End of training
Browse files- README.md +2 -0
- all_results.json +12 -0
- eval_results.json +8 -0
- train_results.json +7 -0
- trainer_state.json +631 -0
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: microsoft/swinv2-base-patch4-window12-192-22k
|
| 4 |
tags:
|
|
|
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: microsoft/swinv2-base-patch4-window12-192-22k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.7000208389151856,
|
| 4 |
+
"eval_loss": 2.1793291568756104,
|
| 5 |
+
"eval_runtime": 1712.7606,
|
| 6 |
+
"eval_samples_per_second": 98.061,
|
| 7 |
+
"eval_steps_per_second": 0.384,
|
| 8 |
+
"train_loss": 0.1121770017593626,
|
| 9 |
+
"train_runtime": 63366.2415,
|
| 10 |
+
"train_samples_per_second": 159.032,
|
| 11 |
+
"train_steps_per_second": 0.621
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.7000208389151856,
|
| 4 |
+
"eval_loss": 2.1793291568756104,
|
| 5 |
+
"eval_runtime": 1712.7606,
|
| 6 |
+
"eval_samples_per_second": 98.061,
|
| 7 |
+
"eval_steps_per_second": 0.384
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"train_loss": 0.1121770017593626,
|
| 4 |
+
"train_runtime": 63366.2415,
|
| 5 |
+
"train_samples_per_second": 159.032,
|
| 6 |
+
"train_steps_per_second": 0.621
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,631 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 39375,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.19,
|
| 13 |
+
"learning_rate": 0.0009873015873015875,
|
| 14 |
+
"loss": 0.4962,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.38,
|
| 19 |
+
"learning_rate": 0.0009746031746031746,
|
| 20 |
+
"loss": 0.5629,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.57,
|
| 25 |
+
"learning_rate": 0.0009619047619047619,
|
| 26 |
+
"loss": 0.6018,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.76,
|
| 31 |
+
"learning_rate": 0.0009492063492063491,
|
| 32 |
+
"loss": 0.6211,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.95,
|
| 37 |
+
"learning_rate": 0.0009365079365079366,
|
| 38 |
+
"loss": 0.6306,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0,
|
| 43 |
+
"eval_accuracy": 0.6565389538864577,
|
| 44 |
+
"eval_loss": 1.9168750047683716,
|
| 45 |
+
"eval_runtime": 5346.8612,
|
| 46 |
+
"eval_samples_per_second": 31.412,
|
| 47 |
+
"eval_steps_per_second": 0.123,
|
| 48 |
+
"step": 2625
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.14,
|
| 52 |
+
"learning_rate": 0.0009238095238095239,
|
| 53 |
+
"loss": 0.5492,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.33,
|
| 58 |
+
"learning_rate": 0.0009111111111111111,
|
| 59 |
+
"loss": 0.5403,
|
| 60 |
+
"step": 3500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.52,
|
| 64 |
+
"learning_rate": 0.0008984126984126985,
|
| 65 |
+
"loss": 0.5678,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.71,
|
| 70 |
+
"learning_rate": 0.0008857142857142857,
|
| 71 |
+
"loss": 0.58,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.9,
|
| 76 |
+
"learning_rate": 0.000873015873015873,
|
| 77 |
+
"loss": 0.5977,
|
| 78 |
+
"step": 5000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 2.0,
|
| 82 |
+
"eval_accuracy": 0.6613973981125897,
|
| 83 |
+
"eval_loss": 1.911996841430664,
|
| 84 |
+
"eval_runtime": 2172.477,
|
| 85 |
+
"eval_samples_per_second": 77.31,
|
| 86 |
+
"eval_steps_per_second": 0.302,
|
| 87 |
+
"step": 5250
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.1,
|
| 91 |
+
"learning_rate": 0.0008603174603174603,
|
| 92 |
+
"loss": 0.5428,
|
| 93 |
+
"step": 5500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.29,
|
| 97 |
+
"learning_rate": 0.0008476190476190476,
|
| 98 |
+
"loss": 0.5113,
|
| 99 |
+
"step": 6000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.48,
|
| 103 |
+
"learning_rate": 0.000834920634920635,
|
| 104 |
+
"loss": 0.5199,
|
| 105 |
+
