End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +538 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 31.03,
|
| 3 |
+
"eval_accuracy": 0.9470198675496688,
|
| 4 |
+
"eval_loss": 0.2553568482398987,
|
| 5 |
+
"eval_runtime": 31.773,
|
| 6 |
+
"eval_samples_per_second": 4.752,
|
| 7 |
+
"eval_steps_per_second": 4.752
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 31.03,
|
| 3 |
+
"eval_accuracy": 0.9470198675496688,
|
| 4 |
+
"eval_loss": 0.2553568482398987,
|
| 5 |
+
"eval_runtime": 31.773,
|
| 6 |
+
"eval_samples_per_second": 4.752,
|
| 7 |
+
"eval_steps_per_second": 4.752
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,538 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9586206896551724,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-soccer-action-recognition/checkpoint-1790",
|
| 4 |
+
"epoch": 31.03125,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2728,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 1.4652014652014653e-05,
|
| 14 |
+
"loss": 1.7115,
|
| 15 |
+
"step": 80
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.03,
|
| 19 |
+
"eval_accuracy": 0.4,
|
| 20 |
+
"eval_loss": 1.4195746183395386,
|
| 21 |
+
"eval_runtime": 150.0417,
|
| 22 |
+
"eval_samples_per_second": 0.966,
|
| 23 |
+
"eval_steps_per_second": 0.966,
|
| 24 |
+
"step": 85
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.03,
|
| 28 |
+
"learning_rate": 2.9304029304029305e-05,
|
| 29 |
+
"loss": 1.0097,
|
| 30 |
+
"step": 160
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.03,
|
| 34 |
+
"eval_accuracy": 0.6758620689655173,
|
| 35 |
+
"eval_loss": 0.7807376980781555,
|
| 36 |
+
"eval_runtime": 30.3768,
|
| 37 |
+
"eval_samples_per_second": 4.773,
|
| 38 |
+
"eval_steps_per_second": 4.773,
|
| 39 |
+
"step": 170
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.03,
|
| 43 |
+
"learning_rate": 4.3956043956043955e-05,
|
| 44 |
+
"loss": 0.6192,
|
| 45 |
+
"step": 240
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.03,
|
| 49 |
+
"eval_accuracy": 0.7034482758620689,
|
| 50 |
+
"eval_loss": 0.795186460018158,
|
| 51 |
+
"eval_runtime": 30.3396,
|
| 52 |
+
"eval_samples_per_second": 4.779,
|
| 53 |
+
"eval_steps_per_second": 4.779,
|
| 54 |
+
"step": 255
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.02,
|
| 58 |
+
"learning_rate": 4.904276985743381e-05,
|
| 59 |
+
"loss": 0.4713,
|
| 60 |
+
"step": 320
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 3.03,
|
| 64 |
+
"eval_accuracy": 0.7931034482758621,
|
| 65 |
+
"eval_loss": 0.6536410450935364,
|
| 66 |
+
"eval_runtime": 28.0955,
|
| 67 |
+
"eval_samples_per_second": 5.161,
|
| 68 |
+
"eval_steps_per_second": 5.161,
|
| 69 |
+
"step": 341
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.02,
|
| 73 |
+
"learning_rate": 4.7413441955193486e-05,
|
| 74 |
+
"loss": 0.3973,
|
| 75 |
+
"step": 400
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 4.03,
|
| 79 |
+
"eval_accuracy": 0.8689655172413793,
|
| 80 |
+
"eval_loss": 0.3637762665748596,
|
| 81 |
+
"eval_runtime": 28.0719,
|
| 82 |
+
"eval_samples_per_second": 5.165,
|
| 83 |
+
"eval_steps_per_second": 5.165,
|
| 84 |
+
"step": 426
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 5.02,
|
| 88 |
+
"learning_rate": 4.578411405295316e-05,
|
| 89 |
+
"loss": 0.3633,
|
| 90 |
+
"step": 480
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 5.03,
|
| 94 |
+
