End of training
Browse files- README.md +43 -43
- all_results.json +10 -10
- config.json +4 -10
- eval_results.json +6 -6
- model.safetensors +2 -2
- runs/Dec01_09-41-13_DESKTOP-SKBE9FB/events.out.tfevents.1733067674.DESKTOP-SKBE9FB.19616.0 +3 -0
- runs/Dec01_09-41-13_DESKTOP-SKBE9FB/events.out.tfevents.1733068268.DESKTOP-SKBE9FB.19616.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +381 -1149
- 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 |
|
|
@@ -67,46 +67,46 @@ The following hyperparameters were used during training:
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
-
|
|
| 71 |
-
|
|
| 72 |
-
|
|
| 73 |
-
|
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 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 |
|
| 111 |
|
| 112 |
### Framework versions
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.616822429906542
|
| 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: 0.6580
|
| 36 |
+
- Accuracy: 0.6168
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 8 | 4.5659 | 0.4112 |
|
| 71 |
+
| 4.5175 | 2.0 | 16 | 3.6471 | 0.4112 |
|
| 72 |
+
| 3.927 | 3.0 | 24 | 1.6286 | 0.4112 |
|
| 73 |
+
| 1.6081 | 4.0 | 32 | 0.6781 | 0.5888 |
|
| 74 |
+
| 0.7702 | 5.0 | 40 | 0.8357 | 0.5888 |
|
| 75 |
+
| 0.7702 | 6.0 | 48 | 0.6766 | 0.5888 |
|
| 76 |
+
| 0.7502 | 7.0 | 56 | 0.7522 | 0.4112 |
|
| 77 |
+
| 0.7266 | 8.0 | 64 | 0.6792 | 0.5888 |
|
| 78 |
+
| 0.6954 | 9.0 | 72 | 0.6881 | 0.5888 |
|
| 79 |
+
| 0.6808 | 10.0 | 80 | 0.6780 | 0.5888 |
|
| 80 |
+
| 0.6808 | 11.0 | 88 | 0.7130 | 0.5888 |
|
| 81 |
+
| 0.7068 | 12.0 | 96 | 0.6771 | 0.5888 |
|
| 82 |
+
| 0.6792 | 13.0 | 104 | 0.6779 | 0.5888 |
|
| 83 |
+
| 0.6841 | 14.0 | 112 | 0.6766 | 0.5888 |
|
| 84 |
+
| 0.6777 | 15.0 | 120 | 0.6861 | 0.5888 |
|
| 85 |
+
| 0.6777 | 16.0 | 128 | 0.6773 | 0.5888 |
|
| 86 |
+
| 0.6818 | 17.0 | 136 | 0.6806 | 0.5888 |
|
| 87 |
+
| 0.6747 | 18.0 | 144 | 0.6929 | 0.5888 |
|
| 88 |
+
| 0.6814 | 19.0 | 152 | 0.6767 | 0.5888 |
|
| 89 |
+
| 0.6714 | 20.0 | 160 | 0.6745 | 0.5888 |
|
| 90 |
+
| 0.6714 | 21.0 | 168 | 0.6852 | 0.5888 |
|
| 91 |
+
| 0.6765 | 22.0 | 176 | 0.6816 | 0.5514 |
|
| 92 |
+
| 0.6822 | 23.0 | 184 | 0.6983 | 0.5888 |
|
| 93 |
+
| 0.6816 | 24.0 | 192 | 0.6706 | 0.5888 |
|
| 94 |
+
| 0.6868 | 25.0 | 200 | 0.6982 | 0.5701 |
|
| 95 |
+
| 0.6868 | 26.0 | 208 | 0.6878 | 0.5701 |
|
| 96 |
+
| 0.6724 | 27.0 | 216 | 0.6785 | 0.5888 |
|
| 97 |
+
| 0.6613 | 28.0 | 224 | 0.6843 | 0.5888 |
|
| 98 |
+
| 0.6501 | 29.0 | 232 | 0.7126 | 0.5888 |
|
| 99 |
+
| 0.6566 | 30.0 | 240 | 0.6917 | 0.5701 |
|
| 100 |
+
| 0.6566 | 31.0 | 248 | 0.7020 | 0.5607 |
|
| 101 |
+
| 0.6583 | 32.0 | 256 | 0.6782 | 0.5888 |
|
| 102 |
+
| 0.6501 | 33.0 | 264 | 0.6647 | 0.5888 |
|
| 103 |
+
| 0.654 | 34.0 | 272 | 0.6603 | 0.5981 |
|
| 104 |
+
| 0.6604 | 35.0 | 280 | 0.6873 | 0.5794 |
|
| 105 |
+
| 0.6604 | 36.0 | 288 | 0.6591 | 0.5794 |
|
| 106 |
+
| 0.6456 | 37.0 | 296 | 0.6580 | 0.6168 |
|
| 107 |
+
| 0.6483 | 38.0 | 304 | 0.6702 | 0.5981 |
|
| 108 |
+
| 0.6151 | 39.0 | 312 | 0.6785 | 0.5981 |
|
| 109 |
+
| 0.6291 | 40.0 | 320 | 0.6806 | 0.5981 |
|
| 110 |
|
| 111 |
|
| 112 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 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": 40.0,
|
| 3 |
+
"eval_accuracy": 0.616822429906542,
|
| 4 |
+
"eval_loss": 0.6579955816268921,
|
| 5 |
+
"eval_runtime": 2.141,
|
| 6 |
+
"eval_samples_per_second": 49.976,
|
| 7 |
+
"eval_steps_per_second": 3.269,
|
| 8 |
+
"train_loss": 0.9269241958856582,
|
| 9 |
+
"train_runtime": 591.2866,
|
| 10 |
+
"train_samples_per_second": 33.689,
|
| 11 |
+
"train_steps_per_second": 0.541
|
| 12 |
}
|
config.json
CHANGED
|
@@ -17,20 +17,14 @@
|
|
| 17 |
"hidden_dropout_prob": 0.0,
|
| 18 |
"hidden_size": 768,
|
| 19 |
"id2label": {
|
| 20 |
-
"0": "
|
| 21 |
-
"1": "
|
| 22 |
-
"2": "No_DR",
|
| 23 |
-
"3": "Proliferate_DR",
|
| 24 |
-
"4": "Severe"
|
| 25 |
},
|
| 26 |
"image_size": 256,
|
| 27 |
"initializer_range": 0.02,
|
| 28 |
"label2id": {
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"No_DR": 2,
|
| 32 |
-
"Proliferate_DR": 3,
|
| 33 |
-
"Severe": 4
|
| 34 |
},
|
| 35 |
"layer_norm_eps": 1e-05,
|
| 36 |
"mlp_ratio": 4.0,
|
|
|
|
| 17 |
"hidden_dropout_prob": 0.0,
|
| 18 |
"hidden_size": 768,
|
| 19 |
"id2label": {
|
| 20 |
+
"0": "HR",
|
| 21 |
+
"1": "No HR"
|
|
|
|
|
|
|
|
|
|
| 22 |
},
|
| 23 |
"image_size": 256,
|
| 24 |
"initializer_range": 0.02,
|
| 25 |
"label2id": {
|
| 26 |
+
"HR": 0,
|
| 27 |
+
"No HR": 1
|
|
|
|
|
|
|
|
|
|
| 28 |
},
|
| 29 |
"layer_norm_eps": 1e-05,
|
| 30 |
"mlp_ratio": 4.0,
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_accuracy": 0.616822429906542,
|
| 4 |
+
"eval_loss": 0.6579955816268921,
|
| 5 |
+
"eval_runtime": 2.141,
|
| 6 |
+
"eval_samples_per_second": 49.976,
|
| 7 |
+
"eval_steps_per_second": 3.269
|
| 8 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:691a7da7dff5da0f33c5a07a6d3ca99d97e130cf310c3632dabed4a981c7d394
|
| 3 |
+
size 110350128
|
runs/Dec01_09-41-13_DESKTOP-SKBE9FB/events.out.tfevents.1733067674.DESKTOP-SKBE9FB.19616.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57cc2384fedf0484f726ed692720df5cf6105b2cc20baffb080dc01e56ed2f0a
|
| 3 |
+
size 22896
|
runs/Dec01_09-41-13_DESKTOP-SKBE9FB/events.out.tfevents.1733068268.DESKTOP-SKBE9FB.19616.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50490b997cfbe439388d6e3f6e241df528bc44b5cf513bfed84d4c1be0ec3a4b
|
| 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": 40.0,
|
| 3 |
+
"train_loss": 0.9269241958856582,
|
| 4 |
+
"train_runtime": 591.2866,
|
| 5 |
+
"train_samples_per_second": 33.689,
|
| 6 |
+
"train_steps_per_second": 0.541
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1349 +1,581 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RD-aptos19\\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 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
"
|
| 19 |
-
"learning_rate": 1.875e-05,
|
| 20 |
-
"loss": 1.5856,
|
| 21 |
-
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch":
|
| 25 |
-
"learning_rate": 2.8125e-05,
|
| 26 |
-
"loss": 1.4604,
|
| 27 |
-
"step": 30
|
| 28 |
-
},
|
| 29 |
-
{
|
| 30 |
-
"epoch": 0.99,
|
| 31 |
-
"learning_rate": 3.75e-05,
|
| 32 |
-
"loss": 1.2888,
|
| 33 |
-
"step": 40
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"epoch": 0.99,
|
| 37 |
-
"eval_accuracy": 0.49272727272727274,
|
| 38 |
-
"eval_loss": 1.2042264938354492,
|
| 39 |
-
"eval_runtime": 5.5152,
|
| 40 |
-
"eval_samples_per_second": 99.724,
|
| 41 |
-
"eval_steps_per_second": 6.346,
|
| 42 |
-
"step": 40
|
| 43 |
-
},
|
| 44 |
-
{
|
| 45 |
-
"epoch": 1.24,
|
| 46 |
"learning_rate": 4.6874999999999994e-05,
|
| 47 |
-
"loss":
|
| 48 |
-
"step":
|
| 49 |
-
},
|
| 50 |
-
{
|
| 51 |
-
"epoch": 1.49,
|
| 52 |
-
"learning_rate": 5.625e-05,
|
| 53 |
-
"loss": 1.0479,
|
| 54 |
-
"step": 60
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 1.74,
|
| 58 |
-
"learning_rate": 6.5625e-05,
|
| 59 |
-
"loss": 0.8743,
|
| 60 |
-
"step": 70
|
| 61 |
-
},
|
| 62 |
-
{
|
| 63 |
-
"epoch": 1.99,
|
| 64 |
-
"learning_rate": 7.5e-05,
|
| 65 |
-
"loss": 0.8739,
|
| 66 |
-
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"eval_accuracy": 0.
|
| 71 |
-
"eval_loss":
|
| 72 |
-
"eval_runtime":
|
| 73 |
-
"eval_samples_per_second":
|
| 74 |
-
"eval_steps_per_second":
|
| 75 |
-
"step":
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch": 2.