"step": 6500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.67,
|
| 109 |
+
"learning_rate": 0.0008222222222222222,
|
| 110 |
+
"loss": 0.5418,
|
| 111 |
+
"step": 7000
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.86,
|
| 115 |
+
"learning_rate": 0.0008095238095238096,
|
| 116 |
+
"loss": 0.5472,
|
| 117 |
+
"step": 7500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.0,
|
| 121 |
+
"eval_accuracy": 0.6635348754130571,
|
| 122 |
+
"eval_loss": 1.9409977197647095,
|
| 123 |
+
"eval_runtime": 2183.1517,
|
| 124 |
+
"eval_samples_per_second": 76.932,
|
| 125 |
+
"eval_steps_per_second": 0.301,
|
| 126 |
+
"step": 7875
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.05,
|
| 130 |
+
"learning_rate": 0.0007968253968253968,
|
| 131 |
+
"loss": 0.5319,
|
| 132 |
+
"step": 8000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.24,
|
| 136 |
+
"learning_rate": 0.0007841269841269841,
|
| 137 |
+
"loss": 0.4719,
|
| 138 |
+
"step": 8500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.43,
|
| 142 |
+
"learning_rate": 0.0007714285714285715,
|
| 143 |
+
"loss": 0.4803,
|
| 144 |
+
"step": 9000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.62,
|
| 148 |
+
"learning_rate": 0.0007587301587301587,
|
| 149 |
+
"loss": 0.4889,
|
| 150 |
+
"step": 9500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 3.81,
|
| 154 |
+
"learning_rate": 0.000746031746031746,
|
| 155 |
+
"loss": 0.5079,
|
| 156 |
+
"step": 10000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.0,
|
| 160 |
+
"learning_rate": 0.0007333333333333333,
|
| 161 |
+
"loss": 0.513,
|
| 162 |
+
"step": 10500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.0,
|
| 166 |
+
"eval_accuracy": 0.6678634157958977,
|
| 167 |
+
"eval_loss": 1.9818364381790161,
|
| 168 |
+
"eval_runtime": 2205.4104,
|
| 169 |
+
"eval_samples_per_second": 76.156,
|
| 170 |
+
"eval_steps_per_second": 0.298,
|
| 171 |
+
"step": 10500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.19,
|
| 175 |
+
"learning_rate": 0.0007206349206349207,
|
| 176 |
+
"loss": 0.4391,
|
| 177 |
+
"step": 11000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.38,
|
| 181 |
+
"learning_rate": 0.000707936507936508,
|
| 182 |
+
"loss": 0.452,
|
| 183 |
+
"step": 11500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.57,
|
| 187 |
+
"learning_rate": 0.0006952380952380952,
|
| 188 |
+
"loss": 0.4703,
|
| 189 |
+
"step": 12000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.76,
|
| 193 |
+
"learning_rate": 0.0006825396825396826,
|
| 194 |
+
"loss": 0.4698,
|
| 195 |
+
"step": 12500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.95,
|
| 199 |
+
"learning_rate": 0.0006698412698412698,
|
| 200 |
+
"loss": 0.4714,
|
| 201 |
+
"step": 13000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 5.0,
|
| 205 |
+
"eval_accuracy": 0.6711261945163883,
|
| 206 |
+
"eval_loss": 1.9427947998046875,
|
| 207 |
+
"eval_runtime": 5170.4,
|
| 208 |
+
"eval_samples_per_second": 32.484,
|
| 209 |
+
"eval_steps_per_second": 0.127,
|
| 210 |
+
"step": 13125
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 5.14,
|
| 214 |
+
"learning_rate": 0.0006571428571428571,
|
| 215 |
+
"loss": 0.4337,
|
| 216 |
+
"step": 13500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.33,
|
| 220 |
+
"learning_rate": 0.0006444444444444444,
|
| 221 |
+
"loss": 0.4168,
|
| 222 |
+
"step": 14000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 5.52,
|
| 226 |
+
"learning_rate": 0.0006317460317460318,
|
| 227 |
+
"loss": 0.4274,
|
| 228 |
+
"step": 14500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 5.71,
|
| 232 |
+
"learning_rate": 0.0006190476190476191,
|
| 233 |
+
"loss": 0.437,
|
| 234 |
+
"step": 15000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.9,
|
| 238 |
+
"learning_rate": 0.0006063492063492063,
|
| 239 |
+
"loss": 0.4378,
|
