End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9994666666666666,
|
| 4 |
+
"eval_loss": 0.15595677495002747,
|
| 5 |
+
"eval_runtime": 28.134,
|
| 6 |
+
"eval_samples_per_second": 66.645,
|
| 7 |
+
"eval_steps_per_second": 2.097,
|
| 8 |
+
"total_flos": 8.232859423714222e+18,
|
| 9 |
+
"train_loss": 0.4019865568861904,
|
| 10 |
+
"train_runtime": 5542.9491,
|
| 11 |
+
"train_samples_per_second": 19.165,
|
| 12 |
+
"train_steps_per_second": 0.15
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.9994666666666666,
|
| 4 |
+
"eval_loss": 0.15595677495002747,
|
| 5 |
+
"eval_runtime": 28.134,
|
| 6 |
+
"eval_samples_per_second": 66.645,
|
| 7 |
+
"eval_steps_per_second": 2.097
|
| 8 |
+
}
|
runs/May22_00-34-38_13c1466b87cd/events.out.tfevents.1684721309.13c1466b87cd.600.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c048039024adf0726ddb6c2d4e3e9d1cc7f1e9590be65afbd47f46c4b5b4a34d
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 8.232859423714222e+18,
|
| 4 |
+
"train_loss": 0.4019865568861904,
|
| 5 |
+
"train_runtime": 5542.9491,
|
| 6 |
+
"train_samples_per_second": 19.165,
|
| 7 |
+
"train_steps_per_second": 0.15
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,613 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9994666666666666,
|
| 3 |
+
"best_model_checkpoint": "plant-vit-model-1/checkpoint-332",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 830,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.12,
|
| 12 |
+
"learning_rate": 6.024096385542169e-06,
|
| 13 |
+
"loss": 2.6748,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.24,
|
| 18 |
+
"learning_rate": 1.2048192771084338e-05,
|
| 19 |
+
"loss": 2.5895,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.36,
|
| 24 |
+
"learning_rate": 1.8072289156626505e-05,
|
| 25 |
+
"loss": 2.4413,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.48,
|
| 30 |
+
"learning_rate": 2.4096385542168677e-05,
|
| 31 |
+
"loss": 2.2745,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.6,
|
| 36 |
+
"learning_rate": 3.012048192771085e-05,
|
| 37 |
+
"loss": 2.0245,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.72,
|
| 42 |
+
"learning_rate": 3.614457831325301e-05,
|
| 43 |
+
"loss": 1.7626,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.84,
|
| 48 |
+
"learning_rate": 4.2168674698795186e-05,
|
| 49 |
+
"loss": 1.5706,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.96,
|
| 54 |
+
"learning_rate": 4.8192771084337354e-05,
|
| 55 |
+
"loss": 1.296,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.0,
|
| 60 |
+
"eval_accuracy": 0.9226666666666666,
|
| 61 |
+
"eval_loss": 1.0360676050186157,
|
| 62 |
+
"eval_runtime": 28.5267,
|
| 63 |
+
"eval_samples_per_second": 65.728,
|
| 64 |
+
"eval_steps_per_second": 2.068,
|
| 65 |
+
"step": 83
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.08,
|
| 69 |
+
"learning_rate": 4.953145917001339e-05,
|
| 70 |
+
"loss": 1.0868,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.2,
|
| 75 |
+
"learning_rate": 4.886211512717537e-05,
|
| 76 |
+
"loss": 0.8857,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.33,
|
| 81 |
+
"learning_rate": 4.8192771084337354e-05,
|
| 82 |
+
"loss": 0.8006,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.45,
|
| 87 |
+
"learning_rate": 4.7523427041499336e-05,
|
| 88 |
+
"loss": 0.6679,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.57,
|
| 93 |
+
"learning_rate": 4.685408299866131e-05,
|
| 94 |
+