|
| 79 |
-
"learning_rate": 8.437499999999999e-05,
|
| 80 |
-
"loss": 0.7431,
|
| 81 |
-
"step": 90
|
| 82 |
-
},
|
| 83 |
-
{
|
| 84 |
-
"epoch": 2.48,
|
| 85 |
"learning_rate": 9.374999999999999e-05,
|
| 86 |
-
"loss":
|
| 87 |
-
"step":
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 2.73,
|
| 91 |
-
"learning_rate": 0.00010312499999999999,
|
| 92 |
-
"loss": 0.7128,
|
| 93 |
-
"step": 110
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 2.98,
|
| 97 |
-
"learning_rate": 0.0001125,
|
| 98 |
-
"loss": 0.7913,
|
| 99 |
-
"step": 120
|
| 100 |
-
},
|
| 101 |
-
{
|
| 102 |
-
"epoch": 2.98,
|
| 103 |
-
"eval_accuracy": 0.7618181818181818,
|
| 104 |
-
"eval_loss": 0.5920261740684509,
|
| 105 |
-
"eval_runtime": 2.9432,
|
| 106 |
-
"eval_samples_per_second": 186.871,
|
| 107 |
-
"eval_steps_per_second": 11.892,
|
| 108 |
-
"step": 120
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 3.
|
| 112 |
-
"
|
| 113 |
-
"
|
| 114 |
-
"
|
|
|
|
|
|
|
|
|
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 3.
|
| 118 |
-
"learning_rate": 0.00013125,
|
| 119 |
-
"loss": 0.7039,
|
| 120 |
-
"step": 140
|
| 121 |
-
},
|
| 122 |
-
{
|
| 123 |
-
"epoch": 3.73,
|
| 124 |
"learning_rate": 0.000140625,
|
| 125 |
-
"loss":
|
| 126 |
-
"step":
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 3.98,
|
| 130 |
-
"learning_rate": 0.00015,
|
| 131 |
-
"loss": 0.6803,
|
| 132 |
-
"step": 160
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 4.0,
|
| 136 |
-
"eval_accuracy": 0.
|
| 137 |
-
"eval_loss": 0.
|
| 138 |
-
"eval_runtime":
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second":
|
| 141 |
-
"step":
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"learning_rate": 0.00014895833333333333,
|
| 146 |
-
"loss": 0.7187,
|
| 147 |
-
"step": 170
|
| 148 |
-
},
|
| 149 |
-
{
|
| 150 |
-
"epoch": 4.47,
|
| 151 |
-
"learning_rate": 0.00014791666666666667,
|
| 152 |
-
"loss": 0.6562,
|
| 153 |
-
"step": 180
|
| 154 |
-
},
|
| 155 |
-
{
|
| 156 |
-
"epoch": 4.72,
|
| 157 |
-
"learning_rate": 0.00014687499999999998,
|
| 158 |
-
"loss": 0.6117,
|
| 159 |
-
"step": 190
|
| 160 |
-
},
|
| 161 |
-
{
|
| 162 |
-
"epoch": 4.97,
|
| 163 |
"learning_rate": 0.00014583333333333332,
|
| 164 |
-
"loss": 0.
|
| 165 |
-
"step":
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 4.99,
|
| 169 |
-
"eval_accuracy": 0.7745454545454545,
|
| 170 |
-
"eval_loss": 0.5211531519889832,
|
| 171 |
-
"eval_runtime": 3.0242,
|
| 172 |
-
"eval_samples_per_second": 181.865,
|
| 173 |
-
"eval_steps_per_second": 11.573,
|
| 174 |
-
"step": 201
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 5.22,
|
| 178 |
-
"learning_rate": 0.00014479166666666666,
|
| 179 |
-
"loss": 0.6747,
|
| 180 |
-
"step": 210
|
| 181 |
-
},
|
| 182 |
-
{
|
| 183 |
-
"epoch": 5.47,
|
| 184 |
-
"learning_rate": 0.00014375,
|
| 185 |
-
"loss": 0.7065,
|
| 186 |
-
"step": 220
|
| 187 |
-
},
|
| 188 |
-
{
|
| 189 |
-
"epoch": 5.71,
|
| 190 |
-
"learning_rate": 0.0001427083333333333,
|
| 191 |
-
"loss": 0.6179,
|
| 192 |
-
"step": 230
|
| 193 |
},
|
| 194 |
{
|
| 195 |
-
"epoch": 5.
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
-
"
|
|
|
|
|
|
|
|
|
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch":
|
| 202 |
-
"eval_accuracy": 0.
|
| 203 |
-
"eval_loss": 0.
|
| 204 |
-
"eval_runtime":
|
| 205 |
-
"eval_samples_per_second":
|
| 206 |
-
"eval_steps_per_second":
|
| 207 |
-
"step":
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 6.
|
| 211 |
"learning_rate": 0.000140625,
|
| 212 |
-
"loss": 0.
|
| 213 |
-
"step":
|
| 214 |
-
},
|
| 215 |
-
{
|
| 216 |
-
"epoch": 6.46,
|
| 217 |
-
"learning_rate": 0.00013958333333333333,
|
| 218 |
-
"loss": 0.6105,
|
| 219 |
-
"step": 260
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 6.71,
|
| 223 |
-
"learning_rate": 0.00013854166666666667,
|
| 224 |
-
"loss": 0.6449,
|
| 225 |
-
"step": 270
|
| 226 |
-
},
|
| 227 |
-
{
|
| 228 |
-
"epoch": 6.96,
|
| 229 |
-
"learning_rate": 0.00013749999999999998,
|
| 230 |
-
"loss": 0.6274,
|
| 231 |
-
"step": 280
|
| 232 |
-
},
|
| 233 |
-
{
|
| 234 |
-
"epoch": 6.98,
|
| 235 |
-
"eval_accuracy": 0.84,
|
| 236 |
-
"eval_loss": 0.4594345986843109,
|
| 237 |
-
"eval_runtime": 3.1042,
|
| 238 |
-
"eval_samples_per_second": 177.178,
|
| 239 |
-
"eval_steps_per_second": 11.275,
|
| 240 |
-
"step": 281
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch": 7.
|
| 244 |
-
"
|
| 245 |
-
"
|
| 246 |
-
"
|
|
|
|
|
|
|
|
|
|
| 247 |
},
|
| 248 |
{
|
| 249 |
-
"epoch": 7.
|
| 250 |
"learning_rate": 0.00013541666666666666,
|
| 251 |
-
"loss": 0.
|
| 252 |
-
"step":
|
| 253 |
-
},
|
| 254 |
-
{
|
| 255 |
-
"epoch": 7.7,
|
| 256 |
-
"learning_rate": 0.000134375,
|
| 257 |
-
"loss": 0.5892,
|
| 258 |
-
"step": 310
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 7.95,
|
| 262 |
-
"learning_rate": 0.0001333333333333333,
|
| 263 |
-
"loss": 0.5571,
|
| 264 |
-
"step": 320
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 8.0,
|
| 268 |
-
"eval_accuracy": 0.
|
| 269 |
-
"eval_loss": 0.
|
| 270 |
-
"eval_runtime":
|
| 271 |
-
"eval_samples_per_second":
|
| 272 |
-
"eval_steps_per_second":
|
| 273 |
-
"step":
|
| 274 |
-
},
|
| 275 |
-
{
|
| 276 |
-
"epoch": 8.2,
|
| 277 |
-
"learning_rate": 0.00013229166666666665,
|
| 278 |
-
"loss": 0.5527,
|
| 279 |
-
"step": 330
|
| 280 |
-
},
|
| 281 |
-
{
|
| 282 |
-
"epoch": 8.45,
|
| 283 |
-
"learning_rate": 0.00013125,
|
| 284 |
-
"loss": 0.5555,
|
| 285 |
-
"step": 340
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch": 8.
|
| 289 |
"learning_rate": 0.00013020833333333333,
|
| 290 |
-
"loss": 0.
|
| 291 |
-
"step":
|
| 292 |
-
},
|
| 293 |
-
{
|
| 294 |
-
"epoch": 8.94,
|
| 295 |
-
"learning_rate": 0.00012916666666666667,
|
| 296 |
-
"loss": 0.5803,
|
| 297 |
-
"step": 360
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 8.99,
|
| 301 |
-
"eval_accuracy": 0.82,
|
| 302 |
-
"eval_loss": 0.4614850878715515,
|
| 303 |
-
"eval_runtime": 2.9457,
|
| 304 |
-
"eval_samples_per_second": 186.714,
|
| 305 |
-
"eval_steps_per_second": 11.882,
|
| 306 |
-
"step": 362
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"epoch": 9.19,
|
| 310 |
-
"learning_rate": 0.00012812499999999998,
|
| 311 |
-
"loss": 0.5186,
|
| 312 |
-
"step": 370
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 9.44,
|
| 316 |
-
"learning_rate": 0.00012708333333333332,
|
| 317 |
-
"loss": 0.543,
|
| 318 |
-
"step": 380
|
| 319 |
},
|
| 320 |
{
|
| 321 |
-
"epoch": 9.
|
| 322 |
-
"
|
| 323 |
-
"
|
| 324 |
-
"
|
|
|
|
|
|
|
|
|
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch":
|
| 328 |
"learning_rate": 0.000125,
|
| 329 |
-
"loss": 0.
|
| 330 |
-
"step":
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 9.99,
|
| 334 |
-
"eval_accuracy": 0.8363636363636363,
|
| 335 |
-
"eval_loss": 0.4558989107608795,
|
| 336 |
-
"eval_runtime": 3.4123,
|
| 337 |
-
"eval_samples_per_second": 161.181,
|
| 338 |
-
"eval_steps_per_second": 10.257,
|
| 339 |
-
"step": 402
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 10.19,
|
| 343 |
-
"learning_rate": 0.00012395833333333332,
|
| 344 |
-
"loss": 0.4907,
|
| 345 |
-
"step": 410
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 10.43,
|
| 349 |
-
"learning_rate": 0.00012291666666666665,
|
| 350 |
-
"loss": 0.4828,
|
| 351 |
-
"step": 420
|
| 352 |
-
},
|
| 353 |
-
{
|
| 354 |
-
"epoch": 10.68,
|
| 355 |
-
"learning_rate": 0.000121875,
|
| 356 |
-
"loss": 0.5777,
|
| 357 |
-
"step": 430
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch": 10.
|
| 361 |
-
"
|
| 362 |
-
"
|
| 363 |
-
"
|
|
|
|
|
|
|
|
|
|
| 364 |
},
|
| 365 |
{
|
| 366 |
-
"epoch":
|
| 367 |
-
"eval_accuracy": 0.
|
| 368 |
-
"eval_loss": 0.
|
| 369 |
-
"eval_runtime":
|
| 370 |
-
"eval_samples_per_second":
|
| 371 |
-
"eval_steps_per_second":
|
| 372 |
-
"step":
|
| 373 |
},
|
| 374 |
{
|
| 375 |
-
"epoch": 11.