| 240 |
+
"step": 15500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 6.0,
|
| 244 |
+
"eval_accuracy": 0.6727397219493316,
|
| 245 |
+
"eval_loss": 2.0051467418670654,
|
| 246 |
+
"eval_runtime": 2183.8633,
|
| 247 |
+
"eval_samples_per_second": 76.907,
|
| 248 |
+
"eval_steps_per_second": 0.301,
|
| 249 |
+
"step": 15750
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.1,
|
| 253 |
+
"learning_rate": 0.0005936507936507937,
|
| 254 |
+
"loss": 0.4139,
|
| 255 |
+
"step": 16000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 6.29,
|
| 259 |
+
"learning_rate": 0.000580952380952381,
|
| 260 |
+
"loss": 0.3956,
|
| 261 |
+
"step": 16500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 6.48,
|
| 265 |
+
"learning_rate": 0.0005682539682539682,
|
| 266 |
+
"loss": 0.3989,
|
| 267 |
+
"step": 17000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 6.67,
|
| 271 |
+
"learning_rate": 0.0005555555555555556,
|
| 272 |
+
"loss": 0.405,
|
| 273 |
+
"step": 17500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.86,
|
| 277 |
+
"learning_rate": 0.0005428571428571428,
|
| 278 |
+
"loss": 0.4105,
|
| 279 |
+
"step": 18000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 7.0,
|
| 283 |
+
"eval_accuracy": 0.677752969545414,
|
| 284 |
+
"eval_loss": 1.9916749000549316,
|
| 285 |
+
"eval_runtime": 2143.2651,
|
| 286 |
+
"eval_samples_per_second": 78.364,
|
| 287 |
+
"eval_steps_per_second": 0.307,
|
| 288 |
+
"step": 18375
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 7.05,
|
| 292 |
+
"learning_rate": 0.0005301587301587302,
|
| 293 |
+
"loss": 0.405,
|
| 294 |
+
"step": 18500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 7.24,
|
| 298 |
+
"learning_rate": 0.0005174603174603176,
|
| 299 |
+
"loss": 0.3653,
|
| 300 |
+
"step": 19000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 7.43,
|
| 304 |
+
"learning_rate": 0.0005047619047619048,
|
| 305 |
+
"loss": 0.3694,
|
| 306 |
+
"step": 19500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 7.62,
|
| 310 |
+
"learning_rate": 0.000492063492063492,
|
| 311 |
+
"loss": 0.3766,
|
| 312 |
+
"step": 20000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 7.81,
|
| 316 |
+
"learning_rate": 0.0004793650793650794,
|
| 317 |
+
"loss": 0.3774,
|
| 318 |
+
"step": 20500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 8.0,
|
| 322 |
+
"learning_rate": 0.00046666666666666666,
|
| 323 |
+
"loss": 0.3837,
|
| 324 |
+
"step": 21000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 8.0,
|
| 328 |
+
"eval_accuracy": 0.679211693608407,
|
| 329 |
+
"eval_loss": 2.041311025619507,
|
| 330 |
+
"eval_runtime": 2155.99,
|
| 331 |
+
"eval_samples_per_second": 77.902,
|
| 332 |
+
"eval_steps_per_second": 0.305,
|
| 333 |
+
"step": 21000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 8.19,
|
| 337 |
+
"learning_rate": 0.000453968253968254,
|
| 338 |
+
"loss": 0.3406,
|
| 339 |
+
"step": 21500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 8.38,
|
| 343 |
+
"learning_rate": 0.00044126984126984127,
|
| 344 |
+
"loss": 0.3469,
|
| 345 |
+
"step": 22000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 8.57,
|
| 349 |
+
"learning_rate": 0.00042857142857142855,
|
| 350 |
+
"loss": 0.3523,
|
| 351 |
+
"step": 22500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 8.76,
|
| 355 |
+
"learning_rate": 0.0004158730158730159,
|
| 356 |
+
"loss": 0.3559,
|
| 357 |
+
"step": 23000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 8.95,
|
| 361 |
+
"learning_rate": 0.0004031746031746032,
|
| 362 |
+
"loss": 0.3602,
|
| 363 |
+
"step": 23500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 9.0,
|
| 367 |
+
"eval_accuracy": 0.6870054478878271,
|
| 368 |
+
"eval_loss": 2.0737974643707275,
|
| 369 |
+
"eval_runtime": 2167.8038,
|
| 370 |
+
"eval_samples_per_second": 77.477,
|
| 371 |
+