"loss": 0.5875,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.69,
|
| 99 |
+
"learning_rate": 4.61847389558233e-05,
|
| 100 |
+
"loss": 0.5278,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.81,
|
| 105 |
+
"learning_rate": 4.5515394912985275e-05,
|
| 106 |
+
"loss": 0.4966,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.93,
|
| 111 |
+
"learning_rate": 4.484605087014726e-05,
|
| 112 |
+
"loss": 0.4476,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.0,
|
| 117 |
+
"eval_accuracy": 0.9904,
|
| 118 |
+
"eval_loss": 0.3645952343940735,
|
| 119 |
+
"eval_runtime": 27.9536,
|
| 120 |
+
"eval_samples_per_second": 67.075,
|
| 121 |
+
"eval_steps_per_second": 2.111,
|
| 122 |
+
"step": 166
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.05,
|
| 126 |
+
"learning_rate": 4.417670682730924e-05,
|
| 127 |
+
"loss": 0.4392,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.17,
|
| 132 |
+
"learning_rate": 4.350736278447122e-05,
|
| 133 |
+
"loss": 0.381,
|
| 134 |
+
"step": 180
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.29,
|
| 138 |
+
"learning_rate": 4.2838018741633203e-05,
|
| 139 |
+
"loss": 0.3494,
|
| 140 |
+
"step": 190
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.41,
|
| 144 |
+
"learning_rate": 4.2168674698795186e-05,
|
| 145 |
+
"loss": 0.336,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.53,
|
| 150 |
+
"learning_rate": 4.149933065595716e-05,
|
| 151 |
+
"loss": 0.3078,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.65,
|
| 156 |
+
"learning_rate": 4.082998661311915e-05,
|
| 157 |
+
"loss": 0.3163,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.77,
|
| 162 |
+
"learning_rate": 4.0160642570281125e-05,
|
| 163 |
+
"loss": 0.2963,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.89,
|
| 168 |
+
"learning_rate": 3.949129852744311e-05,
|
| 169 |
+
"loss": 0.2731,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.0,
|
| 174 |
+
"eval_accuracy": 0.9952,
|
| 175 |
+
"eval_loss": 0.21737419068813324,
|
| 176 |
+
"eval_runtime": 27.9589,
|
| 177 |
+
"eval_samples_per_second": 67.063,
|
| 178 |
+
"eval_steps_per_second": 2.11,
|
| 179 |
+
"step": 249
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.01,
|
| 183 |
+
"learning_rate": 3.882195448460509e-05,
|
| 184 |
+
"loss": 0.284,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.13,
|
| 189 |
+
"learning_rate": 3.815261044176707e-05,
|
| 190 |
+
"loss": 0.2695,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.25,
|
| 195 |
+
"learning_rate": 3.748326639892905e-05,
|
| 196 |
+
"loss": 0.2428,
|
| 197 |
+
"step": 270
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.37,
|
| 201 |
+
"learning_rate": 3.6813922356091035e-05,
|
| 202 |
+
"loss": 0.239,
|
| 203 |
+
"step": 280
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.49,
|
| 207 |
+
"learning_rate": 3.614457831325301e-05,
|
| 208 |
+
"loss": 0.2388,
|
| 209 |
+
"step": 290
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.61,
|
| 213 |
+
"learning_rate": 3.5475234270415e-05,
|
| 214 |
+
"loss": 0.2138,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.73,
|
| 219 |
+
"learning_rate": 3.4805890227576974e-05,
|
| 220 |
+
"loss": 0.2001,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 3.86,
|
| 225 |
+
"learning_rate": 3.413654618473896e-05,
|
| 226 |
+
"loss": 0.2144,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.98,
|
| 231 |
+
"learning_rate": 3.346720214190094e-05,
|
| 232 |
+
"loss": 0.2097,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 4.0,
