Model save
Browse files- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Jun13_18-09-04_67b1b50b776b/events.out.tfevents.1686687847.67b1b50b776b.7844.5 +3 -0
- train_results.json +6 -6
- trainer_state.json +398 -41
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second": 6.
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.75,
|
| 3 |
+
"eval_accuracy": 0.8363636363636363,
|
| 4 |
+
"eval_loss": 0.5505930185317993,
|
| 5 |
+
"eval_runtime": 62.7136,
|
| 6 |
+
"eval_samples_per_second": 5.262,
|
| 7 |
+
"eval_steps_per_second": 0.175,
|
| 8 |
+
"total_flos": 5.1138191421254246e+17,
|
| 9 |
+
"train_loss": 0.39375978350639346,
|
| 10 |
+
"train_runtime": 7915.8379,
|
| 11 |
+
"train_samples_per_second": 6.476,
|
| 12 |
+
"train_steps_per_second": 0.051
|
| 13 |
}
|
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": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.75,
|
| 3 |
+
"eval_accuracy": 0.8363636363636363,
|
| 4 |
+
"eval_loss": 0.5505930185317993,
|
| 5 |
+
"eval_runtime": 62.7136,
|
| 6 |
+
"eval_samples_per_second": 5.262,
|
| 7 |
+
"eval_steps_per_second": 0.175
|
| 8 |
}
|
runs/Jun13_18-09-04_67b1b50b776b/events.out.tfevents.1686687847.67b1b50b776b.7844.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c23d9a1fdb8e8ba12481dce404ab91346e624cf5c73d3b5d12eabfe33feecf43
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 6.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.75,
|
| 3 |
+
"total_flos": 5.1138191421254246e+17,
|
| 4 |
+
"train_loss": 0.39375978350639346,
|
| 5 |
+
"train_runtime": 7915.8379,
|
| 6 |
+
"train_samples_per_second": 6.476,
|
| 7 |
+
"train_steps_per_second": 0.051
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,88 +1,445 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/Classification/ViT/models/resnet-18-finetuned-eurosat/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.49,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss":
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.99,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss":
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.99,
|
| 24 |
-
"eval_accuracy": 0.
|
| 25 |
-
"eval_loss": 0.
|
| 26 |
-
"eval_runtime":
|
| 27 |
-
"eval_samples_per_second":
|
| 28 |
-
"eval_steps_per_second": 0.
|
| 29 |
"step": 20
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 1.48,
|
| 33 |
-
"learning_rate":
|
| 34 |
-
"loss": 0.
|
| 35 |
"step": 30
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 1.98,
|
| 39 |
-
"learning_rate":
|
| 40 |
-
"loss": 0.
|
| 41 |
"step": 40
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 1.98,
|
| 45 |
-
"eval_accuracy": 0.
|
| 46 |
-
"eval_loss": 0.
|
| 47 |
-
"eval_runtime":
|
| 48 |
-
"eval_samples_per_second":
|
| 49 |
-
"eval_steps_per_second": 0.
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 2.47,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 50
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 2.96,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 60
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 2.96,
|
| 66 |
-
"eval_accuracy": 0.
|
| 67 |
-
"eval_loss": 0.
|
| 68 |
-
"eval_runtime":
|
| 69 |
-
"eval_samples_per_second": 7.
|
| 70 |
-
"eval_steps_per_second": 0.