"eval_steps_per_second": 0.303,
|
| 372 |
+
"step": 23625
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 9.14,
|
| 376 |
+
"learning_rate": 0.0003904761904761905,
|
| 377 |
+
"loss": 0.3172,
|
| 378 |
+
"step": 24000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 9.33,
|
| 382 |
+
"learning_rate": 0.00037777777777777777,
|
| 383 |
+
"loss": 0.325,
|
| 384 |
+
"step": 24500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 9.52,
|
| 388 |
+
"learning_rate": 0.00036507936507936505,
|
| 389 |
+
"loss": 0.3255,
|
| 390 |
+
"step": 25000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 9.71,
|
| 394 |
+
"learning_rate": 0.00035238095238095243,
|
| 395 |
+
"loss": 0.3277,
|
| 396 |
+
"step": 25500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 9.9,
|
| 400 |
+
"learning_rate": 0.0003396825396825397,
|
| 401 |
+
"loss": 0.336,
|
| 402 |
+
"step": 26000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 10.0,
|
| 406 |
+
"eval_accuracy": 0.6875770295614897,
|
| 407 |
+
"eval_loss": 2.087229013442993,
|
| 408 |
+
"eval_runtime": 4594.6085,
|
| 409 |
+
"eval_samples_per_second": 36.555,
|
| 410 |
+
"eval_steps_per_second": 0.143,
|
| 411 |
+
"step": 26250
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 10.1,
|
| 415 |
+
"learning_rate": 0.000326984126984127,
|
| 416 |
+
"loss": 0.3184,
|
| 417 |
+
"step": 26500
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 10.29,
|
| 421 |
+
"learning_rate": 0.00031428571428571427,
|
| 422 |
+
"loss": 0.3072,
|
| 423 |
+
"step": 27000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 10.48,
|
| 427 |
+
"learning_rate": 0.0003015873015873016,
|
| 428 |
+
"loss": 0.3024,
|
| 429 |
+
"step": 27500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 10.67,
|
| 433 |
+
"learning_rate": 0.0002888888888888889,
|
| 434 |
+
"loss": 0.3112,
|
| 435 |
+
"step": 28000
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 10.86,
|
| 439 |
+
"learning_rate": 0.0002761904761904762,
|
| 440 |
+
"loss": 0.3057,
|
| 441 |
+
"step": 28500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 11.0,
|
| 445 |
+
"eval_accuracy": 0.6893870381947546,
|
| 446 |
+
"eval_loss": 2.1162524223327637,
|
| 447 |
+
"eval_runtime": 1647.7962,
|
| 448 |
+
"eval_samples_per_second": 101.927,
|
| 449 |
+
"eval_steps_per_second": 0.399,
|
| 450 |
+
"step": 28875
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 11.05,
|
| 454 |
+
"learning_rate": 0.0002634920634920635,
|
| 455 |
+
"loss": 0.2991,
|
| 456 |
+
"step": 29000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 11.24,
|
| 460 |
+
"learning_rate": 0.0002507936507936508,
|
| 461 |
+
"loss": 0.2861,
|
| 462 |
+
"step": 29500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 11.43,
|
| 466 |
+
"learning_rate": 0.0002380952380952381,
|
| 467 |
+
"loss": 0.2849,
|
| 468 |
+
"step": 30000
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 11.62,
|
| 472 |
+
"learning_rate": 0.0002253968253968254,
|
| 473 |
+
"loss": 0.2897,
|
| 474 |
+
"step": 30500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 11.81,
|
| 478 |
+
"learning_rate": 0.0002126984126984127,
|
| 479 |
+
"loss": 0.2864,
|
| 480 |
+
"step": 31000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 12.0,
|
| 484 |
+
"learning_rate": 0.0002,
|
| 485 |
+
"loss": 0.2856,
|
| 486 |
+
"step": 31500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 12.0,
|
| 490 |
+
"eval_accuracy": 0.6936441308683874,
|
| 491 |
+
"eval_loss": 2.1104633808135986,
|
| 492 |
+
"eval_runtime": 1643.6927,
|
| 493 |
+
"eval_samples_per_second": 102.182,
|
| 494 |
+
"eval_steps_per_second": 0.4,
|
| 495 |
+
"step": 31500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 12.19,
|
| 499 |
+
"learning_rate": 0.00018730158730158731,
|
| 500 |
+
"loss": 0.2704,
|
| 501 |
+
"step": 32000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 12.38,
