End of training
Browse files- README.md +2 -2
- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +309 -71
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1451
|
| 22 |
+
- Accuracy: 0.9247
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy":
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.51219512195122,
|
| 3 |
+
"eval_accuracy": 0.9246575342465754,
|
| 4 |
+
"eval_loss": 0.14509864151477814,
|
| 5 |
+
"eval_runtime": 1.219,
|
| 6 |
+
"eval_samples_per_second": 119.771,
|
| 7 |
+
"eval_steps_per_second": 4.102,
|
| 8 |
+
"total_flos": 6.330428470091981e+17,
|
| 9 |
+
"train_loss": 0.25806016743183136,
|
| 10 |
+
"train_runtime": 356.8843,
|
| 11 |
+
"train_samples_per_second": 73.133,
|
| 12 |
+
"train_steps_per_second": 0.56
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy":
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.51219512195122,
|
| 3 |
+
"eval_accuracy": 0.9246575342465754,
|
| 4 |
+
"eval_loss": 0.14509864151477814,
|
| 5 |
+
"eval_runtime": 1.219,
|
| 6 |
+
"eval_samples_per_second": 119.771,
|
| 7 |
+
"eval_steps_per_second": 4.102
|
| 8 |
}
|
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":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 19.51219512195122,
|
| 3 |
+
"total_flos": 6.330428470091981e+17,
|
| 4 |
+
"train_loss": 0.25806016743183136,
|
| 5 |
+
"train_runtime": 356.8843,
|
| 6 |
+
"train_samples_per_second": 73.133,
|
| 7 |
+
"train_steps_per_second": 0.56
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,107 +1,345 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "/kaggle/working/swin-brain-modality-classification/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 |
-
"eval_steps_per_second": 3.75,
|
| 18 |
-
"step": 7
|
| 19 |
},
|
| 20 |
{
|
| 21 |
-
"epoch":
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
|
|
|
|
|
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
-
"epoch":
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"eval_steps_per_second": 4.258,
|
| 34 |
-
"step": 15
|
| 35 |
},
|
| 36 |
{
|
| 37 |
-
"epoch":
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"
|
|
|
|
|
|
|
| 41 |
"step": 20
|
| 42 |
},
|
| 43 |
{
|
| 44 |
-
"epoch": 2.
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"eval_steps_per_second": 4.285,
|
| 50 |
-
"step": 22
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
|
|
|
|
|
|
| 57 |
"step": 30
|
| 58 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
{
|
| 60 |
"epoch": 4.0,
|
| 61 |
-
"eval_accuracy": 0.
|
| 62 |
-
"eval_loss": 0.
|
| 63 |
-
"eval_runtime":
|
| 64 |
-
"eval_samples_per_second":
|
| 65 |
-
"eval_steps_per_second": 4.
|
| 66 |
-
"step":
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch": 4.
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"eval_steps_per_second": 4.019,
|
| 75 |
-
"step": 37
|
| 76 |
},
|
| 77 |
{
|
| 78 |
-
"epoch":
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
},
|
| 84 |
{
|
| 85 |
-
"epoch":
|
| 86 |
-
"eval_accuracy":
|
| 87 |
-
"eval_loss": 0.
|
| 88 |
-
"eval_runtime": 1.
|
| 89 |
-
"eval_samples_per_second":
|
| 90 |
-
"eval_steps_per_second":
|
| 91 |
-
"step":
|
| 92 |
},
|
| 93 |
{
|
| 94 |
-
"epoch":
|
| 95 |
-
"step":
|
| 96 |
-
"total_flos":
|
| 97 |
-
"train_loss": 0.