"eval_accuracy": 0.896551724137931,
|
| 95 |
+
"eval_loss": 0.36160850524902344,
|
| 96 |
+
"eval_runtime": 28.2429,
|
| 97 |
+
"eval_samples_per_second": 5.134,
|
| 98 |
+
"eval_steps_per_second": 5.134,
|
| 99 |
+
"step": 511
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.02,
|
| 103 |
+
"learning_rate": 4.415478615071284e-05,
|
| 104 |
+
"loss": 0.2336,
|
| 105 |
+
"step": 560
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.03,
|
| 109 |
+
"eval_accuracy": 0.896551724137931,
|
| 110 |
+
"eval_loss": 0.4579198360443115,
|
| 111 |
+
"eval_runtime": 30.0911,
|
| 112 |
+
"eval_samples_per_second": 4.819,
|
| 113 |
+
"eval_steps_per_second": 4.819,
|
| 114 |
+
"step": 596
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 7.02,
|
| 118 |
+
"learning_rate": 4.2525458248472504e-05,
|
| 119 |
+
"loss": 0.1997,
|
| 120 |
+
"step": 640
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 7.03,
|
| 124 |
+
"eval_accuracy": 0.6068965517241379,
|
| 125 |
+
"eval_loss": 1.597042202949524,
|
| 126 |
+
"eval_runtime": 27.9534,
|
| 127 |
+
"eval_samples_per_second": 5.187,
|
| 128 |
+
"eval_steps_per_second": 5.187,
|
| 129 |
+
"step": 682
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 8.01,
|
| 133 |
+
"learning_rate": 4.089613034623218e-05,
|
| 134 |
+
"loss": 0.2738,
|
| 135 |
+
"step": 720
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.03,
|
| 139 |
+
"eval_accuracy": 0.8689655172413793,
|
| 140 |
+
"eval_loss": 0.4101611375808716,
|
| 141 |
+
"eval_runtime": 27.8973,
|
| 142 |
+
"eval_samples_per_second": 5.198,
|
| 143 |
+
"eval_steps_per_second": 5.198,
|
| 144 |
+
"step": 767
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.01,
|
| 148 |
+
"learning_rate": 3.9266802443991856e-05,
|
| 149 |
+
"loss": 0.2492,
|
| 150 |
+
"step": 800
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 9.03,
|
| 154 |
+
"eval_accuracy": 0.8344827586206897,
|
| 155 |
+
"eval_loss": 0.7651154398918152,
|
| 156 |
+
"eval_runtime": 29.2625,
|
| 157 |
+
"eval_samples_per_second": 4.955,
|
| 158 |
+
"eval_steps_per_second": 4.955,
|
| 159 |
+
"step": 852
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 10.01,
|
| 163 |
+
"learning_rate": 3.763747454175153e-05,
|
| 164 |
+
"loss": 0.1568,
|
| 165 |
+
"step": 880
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 10.03,
|
| 169 |
+
"eval_accuracy": 0.8137931034482758,
|
| 170 |
+
"eval_loss": 0.8560731410980225,
|
| 171 |
+
"eval_runtime": 30.5796,
|
| 172 |
+
"eval_samples_per_second": 4.742,
|
| 173 |
+
"eval_steps_per_second": 4.742,
|
| 174 |
+
"step": 937
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 11.01,
|
| 178 |
+
"learning_rate": 3.60081466395112e-05,
|
| 179 |
+
"loss": 0.1856,
|
| 180 |
+
"step": 960
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 11.03,
|
| 184 |
+
"eval_accuracy": 0.9241379310344827,
|
| 185 |
+
"eval_loss": 0.2810556888580322,
|
| 186 |
+
"eval_runtime": 27.9183,
|
| 187 |
+
"eval_samples_per_second": 5.194,
|
| 188 |
+
"eval_steps_per_second": 5.194,
|
| 189 |
+
"step": 1023
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 12.01,
|
| 193 |
+
"learning_rate": 3.437881873727088e-05,
|
| 194 |
+
"loss": 0.1296,
|
| 195 |
+
"step": 1040
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.03,
|
| 199 |
+
"eval_accuracy": 0.9172413793103448,
|
| 200 |
+
"eval_loss": 0.3444097340106964,
|
| 201 |
+
"eval_runtime": 29.2588,