|
| 237 |
+
"eval_accuracy": 0.9994666666666666,
|
| 238 |
+
"eval_loss": 0.15595677495002747,
|
| 239 |
+
"eval_runtime": 27.9371,
|
| 240 |
+
"eval_samples_per_second": 67.115,
|
| 241 |
+
"eval_steps_per_second": 2.112,
|
| 242 |
+
"step": 332
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.1,
|
| 246 |
+
"learning_rate": 3.279785809906292e-05,
|
| 247 |
+
"loss": 0.1877,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.22,
|
| 252 |
+
"learning_rate": 3.21285140562249e-05,
|
| 253 |
+
"loss": 0.1834,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.34,
|
| 258 |
+
"learning_rate": 3.1459170013386885e-05,
|
| 259 |
+
"loss": 0.1849,
|
| 260 |
+
"step": 360
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.46,
|
| 264 |
+
"learning_rate": 3.078982597054887e-05,
|
| 265 |
+
"loss": 0.1581,
|
| 266 |
+
"step": 370
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.58,
|
| 270 |
+
"learning_rate": 3.012048192771085e-05,
|
| 271 |
+
"loss": 0.1943,
|
| 272 |
+
"step": 380
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.7,
|
| 276 |
+
"learning_rate": 2.9451137884872827e-05,
|
| 277 |
+
"loss": 0.1651,
|
| 278 |
+
"step": 390
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.82,
|
| 282 |
+
"learning_rate": 2.878179384203481e-05,
|
| 283 |
+
"loss": 0.1896,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.94,
|
| 288 |
+
"learning_rate": 2.8112449799196788e-05,
|
| 289 |
+
"loss": 0.1679,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.0,
|
| 294 |
+
"eval_accuracy": 0.9973333333333333,
|
| 295 |
+
"eval_loss": 0.12879624962806702,
|
| 296 |
+
"eval_runtime": 27.9408,
|
| 297 |
+
"eval_samples_per_second": 67.106,
|
| 298 |
+
"eval_steps_per_second": 2.112,
|
| 299 |
+
"step": 415
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.06,
|
| 303 |
+
"learning_rate": 2.7443105756358774e-05,
|
| 304 |
+
"loss": 0.1691,
|
| 305 |
+
"step": 420
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 5.18,
|
| 309 |
+
"learning_rate": 2.6773761713520752e-05,
|
| 310 |
+
"loss": 0.1524,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 5.3,
|
| 315 |
+
"learning_rate": 2.6104417670682734e-05,
|
| 316 |
+
"loss": 0.1379,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 5.42,
|
| 321 |
+
"learning_rate": 2.5435073627844713e-05,
|
| 322 |
+
"loss": 0.1401,
|
| 323 |
+
"step": 450
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 5.54,
|
| 327 |
+
"learning_rate": 2.4765729585006695e-05,
|
| 328 |
+
"loss": 0.1446,
|
| 329 |
+
"step": 460
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 5.66,
|
| 333 |
+
"learning_rate": 2.4096385542168677e-05,
|
| 334 |
+
"loss": 0.1384,
|
| 335 |
+
"step": 470
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 5.78,
|
| 339 |
+
"learning_rate": 2.3427041499330656e-05,
|
| 340 |
+
"loss": 0.1356,
|
| 341 |
+
"step": 480
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 5.9,
|
| 345 |
+
"learning_rate": 2.2757697456492638e-05,
|
| 346 |
+
"loss": 0.135,
|
| 347 |
+
"step": 490
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 6.0,
|
| 351 |
+
"eval_accuracy": 0.9984,
|
| 352 |
+
"eval_loss": 0.10523158311843872,
|
| 353 |
+
"eval_runtime": 27.794,
|
| 354 |
+
"eval_samples_per_second": 67.461,
|
| 355 |
+
"eval_steps_per_second": 2.123,
|
| 356 |
+
"step": 498
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.02,
|
| 360 |
+
"learning_rate": 2.208835341365462e-05,
|
| 361 |
+
"loss": 0.135,
|
| 362 |
+