|
| 98 |
-
"train_runtime":
|
| 99 |
-
"train_samples_per_second":
|
| 100 |
-
"train_steps_per_second":
|
| 101 |
}
|
| 102 |
],
|
| 103 |
"logging_steps": 10,
|
| 104 |
-
"max_steps":
|
| 105 |
"num_input_tokens_seen": 0,
|
| 106 |
"num_train_epochs": 20,
|
| 107 |
"save_steps": 500,
|
|
@@ -126,7 +364,7 @@
|
|
| 126 |
"attributes": {}
|
| 127 |
}
|
| 128 |
},
|
| 129 |
-
"total_flos":
|
| 130 |
"train_batch_size": 32,
|
| 131 |
"trial_name": null,
|
| 132 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9246575342465754,
|
| 3 |
+
"best_model_checkpoint": "/kaggle/working/swin-brain-modality-classification/checkpoint-82",
|
| 4 |
+
"epoch": 19.51219512195122,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.975609756097561,
|
| 13 |
+
"grad_norm": 8.406940460205078,
|
| 14 |
+
"learning_rate": 2.5e-05,
|
| 15 |
+
"loss": 1.2625,
|
| 16 |
+
"step": 10
|
|
|
|
|
|
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.975609756097561,
|
| 20 |
+
"eval_accuracy": 0.589041095890411,
|
| 21 |
+
"eval_loss": 1.0232338905334473,
|
| 22 |
+
"eval_runtime": 1.1501,
|
| 23 |
+
"eval_samples_per_second": 126.951,
|
| 24 |
+
"eval_steps_per_second": 4.348,
|
| 25 |
"step": 10
|
| 26 |
},
|
| 27 |
{
|
| 28 |
+
"epoch": 1.951219512195122,
|
| 29 |
+
"grad_norm": 4.960095405578613,
|
| 30 |
+
"learning_rate": 5e-05,
|
| 31 |
+
"loss": 0.8162,
|
| 32 |
+
"step": 20
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 1.951219512195122,
|
| 36 |
+
"eval_accuracy": 0.8561643835616438,
|
| 37 |
+
"eval_loss": 0.5372681021690369,
|
| 38 |
+
"eval_runtime": 1.124,
|
| 39 |
+
"eval_samples_per_second": 129.89,
|
| 40 |
+
"eval_steps_per_second": 4.448,
|
| 41 |
"step": 20
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 2.926829268292683,
|
| 45 |
+
"grad_norm": 5.591886043548584,
|
| 46 |
+
"learning_rate": 4.722222222222222e-05,
|
| 47 |
+
"loss": 0.3924,
|
| 48 |
+
"step": 30
|
|
|
|
|
|
|
| 49 |
},
|
| 50 |
{
|
| 51 |
+
"epoch": 2.926829268292683,
|
| 52 |
+
"eval_accuracy": 0.8904109589041096,
|
| 53 |
+
"eval_loss": 0.24904736876487732,
|
| 54 |
+
"eval_runtime": 1.1996,
|
| 55 |
+
"eval_samples_per_second": 121.707,
|
| 56 |
+
"eval_steps_per_second": 4.168,
|
| 57 |
"step": 30
|
| 58 |
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.902439024390244,
|
| 61 |
+
"grad_norm": 8.885392189025879,
|
| 62 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 63 |
+
"loss": 0.2528,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
{
|
| 67 |
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.8767123287671232,
|
| 69 |
+
"eval_loss": 0.27159520983695984,
|
| 70 |
+
"eval_runtime": 1.1285,
|
| 71 |
+
"eval_samples_per_second": 129.37,
|
| 72 |
+
"eval_steps_per_second": 4.43,
|
| 73 |
+
"step": 41
|
| 74 |
},
|
| 75 |
{
|
| 76 |
+
"epoch": 4.878048780487805,
|
| 77 |
+
"grad_norm": 5.296258449554443,
|
| 78 |
+
"learning_rate": 4.166666666666667e-05,
|
| 79 |
+
"loss": 0.2311,
|
| 80 |
+
"step": 50
|
|
|
|
|
|
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 4.975609756097561,
|
| 84 |
+
"eval_accuracy": 0.8904109589041096,
|
| 85 |
+
"eval_loss": 0.2249891459941864,
|
| 86 |
+
"eval_runtime": 1.1296,
|
| 87 |
+
"eval_samples_per_second": 129.247,
|
| 88 |
+
"eval_steps_per_second": 4.426,
|
| 89 |
+
"step": 51
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.853658536585366,
|
| 93 |
+
"grad_norm": 4.622660160064697,
|
| 94 |
+
"learning_rate": 3.888888888888889e-05,
|
| 95 |
+
"loss": 0.2013,
|
| 96 |
+
"step": 60
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.951219512195122,
|
| 100 |
+
"eval_accuracy": 0.910958904109589,
|
| 101 |
+
"eval_loss": 0.21542568504810333,
|
| 102 |
+
"eval_runtime": 1.1318,
|
| 103 |
+
"eval_samples_per_second": 128.996,
|
| 104 |
+
"eval_steps_per_second": 4.418,
|
| 105 |
+
"step": 61
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.829268292682927,
|
| 109 |
+
"grad_norm": 1.8751587867736816,
|
| 110 |
+
"learning_rate": 3.611111111111111e-05,