|
| 71 |
"step": 60
|
| 72 |
},
|
| 73 |
{
|
| 74 |
-
"epoch":
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
}
|
| 82 |
],
|
| 83 |
-
"max_steps":
|
| 84 |
-
"num_train_epochs":
|
| 85 |
-
"total_flos":
|
| 86 |
"trial_name": null,
|
| 87 |
"trial_params": null
|
| 88 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8363636363636363,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Colab Notebooks/Classification/ViT/models/resnet-18-finetuned-eurosat/checkpoint-303",
|
| 4 |
+
"epoch": 19.753086419753085,
|
| 5 |
+
"global_step": 400,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.49,
|
| 12 |
+
"learning_rate": 1.25e-05,
|
| 13 |
+
"loss": 0.3227,
|
| 14 |
"step": 10
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.99,
|
| 18 |
+
"learning_rate": 2.5e-05,
|
| 19 |
+
"loss": 0.3846,
|
| 20 |
"step": 20
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.99,
|
| 24 |
+
"eval_accuracy": 0.7575757575757576,
|
| 25 |
+
"eval_loss": 0.6352207660675049,
|
| 26 |
+
"eval_runtime": 46.0823,
|
| 27 |
+
"eval_samples_per_second": 7.161,
|
| 28 |
+
"eval_steps_per_second": 0.239,
|
| 29 |
"step": 20
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 1.48,
|
| 33 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 34 |
+
"loss": 0.3732,
|
| 35 |
"step": 30
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 1.98,
|
| 39 |
+
"learning_rate": 5e-05,
|
| 40 |
+
"loss": 0.5009,
|
| 41 |
"step": 40
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 1.98,
|
| 45 |
+
"eval_accuracy": 0.7484848484848485,
|
| 46 |
+
"eval_loss": 0.6438900828361511,
|
| 47 |
+
"eval_runtime": 49.1686,
|
| 48 |
+
"eval_samples_per_second": 6.712,
|
| 49 |
+
"eval_steps_per_second": 0.224,
|
| 50 |
"step": 40
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 2.47,
|
| 54 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 55 |
+
"loss": 0.4765,
|
| 56 |
"step": 50
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 2.96,
|
| 60 |
+
"learning_rate": 4.722222222222222e-05,
|
| 61 |
+
"loss": 0.5625,
|
| 62 |
"step": 60
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 2.96,
|
| 66 |
+
"eval_accuracy": 0.7909090909090909,
|
| 67 |
+
"eval_loss": 0.5722424387931824,
|
| 68 |
+
"eval_runtime": 46.1274,
|
| 69 |
+
"eval_samples_per_second": 7.154,
|
| 70 |
+
"eval_steps_per_second": 0.238,
|
| 71 |
"step": 60
|
| 72 |
},
|
| 73 |
{
|
| 74 |
+
"epoch": 3.46,
|
| 75 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 76 |
+
"loss": 0.5104,
|
| 77 |
+
"step": 70
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.95,
|
| 81 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 82 |
+
"loss": 0.4928,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.0,
|
| 87 |
+
"eval_accuracy": 0.796969696969697,
|
| 88 |
+
"eval_loss": 0.5514332056045532,
|
| 89 |
+
"eval_runtime": 45.9331,
|
| 90 |
+
"eval_samples_per_second": 7.184,
|
| 91 |
+
"eval_steps_per_second": 0.239,
|
| 92 |
+
"step": 81
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.44,
|
| 96 |
+
"learning_rate": 4.305555555555556e-05,
|
| 97 |
+
"loss": 0.5148,
|
| 98 |
+
"step": 90
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.94,
|
| 102 |
+
"learning_rate": 4.166666666666667e-05,
|
| 103 |
+
"loss": 0.4621,
|
| 104 |
+
"step": 100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.99,
|
| 108 |
+
"eval_accuracy": 0.7696969696969697,
|
| 109 |
+