|
| 505 |
+
"learning_rate": 0.0001746031746031746,
|
| 506 |
+
"loss": 0.2688,
|
| 507 |
+
"step": 32500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 12.57,
|
| 511 |
+
"learning_rate": 0.00016190476190476192,
|
| 512 |
+
"loss": 0.2634,
|
| 513 |
+
"step": 33000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 12.76,
|
| 517 |
+
"learning_rate": 0.0001492063492063492,
|
| 518 |
+
"loss": 0.2713,
|
| 519 |
+
"step": 33500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 12.95,
|
| 523 |
+
"learning_rate": 0.0001365079365079365,
|
| 524 |
+
"loss": 0.2704,
|
| 525 |
+
"step": 34000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 13.0,
|
| 529 |
+
"eval_accuracy": 0.6964782233336311,
|
| 530 |
+
"eval_loss": 2.168531894683838,
|
| 531 |
+
"eval_runtime": 1642.8004,
|
| 532 |
+
"eval_samples_per_second": 102.237,
|
| 533 |
+
"eval_steps_per_second": 0.4,
|
| 534 |
+
"step": 34125
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 13.14,
|
| 538 |
+
"learning_rate": 0.0001238095238095238,
|
| 539 |
+
"loss": 0.2586,
|
| 540 |
+
"step": 34500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 13.33,
|
| 544 |
+
"learning_rate": 0.0001111111111111111,
|
| 545 |
+
"loss": 0.2544,
|
| 546 |
+
"step": 35000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 13.52,
|
| 550 |
+
"learning_rate": 9.841269841269841e-05,
|
| 551 |
+
"loss": 0.2483,
|
| 552 |
+
"step": 35500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 13.71,
|
| 556 |
+
"learning_rate": 8.571428571428571e-05,
|
| 557 |
+
"loss": 0.2612,
|
| 558 |
+
"step": 36000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 13.9,
|
| 562 |
+
"learning_rate": 7.301587301587302e-05,
|
| 563 |
+
"loss": 0.2503,
|
| 564 |
+
"step": 36500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 14.0,
|
| 568 |
+
"eval_accuracy": 0.699431395314221,
|
| 569 |
+
"eval_loss": 2.162724733352661,
|
| 570 |
+
"eval_runtime": 1648.5219,
|
| 571 |
+
"eval_samples_per_second": 101.882,
|
| 572 |
+
"eval_steps_per_second": 0.399,
|
| 573 |
+
"step": 36750
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 14.1,
|
| 577 |
+
"learning_rate": 6.031746031746032e-05,
|
| 578 |
+
"loss": 0.2471,
|
| 579 |
+
"step": 37000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 14.29,
|
| 583 |
+
"learning_rate": 4.761904761904762e-05,
|
| 584 |
+
"loss": 0.2452,
|
| 585 |
+
"step": 37500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 14.48,
|
| 589 |
+
"learning_rate": 3.4920634920634925e-05,
|
| 590 |
+
"loss": 0.2433,
|
| 591 |
+
"step": 38000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 14.67,
|
| 595 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 596 |
+
"loss": 0.2392,
|
| 597 |
+
"step": 38500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 14.86,
|
| 601 |
+
"learning_rate": 9.523809523809525e-06,
|
| 602 |
+
"loss": 0.2362,
|
| 603 |
+
"step": 39000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 15.0,
|
| 607 |
+
"eval_accuracy": 0.7000208389151856,
|
| 608 |
+
"eval_loss": 2.1793291568756104,
|
| 609 |
+
"eval_runtime": 1654.6492,
|
| 610 |
+
"eval_samples_per_second": 101.505,
|
| 611 |
+
"eval_steps_per_second": 0.397,
|
| 612 |
+
"step": 39375
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 15.0,
|
| 616 |
+
"step": 39375,
|
| 617 |
+
"total_flos": 6.872831806674565e+20,
|
| 618 |
+
"train_loss": 0.1121770017593626,
|
| 619 |
+
"train_runtime": 63366.2415,
|
| 620 |
+
"train_samples_per_second": 159.032,
|
| 621 |
+
"train_steps_per_second": 0.621
|
| 622 |
+
}
|
| 623 |
+
],
|
| 624 |
+
"logging_steps": 500,
|
| 625 |
+
"max_steps": 39375,
|
| 626 |
+
"num_train_epochs": 15,
|
| 627 |
+
"save_steps": 500,
|
| 628 |
+
"total_flos": 6.872831806674565e+20,
|
| 629 |
+
"trial_name": null,
|
| 630 |
+
"trial_params": null
|
| 631 |
+
}
|