|
| 376 |
"learning_rate": 0.00011979166666666666,
|
| 377 |
-
"loss": 0.
|
| 378 |
-
"step":
|
| 379 |
-
},
|
| 380 |
-
{
|
| 381 |
-
"epoch": 11.43,
|
| 382 |
-
"learning_rate": 0.00011874999999999999,
|
| 383 |
-
"loss": 0.4665,
|
| 384 |
-
"step": 460
|
| 385 |
-
},
|
| 386 |
-
{
|
| 387 |
-
"epoch": 11.68,
|
| 388 |
-
"learning_rate": 0.00011770833333333333,
|
| 389 |
-
"loss": 0.5583,
|
| 390 |
-
"step": 470
|
| 391 |
-
},
|
| 392 |
-
{
|
| 393 |
-
"epoch": 11.93,
|
| 394 |
-
"learning_rate": 0.00011666666666666665,
|
| 395 |
-
"loss": 0.5287,
|
| 396 |
-
"step": 480
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 12.0,
|
| 400 |
-
"eval_accuracy": 0.
|
| 401 |
-
"eval_loss": 0.
|
| 402 |
-
"eval_runtime":
|
| 403 |
-
"eval_samples_per_second":
|
| 404 |
-
"eval_steps_per_second":
|
| 405 |
-
"step":
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch": 12.
|
| 409 |
-
"learning_rate": 0.00011562499999999999,
|
| 410 |
-
"loss": 0.5208,
|
| 411 |
-
"step": 490
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 12.42,
|
| 415 |
"learning_rate": 0.00011458333333333332,
|
| 416 |
-
"loss": 0.
|
| 417 |
-
"step":
|
| 418 |
-
},
|
| 419 |
-
{
|
| 420 |
-
"epoch": 12.67,
|
| 421 |
-
"learning_rate": 0.00011354166666666666,
|
| 422 |
-
"loss": 0.4893,
|
| 423 |
-
"step": 510
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 12.92,
|
| 427 |
-
"learning_rate": 0.0001125,
|
| 428 |
-
"loss": 0.4689,
|
| 429 |
-
"step": 520
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 12.99,
|
| 433 |
-
"eval_accuracy": 0.8327272727272728,
|
| 434 |
-
"eval_loss": 0.45357394218444824,
|
| 435 |
-
"eval_runtime": 3.2638,
|
| 436 |
-
"eval_samples_per_second": 168.516,
|
| 437 |
-
"eval_steps_per_second": 10.724,
|
| 438 |
-
"step": 523
|
| 439 |
-
},
|
| 440 |
-
{
|
| 441 |
-
"epoch": 13.17,
|
| 442 |
-
"learning_rate": 0.00011145833333333332,
|
| 443 |
-
"loss": 0.5399,
|
| 444 |
-
"step": 530
|
| 445 |
},
|
| 446 |
{
|
| 447 |
-
"epoch": 13.
|
| 448 |
-
"
|
| 449 |
-
"
|
| 450 |
-
"
|
|
|
|
|
|
|
|
|
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch": 13.
|
| 454 |
"learning_rate": 0.00010937499999999999,
|
| 455 |
-
"loss": 0.
|
| 456 |
-
"step":
|
| 457 |
-
},
|
| 458 |
-
{
|
| 459 |
-
"epoch": 13.91,
|
| 460 |
-
"learning_rate": 0.00010833333333333333,
|
| 461 |
-
"loss": 0.422,
|
| 462 |
-
"step": 560
|
| 463 |
-
},
|
| 464 |
-
{
|
| 465 |
-
"epoch": 13.99,
|
| 466 |
-
"eval_accuracy": 0.8745454545454545,
|
| 467 |
-
"eval_loss": 0.3475695550441742,
|
| 468 |
-
"eval_runtime": 2.9537,
|
| 469 |
-
"eval_samples_per_second": 186.206,
|
| 470 |
-
"eval_steps_per_second": 11.849,
|
| 471 |
-
"step": 563
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 14.16,
|
| 475 |
-
"learning_rate": 0.00010729166666666665,
|
| 476 |
-
"loss": 0.4511,
|
| 477 |
-
"step": 570
|
| 478 |
-
},
|
| 479 |
-
{
|
| 480 |
-
"epoch": 14.41,
|
| 481 |
-
"learning_rate": 0.00010625,
|
| 482 |
-
"loss": 0.492,
|
| 483 |
-
"step": 580
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch": 14.
|
| 487 |
-
"
|
| 488 |
-
"
|
| 489 |
-
"
|
|
|
|
|
|
|
|
|
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch":
|
| 493 |
"learning_rate": 0.00010416666666666666,
|
| 494 |
-
"loss": 0.
|
| 495 |
-
"step":
|
| 496 |
-
},
|
| 497 |
-
{
|
| 498 |
-
"epoch": 14.98,
|
| 499 |
-
"eval_accuracy": 0.8545454545454545,
|
| 500 |
-
"eval_loss": 0.3863639831542969,
|
| 501 |
-
"eval_runtime": 2.9867,
|
| 502 |
-
"eval_samples_per_second": 184.147,
|
| 503 |
-
"eval_steps_per_second": 11.718,
|
| 504 |
-
"step": 603
|
| 505 |
-
},
|
| 506 |
-
{
|
| 507 |
-
"epoch": 15.16,
|
| 508 |
-
"learning_rate": 0.00010312499999999999,
|
| 509 |
-
"loss": 0.5208,
|
| 510 |
-
"step": 610
|
| 511 |
-
},
|
| 512 |
-
{
|
| 513 |
-
"epoch": 15.4,
|
| 514 |
-
"learning_rate": 0.00010208333333333333,
|
| 515 |
-
"loss": 0.5145,
|
| 516 |
-
"step": 620
|
| 517 |
-
},
|
| 518 |
-
{
|
| 519 |
-
"epoch": 15.65,
|
| 520 |
-
"learning_rate": 0.00010104166666666667,
|
| 521 |
-
"loss": 0.4778,
|
| 522 |
-
"step": 630
|
| 523 |
},
|
| 524 |
{
|
| 525 |
-
"epoch": 15.
|
| 526 |
-
"
|
| 527 |
-
"
|
| 528 |
-
"
|
|
|
|
|
|
|
|
|
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 16.0,
|
| 532 |
-
"eval_accuracy": 0.
|
| 533 |
-
"eval_loss": 0.
|
| 534 |
-
"eval_runtime":
|
| 535 |
-
"eval_samples_per_second":
|
| 536 |
-
"eval_steps_per_second":
|
| 537 |
-
"step":
|
| 538 |
},
|
| 539 |
{
|
| 540 |
-
"epoch": 16.
|
| 541 |
"learning_rate": 9.895833333333332e-05,
|
| 542 |
-
"loss": 0.
|
| 543 |
-
"step":
|
| 544 |
-
},
|
| 545 |
-
{
|
| 546 |
-
"epoch": 16.4,
|
| 547 |
-
"learning_rate": 9.791666666666666e-05,
|
| 548 |
-
"loss": 0.3966,
|
| 549 |
-
"step": 660
|
| 550 |
-
},
|
| 551 |
-
{
|
| 552 |
-
"epoch": 16.65,
|
| 553 |
-
"learning_rate": 9.6875e-05,
|
| 554 |
-
"loss": 0.4172,
|
| 555 |
-
"step": 670
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 16.89,
|
| 559 |
-
"learning_rate": 9.583333333333332e-05,
|
| 560 |
-
"loss": 0.4598,
|
| 561 |
-
"step": 680
|
| 562 |
-
},
|
| 563 |
-
{
|
| 564 |
-
"epoch": 16.99,
|
| 565 |
-
"eval_accuracy": 0.8654545454545455,
|
| 566 |
-
"eval_loss": 0.3689936697483063,
|
| 567 |
-
"eval_runtime": 2.9832,
|
| 568 |
-
"eval_samples_per_second": 184.366,
|
| 569 |
-
"eval_steps_per_second": 11.732,
|
| 570 |
-
"step": 684
|
| 571 |
},
|
| 572 |
{
|
| 573 |
-
"epoch": 17.
|
| 574 |
-
"
|
| 575 |
-
"
|
| 576 |
-
"
|
|
|
|
|
|
|
|
|
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch": 17.
|
| 580 |
"learning_rate": 9.374999999999999e-05,
|
| 581 |
-
"loss": 0.
|
| 582 |
-
"step":
|
| 583 |
-
},
|
| 584 |
-
{
|
| 585 |
-
"epoch": 17.64,
|
| 586 |
-
"learning_rate": 9.270833333333333e-05,
|
| 587 |
-
"loss": 0.4742,
|
| 588 |
-
"step": 710
|
| 589 |
-
},
|
| 590 |
-
{
|
| 591 |
-
"epoch": 17.89,
|
| 592 |
-
"learning_rate": 9.166666666666667e-05,
|
| 593 |
-
"loss": 0.4846,
|
| 594 |
-
"step": 720
|
| 595 |
-
},
|
| 596 |
-
{
|
| 597 |
-
"epoch": 17.99,
|
| 598 |
-
"eval_accuracy": 0.8654545454545455,
|
| 599 |
-
"eval_loss": 0.3708234429359436,
|
| 600 |
-
"eval_runtime": 2.9987,
|
| 601 |
-
"eval_samples_per_second": 183.412,
|
| 602 |
-
"eval_steps_per_second": 11.672,
|
| 603 |
-
"step": 724
|
| 604 |
-
},
|
| 605 |
-
{
|
| 606 |
-
"epoch": 18.14,
|
| 607 |
-
"learning_rate": 9.062499999999998e-05,
|
| 608 |
-
"loss": 0.529,
|
| 609 |
-
"step": 730
|
| 610 |
},
|
| 611 |
{
|
| 612 |
-
"epoch": 18.
|
| 613 |
-
"
|
| 614 |
-
"
|
| 615 |
-
"
|
|
|
|
|
|
|
|
|
|
| 616 |
},
|
| 617 |
{
|
| 618 |
-
"epoch": 18.
|
| 619 |
"learning_rate": 8.854166666666666e-05,
|
| 620 |
-
"loss": 0.
|
| 621 |
-
"step":
|
| 622 |
-
},
|
| 623 |
-
{
|
| 624 |
-
"epoch": 18.88,
|
| 625 |
-
"learning_rate": 8.75e-05,
|
| 626 |
-
"loss": 0.4126,
|
| 627 |
-
"step": 760
|
| 628 |
-
},
|
| 629 |
-
{
|
| 630 |
-
"epoch": 18.98,
|
| 631 |
-
"eval_accuracy": 0.86,
|
| 632 |
-
"eval_loss": 0.35055941343307495,
|
| 633 |
-
"eval_runtime": 3.0008,
|
| 634 |
-
"eval_samples_per_second": 183.287,
|
| 635 |
-
"eval_steps_per_second": 11.664,
|
| 636 |
-
"step": 764
|
| 637 |
-
},
|
| 638 |
-
{
|
| 639 |
-
"epoch": 19.13,
|
| 640 |
-
"learning_rate": 8.645833333333331e-05,
|
| 641 |
-
"loss": 0.3954,
|
| 642 |
-
"step": 770
|
| 643 |
-
},
|
| 644 |
-
{
|
| 645 |
-
"epoch": 19.38,
|
| 646 |
-
"learning_rate": 8.541666666666665e-05,
|
| 647 |
-
"loss": 0.3751,
|
| 648 |
-
"step": 780
|
| 649 |
},
|
| 650 |
{
|
| 651 |
-
"epoch": 19.
