval_steps_per_second": 3.741,
|
| 117 |
"step": 64
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 8.75,
|
| 121 |
+
"learning_rate": 3.472222222222223e-05,
|
| 122 |
+
"loss": 0.696,
|
| 123 |
"step": 70
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 9.0,
|
| 127 |
"eval_accuracy": 0.5887850467289719,
|
| 128 |
+
"eval_loss": 0.7044364213943481,
|
| 129 |
+
"eval_runtime": 1.8454,
|
| 130 |
+
"eval_samples_per_second": 57.981,
|
| 131 |
+
"eval_steps_per_second": 3.793,
|
| 132 |
"step": 72
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 10.0,
|
| 136 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 137 |
+
"loss": 0.6893,
|
| 138 |
"step": 80
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 10.0,
|
| 142 |
+
"eval_accuracy": 0.5887850467289719,
|
| 143 |
+
"eval_loss": 0.6777833104133606,
|
| 144 |
+
"eval_runtime": 1.8339,
|
| 145 |
+
"eval_samples_per_second": 58.344,
|
| 146 |
+
"eval_steps_per_second": 3.817,
|
| 147 |
"step": 80
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 11.0,
|
| 151 |
"eval_accuracy": 0.5887850467289719,
|
| 152 |
+
"eval_loss": 0.686574399471283,
|
| 153 |
+
"eval_runtime": 1.8689,
|
| 154 |
+
"eval_samples_per_second": 57.252,
|
| 155 |
+
"eval_steps_per_second": 3.745,
|
| 156 |
"step": 88
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 11.25,
|
| 160 |
+
"learning_rate": 3.194444444444445e-05,
|
| 161 |
+
"loss": 0.6961,
|
| 162 |
"step": 90
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 12.0,
|
| 166 |
"eval_accuracy": 0.5887850467289719,
|
| 167 |
+
"eval_loss": 0.6933708786964417,
|
| 168 |
+
"eval_runtime": 1.8659,
|
| 169 |
+
"eval_samples_per_second": 57.344,
|
| 170 |
+
"eval_steps_per_second": 3.751,
|
| 171 |
"step": 96
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 12.5,
|
| 175 |
+
"learning_rate": 3.0555555555555554e-05,
|
| 176 |
+
"loss": 0.7329,
|
| 177 |
"step": 100
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 13.0,
|
| 181 |
"eval_accuracy": 0.5887850467289719,
|
| 182 |
+
"eval_loss": 0.6915177702903748,
|
| 183 |
+
"eval_runtime": 1.8689,
|
| 184 |
+
"eval_samples_per_second": 57.252,
|
| 185 |
+
"eval_steps_per_second": 3.745,
|
| 186 |
"step": 104
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 13.75,
|
| 190 |
+
"learning_rate": 2.9166666666666666e-05,
|
| 191 |
+
"loss": 0.6948,
|
| 192 |
"step": 110
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 14.0,
|
| 196 |
"eval_accuracy": 0.5887850467289719,
|
| 197 |
+
"eval_loss": 0.6761561036109924,
|
| 198 |
+
"eval_runtime": 1.873,
|
| 199 |
+
"eval_samples_per_second": 57.129,
|
| 200 |
+
"eval_steps_per_second": 3.737,
|
| 201 |
"step": 112
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 15.0,
|
| 205 |
+
"learning_rate": 2.777777777777778e-05,
|
| 206 |
+
"loss": 0.6771,
|
| 207 |
"step": 120
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 15.0,
|
| 211 |
"eval_accuracy": 0.5887850467289719,
|
| 212 |
+
"eval_loss": 0.6794873476028442,
|
| 213 |
+
"eval_runtime": 1.8549,
|
| 214 |
+
"eval_samples_per_second": 57.684,
|
| 215 |
+
"eval_steps_per_second": 3.774,
|
| 216 |
"step": 120
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 16.0,
|
| 220 |
"eval_accuracy": 0.5887850467289719,
|
| 221 |
+
"eval_loss": 0.6800874471664429,
|
| 222 |
+
"eval_runtime": 1.871,
|
| 223 |
+
"eval_samples_per_second": 57.19,
|
| 224 |
+
"eval_steps_per_second": 3.741,
|
| 225 |
"step": 128
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 16.25,
|
| 229 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 230 |
+
"loss": 0.6763,
|
| 231 |
"step": 130