|
| 202 |
+
"eval_samples_per_second": 4.956,
|
| 203 |
+
"eval_steps_per_second": 4.956,
|
| 204 |
+
"step": 1108
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 13.0,
|
| 208 |
+
"learning_rate": 3.274949083503055e-05,
|
| 209 |
+
"loss": 0.0782,
|
| 210 |
+
"step": 1120
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 13.03,
|
| 214 |
+
"eval_accuracy": 0.9241379310344827,
|
| 215 |
+
"eval_loss": 0.34232720732688904,
|
| 216 |
+
"eval_runtime": 29.8187,
|
| 217 |
+
"eval_samples_per_second": 4.863,
|
| 218 |
+
"eval_steps_per_second": 4.863,
|
| 219 |
+
"step": 1193
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 14.0,
|
| 223 |
+
"learning_rate": 3.1120162932790225e-05,
|
| 224 |
+
"loss": 0.14,
|
| 225 |
+
"step": 1200
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 14.03,
|
| 229 |
+
"eval_accuracy": 0.9241379310344827,
|
| 230 |
+
"eval_loss": 0.31215447187423706,
|
| 231 |
+
"eval_runtime": 30.9503,
|
| 232 |
+
"eval_samples_per_second": 4.685,
|
| 233 |
+
"eval_steps_per_second": 4.685,
|
| 234 |
+
"step": 1278
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 15.0,
|
| 238 |
+
"learning_rate": 2.94908350305499e-05,
|
| 239 |
+
"loss": 0.0802,
|
| 240 |
+
"step": 1280
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.03,
|
| 244 |
+
"learning_rate": 2.786150712830957e-05,
|
| 245 |
+
"loss": 0.0689,
|
| 246 |
+
"step": 1360
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.03,
|
| 250 |
+
"eval_accuracy": 0.9172413793103448,
|
| 251 |
+
"eval_loss": 0.35335081815719604,
|
| 252 |
+
"eval_runtime": 30.933,
|
| 253 |
+
"eval_samples_per_second": 4.688,
|
| 254 |
+
"eval_steps_per_second": 4.688,
|
| 255 |
+
"step": 1364
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 16.03,
|
| 259 |
+
"learning_rate": 2.6232179226069247e-05,
|
| 260 |
+
"loss": 0.036,
|
| 261 |
+
"step": 1440
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 16.03,
|
| 265 |
+
"eval_accuracy": 0.9103448275862069,
|
| 266 |
+
"eval_loss": 0.4814639985561371,
|
| 267 |
+
"eval_runtime": 30.7939,
|
| 268 |
+
"eval_samples_per_second": 4.709,
|
| 269 |
+
"eval_steps_per_second": 4.709,
|
| 270 |
+
"step": 1449
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 17.03,
|
| 274 |
+
"learning_rate": 2.4602851323828923e-05,
|
| 275 |
+
"loss": 0.0695,
|
| 276 |
+
"step": 1520
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 17.03,
|
| 280 |
+
"eval_accuracy": 0.8827586206896552,
|
| 281 |
+
"eval_loss": 0.5698482394218445,
|
| 282 |
+
"eval_runtime": 30.7434,
|
| 283 |
+
"eval_samples_per_second": 4.716,
|
| 284 |
+
"eval_steps_per_second": 4.716,
|
| 285 |
+
"step": 1534
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 18.02,
|
| 289 |
+
"learning_rate": 2.29735234215886e-05,
|
| 290 |
+
"loss": 0.0618,
|
| 291 |
+
"step": 1600
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 18.03,
|
| 295 |
+
"eval_accuracy": 0.9310344827586207,
|
| 296 |
+
"eval_loss": 0.3052562177181244,
|
| 297 |
+
"eval_runtime": 29.2874,
|
| 298 |
+
"eval_samples_per_second": 4.951,
|
| 299 |
+
"eval_steps_per_second": 4.951,
|
| 300 |
+
"step": 1619
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 19.02,
|
| 304 |
+
"learning_rate": 2.134419551934827e-05,
|
| 305 |
+
"loss": 0.0553,
|
| 306 |
+
"step": 1680
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 19.03,
|
| 310 |
+
"eval_accuracy": 0.9241379310344827,
|