"eval_loss": 0.6103599071502686,
|
| 110 |
+
"eval_runtime": 47.2344,
|
| 111 |
+
"eval_samples_per_second": 6.986,
|
| 112 |
+
"eval_steps_per_second": 0.233,
|
| 113 |
+
"step": 101
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 5.43,
|
| 117 |
+
"learning_rate": 4.027777777777778e-05,
|
| 118 |
+
"loss": 0.4939,
|
| 119 |
+
"step": 110
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 5.93,
|
| 123 |
+
"learning_rate": 3.888888888888889e-05,
|
| 124 |
+
"loss": 0.4367,
|
| 125 |
+
"step": 120
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 5.98,
|
| 129 |
+
"eval_accuracy": 0.793939393939394,
|
| 130 |
+
"eval_loss": 0.573406994342804,
|
| 131 |
+
"eval_runtime": 46.1152,
|
| 132 |
+
"eval_samples_per_second": 7.156,
|
| 133 |
+
"eval_steps_per_second": 0.239,
|
| 134 |
+
"step": 121
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.42,
|
| 138 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 139 |
+
"loss": 0.4252,
|
| 140 |
+
"step": 130
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.91,
|
| 144 |
+
"learning_rate": 3.611111111111111e-05,
|
| 145 |
+
"loss": 0.4238,
|
| 146 |
+
"step": 140
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.96,
|
| 150 |
+
"eval_accuracy": 0.8,
|
| 151 |
+
"eval_loss": 0.5557721853256226,
|
| 152 |
+
"eval_runtime": 48.2781,
|
| 153 |
+
"eval_samples_per_second": 6.835,
|
| 154 |
+
"eval_steps_per_second": 0.228,
|
| 155 |
+
"step": 141
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 7.41,
|
| 159 |
+
"learning_rate": 3.472222222222222e-05,
|
| 160 |
+
"loss": 0.4367,
|
| 161 |
+
"step": 150
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 7.9,
|
| 165 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 166 |
+
"loss": 0.4011,
|
| 167 |
+
"step": 160
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 8.0,
|
| 171 |
+
"eval_accuracy": 0.803030303030303,
|
| 172 |
+
"eval_loss": 0.554872989654541,
|
| 173 |
+
"eval_runtime": 46.9595,
|
| 174 |
+
"eval_samples_per_second": 7.027,
|
| 175 |
+
"eval_steps_per_second": 0.234,
|
| 176 |
+
"step": 162
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 8.4,
|
| 180 |
+
"learning_rate": 3.194444444444444e-05,
|
| 181 |
+
"loss": 0.4059,
|
| 182 |
+
"step": 170
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 8.89,
|
| 186 |
+
"learning_rate": 3.055555555555556e-05,
|
| 187 |
+
"loss": 0.4129,
|
| 188 |
+
"step": 180
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 8.99,
|
| 192 |
+
"eval_accuracy": 0.806060606060606,
|
| 193 |
+
"eval_loss": 0.5553537607192993,
|
| 194 |
+
"eval_runtime": 46.217,
|
| 195 |
+
"eval_samples_per_second": 7.14,
|
| 196 |
+
"eval_steps_per_second": 0.238,
|
| 197 |
+
"step": 182
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 9.38,
|
| 201 |
+
"learning_rate": 2.916666666666667e-05,
|
| 202 |
+
"loss": 0.4125,
|
| 203 |
+
"step": 190
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 9.88,
|
| 207 |
+
"learning_rate": 2.777777777777778e-05,
|
| 208 |
+
"loss": 0.384,
|
| 209 |
+
"step": 200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.98,
|
| 213 |
+
"eval_accuracy": 0.8151515151515152,
|
| 214 |
+
"eval_loss": 0.5550632476806641,
|
| 215 |
+
"eval_runtime": 47.8897,
|
| 216 |
+
"eval_samples_per_second": 6.891,
|
| 217 |
+
"eval_steps_per_second": 0.23,
|
| 218 |
+
"step": 202
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 10.37,
|
| 222 |
+