|
| 652 |
-
"
|
| 653 |
-
"
|
| 654 |
-
"
|
|
|
|
|
|
|
|
|
|
| 655 |
},
|
| 656 |
{
|
| 657 |
-
"epoch":
|
| 658 |
"learning_rate": 8.333333333333333e-05,
|
| 659 |
-
"loss": 0.
|
| 660 |
-
"step":
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 20.0,
|
| 664 |
-
"eval_accuracy": 0.
|
| 665 |
-
"eval_loss": 0.
|
| 666 |
-
"eval_runtime":
|
| 667 |
-
"eval_samples_per_second":
|
| 668 |
-
"eval_steps_per_second":
|
| 669 |
-
"step":
|
| 670 |
-
},
|
| 671 |
-
{
|
| 672 |
-
"epoch": 20.12,
|
| 673 |
-
"learning_rate": 8.229166666666667e-05,
|
| 674 |
-
"loss": 0.4148,
|
| 675 |
-
"step": 810
|
| 676 |
-
},
|
| 677 |
-
{
|
| 678 |
-
"epoch": 20.37,
|
| 679 |
-
"learning_rate": 8.124999999999998e-05,
|
| 680 |
-
"loss": 0.481,
|
| 681 |
-
"step": 820
|
| 682 |
-
},
|
| 683 |
-
{
|
| 684 |
-
"epoch": 20.62,
|
| 685 |
-
"learning_rate": 8.020833333333332e-05,
|
| 686 |
-
"loss": 0.4227,
|
| 687 |
-
"step": 830
|
| 688 |
-
},
|
| 689 |
-
{
|
| 690 |
-
"epoch": 20.87,
|
| 691 |
-
"learning_rate": 7.916666666666666e-05,
|
| 692 |
-
"loss": 0.4594,
|
| 693 |
-
"step": 840
|
| 694 |
},
|
| 695 |
{
|
| 696 |
-
"epoch":
|
| 697 |
-
"eval_accuracy": 0.
|
| 698 |
-
"eval_loss": 0.
|
| 699 |
-
"eval_runtime":
|
| 700 |
-
"eval_samples_per_second":
|
| 701 |
-
"eval_steps_per_second":
|
| 702 |
-
"step":
|
| 703 |
},
|
| 704 |
{
|
| 705 |
-
"epoch": 21.
|
| 706 |
"learning_rate": 7.8125e-05,
|
| 707 |
-
"loss": 0.
|
| 708 |
-
"step":
|
| 709 |
-
},
|
| 710 |
-
{
|
| 711 |
-
"epoch": 21.37,
|
| 712 |
-
"learning_rate": 7.708333333333331e-05,
|
| 713 |
-
"loss": 0.3531,
|
| 714 |
-
"step": 860
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 21.61,
|
| 718 |
-
"learning_rate": 7.604166666666665e-05,
|
| 719 |
-
"loss": 0.3841,
|
| 720 |
-
"step": 870
|
| 721 |
-
},
|
| 722 |
-
{
|
| 723 |
-
"epoch": 21.86,
|
| 724 |
-
"learning_rate": 7.5e-05,
|
| 725 |
-
"loss": 0.4163,
|
| 726 |
-
"step": 880
|
| 727 |
-
},
|
| 728 |
-
{
|
| 729 |
-
"epoch": 21.99,
|
| 730 |
-
"eval_accuracy": 0.8581818181818182,
|
| 731 |
-
"eval_loss": 0.370274156332016,
|
| 732 |
-
"eval_runtime": 3.0552,
|
| 733 |
-
"eval_samples_per_second": 180.019,
|
| 734 |
-
"eval_steps_per_second": 11.456,
|
| 735 |
-
"step": 885
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch": 22.
|
| 739 |
-
"
|
| 740 |
-
"
|
| 741 |
-
"
|
|
|
|
|
|
|
|
|
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"epoch": 22.
|
| 745 |
"learning_rate": 7.291666666666666e-05,
|
| 746 |
-
"loss": 0.
|
| 747 |
-
"step":
|
| 748 |
-
},
|
| 749 |
-
{
|
| 750 |
-
"epoch": 22.61,
|
| 751 |
-
"learning_rate": 7.1875e-05,
|
| 752 |
-
"loss": 0.4317,
|
| 753 |
-
"step": 910
|
| 754 |
-
},
|
| 755 |
-
{
|
| 756 |
-
"epoch": 22.86,
|
| 757 |
-
"learning_rate": 7.083333333333332e-05,
|
| 758 |
-
"loss": 0.3539,
|
| 759 |
-
"step": 920
|
| 760 |
-
},
|
| 761 |
-
{
|
| 762 |
-
"epoch": 22.98,
|
| 763 |
-
"eval_accuracy": 0.8636363636363636,
|
| 764 |
-
"eval_loss": 0.359360009431839,
|
| 765 |
-
"eval_runtime": 3.0137,
|
| 766 |
-
"eval_samples_per_second": 182.499,
|
| 767 |
-
"eval_steps_per_second": 11.614,
|
| 768 |
-
"step": 925
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 23.11,
|
| 772 |
-
"learning_rate": 6.979166666666666e-05,
|
| 773 |
-
"loss": 0.3941,
|
| 774 |
-
"step": 930
|
| 775 |
},
|
| 776 |
{
|
| 777 |
-
"epoch": 23.
|
| 778 |
-
"
|
| 779 |
-
"
|
| 780 |
-
"
|
|
|
|
|
|
|
|
|
|
| 781 |
},
|
| 782 |
{
|
| 783 |
-
"epoch": 23.
|
| 784 |
"learning_rate": 6.770833333333333e-05,
|
| 785 |
-
"loss": 0.
|
| 786 |
-
"step":
|
| 787 |
-
},
|
| 788 |
-
{
|
| 789 |
-
"epoch": 23.85,
|
| 790 |
-
"learning_rate": 6.666666666666666e-05,
|
| 791 |
-
"loss": 0.3751,
|
| 792 |
-
"step": 960
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 24.0,
|
| 796 |
-
"eval_accuracy": 0.
|
| 797 |
-
"eval_loss": 0.
|
| 798 |
-
"eval_runtime":
|
| 799 |
-
"eval_samples_per_second":
|
| 800 |
-
"eval_steps_per_second":
|
| 801 |
-
"step":
|
| 802 |
-
},
|
| 803 |
-
{
|
| 804 |
-
"epoch": 24.1,
|
| 805 |
-
"learning_rate": 6.5625e-05,
|
| 806 |
-
"loss": 0.4075,
|
| 807 |
-
"step": 970
|
| 808 |
-
},
|
| 809 |
-
{
|
| 810 |
-
"epoch": 24.35,
|
| 811 |
-
"learning_rate": 6.458333333333334e-05,
|
| 812 |
-
"loss": 0.3459,
|
| 813 |
-
"step": 980
|
| 814 |
},
|
| 815 |
{
|
| 816 |
-
"epoch":
|
| 817 |
-
"learning_rate": 6.354166666666666e-05,
|
| 818 |
-
"loss": 0.3511,
|
| 819 |
-
"step": 990
|
| 820 |
-
},
|
| 821 |
-
{
|
| 822 |
-
"epoch": 24.84,
|
| 823 |
"learning_rate": 6.25e-05,
|
| 824 |
-
"loss": 0.
|
| 825 |
-
"step":
|
| 826 |
-
},
|
| 827 |
-
{
|
| 828 |
-
"epoch": 24.99,
|
| 829 |
-
"eval_accuracy": 0.8818181818181818,
|
| 830 |
-
"eval_loss": 0.3315516710281372,
|
| 831 |
-
"eval_runtime": 2.9972,
|
| 832 |
-
"eval_samples_per_second": 183.503,
|
| 833 |
-
"eval_steps_per_second": 11.677,
|
| 834 |
-
"step": 1006
|
| 835 |
-
},
|
| 836 |
-
{
|
| 837 |
-
"epoch": 25.09,
|
| 838 |
-
"learning_rate": 6.145833333333333e-05,
|
| 839 |
-
"loss": 0.344,
|
| 840 |
-
"step": 1010
|
| 841 |
-
},
|
| 842 |
-
{
|
| 843 |
-
"epoch": 25.34,
|
| 844 |
-
"learning_rate": 6.041666666666666e-05,
|
| 845 |
-
"loss": 0.3362,
|
| 846 |
-
"step": 1020
|
| 847 |
-
},
|
| 848 |
-
{
|
| 849 |
-
"epoch": 25.59,
|
| 850 |
-
"learning_rate": 5.937499999999999e-05,
|
| 851 |
-
"loss": 0.3773,
|
| 852 |
-
"step": 1030
|
| 853 |
},
|
| 854 |
{
|
| 855 |
-
"epoch": 25.
|
| 856 |
-
"
|
| 857 |
-
"
|
| 858 |
-
"
|
|
|
|
|
|
|
|
|
|
| 859 |
},
|
| 860 |
{
|
| 861 |
-
"epoch":
|
| 862 |
-
"eval_accuracy": 0.
|
| 863 |
-
"eval_loss": 0.
|
| 864 |
-
"eval_runtime":
|
| 865 |
-
"eval_samples_per_second":
|
| 866 |
-
"eval_steps_per_second":
|
| 867 |
-
"step":
|
| 868 |
},
|
| 869 |
{
|
| 870 |
-
"epoch": 26.
|
| 871 |
"learning_rate": 5.729166666666666e-05,
|
| 872 |
-
"loss": 0.
|
| 873 |
-
"step":
|
| 874 |
-
},
|
| 875 |
-
{
|
| 876 |
-
"epoch": 26.34,
|
| 877 |
-
"learning_rate": 5.625e-05,
|
| 878 |
-
"loss": 0.385,
|
| 879 |
-
"step": 1060
|
| 880 |
-
},
|
| 881 |
-
{
|
| 882 |
-
"epoch": 26.58,
|
| 883 |
-
"learning_rate": 5.520833333333333e-05,
|
| 884 |
-
"loss": 0.3951,
|
| 885 |
-
"step": 1070
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"epoch": 26.83,
|
| 889 |
-
"learning_rate": 5.4166666666666664e-05,
|
| 890 |
-
"loss": 0.3029,
|
| 891 |
-
"step": 1080
|
| 892 |
-
},
|
| 893 |
-
{
|
| 894 |
-
"epoch": 26.98,
|
| 895 |
-
"eval_accuracy": 0.88,
|
| 896 |
-
"eval_loss": 0.3473585844039917,
|
| 897 |
-
"eval_runtime": 3.4048,
|
| 898 |
-
"eval_samples_per_second": 161.536,
|
| 899 |
-
"eval_steps_per_second": 10.28,
|
| 900 |
-
"step": 1086
|
| 901 |
},
|
| 902 |
{
|
| 903 |
-
"epoch": 27.