| 311 |
+
"eval_loss": 0.3443007469177246,
|
| 312 |
+
"eval_runtime": 30.1383,
|
| 313 |
+
"eval_samples_per_second": 4.811,
|
| 314 |
+
"eval_steps_per_second": 4.811,
|
| 315 |
+
"step": 1705
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 20.02,
|
| 319 |
+
"learning_rate": 1.9714867617107944e-05,
|
| 320 |
+
"loss": 0.0301,
|
| 321 |
+
"step": 1760
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 20.03,
|
| 325 |
+
"eval_accuracy": 0.9586206896551724,
|
| 326 |
+
"eval_loss": 0.1426996886730194,
|
| 327 |
+
"eval_runtime": 29.78,
|
| 328 |
+
"eval_samples_per_second": 4.869,
|
| 329 |
+
"eval_steps_per_second": 4.869,
|
| 330 |
+
"step": 1790
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 21.02,
|
| 334 |
+
"learning_rate": 1.808553971486762e-05,
|
| 335 |
+
"loss": 0.0412,
|
| 336 |
+
"step": 1840
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 21.03,
|
| 340 |
+
"eval_accuracy": 0.8689655172413793,
|
| 341 |
+
"eval_loss": 0.5618650317192078,
|
| 342 |
+
"eval_runtime": 29.9124,
|
| 343 |
+
"eval_samples_per_second": 4.847,
|
| 344 |
+
"eval_steps_per_second": 4.847,
|
| 345 |
+
"step": 1875
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 22.02,
|
| 349 |
+
"learning_rate": 1.6456211812627292e-05,
|
| 350 |
+
"loss": 0.0492,
|
| 351 |
+
"step": 1920
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 22.03,
|
| 355 |
+
"eval_accuracy": 0.8896551724137931,
|
| 356 |
+
"eval_loss": 0.5700664520263672,
|
| 357 |
+
"eval_runtime": 27.7486,
|
| 358 |
+
"eval_samples_per_second": 5.225,
|
| 359 |
+
"eval_steps_per_second": 5.225,
|
| 360 |
+
"step": 1960
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 23.01,
|
| 364 |
+
"learning_rate": 1.4826883910386965e-05,
|
| 365 |
+
"loss": 0.0171,
|
| 366 |
+
"step": 2000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 23.03,
|
| 370 |
+
"eval_accuracy": 0.8689655172413793,
|
| 371 |
+
"eval_loss": 0.6377372145652771,
|
| 372 |
+
"eval_runtime": 29.1792,
|
| 373 |
+
"eval_samples_per_second": 4.969,
|
| 374 |
+
"eval_steps_per_second": 4.969,
|
| 375 |
+
"step": 2046
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 24.01,
|
| 379 |
+
"learning_rate": 1.3197556008146641e-05,
|
| 380 |
+
"loss": 0.0181,
|
| 381 |
+
"step": 2080
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 24.03,
|
| 385 |
+
"eval_accuracy": 0.8827586206896552,
|
| 386 |
+
"eval_loss": 0.5981259346008301,
|
| 387 |
+
"eval_runtime": 30.3638,
|
| 388 |
+
"eval_samples_per_second": 4.775,
|
| 389 |
+
"eval_steps_per_second": 4.775,
|
| 390 |
+
"step": 2131
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 25.01,
|
| 394 |
+
"learning_rate": 1.1568228105906315e-05,
|
| 395 |
+
"loss": 0.0305,
|
| 396 |
+
"step": 2160
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 25.03,
|
| 400 |
+
"eval_accuracy": 0.9448275862068966,
|
| 401 |
+
"eval_loss": 0.3177809715270996,
|
| 402 |
+
"eval_runtime": 30.2408,
|
| 403 |
+
"eval_samples_per_second": 4.795,
|
| 404 |
+
"eval_steps_per_second": 4.795,
|
| 405 |
+
"step": 2216
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 26.01,
|
| 409 |
+
"learning_rate": 9.938900203665988e-06,
|
| 410 |
+
"loss": 0.0393,
|
| 411 |
+
"step": 2240
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 26.03,
|
| 415 |
+
"eval_accuracy": 0.9103448275862069,
|
| 416 |
+
"eval_loss": 0.5434169173240662,
|
| 417 |
+
"eval_runtime": 29.452,