|
| 111 |
+
"loss": 0.1955,
|
| 112 |
+
"step": 70
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.926829268292683,
|
| 116 |
+
"eval_accuracy": 0.9178082191780822,
|
| 117 |
+
"eval_loss": 0.17689338326454163,
|
| 118 |
+
"eval_runtime": 1.1592,
|
| 119 |
+
"eval_samples_per_second": 125.952,
|
| 120 |
+
"eval_steps_per_second": 4.313,
|
| 121 |
+
"step": 71
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 7.804878048780488,
|
| 125 |
+
"grad_norm": 2.4484364986419678,
|
| 126 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 127 |
+
"loss": 0.1743,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_accuracy": 0.9246575342465754,
|
| 133 |
+
"eval_loss": 0.14509864151477814,
|
| 134 |
+
"eval_runtime": 1.129,
|
| 135 |
+
"eval_samples_per_second": 129.323,
|
| 136 |
+
"eval_steps_per_second": 4.429,
|
| 137 |
+
"step": 82
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 8.78048780487805,
|
| 141 |
+
"grad_norm": 4.154516220092773,
|
| 142 |
+
"learning_rate": 3.055555555555556e-05,
|
| 143 |
+
"loss": 0.1664,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.975609756097562,
|
| 148 |
+
"eval_accuracy": 0.9178082191780822,
|
| 149 |
+
"eval_loss": 0.1488887518644333,
|
| 150 |
+
"eval_runtime": 1.1207,
|
| 151 |
+
"eval_samples_per_second": 130.276,
|
| 152 |
+
"eval_steps_per_second": 4.462,
|
| 153 |
+
"step": 92
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 9.75609756097561,
|
| 157 |
+
"grad_norm": 2.7535204887390137,
|
| 158 |
+
"learning_rate": 2.777777777777778e-05,
|
| 159 |
+
"loss": 0.1503,
|
| 160 |
+
"step": 100
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 9.951219512195122,
|
| 164 |
+
"eval_accuracy": 0.8972602739726028,
|
| 165 |
+
"eval_loss": 0.1964411437511444,
|
| 166 |
+
"eval_runtime": 1.1259,
|
| 167 |
+
"eval_samples_per_second": 129.67,
|
| 168 |
+
"eval_steps_per_second": 4.441,
|
| 169 |
+
"step": 102
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 10.731707317073171,
|
| 173 |
+
"grad_norm": 3.03983473777771,
|
| 174 |
+
"learning_rate": 2.5e-05,
|
| 175 |
+
"loss": 0.1518,
|
| 176 |
+
"step": 110
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.926829268292684,
|
| 180 |
+
"eval_accuracy": 0.910958904109589,
|
| 181 |
+
"eval_loss": 0.17079411447048187,
|
| 182 |
+
"eval_runtime": 1.1948,
|
| 183 |
+
"eval_samples_per_second": 122.195,
|
| 184 |
+
"eval_steps_per_second": 4.185,
|
| 185 |
+
"step": 112
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 11.707317073170731,
|
| 189 |
+
"grad_norm": 2.2469286918640137,
|
| 190 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 191 |
+
"loss": 0.1456,
|
| 192 |
+
"step": 120
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_accuracy": 0.9041095890410958,
|
| 197 |
+
"eval_loss": 0.1498766541481018,
|
| 198 |
+
"eval_runtime": 1.1695,
|
| 199 |
+
"eval_samples_per_second": 124.845,
|
| 200 |
+
"eval_steps_per_second": 4.275,
|
| 201 |
+
"step": 123
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.682926829268293,
|
| 205 |
+
"grad_norm": 7.290715217590332,
|
| 206 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 207 |
+
"loss": 0.1307,
|
| 208 |
+
"step": 130
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 12.975609756097562,
|
| 212 |
+
"eval_accuracy": 0.9041095890410958,
|
| 213 |
+
"eval_loss": 0.15838505327701569,
|
| 214 |
+
"eval_runtime": 1.122,
|
| 215 |
+
"eval_samples_per_second": 130.13,
|
| 216 |
+
"eval_steps_per_second": 4.457,
|
| 217 |
+
"step": 133
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 13.658536585365853,
|
| 221 |
+
"grad_norm": 4.910462379455566,
|
| 222 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 223 |
+
"loss": 0.1546,
|
| 224 |
+
"step": 140
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.951219512195122,
|
| 228 |
+
"eval_accuracy": 0.910958904109589,
|
| 229 |
+
"eval_loss": 0.16728605329990387,
|
| 230 |
+
"eval_runtime": 1.1455,
|
| 231 |
+
"eval_samples_per_second": 127.459,
|