|
| 904 |
-
"
|
| 905 |
-
"
|
| 906 |
-
"
|
|
|
|
|
|
|
|
|
|
| 907 |
},
|
| 908 |
{
|
| 909 |
-
"epoch": 27.
|
| 910 |
"learning_rate": 5.208333333333333e-05,
|
| 911 |
-
"loss": 0.
|
| 912 |
-
"step":
|
| 913 |
-
},
|
| 914 |
-
{
|
| 915 |
-
"epoch": 27.58,
|
| 916 |
-
"learning_rate": 5.104166666666666e-05,
|
| 917 |
-
"loss": 0.3304,
|
| 918 |
-
"step": 1110
|
| 919 |
-
},
|
| 920 |
-
{
|
| 921 |
-
"epoch": 27.83,
|
| 922 |
-
"learning_rate": 4.9999999999999996e-05,
|
| 923 |
-
"loss": 0.286,
|
| 924 |
-
"step": 1120
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 28.0,
|
| 928 |
-
"eval_accuracy": 0.
|
| 929 |
-
"eval_loss": 0.
|
| 930 |
-
"eval_runtime":
|
| 931 |
-
"eval_samples_per_second":
|
| 932 |
-
"eval_steps_per_second":
|
| 933 |
-
"step":
|
| 934 |
-
},
|
| 935 |
-
{
|
| 936 |
-
"epoch": 28.07,
|
| 937 |
-
"learning_rate": 4.895833333333333e-05,
|
| 938 |
-
"loss": 0.332,
|
| 939 |
-
"step": 1130
|
| 940 |
-
},
|
| 941 |
-
{
|
| 942 |
-
"epoch": 28.32,
|
| 943 |
-
"learning_rate": 4.791666666666666e-05,
|
| 944 |
-
"loss": 0.3077,
|
| 945 |
-
"step": 1140
|
| 946 |
},
|
| 947 |
{
|
| 948 |
-
"epoch": 28.
|
| 949 |
"learning_rate": 4.6874999999999994e-05,
|
| 950 |
-
"loss": 0.
|
| 951 |
-
"step":
|
| 952 |
-
},
|
| 953 |
-
{
|
| 954 |
-
"epoch": 28.82,
|
| 955 |
-
"learning_rate": 4.5833333333333334e-05,
|
| 956 |
-
"loss": 0.361,
|
| 957 |
-
"step": 1160
|
| 958 |
-
},
|
| 959 |
-
{
|
| 960 |
-
"epoch": 28.99,
|
| 961 |
-
"eval_accuracy": 0.8709090909090909,
|
| 962 |
-
"eval_loss": 0.36599376797676086,
|
| 963 |
-
"eval_runtime": 3.5838,
|
| 964 |
-
"eval_samples_per_second": 153.466,
|
| 965 |
-
"eval_steps_per_second": 9.766,
|
| 966 |
-
"step": 1167
|
| 967 |
-
},
|
| 968 |
-
{
|
| 969 |
-
"epoch": 29.07,
|
| 970 |
-
"learning_rate": 4.479166666666666e-05,
|
| 971 |
-
"loss": 0.3393,
|
| 972 |
-
"step": 1170
|
| 973 |
-
},
|
| 974 |
-
{
|
| 975 |
-
"epoch": 29.32,
|
| 976 |
-
"learning_rate": 4.375e-05,
|
| 977 |
-
"loss": 0.3026,
|
| 978 |
-
"step": 1180
|
| 979 |
},
|
| 980 |
{
|
| 981 |
-
"epoch": 29.
|
| 982 |
-
"
|
| 983 |
-
"
|
| 984 |
-
"
|
|
|
|
|
|
|
|
|
|
| 985 |
},
|
| 986 |
{
|
| 987 |
-
"epoch":
|
| 988 |
"learning_rate": 4.1666666666666665e-05,
|
| 989 |
-
"loss": 0.
|
| 990 |
-
"step":
|
| 991 |
-
},
|
| 992 |
-
{
|
| 993 |
-
"epoch": 29.99,
|
| 994 |
-
"eval_accuracy": 0.8654545454545455,
|
| 995 |
-
"eval_loss": 0.396790087223053,
|
| 996 |
-
"eval_runtime": 3.0612,
|
| 997 |
-
"eval_samples_per_second": 179.667,
|
| 998 |
-
"eval_steps_per_second": 11.433,
|
| 999 |
-
"step": 1207
|
| 1000 |
-
},
|
| 1001 |
-
{
|
| 1002 |
-
"epoch": 30.06,
|
| 1003 |
-
"learning_rate": 4.062499999999999e-05,
|
| 1004 |
-
"loss": 0.3777,
|
| 1005 |
-
"step": 1210
|
| 1006 |
-
},
|
| 1007 |
-
{
|
| 1008 |
-
"epoch": 30.31,
|
| 1009 |
-
"learning_rate": 3.958333333333333e-05,
|
| 1010 |
-
"loss": 0.3046,
|
| 1011 |
-
"step": 1220
|
| 1012 |
-
},
|
| 1013 |
-
{
|
| 1014 |
-
"epoch": 30.56,
|
| 1015 |
-
"learning_rate": 3.854166666666666e-05,
|
| 1016 |
-
"loss": 0.3262,
|
| 1017 |
-
"step": 1230
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
-
"epoch": 30.
|
| 1021 |
-
"
|
| 1022 |
-
"
|
| 1023 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
-
"epoch":
|
| 1027 |
-
"eval_accuracy": 0.
|
| 1028 |
-
"eval_loss": 0.
|
| 1029 |
-
"eval_runtime":
|
| 1030 |
-
"eval_samples_per_second":
|
| 1031 |
-
"eval_steps_per_second":
|
| 1032 |
-
"step":
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
-
"epoch": 31.
|
| 1036 |
"learning_rate": 3.645833333333333e-05,
|
| 1037 |
-
"loss": 0.
|
| 1038 |
-
"step":
|
| 1039 |
-
},
|
| 1040 |
-
{
|
| 1041 |
-
"epoch": 31.3,
|
| 1042 |
-
"learning_rate": 3.541666666666666e-05,
|
| 1043 |
-
"loss": 0.2833,
|
| 1044 |
-
"step": 1260
|
| 1045 |
-
},
|
| 1046 |
-
{
|
| 1047 |
-
"epoch": 31.55,
|
| 1048 |
-
"learning_rate": 3.4374999999999995e-05,
|
| 1049 |
-
"loss": 0.2922,
|
| 1050 |
-
"step": 1270
|
| 1051 |
-
},
|
| 1052 |
-
{
|
| 1053 |
-
"epoch": 31.8,
|
| 1054 |
-
"learning_rate": 3.333333333333333e-05,
|
| 1055 |
-
"loss": 0.3127,
|
| 1056 |
-
"step": 1280
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 32.0,
|
| 1060 |
-
"eval_accuracy": 0.
|
| 1061 |
-
"eval_loss": 0.
|
| 1062 |
-
"eval_runtime":
|
| 1063 |
-
"eval_samples_per_second":
|
| 1064 |
-
"eval_steps_per_second":
|
| 1065 |
-
"step":
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
-
"epoch": 32.
|
| 1069 |
-
"learning_rate": 3.229166666666667e-05,
|
| 1070 |
-
"loss": 0.3219,
|
| 1071 |
-
"step": 1290
|
| 1072 |
-
},
|
| 1073 |
-
{
|
| 1074 |
-
"epoch": 32.3,
|
| 1075 |
"learning_rate": 3.125e-05,
|
| 1076 |
-
"loss": 0.
|
| 1077 |
-
"step":
|
| 1078 |
-
},
|
| 1079 |
-
{
|
| 1080 |
-
"epoch": 32.55,
|
| 1081 |
-
"learning_rate": 3.020833333333333e-05,
|
| 1082 |
-
"loss": 0.282,
|
| 1083 |
-
"step": 1310
|
| 1084 |
-
},
|
| 1085 |
-
{
|
| 1086 |
-
"epoch": 32.8,
|
| 1087 |
-
"learning_rate": 2.9166666666666663e-05,
|
| 1088 |
-
"loss": 0.2907,
|
| 1089 |
-
"step": 1320
|
| 1090 |
-
},
|
| 1091 |
-
{
|
| 1092 |
-
"epoch": 32.99,
|
| 1093 |
-
"eval_accuracy": 0.8690909090909091,
|
| 1094 |
-
"eval_loss": 0.4207320809364319,
|
| 1095 |
-
"eval_runtime": 3.4088,
|
| 1096 |
-
"eval_samples_per_second": 161.347,
|
| 1097 |
-
"eval_steps_per_second": 10.268,
|
| 1098 |
-
"step": 1328
|
| 1099 |
-
},
|
| 1100 |
-
{
|
| 1101 |
-
"epoch": 33.04,
|
| 1102 |
-
"learning_rate": 2.8125e-05,
|
| 1103 |
-
"loss": 0.3023,
|
| 1104 |
-
"step": 1330
|
| 1105 |
},
|
| 1106 |
{
|
| 1107 |
-
"epoch": 33.
|
| 1108 |
-
"
|
| 1109 |
-
"
|
| 1110 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1111 |
},
|
| 1112 |
{
|
| 1113 |
-
"epoch": 33.
|
| 1114 |
"learning_rate": 2.6041666666666665e-05,
|
| 1115 |
-
"loss": 0.
|
| 1116 |
-
"step":
|
| 1117 |
-
},
|
| 1118 |
-
{
|
| 1119 |
-
"epoch": 33.79,
|
| 1120 |
-
"learning_rate": 2.4999999999999998e-05,
|
| 1121 |
-
"loss": 0.2715,
|
| 1122 |
-
"step": 1360
|
| 1123 |
-
},
|
| 1124 |
-
{
|
| 1125 |
-
"epoch": 33.99,
|
| 1126 |
-
"eval_accuracy": 0.8727272727272727,
|
| 1127 |
-
"eval_loss": 0.42976346611976624,
|
| 1128 |
-
"eval_runtime": 3.6254,
|
| 1129 |
-
"eval_samples_per_second": 151.709,
|
| 1130 |
-
"eval_steps_per_second": 9.654,
|
| 1131 |
-
"step": 1368
|
| 1132 |
-
},
|
| 1133 |
-
{
|
| 1134 |
-
"epoch": 34.04,
|
| 1135 |
-
"learning_rate": 2.395833333333333e-05,
|
| 1136 |
-
"loss": 0.3249,
|
| 1137 |
-
"step": 1370
|
| 1138 |
-
},
|
| 1139 |
-
{
|
| 1140 |
-
"epoch": 34.29,
|
| 1141 |
-
"learning_rate": 2.2916666666666667e-05,
|
| 1142 |
-
"loss": 0.2499,
|
| 1143 |
-
"step": 1380
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
-
"epoch": 34.