"step": 500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.14,
|
| 366 |
+
"learning_rate": 2.1419009370816602e-05,
|
| 367 |
+
"loss": 0.1418,
|
| 368 |
+
"step": 510
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.27,
|
| 372 |
+
"learning_rate": 2.074966532797858e-05,
|
| 373 |
+
"loss": 0.1291,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.39,
|
| 378 |
+
"learning_rate": 2.0080321285140562e-05,
|
| 379 |
+
"loss": 0.1321,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 6.51,
|
| 384 |
+
"learning_rate": 1.9410977242302544e-05,
|
| 385 |
+
"loss": 0.1349,
|
| 386 |
+
"step": 540
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 6.63,
|
| 390 |
+
"learning_rate": 1.8741633199464527e-05,
|
| 391 |
+
"loss": 0.1229,
|
| 392 |
+
"step": 550
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 6.75,
|
| 396 |
+
"learning_rate": 1.8072289156626505e-05,
|
| 397 |
+
"loss": 0.1285,
|
| 398 |
+
"step": 560
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.87,
|
| 402 |
+
"learning_rate": 1.7402945113788487e-05,
|
| 403 |
+
"loss": 0.1246,
|
| 404 |
+
"step": 570
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 6.99,
|
| 408 |
+
"learning_rate": 1.673360107095047e-05,
|
| 409 |
+
"loss": 0.118,
|
| 410 |
+
"step": 580
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 7.0,
|
| 414 |
+
"eval_accuracy": 0.9989333333333333,
|
| 415 |
+
"eval_loss": 0.09175615012645721,
|
| 416 |
+
"eval_runtime": 27.7375,
|
| 417 |
+
"eval_samples_per_second": 67.598,
|
| 418 |
+
"eval_steps_per_second": 2.127,
|
| 419 |
+
"step": 581
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 7.11,
|
| 423 |
+
"learning_rate": 1.606425702811245e-05,
|
| 424 |
+
"loss": 0.1359,
|
| 425 |
+
"step": 590
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 7.23,
|
| 429 |
+
"learning_rate": 1.5394912985274433e-05,
|
| 430 |
+
"loss": 0.1081,
|
| 431 |
+
"step": 600
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 7.35,
|
| 435 |
+
"learning_rate": 1.4725568942436414e-05,
|
| 436 |
+
"loss": 0.1331,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 7.47,
|
| 441 |
+
"learning_rate": 1.4056224899598394e-05,
|
| 442 |
+
"loss": 0.1095,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 7.59,
|
| 447 |
+
"learning_rate": 1.3386880856760376e-05,
|
| 448 |
+
"loss": 0.1183,
|
| 449 |
+
"step": 630
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 7.71,
|
| 453 |
+
"learning_rate": 1.2717536813922356e-05,
|
| 454 |
+
"loss": 0.1257,
|
| 455 |
+
"step": 640
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 7.83,
|
| 459 |
+
"learning_rate": 1.2048192771084338e-05,
|
| 460 |
+
"loss": 0.1201,
|
| 461 |
+
"step": 650
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 7.95,
|
| 465 |
+
"learning_rate": 1.1378848728246319e-05,
|
| 466 |
+
"loss": 0.1054,
|
| 467 |
+
"step": 660
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 8.0,
|
| 471 |
+
"eval_accuracy": 0.9989333333333333,
|
| 472 |
+
"eval_loss": 0.08257802575826645,
|
| 473 |
+
"eval_runtime": 27.821,
|
| 474 |
+
"eval_samples_per_second": 67.395,
|
| 475 |
+
"eval_steps_per_second": 2.121,
|
| 476 |
+
"step": 664
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 8.07,
|
| 480 |
+
"learning_rate": 1.0709504685408301e-05,
|
| 481 |
+
"loss": 0.0961,
|
| 482 |
+
"step": 670
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 8.19,
|
| 486 |
+
"learning_rate": 1.0040160642570281e-05,
|
| 487 |
+
"loss": 0.1112,
|
| 488 |
+
"step": 680