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 17.0,
|
| 235 |
"eval_accuracy": 0.5887850467289719,
|
| 236 |
+
"eval_loss": 0.6819825172424316,
|
| 237 |
+
"eval_runtime": 1.8614,
|
| 238 |
+
"eval_samples_per_second": 57.483,
|
| 239 |
+
"eval_steps_per_second": 3.761,
|
| 240 |
"step": 136
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 17.5,
|
| 244 |
+
"learning_rate": 2.5e-05,
|
| 245 |
+
"loss": 0.6822,
|
| 246 |
"step": 140
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 18.0,
|
| 250 |
+
"eval_accuracy": 0.5887850467289719,
|
| 251 |
+
"eval_loss": 0.6799528002738953,
|
| 252 |
+
"eval_runtime": 1.8664,
|
| 253 |
+
"eval_samples_per_second": 57.328,
|
| 254 |
+
"eval_steps_per_second": 3.75,
|
| 255 |
"step": 144
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 18.75,
|
| 259 |
+
"learning_rate": 2.3611111111111114e-05,
|
| 260 |
+
"loss": 0.6723,
|
| 261 |
"step": 150
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 19.0,
|
| 265 |
"eval_accuracy": 0.5887850467289719,
|
| 266 |
+
"eval_loss": 0.6740810871124268,
|
| 267 |
+
"eval_runtime": 1.8689,
|
| 268 |
+
"eval_samples_per_second": 57.252,
|
| 269 |
+
"eval_steps_per_second": 3.745,
|
| 270 |
"step": 152
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 20.0,
|
| 274 |
+
"learning_rate": 2.2222222222222227e-05,
|
| 275 |
+
"loss": 0.6757,
|
| 276 |
"step": 160
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 20.0,
|
| 280 |
+
"eval_accuracy": 0.5887850467289719,
|
| 281 |
+
"eval_loss": 0.681536078453064,
|
| 282 |
+
"eval_runtime": 1.8439,
|
| 283 |
+
"eval_samples_per_second": 58.028,
|
| 284 |
+
"eval_steps_per_second": 3.796,
|
| 285 |
"step": 160
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 21.0,
|
| 289 |
"eval_accuracy": 0.5887850467289719,
|
| 290 |
+
"eval_loss": 0.6728676557540894,
|
| 291 |
+
"eval_runtime": 1.8774,
|
| 292 |
+
"eval_samples_per_second": 56.993,
|
| 293 |
+
"eval_steps_per_second": 3.729,
|
| 294 |
"step": 168
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 21.25,
|
| 298 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 299 |
+
"loss": 0.6711,
|
| 300 |
"step": 170
|
| 301 |
},
|
| 302 |
{
|
| 303 |
"epoch": 22.0,
|
| 304 |
+
"eval_accuracy": 0.5887850467289719,
|
| 305 |
+
"eval_loss": 0.6811678409576416,
|
| 306 |
+
"eval_runtime": 1.8474,
|
| 307 |
+
"eval_samples_per_second": 57.918,
|
| 308 |
+
"eval_steps_per_second": 3.789,
|
| 309 |
"step": 176
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 22.5,
|
| 313 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 314 |
+
"loss": 0.6784,
|
| 315 |
"step": 180
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 23.0,
|
| 319 |
+
"eval_accuracy": 0.5794392523364486,
|
| 320 |
+
"eval_loss": 0.6780757308006287,
|
| 321 |
+
"eval_runtime": 1.9144,
|
| 322 |
+
"eval_samples_per_second": 55.891,
|
| 323 |
+
"eval_steps_per_second": 3.656,
|
| 324 |
"step": 184
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 23.75,
|
| 328 |
+
"learning_rate": 1.8055555555555558e-05,
|
| 329 |
+
"loss": 0.6665,
|
| 330 |
"step": 190
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 24.0,
|
| 334 |
+
"eval_accuracy": 0.5794392523364486,
|
| 335 |
+
"eval_loss": 0.6697570085525513,
|
| 336 |
+
"eval_runtime": 1.8669,
|
| 337 |
+
"eval_samples_per_second": 57.313,
|
| 338 |
+
"eval_steps_per_second": 3.749,
|
| 339 |
"step": 192
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 25.0,
|
| 343 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 344 |
+
"loss": 0.6723,
|
| 345 |
"step": 200
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 25.0,