|
| 1147 |
-
"
|
| 1148 |
-
"
|
| 1149 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1150 |
},
|
| 1151 |
{
|
| 1152 |
-
"epoch":
|
| 1153 |
"learning_rate": 2.0833333333333333e-05,
|
| 1154 |
-
"loss": 0.
|
| 1155 |
-
"step":
|
| 1156 |
-
},
|
| 1157 |
-
{
|
| 1158 |
-
"epoch": 34.98,
|
| 1159 |
-
"eval_accuracy": 0.8818181818181818,
|
| 1160 |
-
"eval_loss": 0.4064685106277466,
|
| 1161 |
-
"eval_runtime": 3.0877,
|
| 1162 |
-
"eval_samples_per_second": 178.124,
|
| 1163 |
-
"eval_steps_per_second": 11.335,
|
| 1164 |
-
"step": 1408
|
| 1165 |
-
},
|
| 1166 |
-
{
|
| 1167 |
-
"epoch": 35.03,
|
| 1168 |
-
"learning_rate": 1.9791666666666665e-05,
|
| 1169 |
-
"loss": 0.2951,
|
| 1170 |
-
"step": 1410
|
| 1171 |
-
},
|
| 1172 |
-
{
|
| 1173 |
-
"epoch": 35.28,
|
| 1174 |
-
"learning_rate": 1.875e-05,
|
| 1175 |
-
"loss": 0.2617,
|
| 1176 |
-
"step": 1420
|
| 1177 |
-
},
|
| 1178 |
-
{
|
| 1179 |
-
"epoch": 35.53,
|
| 1180 |
-
"learning_rate": 1.770833333333333e-05,
|
| 1181 |
-
"loss": 0.2896,
|
| 1182 |
-
"step": 1430
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
-
"epoch": 35.
|
| 1186 |
-
"
|
| 1187 |
-
"
|
| 1188 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
"epoch": 36.0,
|
| 1192 |
-
"eval_accuracy": 0.
|
| 1193 |
-
"eval_loss": 0.
|
| 1194 |
-
"eval_runtime":
|
| 1195 |
-
"eval_samples_per_second":
|
| 1196 |
-
"eval_steps_per_second":
|
| 1197 |
-
"step":
|
| 1198 |
},
|
| 1199 |
{
|
| 1200 |
-
"epoch": 36.
|
| 1201 |
"learning_rate": 1.5625e-05,
|
| 1202 |
-
"loss": 0.
|
| 1203 |
-
"step":
|
| 1204 |
-
},
|
| 1205 |
-
{
|
| 1206 |
-
"epoch": 36.27,
|
| 1207 |
-
"learning_rate": 1.4583333333333331e-05,
|
| 1208 |
-
"loss": 0.2874,
|
| 1209 |
-
"step": 1460
|
| 1210 |
-
},
|
| 1211 |
-
{
|
| 1212 |
-
"epoch": 36.52,
|
| 1213 |
-
"learning_rate": 1.3541666666666666e-05,
|
| 1214 |
-
"loss": 0.2804,
|
| 1215 |
-
"step": 1470
|
| 1216 |
-
},
|
| 1217 |
-
{
|
| 1218 |
-
"epoch": 36.77,
|
| 1219 |
-
"learning_rate": 1.2499999999999999e-05,
|
| 1220 |
-
"loss": 0.2137,
|
| 1221 |
-
"step": 1480
|
| 1222 |
-
},
|
| 1223 |
-
{
|
| 1224 |
-
"epoch": 36.99,
|
| 1225 |
-
"eval_accuracy": 0.8836363636363637,
|
| 1226 |
-
"eval_loss": 0.4129485487937927,
|
| 1227 |
-
"eval_runtime": 3.0673,
|
| 1228 |
-
"eval_samples_per_second": 179.31,
|
| 1229 |
-
"eval_steps_per_second": 11.411,
|
| 1230 |
-
"step": 1489
|
| 1231 |
},
|
| 1232 |
{
|
| 1233 |
-
"epoch": 37.
|
| 1234 |
-
"
|
| 1235 |
-
"
|
| 1236 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
-
"epoch": 37.
|
| 1240 |
"learning_rate": 1.0416666666666666e-05,
|
| 1241 |
-
"loss": 0.
|
| 1242 |
-
"step":
|
| 1243 |
-
},
|
| 1244 |
-
{
|
| 1245 |
-
"epoch": 37.52,
|
| 1246 |
-
"learning_rate": 9.375e-06,
|
| 1247 |
-
"loss": 0.2013,
|
| 1248 |
-
"step": 1510
|
| 1249 |
-
},
|
| 1250 |
-
{
|
| 1251 |
-
"epoch": 37.76,
|
| 1252 |
-
"learning_rate": 8.333333333333332e-06,
|
| 1253 |
-
"loss": 0.24,
|
| 1254 |
-
"step": 1520
|
| 1255 |
-
},
|
| 1256 |
-
{
|
| 1257 |
-
"epoch": 37.99,
|
| 1258 |
-
"eval_accuracy": 0.88,
|
| 1259 |
-
"eval_loss": 0.4160398244857788,
|
| 1260 |
-
"eval_runtime": 3.0337,
|
| 1261 |
-
"eval_samples_per_second": 181.296,
|
| 1262 |
-
"eval_steps_per_second": 11.537,
|
| 1263 |
-
"step": 1529
|
| 1264 |
-
},
|
| 1265 |
-
{
|
| 1266 |
-
"epoch": 38.01,
|
| 1267 |
-
"learning_rate": 7.291666666666666e-06,
|
| 1268 |
-
"loss": 0.3177,
|
| 1269 |
-
"step": 1530
|
| 1270 |
},
|
| 1271 |
{
|
| 1272 |
-
"epoch": 38.
|
| 1273 |
-
"
|
| 1274 |
-
"
|
| 1275 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1276 |
},
|
| 1277 |
{
|
| 1278 |
-
"epoch": 38.
|
| 1279 |
"learning_rate": 5.208333333333333e-06,
|
| 1280 |
-
"loss": 0.
|
| 1281 |
-
"step":
|
| 1282 |
-
},
|
| 1283 |
-
{
|
| 1284 |
-
"epoch": 38.76,
|
| 1285 |
-
"learning_rate": 4.166666666666666e-06,
|
| 1286 |
-
"loss": 0.2326,
|
| 1287 |
-
"step": 1560
|
| 1288 |
-
},
|
| 1289 |
-
{
|
| 1290 |
-
"epoch": 38.98,
|
| 1291 |
-
"eval_accuracy": 0.8781818181818182,
|
| 1292 |
-
"eval_loss": 0.4104275703430176,
|
| 1293 |
-
"eval_runtime": 3.0605,
|
| 1294 |
-
"eval_samples_per_second": 179.71,
|
| 1295 |
-
"eval_steps_per_second": 11.436,
|
| 1296 |
-
"step": 1569
|
| 1297 |
},
|
| 1298 |
{
|
| 1299 |
-
"epoch": 39.
|
| 1300 |
-
"
|
| 1301 |
-
"
|
| 1302 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
-
"epoch":
|
| 1306 |
-
"learning_rate":
|
| 1307 |
-
"loss": 0.
|
| 1308 |
-
"step":
|
| 1309 |
},
|
| 1310 |
{
|
| 1311 |
-
"epoch":
|
| 1312 |
-
"
|
| 1313 |
-
"
|
| 1314 |
-
"
|
|
|
|
|
|
|
|
|
|
| 1315 |
},
|
| 1316 |
{
|
| 1317 |
-
"epoch":
|
| 1318 |
-
"
|
| 1319 |
-
"
|
| 1320 |
-
"
|
| 1321 |
-
|
| 1322 |
-
|
| 1323 |
-
"
|
| 1324 |
-
"eval_accuracy": 0.8781818181818182,
|
| 1325 |
-
"eval_loss": 0.4129771888256073,
|
| 1326 |
-
"eval_runtime": 3.0837,
|
| 1327 |
-
"eval_samples_per_second": 178.356,
|
| 1328 |
-
"eval_steps_per_second": 11.35,
|
| 1329 |
-
"step": 1600
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 39.75,
|
| 1333 |
-
"step": 1600,
|
| 1334 |
-
"total_flos": 3.3152976312025743e+18,
|
| 1335 |
-
"train_loss": 0.4701251982152462,
|
| 1336 |
-
"train_runtime": 1462.7895,
|
| 1337 |
-
"train_samples_per_second": 70.085,
|
| 1338 |
-
"train_steps_per_second": 1.094
|
| 1339 |
}
|
| 1340 |
],
|
| 1341 |
"logging_steps": 10,
|
| 1342 |
-
"max_steps":
|
| 1343 |
"num_input_tokens_seen": 0,
|
| 1344 |
"num_train_epochs": 40,
|
| 1345 |
"save_steps": 500,
|
| 1346 |
-
"total_flos":
|
| 1347 |
"train_batch_size": 16,
|
| 1348 |
"trial_name": null,
|
| 1349 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.616822429906542,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-RD-aptos19\\checkpoint-296",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 320,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.411214953271028,
|
| 14 |
+
"eval_loss": 4.565852165222168,
|
| 15 |
+
"eval_runtime": 2.7444,
|
| 16 |
+
"eval_samples_per_second": 38.988,
|
| 17 |
+
"eval_steps_per_second": 2.551,
|
| 18 |
+
"step": 8
|
|
|
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
{
|
| 21 |
+
"epoch": 1.25,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"learning_rate": 4.6874999999999994e-05,
|
| 23 |
+
"loss": 4.5175,
|
| 24 |
+
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.411214953271028,
|
| 29 |
+
"eval_loss": 3.647094964981079,
|
| 30 |
+
"eval_runtime": 1.9164,
|
| 31 |
+
"eval_samples_per_second": 55.833,
|
| 32 |
+
"eval_steps_per_second": 3.653,
|
| 33 |
+
"step": 16
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 2.5,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
"learning_rate": 9.374999999999999e-05,
|
| 38 |
+
"loss": 3.927,
|
| 39 |
+
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 3.0,
|
| 43 |
+
"eval_accuracy": 0.411214953271028,
|
| 44 |
+
"eval_loss": 1.6286081075668335,
|
| 45 |
+
"eval_runtime": 1.9645,
|
| 46 |
+
"eval_samples_per_second": 54.468,
|
| 47 |
+
"eval_steps_per_second": 3.563,
|
| 48 |
+
"step": 24
|
| 49 |
},
|
| 50 |
{
|
| 51 |
+
"epoch": 3.75,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
"learning_rate": 0.000140625,
|
| 53 |
+
"loss": 1.6081,
|
| 54 |
+
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 4.0,
|
| 58 |
+
"eval_accuracy": 0.5887850467289719,
|
| 59 |
+
"eval_loss": 0.6780943274497986,
|
| 60 |
+
"eval_runtime": 1.9235,
|
| 61 |
+
"eval_samples_per_second": 55.629,
|
| 62 |
+
"eval_steps_per_second": 3.639,
|
| 63 |
+
"step": 32
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 5.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"learning_rate": 0.00014583333333333332,
|
| 68 |
+
"loss": 0.7702,
|
| 69 |
+
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 5.0,
|
| 73 |
+
"eval_accuracy": 0.5887850467289719,
|
| 74 |
+
"eval_loss": 0.8356828689575195,
|
| 75 |
+
"eval_runtime": 2.0574,
|
| 76 |
+
"eval_samples_per_second": 52.007,
|
| 77 |
+
"eval_steps_per_second": 3.402,
|
| 78 |
+
"step": 40
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 6.0,
|
| 82 |
+
"eval_accuracy": 0.5887850467289719,
|