"learning_rate": 2.6388888888888892e-05,
|
| 223 |
+
"loss": 0.3823,
|
| 224 |
+
"step": 210
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 10.86,
|
| 228 |
+
"learning_rate": 2.5e-05,
|
| 229 |
+
"loss": 0.3839,
|
| 230 |
+
"step": 220
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 10.96,
|
| 234 |
+
"eval_accuracy": 0.8090909090909091,
|
| 235 |
+
"eval_loss": 0.5741792917251587,
|
| 236 |
+
"eval_runtime": 46.8547,
|
| 237 |
+
"eval_samples_per_second": 7.043,
|
| 238 |
+
"eval_steps_per_second": 0.235,
|
| 239 |
+
"step": 222
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 11.36,
|
| 243 |
+
"learning_rate": 2.361111111111111e-05,
|
| 244 |
+
"loss": 0.4025,
|
| 245 |
+
"step": 230
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 11.85,
|
| 249 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 250 |
+
"loss": 0.3496,
|
| 251 |
+
"step": 240
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 12.0,
|
| 255 |
+
"eval_accuracy": 0.8303030303030303,
|
| 256 |
+
"eval_loss": 0.5517680048942566,
|
| 257 |
+
"eval_runtime": 45.796,
|
| 258 |
+
"eval_samples_per_second": 7.206,
|
| 259 |
+
"eval_steps_per_second": 0.24,
|
| 260 |
+
"step": 243
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 12.35,
|
| 264 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 265 |
+
"loss": 0.3389,
|
| 266 |
+
"step": 250
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 12.84,
|
| 270 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 271 |
+
"loss": 0.3482,
|
| 272 |
+
"step": 260
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 12.99,
|
| 276 |
+
"eval_accuracy": 0.8303030303030303,
|
| 277 |
+
"eval_loss": 0.5389552116394043,
|
| 278 |
+
"eval_runtime": 45.5677,
|
| 279 |
+
"eval_samples_per_second": 7.242,
|
| 280 |
+
"eval_steps_per_second": 0.241,
|
| 281 |
+
"step": 263
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 13.33,
|
| 285 |
+
"learning_rate": 1.8055555555555555e-05,
|
| 286 |
+
"loss": 0.3486,
|
| 287 |
+
"step": 270
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 13.83,
|
| 291 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 292 |
+
"loss": 0.357,
|
| 293 |
+
"step": 280
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 13.98,
|
| 297 |
+
"eval_accuracy": 0.8181818181818182,
|
| 298 |
+
"eval_loss": 0.5543653964996338,
|
| 299 |
+
"eval_runtime": 45.3586,
|
| 300 |
+
"eval_samples_per_second": 7.275,
|
| 301 |
+
"eval_steps_per_second": 0.243,
|
| 302 |
+
"step": 283
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 14.32,
|
| 306 |
+
"learning_rate": 1.527777777777778e-05,
|
| 307 |
+
"loss": 0.3397,
|
| 308 |
+
"step": 290
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 14.81,
|
| 312 |
+
"learning_rate": 1.388888888888889e-05,
|
| 313 |
+
"loss": 0.3341,
|
| 314 |
+
"step": 300
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 14.96,
|
| 318 |
+
"eval_accuracy": 0.8363636363636363,
|
| 319 |
+
"eval_loss": 0.5505930185317993,
|
| 320 |
+
"eval_runtime": 45.3368,
|
| 321 |
+
"eval_samples_per_second": 7.279,
|
| 322 |
+
"eval_steps_per_second": 0.243,
|
| 323 |
+
"step": 303
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 15.31,
|
| 327 |
+
"learning_rate": 1.25e-05,
|
| 328 |
+
"loss": 0.3923,
|
| 329 |
+
"step": 310
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 15.8,
|
| 333 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 334 |
+