| 232 |
+
"eval_steps_per_second": 4.365,
|
| 233 |
+
"step": 143
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 14.634146341463415,
|
| 237 |
+
"grad_norm": 3.007720947265625,
|
| 238 |
+
"learning_rate": 1.388888888888889e-05,
|
| 239 |
+
"loss": 0.1282,
|
| 240 |
+
"step": 150
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 14.926829268292684,
|
| 244 |
+
"eval_accuracy": 0.9041095890410958,
|
| 245 |
+
"eval_loss": 0.15455295145511627,
|
| 246 |
+
"eval_runtime": 1.1933,
|
| 247 |
+
"eval_samples_per_second": 122.354,
|
| 248 |
+
"eval_steps_per_second": 4.19,
|
| 249 |
+
"step": 153
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 15.609756097560975,
|
| 253 |
+
"grad_norm": 3.2155206203460693,
|
| 254 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 255 |
+
"loss": 0.121,
|
| 256 |
+
"step": 160
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_accuracy": 0.9041095890410958,
|
| 261 |
+
"eval_loss": 0.163113534450531,
|
| 262 |
+
"eval_runtime": 1.1449,
|
| 263 |
+
"eval_samples_per_second": 127.52,
|
| 264 |
+
"eval_steps_per_second": 4.367,
|
| 265 |
+
"step": 164
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 16.585365853658537,
|
| 269 |
+
"grad_norm": 2.8936450481414795,
|
| 270 |
+
"learning_rate": 8.333333333333334e-06,
|
| 271 |
+
"loss": 0.1311,
|
| 272 |
+
"step": 170
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 16.975609756097562,
|
| 276 |
+
"eval_accuracy": 0.9041095890410958,
|
| 277 |
+
"eval_loss": 0.148574560880661,
|
| 278 |
+
"eval_runtime": 1.1408,
|
| 279 |
+
"eval_samples_per_second": 127.98,
|
| 280 |
+
"eval_steps_per_second": 4.383,
|
| 281 |
+
"step": 174
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 17.5609756097561,
|
| 285 |
+
"grad_norm": 3.644867420196533,
|
| 286 |
+
"learning_rate": 5.555555555555556e-06,
|
| 287 |
+
"loss": 0.1259,
|
| 288 |
+
"step": 180
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 17.951219512195124,
|
| 292 |
+
"eval_accuracy": 0.9178082191780822,
|
| 293 |
+
"eval_loss": 0.1642705798149109,
|
| 294 |
+
"eval_runtime": 1.1481,
|
| 295 |
+
"eval_samples_per_second": 127.169,
|
| 296 |
+
"eval_steps_per_second": 4.355,
|
| 297 |
+
"step": 184
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 18.536585365853657,
|
| 301 |
+
"grad_norm": 3.4987175464630127,
|
| 302 |
+
"learning_rate": 2.777777777777778e-06,
|
| 303 |
+
"loss": 0.1254,
|
| 304 |
+
"step": 190
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 18.926829268292682,
|
| 308 |
+
"eval_accuracy": 0.910958904109589,
|
| 309 |
+
"eval_loss": 0.15694867074489594,
|
| 310 |
+
"eval_runtime": 1.1825,
|
| 311 |
+
"eval_samples_per_second": 123.462,
|
| 312 |
+
"eval_steps_per_second": 4.228,
|
| 313 |
+
"step": 194
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 19.51219512195122,
|
| 317 |
+
"grad_norm": 3.0996928215026855,
|
| 318 |
+
"learning_rate": 0.0,
|
| 319 |
+
"loss": 0.1039,
|
| 320 |
+
"step": 200
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 19.51219512195122,
|
| 324 |
+
"eval_accuracy": 0.910958904109589,
|
| 325 |
+
"eval_loss": 0.1550000011920929,
|
| 326 |
+
"eval_runtime": 1.2474,
|
| 327 |
+
"eval_samples_per_second": 117.047,
|
| 328 |
+
"eval_steps_per_second": 4.008,
|
| 329 |
+
"step": 200
|
| 330 |
},
|
| 331 |
{
|
| 332 |
+
"epoch": 19.51219512195122,
|
| 333 |
+
"step": 200,
|
| 334 |
+
"total_flos": 6.330428470091981e+17,
|
| 335 |
+
"train_loss": 0.25806016743183136,
|
| 336 |
+
"train_runtime": 356.8843,
|
| 337 |
+
"train_samples_per_second": 73.133,
|
| 338 |
+
"train_steps_per_second": 0.56
|
| 339 |
}
|
| 340 |
],
|
| 341 |
"logging_steps": 10,
|
| 342 |
+
"max_steps": 200,
|
| 343 |
"num_input_tokens_seen": 0,
|
| 344 |
"num_train_epochs": 20,
|
| 345 |
"save_steps": 500,
|
|
|
|
| 364 |
"attributes": {}
|
| 365 |
}
|
| 366 |
},
|
| 367 |
+
"total_flos": 6.330428470091981e+17,
|
| 368 |
"train_batch_size": 32,
|
| 369 |
"trial_name": null,
|
| 370 |
"trial_params": null
|