| 83 |
+
"eval_loss": 0.6765593886375427,
|
| 84 |
+
"eval_runtime": 1.9495,
|
| 85 |
+
"eval_samples_per_second": 54.887,
|
| 86 |
+
"eval_steps_per_second": 3.591,
|
| 87 |
+
"step": 48
|
| 88 |
},
|
| 89 |
{
|
| 90 |
+
"epoch": 6.25,
|
| 91 |
"learning_rate": 0.000140625,
|
| 92 |
+
"loss": 0.7502,
|
| 93 |
+
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 7.0,
|
| 97 |
+
"eval_accuracy": 0.411214953271028,
|
| 98 |
+
"eval_loss": 0.7522286176681519,
|
| 99 |
+
"eval_runtime": 2.091,
|
| 100 |
+
"eval_samples_per_second": 51.172,
|
| 101 |
+
"eval_steps_per_second": 3.348,
|
| 102 |
+
"step": 56
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 7.5,
|
| 106 |
"learning_rate": 0.00013541666666666666,
|
| 107 |
+
"loss": 0.7266,
|
| 108 |
+
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 8.0,
|
| 112 |
+
"eval_accuracy": 0.5887850467289719,
|
| 113 |
+
"eval_loss": 0.679230809211731,
|
| 114 |
+
"eval_runtime": 2.0074,
|
| 115 |
+
"eval_samples_per_second": 53.301,
|
| 116 |
+
"eval_steps_per_second": 3.487,
|
| 117 |
+
"step": 64
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 8.75,
|
| 121 |
"learning_rate": 0.00013020833333333333,
|
| 122 |
+
"loss": 0.6954,
|
| 123 |
+
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 9.0,
|
| 127 |
+
"eval_accuracy": 0.5887850467289719,
|
| 128 |
+
"eval_loss": 0.6881440877914429,
|
| 129 |
+
"eval_runtime": 1.8339,
|
| 130 |
+
"eval_samples_per_second": 58.345,
|
| 131 |
+
"eval_steps_per_second": 3.817,
|
| 132 |
+
"step": 72
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 10.0,
|
| 136 |
"learning_rate": 0.000125,
|
| 137 |
+
"loss": 0.6808,
|
| 138 |
+
"step": 80
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 10.0,
|
| 142 |
+
"eval_accuracy": 0.5887850467289719,
|
| 143 |
+
"eval_loss": 0.6780060529708862,
|
| 144 |
+
"eval_runtime": 1.8679,
|
| 145 |
+
"eval_samples_per_second": 57.282,
|
| 146 |
+
"eval_steps_per_second": 3.747,
|
| 147 |
+
"step": 80
|
| 148 |
},
|
| 149 |
{
|
| 150 |
+
"epoch": 11.0,
|
| 151 |
+
"eval_accuracy": 0.5887850467289719,
|
| 152 |
+
"eval_loss": 0.7129637598991394,
|
| 153 |
+
"eval_runtime": 2.0595,
|
| 154 |
+
"eval_samples_per_second": 51.955,
|
| 155 |
+
"eval_steps_per_second": 3.399,
|
| 156 |
+
"step": 88
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 11.25,
|
| 160 |
"learning_rate": 0.00011979166666666666,
|
| 161 |
+
"loss": 0.7068,
|
| 162 |
+
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 163 |
},
|
| 164 |
{
|
| 165 |
"epoch": 12.0,
|
| 166 |
+
"eval_accuracy": 0.5887850467289719,
|
| 167 |
+
"eval_loss": 0.6770886778831482,
|
| 168 |
+
"eval_runtime": 1.8579,
|
| 169 |
+
"eval_samples_per_second": 57.591,
|
| 170 |
+
"eval_steps_per_second": 3.768,
|
| 171 |
+
"step": 96
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 12.5,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 175 |
"learning_rate": 0.00011458333333333332,
|
| 176 |
+
"loss": 0.6792,
|
| 177 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 13.0,
|
| 181 |
+
"eval_accuracy": 0.5887850467289719,
|
| 182 |
+
"eval_loss": 0.6779045462608337,
|
| 183 |
+
"eval_runtime": 1.9391,
|
| 184 |
+
"eval_samples_per_second": 55.179,
|
| 185 |
+
"eval_steps_per_second": 3.61,
|
| 186 |
+
"step": 104
|
| 187 |
},
|
| 188 |
{
|
| 189 |
+
"epoch": 13.75,
|
| 190 |
"learning_rate": 0.00010937499999999999,
|
| 191 |
+
"loss": 0.6841,
|
| 192 |
+
"step": 110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 14.0,
|
| 196 |
+
"eval_accuracy": 0.5887850467289719,
|
| 197 |
+
"eval_loss": 0.6766365170478821,
|
| 198 |
+
"eval_runtime": 2.0285,
|
| 199 |
+
"eval_samples_per_second": 52.749,
|
| 200 |
+
"eval_steps_per_second": 3.451,
|
| 201 |
+
"step": 112
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 15.0,
|
| 205 |
"learning_rate": 0.00010416666666666666,
|
| 206 |
+
"loss": 0.6777,
|
| 207 |
+
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 15.0,
|
| 211 |
+
"eval_accuracy": 0.5887850467289719,
|
| 212 |
+
"eval_loss": 0.6860565543174744,
|
| 213 |
+
"eval_runtime": 2.0915,
|
| 214 |
+
"eval_samples_per_second": 51.159,
|
| 215 |
+
"eval_steps_per_second": 3.347,
|
| 216 |
+
"step": 120
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 16.0,
|
| 220 |
+
"eval_accuracy": 0.5887850467289719,
|
| 221 |
+
"eval_loss": 0.6773396134376526,
|
| 222 |
+
"eval_runtime": 1.948,
|
| 223 |
+
"eval_samples_per_second": 54.928,
|
| 224 |
+
"eval_steps_per_second": 3.593,
|
| 225 |
+
"step": 128
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 16.25,
|
| 229 |
"learning_rate": 9.895833333333332e-05,
|
| 230 |
+
"loss": 0.6818,
|
| 231 |
+
"step": 130
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 17.0,
|
| 235 |
+
"eval_accuracy": 0.5887850467289719,
|
| 236 |
+
"eval_loss": 0.6805893182754517,
|
| 237 |
+
"eval_runtime": 1.8914,
|
| 238 |
+
"eval_samples_per_second": 56.57,
|
| 239 |
+
"eval_steps_per_second": 3.701,
|
| 240 |
+
"step": 136
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 17.5,
|
| 244 |
"learning_rate": 9.374999999999999e-05,
|
| 245 |
+
"loss": 0.6747,
|
| 246 |
+
"step": 140
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 18.0,
|
| 250 |
+
"eval_accuracy": 0.5887850467289719,
|
| 251 |
+
"eval_loss": 0.6928897500038147,
|
| 252 |
+
"eval_runtime": 1.9231,
|
| 253 |
+
"eval_samples_per_second": 55.639,
|
| 254 |
+
"eval_steps_per_second": 3.64,
|
| 255 |
+
"step": 144
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 18.75,
|
| 259 |
"learning_rate": 8.854166666666666e-05,
|
| 260 |
+
"loss": 0.6814,
|
| 261 |
+
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 19.0,
|
| 265 |
+
"eval_accuracy": 0.5887850467289719,
|
| 266 |
+
"eval_loss": 0.6767390370368958,
|
| 267 |
+
"eval_runtime": 1.8514,
|
| 268 |
+
"eval_samples_per_second": 57.793,
|
| 269 |
+
"eval_steps_per_second": 3.781,
|
| 270 |
+
"step": 152
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"epoch": 20.0,
|
| 274 |
"learning_rate": 8.333333333333333e-05,
|
| 275 |
+
"loss": 0.6714,
|
| 276 |
+
"step": 160
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 20.0,
|
| 280 |
+
"eval_accuracy": 0.5887850467289719,
|
| 281 |
+
"eval_loss": 0.6744682788848877,
|
| 282 |
+
"eval_runtime": 1.9225,
|
| 283 |
+
"eval_samples_per_second": 55.658,
|
| 284 |
+
"eval_steps_per_second": 3.641,
|
| 285 |
+
"step": 160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 21.0,
|
| 289 |
+
"eval_accuracy": 0.5887850467289719,
|
| 290 |
+
"eval_loss": 0.6852397322654724,
|
| 291 |
+
"eval_runtime": 1.91,
|
| 292 |
+
"eval_samples_per_second": 56.022,
|
| 293 |
+
"eval_steps_per_second": 3.665,
|
| 294 |
+
"step": 168
|
| 295 |
},
|
| 296 |
{
|
| 297 |
+
"epoch": 21.25,
|
| 298 |
"learning_rate": 7.8125e-05,
|
| 299 |
+
"loss": 0.6765,
|
| 300 |
+
"step": 170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"epoch": 22.0,
|
| 304 |
+
"eval_accuracy": 0.5514018691588785,
|
| 305 |
+
"eval_loss": 0.6815980672836304,
|
| 306 |
+
"eval_runtime": 1.932,
|
| 307 |
+
"eval_samples_per_second": 55.384,
|
| 308 |
+
"eval_steps_per_second": 3.623,
|
| 309 |
+
"step": 176
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 22.5,
|
| 313 |
"learning_rate": 7.291666666666666e-05,
|
| 314 |
+
"loss": 0.6822,
|
| 315 |
+
"step": 180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 316 |
},
|
| 317 |
{
|
| 318 |
+
"epoch": 23.0,
|
| 319 |
+
"eval_accuracy": 0.5887850467289719,
|
| 320 |
+
"eval_loss": 0.6982948184013367,
|
| 321 |
+
"eval_runtime": 1.964,
|
| 322 |
+
"eval_samples_per_second": 54.482,
|
| 323 |
+
"eval_steps_per_second": 3.564,
|
| 324 |
+
"step": 184
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 23.75,
|
| 328 |
"learning_rate": 6.770833333333333e-05,
|
| 329 |
+
"loss": 0.6816,
|
| 330 |
+
"step": 190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 24.0,
|
| 334 |
+
"eval_accuracy": 0.5887850467289719,
|
| 335 |
+
"eval_loss": 0.6706489324569702,
|
| 336 |
+
"eval_runtime": 1.8679,
|
| 337 |
+
"eval_samples_per_second": 57.282,
|
| 338 |
+