"loss": 0.3605,
|
| 335 |
+
"step": 320
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 16.0,
|
| 339 |
+
"eval_accuracy": 0.8212121212121212,
|
| 340 |
+
"eval_loss": 0.5546284914016724,
|
| 341 |
+
"eval_runtime": 45.4708,
|
| 342 |
+
"eval_samples_per_second": 7.257,
|
| 343 |
+
"eval_steps_per_second": 0.242,
|
| 344 |
+
"step": 324
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 16.3,
|
| 348 |
+
"learning_rate": 9.722222222222223e-06,
|
| 349 |
+
"loss": 0.3401,
|
| 350 |
+
"step": 330
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 16.79,
|
| 354 |
+
"learning_rate": 8.333333333333334e-06,
|
| 355 |
+
"loss": 0.3041,
|
| 356 |
+
"step": 340
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 16.99,
|
| 360 |
+
"eval_accuracy": 0.8212121212121212,
|
| 361 |
+
"eval_loss": 0.5597090125083923,
|
| 362 |
+
"eval_runtime": 45.2134,
|
| 363 |
+
"eval_samples_per_second": 7.299,
|
| 364 |
+
"eval_steps_per_second": 0.243,
|
| 365 |
+
"step": 344
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 17.28,
|
| 369 |
+
"learning_rate": 6.944444444444445e-06,
|
| 370 |
+
"loss": 0.3422,
|
| 371 |
+
"step": 350
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 17.78,
|
| 375 |
+
"learning_rate": 5.555555555555556e-06,
|
| 376 |
+
"loss": 0.3364,
|
| 377 |
+
"step": 360
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 17.98,
|
| 381 |
+
"eval_accuracy": 0.8090909090909091,
|
| 382 |
+
"eval_loss": 0.5729926228523254,
|
| 383 |
+
"eval_runtime": 45.0505,
|
| 384 |
+
"eval_samples_per_second": 7.325,
|
| 385 |
+
"eval_steps_per_second": 0.244,
|
| 386 |
+
"step": 364
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 18.27,
|
| 390 |
+
"learning_rate": 4.166666666666667e-06,
|
| 391 |
+
"loss": 0.3156,
|
| 392 |
+
"step": 370
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 18.77,
|
| 396 |
+
"learning_rate": 2.777777777777778e-06,
|
| 397 |
+
"loss": 0.2976,
|
| 398 |
+
"step": 380
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 18.96,
|
| 402 |
+
"eval_accuracy": 0.8090909090909091,
|
| 403 |
+
"eval_loss": 0.5741696357727051,
|
| 404 |
+
"eval_runtime": 45.8457,
|
| 405 |
+
"eval_samples_per_second": 7.198,
|
| 406 |
+
"eval_steps_per_second": 0.24,
|
| 407 |
+
"step": 384
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 19.26,
|
| 411 |
+
"learning_rate": 1.388888888888889e-06,
|
| 412 |
+
"loss": 0.3209,
|
| 413 |
+
"step": 390
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 19.75,
|
| 417 |
+
"learning_rate": 0.0,
|
| 418 |
+
"loss": 0.3229,
|
| 419 |
+
"step": 400
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 19.75,
|
| 423 |
+
"eval_accuracy": 0.8121212121212121,
|
| 424 |
+
"eval_loss": 0.5653126835823059,
|
| 425 |
+
"eval_runtime": 41.6194,
|
| 426 |
+
"eval_samples_per_second": 7.929,
|
| 427 |
+
"eval_steps_per_second": 0.264,
|
| 428 |
+
"step": 400
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 19.75,
|
| 432 |
+
"step": 400,
|
| 433 |
+
"total_flos": 5.1138191421254246e+17,
|
| 434 |
+
"train_loss": 0.39375978350639346,
|
| 435 |
+
"train_runtime": 7915.8379,
|
| 436 |
+
"train_samples_per_second": 6.476,
|
| 437 |
+
"train_steps_per_second": 0.051
|
| 438 |
}
|
| 439 |
],
|
| 440 |
+
"max_steps": 400,
|
| 441 |
+
"num_train_epochs": 20,
|
| 442 |
+
"total_flos": 5.1138191421254246e+17,
|
| 443 |
"trial_name": null,
|
| 444 |
"trial_params": null
|
| 445 |
}
|