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 8.31,
|
| 492 |
+
"learning_rate": 9.370816599732263e-06,
|
| 493 |
+
"loss": 0.1009,
|
| 494 |
+
"step": 690
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 8.43,
|
| 498 |
+
"learning_rate": 8.701472556894244e-06,
|
| 499 |
+
"loss": 0.0931,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 8.55,
|
| 504 |
+
"learning_rate": 8.032128514056226e-06,
|
| 505 |
+
"loss": 0.0987,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 8.67,
|
| 510 |
+
"learning_rate": 7.362784471218207e-06,
|
| 511 |
+
"loss": 0.1074,
|
| 512 |
+
"step": 720
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 8.8,
|
| 516 |
+
"learning_rate": 6.693440428380188e-06,
|
| 517 |
+
"loss": 0.1096,
|
| 518 |
+
"step": 730
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 8.92,
|
| 522 |
+
"learning_rate": 6.024096385542169e-06,
|
| 523 |
+
"loss": 0.1083,
|
| 524 |
+
"step": 740
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 9.0,
|
| 528 |
+
"eval_accuracy": 0.9989333333333333,
|
| 529 |
+
"eval_loss": 0.07765089720487595,
|
| 530 |
+
"eval_runtime": 27.9635,
|
| 531 |
+
"eval_samples_per_second": 67.052,
|
| 532 |
+
"eval_steps_per_second": 2.11,
|
| 533 |
+
"step": 747
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 9.04,
|
| 537 |
+
"learning_rate": 5.3547523427041504e-06,
|
| 538 |
+
"loss": 0.1025,
|
| 539 |
+
"step": 750
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.16,
|
| 543 |
+
"learning_rate": 4.685408299866132e-06,
|
| 544 |
+
"loss": 0.0993,
|
| 545 |
+
"step": 760
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 9.28,
|
| 549 |
+
"learning_rate": 4.016064257028113e-06,
|
| 550 |
+
"loss": 0.0878,
|
| 551 |
+
"step": 770
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 9.4,
|
| 555 |
+
"learning_rate": 3.346720214190094e-06,
|
| 556 |
+
"loss": 0.1114,
|
| 557 |
+
"step": 780
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 9.52,
|
| 561 |
+
"learning_rate": 2.6773761713520752e-06,
|
| 562 |
+
"loss": 0.1085,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 9.64,
|
| 567 |
+
"learning_rate": 2.0080321285140564e-06,
|
| 568 |
+
"loss": 0.0873,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 9.76,
|
| 573 |
+
"learning_rate": 1.3386880856760376e-06,
|
| 574 |
+
"loss": 0.1037,
|
| 575 |
+
"step": 810
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 9.88,
|
| 579 |
+
"learning_rate": 6.693440428380188e-07,
|
| 580 |
+
"loss": 0.0947,
|
| 581 |
+
"step": 820
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 10.0,
|
| 585 |
+
"learning_rate": 0.0,
|
| 586 |
+
"loss": 0.0918,
|
| 587 |
+
"step": 830
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 10.0,
|
| 591 |
+
"eval_accuracy": 0.9994666666666666,
|
| 592 |
+
"eval_loss": 0.07559256255626678,
|
| 593 |
+
"eval_runtime": 27.9992,
|
| 594 |
+
"eval_samples_per_second": 66.966,
|
| 595 |
+
"eval_steps_per_second": 2.107,
|
| 596 |
+
"step": 830
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 10.0,
|
| 600 |
+
"step": 830,
|
| 601 |
+
"total_flos": 8.232859423714222e+18,
|
| 602 |
+
"train_loss": 0.4019865568861904,
|
| 603 |
+
"train_runtime": 5542.9491,
|
| 604 |
+
"train_samples_per_second": 19.165,
|
| 605 |
+
"train_steps_per_second": 0.15
|
| 606 |
+
}
|
| 607 |
+
],
|
| 608 |
+
"max_steps": 830,
|
| 609 |
+
"num_train_epochs": 10,
|
| 610 |
+
"total_flos": 8.232859423714222e+18,
|
| 611 |
+
"trial_name": null,
|
| 612 |
+
"trial_params": null
|
| 613 |
+
}
|