"eval_steps_per_second": 3.747,
|
| 339 |
+
"step": 192
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 25.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 343 |
"learning_rate": 6.25e-05,
|
| 344 |
+
"loss": 0.6868,
|
| 345 |
+
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 25.0,
|
| 349 |
+
"eval_accuracy": 0.5700934579439252,
|
| 350 |
+
"eval_loss": 0.6981963515281677,
|
| 351 |
+
"eval_runtime": 1.8699,
|
| 352 |
+
"eval_samples_per_second": 57.221,
|
| 353 |
+
"eval_steps_per_second": 3.743,
|
| 354 |
+
"step": 200
|
| 355 |
},
|
| 356 |
{
|
| 357 |
+
"epoch": 26.0,
|
| 358 |
+
"eval_accuracy": 0.5700934579439252,
|
| 359 |
+
"eval_loss": 0.687846839427948,
|
| 360 |
+
"eval_runtime": 1.861,
|
| 361 |
+
"eval_samples_per_second": 57.497,
|
| 362 |
+
"eval_steps_per_second": 3.762,
|
| 363 |
+
"step": 208
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 26.25,
|
| 367 |
"learning_rate": 5.729166666666666e-05,
|
| 368 |
+
"loss": 0.6724,
|
| 369 |
+
"step": 210
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 27.0,
|
| 373 |
+
"eval_accuracy": 0.5887850467289719,
|
| 374 |
+
"eval_loss": 0.678459107875824,
|
| 375 |
+
"eval_runtime": 2.0455,
|
| 376 |
+
"eval_samples_per_second": 52.31,
|
| 377 |
+
"eval_steps_per_second": 3.422,
|
| 378 |
+
"step": 216
|
| 379 |
},
|
| 380 |
{
|
| 381 |
+
"epoch": 27.5,
|
| 382 |
"learning_rate": 5.208333333333333e-05,
|
| 383 |
+
"loss": 0.6613,
|
| 384 |
+
"step": 220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 28.0,
|
| 388 |
+
"eval_accuracy": 0.5887850467289719,
|
| 389 |
+
"eval_loss": 0.6843389272689819,
|
| 390 |
+
"eval_runtime": 1.9034,
|
| 391 |
+
"eval_samples_per_second": 56.214,
|
| 392 |
+
"eval_steps_per_second": 3.678,
|
| 393 |
+
"step": 224
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 28.75,
|
| 397 |
"learning_rate": 4.6874999999999994e-05,
|
| 398 |
+
"loss": 0.6501,
|
| 399 |
+
"step": 230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 29.0,
|
| 403 |
+
"eval_accuracy": 0.5887850467289719,
|
| 404 |
+
"eval_loss": 0.7126495242118835,
|
| 405 |
+
"eval_runtime": 1.8679,
|
| 406 |
+
"eval_samples_per_second": 57.283,
|
| 407 |
+
"eval_steps_per_second": 3.747,
|
| 408 |
+
"step": 232
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 30.0,
|
| 412 |
"learning_rate": 4.1666666666666665e-05,
|
| 413 |
+
"loss": 0.6566,
|
| 414 |
+
"step": 240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 415 |
},
|
| 416 |
{
|
| 417 |
+
"epoch": 30.0,
|
| 418 |
+
"eval_accuracy": 0.5700934579439252,
|
| 419 |
+
"eval_loss": 0.6917204260826111,
|
| 420 |
+
"eval_runtime": 1.9,
|
| 421 |
+
"eval_samples_per_second": 56.317,
|
| 422 |
+
"eval_steps_per_second": 3.684,
|
| 423 |
+
"step": 240
|
| 424 |
},
|
| 425 |
{
|
| 426 |
+
"epoch": 31.0,
|
| 427 |
+
"eval_accuracy": 0.5607476635514018,
|
| 428 |
+
"eval_loss": 0.7020335793495178,
|
| 429 |
+
"eval_runtime": 1.9735,
|
| 430 |
+
"eval_samples_per_second": 54.219,
|
| 431 |
+
"eval_steps_per_second": 3.547,
|
| 432 |
+
"step": 248
|
| 433 |
},
|
| 434 |
{
|
| 435 |
+
"epoch": 31.25,
|
| 436 |
"learning_rate": 3.645833333333333e-05,
|
| 437 |
+
"loss": 0.6583,
|
| 438 |
+
"step": 250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 32.0,
|
| 442 |
+
"eval_accuracy": 0.5887850467289719,
|
| 443 |
+
"eval_loss": 0.6781743764877319,
|
| 444 |
+
"eval_runtime": 1.9435,
|
| 445 |
+
"eval_samples_per_second": 55.056,
|
| 446 |
+
"eval_steps_per_second": 3.602,
|
| 447 |
+
"step": 256
|
| 448 |
},
|
| 449 |
{
|
| 450 |
+
"epoch": 32.5,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 451 |
"learning_rate": 3.125e-05,
|
| 452 |
+
"loss": 0.6501,
|
| 453 |
+
"step": 260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 33.0,
|
| 457 |
+
"eval_accuracy": 0.5887850467289719,
|
| 458 |
+
"eval_loss": 0.664716362953186,
|
| 459 |
+
"eval_runtime": 1.995,
|
| 460 |
+
"eval_samples_per_second": 53.635,
|
| 461 |
+
"eval_steps_per_second": 3.509,
|
| 462 |
+
"step": 264
|
| 463 |
},
|
| 464 |
{
|
| 465 |
+
"epoch": 33.75,
|
| 466 |
"learning_rate": 2.6041666666666665e-05,
|
| 467 |
+
"loss": 0.654,
|
| 468 |
+
"step": 270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 469 |
},
|
| 470 |
{
|
| 471 |
+
"epoch": 34.0,
|
| 472 |
+
"eval_accuracy": 0.5981308411214953,
|
| 473 |
+
"eval_loss": 0.6602646112442017,
|
| 474 |
+
"eval_runtime": 1.9045,
|
| 475 |
+
"eval_samples_per_second": 56.184,
|
| 476 |
+
"eval_steps_per_second": 3.676,
|
| 477 |
+
"step": 272
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 35.0,
|
| 481 |
"learning_rate": 2.0833333333333333e-05,
|
| 482 |
+
"loss": 0.6604,
|
| 483 |
+
"step": 280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 35.0,
|
| 487 |
+
"eval_accuracy": 0.5794392523364486,
|
| 488 |
+
"eval_loss": 0.6873165965080261,
|
| 489 |
+
"eval_runtime": 2.238,
|
| 490 |
+
"eval_samples_per_second": 47.81,
|
| 491 |
+
"eval_steps_per_second": 3.128,
|
| 492 |
+
"step": 280
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 36.0,
|
| 496 |
+
"eval_accuracy": 0.5794392523364486,
|
| 497 |
+
"eval_loss": 0.6591372489929199,
|
| 498 |
+
"eval_runtime": 1.8624,
|
| 499 |
+
"eval_samples_per_second": 57.451,
|
| 500 |
+
"eval_steps_per_second": 3.758,
|
| 501 |
+
"step": 288
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"epoch": 36.25,
|
| 505 |
"learning_rate": 1.5625e-05,
|
| 506 |
+
"loss": 0.6456,
|
| 507 |
+
"step": 290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 508 |
},
|
| 509 |
{
|
| 510 |
+
"epoch": 37.0,
|
| 511 |
+
"eval_accuracy": 0.616822429906542,
|
| 512 |
+
"eval_loss": 0.6579955816268921,
|
| 513 |
+
"eval_runtime": 1.9735,
|
| 514 |
+
"eval_samples_per_second": 54.218,
|
| 515 |
+
"eval_steps_per_second": 3.547,
|
| 516 |
+
"step": 296
|
| 517 |
},
|
| 518 |
{
|
| 519 |
+
"epoch": 37.5,
|
| 520 |
"learning_rate": 1.0416666666666666e-05,
|
| 521 |
+
"loss": 0.6483,
|
| 522 |
+
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 523 |
},
|
| 524 |
{
|
| 525 |
+
"epoch": 38.0,
|
| 526 |
+
"eval_accuracy": 0.5981308411214953,
|
| 527 |
+
"eval_loss": 0.6702041029930115,
|
| 528 |
+
"eval_runtime": 1.9475,
|
| 529 |
+
"eval_samples_per_second": 54.943,
|
| 530 |
+
"eval_steps_per_second": 3.594,
|
| 531 |
+
"step": 304
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 38.75,
|
| 535 |
"learning_rate": 5.208333333333333e-06,
|
| 536 |
+
"loss": 0.6151,
|
| 537 |
+
"step": 310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"epoch": 39.0,
|
| 541 |
+
"eval_accuracy": 0.5981308411214953,
|
| 542 |
+
"eval_loss": 0.6784998774528503,
|
| 543 |
+
"eval_runtime": 2.054,
|
| 544 |
+
"eval_samples_per_second": 52.094,
|
| 545 |
+
"eval_steps_per_second": 3.408,
|
| 546 |
+
"step": 312
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 40.0,
|
| 550 |
+
"learning_rate": 0.0,
|
| 551 |
+
"loss": 0.6291,
|
| 552 |
+
"step": 320
|
| 553 |
},
|
| 554 |
{
|
| 555 |
+
"epoch": 40.0,
|
| 556 |
+
"eval_accuracy": 0.5981308411214953,
|
| 557 |
+
"eval_loss": 0.6806396245956421,
|
| 558 |
+
"eval_runtime": 1.92,
|
| 559 |
+
"eval_samples_per_second": 55.73,
|
| 560 |
+
"eval_steps_per_second": 3.646,
|
| 561 |
+
"step": 320
|
| 562 |
},
|
| 563 |
{
|
| 564 |
+
"epoch": 40.0,
|
| 565 |
+
"step": 320,
|
| 566 |
+
"total_flos": 6.480838238876467e+17,
|
| 567 |
+
"train_loss": 0.9269241958856582,
|
| 568 |
+
"train_runtime": 591.2866,
|
| 569 |
+
"train_samples_per_second": 33.689,
|
| 570 |
+
"train_steps_per_second": 0.541
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 571 |
}
|
| 572 |
],
|
| 573 |
"logging_steps": 10,
|
| 574 |
+
"max_steps": 320,
|
| 575 |
"num_input_tokens_seen": 0,
|
| 576 |
"num_train_epochs": 40,
|
| 577 |
"save_steps": 500,
|
| 578 |
+
"total_flos": 6.480838238876467e+17,
|
| 579 |
"train_batch_size": 16,
|
| 580 |
"trial_name": null,
|
| 581 |
"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 4792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:286446616bdd5be4f0ebdfa59bcd1e531fbeabf7ae4299f8fc32c01515d20841
|
| 3 |
size 4792
|