|
| 349 |
+
"eval_accuracy": 0.5981308411214953,
|
| 350 |
+
"eval_loss": 0.6646633744239807,
|
| 351 |
+
"eval_runtime": 1.8769,
|
| 352 |
+
"eval_samples_per_second": 57.008,
|
| 353 |
+
"eval_steps_per_second": 3.729,
|
| 354 |
"step": 200
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 26.0,
|
| 358 |
+
"eval_accuracy": 0.5794392523364486,
|
| 359 |
+
"eval_loss": 0.6761506199836731,
|
| 360 |
+
"eval_runtime": 1.8489,
|
| 361 |
+
"eval_samples_per_second": 57.871,
|
| 362 |
+
"eval_steps_per_second": 3.786,
|
| 363 |
"step": 208
|
| 364 |
},
|
| 365 |
{
|
| 366 |
"epoch": 26.25,
|
| 367 |
+
"learning_rate": 1.5277777777777777e-05,
|
| 368 |
+
"loss": 0.6675,
|
| 369 |
"step": 210
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 27.0,
|
| 373 |
+
"eval_accuracy": 0.5700934579439252,
|
| 374 |
+
"eval_loss": 0.659662127494812,
|
| 375 |
+
"eval_runtime": 1.8699,
|
| 376 |
+
"eval_samples_per_second": 57.221,
|
| 377 |
+
"eval_steps_per_second": 3.743,
|
| 378 |
"step": 216
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 27.5,
|
| 382 |
+
"learning_rate": 1.388888888888889e-05,
|
| 383 |
+
"loss": 0.6628,
|
| 384 |
"step": 220
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 28.0,
|
| 388 |
+
"eval_accuracy": 0.6355140186915887,
|
| 389 |
+
"eval_loss": 0.6563044190406799,
|
| 390 |
+
"eval_runtime": 1.901,
|
| 391 |
+
"eval_samples_per_second": 56.288,
|
| 392 |
+
"eval_steps_per_second": 3.682,
|
| 393 |
"step": 224
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 28.75,
|
| 397 |
+
"learning_rate": 1.25e-05,
|
| 398 |
+
"loss": 0.6478,
|
| 399 |
"step": 230
|
| 400 |
},
|
| 401 |
{
|
| 402 |
"epoch": 29.0,
|
| 403 |
+
"eval_accuracy": 0.5794392523364486,
|
| 404 |
+
"eval_loss": 0.6790612936019897,
|
| 405 |
+
"eval_runtime": 1.8634,
|
| 406 |
+
"eval_samples_per_second": 57.421,
|
| 407 |
+
"eval_steps_per_second": 3.757,
|
| 408 |
"step": 232
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 30.0,
|
| 412 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 413 |
+
"loss": 0.6642,
|
| 414 |
"step": 240
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 30.0,
|
| 418 |
+
"eval_accuracy": 0.5887850467289719,
|
| 419 |
+
"eval_loss": 0.6573609709739685,
|
| 420 |
+
"eval_runtime": 1.884,
|
| 421 |
+
"eval_samples_per_second": 56.796,
|
| 422 |
+
"eval_steps_per_second": 3.716,
|
| 423 |
"step": 240
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 31.0,
|
| 427 |
+
"eval_accuracy": 0.5607476635514018,
|
| 428 |
+
"eval_loss": 0.6556074023246765,
|
| 429 |
+
"eval_runtime": 1.872,
|
| 430 |
+
"eval_samples_per_second": 57.159,
|
| 431 |
+
"eval_steps_per_second": 3.739,
|
| 432 |
"step": 248
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 31.25,
|
| 436 |
+
"learning_rate": 9.722222222222223e-06,
|
| 437 |
+
"loss": 0.654,
|
| 438 |
"step": 250
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 32.0,
|
| 442 |
+
"eval_accuracy": 0.5887850467289719,
|
| 443 |
+
"eval_loss": 0.6523457169532776,
|
| 444 |
+
"eval_runtime": 1.871,
|
| 445 |
+
"eval_samples_per_second": 57.19,
|
| 446 |
+
"eval_steps_per_second": 3.741,
|
| 447 |
"step": 256
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 32.5,
|
| 451 |
+
"learning_rate": 8.333333333333334e-06,
|
| 452 |
+
"loss": 0.6602,
|
| 453 |
"step": 260
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 33.0,
|
| 457 |
+
"eval_accuracy": 0.6261682242990654,
|
| 458 |
+
"eval_loss": 0.6463862657546997,
|
| 459 |
+
"eval_runtime": 1.8604,
|
| 460 |
+
"eval_samples_per_second": 57.513,
|
| 461 |
+
"eval_steps_per_second": 3.763,
|
| 462 |
"step": 264
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 33.75,
|
| 466 |
+
"learning_rate": 6.944444444444445e-06,
|
| 467 |
+
"loss": 0.6535,
|
| 468 |
"step": 270
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 34.0,
|
| 472 |
+
"eval_accuracy": 0.616822429906542,
|
| 473 |
+
"eval_loss": 0.6450387835502625,
|
| 474 |
+
"eval_runtime": 2.0415,
|
| 475 |
+
"eval_samples_per_second": 52.413,
|
| 476 |
+
"eval_steps_per_second": 3.429,
|
| 477 |
"step": 272
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 35.0,
|
| 481 |
+
"learning_rate": 5.555555555555557e-06,
|
| 482 |
+
"loss": 0.6506,
|
| 483 |
"step": 280
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 35.0,
|
| 487 |
+
"eval_accuracy": 0.5794392523364486,
|
| 488 |
+
"eval_loss": 0.6549742221832275,
|
| 489 |
+
"eval_runtime": 1.8524,
|
| 490 |
+
"eval_samples_per_second": 57.762,
|
| 491 |
+
"eval_steps_per_second": 3.779,
|
| 492 |
"step": 280
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 36.0,
|
| 496 |
+
"eval_accuracy": 0.6074766355140186,
|
| 497 |
+
"eval_loss": 0.6437696218490601,
|
| 498 |
+
"eval_runtime": 1.837,
|
| 499 |
+
"eval_samples_per_second": 58.249,
|
| 500 |
+
"eval_steps_per_second": 3.811,
|
| 501 |
"step": 288
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 36.25,
|
| 505 |
+
"learning_rate": 4.166666666666667e-06,
|
| 506 |
+
"loss": 0.6533,
|
| 507 |
"step": 290
|
| 508 |
},
|
| 509 |
{
|
| 510 |
"epoch": 37.0,
|
| 511 |
+
"eval_accuracy": 0.6822429906542056,
|
| 512 |
+
"eval_loss": 0.6395505666732788,
|
| 513 |
+
"eval_runtime": 1.8519,
|
| 514 |
+
"eval_samples_per_second": 57.777,
|
| 515 |
+
"eval_steps_per_second": 3.78,
|
| 516 |
"step": 296
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 37.5,
|
| 520 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 521 |
+
"loss": 0.6443,
|
| 522 |
"step": 300
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 38.0,
|
| 526 |
+
"eval_accuracy": 0.6635514018691588,
|
| 527 |
+
"eval_loss": 0.6383424997329712,
|
| 528 |
+
"eval_runtime": 1.8994,
|
| 529 |
+
"eval_samples_per_second": 56.332,
|
| 530 |
+
"eval_steps_per_second": 3.685,
|
| 531 |
"step": 304
|
| 532 |
},
|
| 533 |
{
|
| 534 |
"epoch": 38.75,
|
| 535 |
+
"learning_rate": 1.3888888888888892e-06,
|
| 536 |
+
"loss": 0.6263,
|
| 537 |
"step": 310
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 39.0,
|
| 541 |
+
"eval_accuracy": 0.6448598130841121,
|
| 542 |
+
"eval_loss": 0.6377760171890259,
|
| 543 |
+
"eval_runtime": 1.8969,
|
| 544 |
+
"eval_samples_per_second": 56.406,
|
| 545 |
+
"eval_steps_per_second": 3.69,
|
| 546 |
"step": 312
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 40.0,
|
| 550 |
"learning_rate": 0.0,
|
| 551 |
+
"loss": 0.6283,
|
| 552 |
"step": 320
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 40.0,
|
| 556 |
+
"eval_accuracy": 0.6448598130841121,
|
| 557 |
+
"eval_loss": 0.6378776431083679,
|
| 558 |
+
"eval_runtime": 1.8389,
|
| 559 |
+
"eval_samples_per_second": 58.186,
|
| 560 |
+
"eval_steps_per_second": 3.807,
|
| 561 |
"step": 320
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 40.0,
|
| 565 |
"step": 320,
|
| 566 |
"total_flos": 6.480838238876467e+17,
|
| 567 |
+
"train_loss": 1.1531404286623002,
|
| 568 |
+
"train_runtime": 569.0029,
|
| 569 |
+
"train_samples_per_second": 35.009,
|
| 570 |
+
"train_steps_per_second": 0.562
|
| 571 |
}
|
| 572 |
],
|
| 573 |
"logging_steps": 10,
|
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 sha256:4b7e74dff4ca6ca6685230bb17bfaae8471c3a7c204cf2ade59db4ef7c494d01
|
| 3 |
size 4728
|