|
| 418 |
+
"eval_samples_per_second": 4.923,
|
| 419 |
+
"eval_steps_per_second": 4.923,
|
| 420 |
+
"step": 2301
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 27.01,
|
| 424 |
+
"learning_rate": 8.309572301425662e-06,
|
| 425 |
+
"loss": 0.0248,
|
| 426 |
+
"step": 2320
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 27.03,
|
| 430 |
+
"eval_accuracy": 0.9241379310344827,
|
| 431 |
+
"eval_loss": 0.40973013639450073,
|
| 432 |
+
"eval_runtime": 30.9246,
|
| 433 |
+
"eval_samples_per_second": 4.689,
|
| 434 |
+
"eval_steps_per_second": 4.689,
|
| 435 |
+
"step": 2387
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 28.0,
|
| 439 |
+
"learning_rate": 6.6802443991853366e-06,
|
| 440 |
+
"loss": 0.0146,
|
| 441 |
+
"step": 2400
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 28.03,
|
| 445 |
+
"eval_accuracy": 0.9103448275862069,
|
| 446 |
+
"eval_loss": 0.44273480772972107,
|
| 447 |
+
"eval_runtime": 29.0928,
|
| 448 |
+
"eval_samples_per_second": 4.984,
|
| 449 |
+
"eval_steps_per_second": 4.984,
|
| 450 |
+
"step": 2472
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 29.0,
|
| 454 |
+
"learning_rate": 5.05091649694501e-06,
|
| 455 |
+
"loss": 0.012,
|
| 456 |
+
"step": 2480
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 29.03,
|
| 460 |
+
"eval_accuracy": 0.903448275862069,
|
| 461 |
+
"eval_loss": 0.5618546605110168,
|
| 462 |
+
"eval_runtime": 29.5423,
|
| 463 |
+
"eval_samples_per_second": 4.908,
|
| 464 |
+
"eval_steps_per_second": 4.908,
|
| 465 |
+
"step": 2557
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 30.0,
|
| 469 |
+
"learning_rate": 3.4215885947046847e-06,
|
| 470 |
+
"loss": 0.0036,
|
| 471 |
+
"step": 2560
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 30.03,
|
| 475 |
+
"learning_rate": 1.7922606924643586e-06,
|
| 476 |
+
"loss": 0.0065,
|
| 477 |
+
"step": 2640
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 30.03,
|
| 481 |
+
"eval_accuracy": 0.9103448275862069,
|
| 482 |
+
"eval_loss": 0.5383774042129517,
|
| 483 |
+
"eval_runtime": 30.5686,
|
| 484 |
+
"eval_samples_per_second": 4.743,
|
| 485 |
+
"eval_steps_per_second": 4.743,
|
| 486 |
+
"step": 2642
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 31.03,
|
| 490 |
+
"learning_rate": 1.629327902240326e-07,
|
| 491 |
+
"loss": 0.009,
|
| 492 |
+
"step": 2720
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 31.03,
|
| 496 |
+
"eval_accuracy": 0.9172413793103448,
|
| 497 |
+
"eval_loss": 0.5013585686683655,
|
| 498 |
+
"eval_runtime": 30.4753,
|
| 499 |
+
"eval_samples_per_second": 4.758,
|
| 500 |
+
"eval_steps_per_second": 4.758,
|
| 501 |
+
"step": 2728
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 31.03,
|
| 505 |
+
"step": 2728,
|
| 506 |
+
"total_flos": 2.719508368433401e+19,
|
| 507 |
+
"train_loss": 0.20195167288498247,
|
| 508 |
+
"train_runtime": 11757.4892,
|
| 509 |
+
"train_samples_per_second": 1.856,
|
| 510 |
+
"train_steps_per_second": 0.232
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 31.03,
|
| 514 |
+
"eval_accuracy": 0.9470198675496688,
|
| 515 |
+
"eval_loss": 0.2553568482398987,
|
| 516 |
+
"eval_runtime": 163.4914,
|
| 517 |
+
"eval_samples_per_second": 0.924,
|
| 518 |
+
"eval_steps_per_second": 0.924,
|
| 519 |
+
"step": 2728
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 31.03,
|
| 523 |
+
"eval_accuracy": 0.9470198675496688,
|
| 524 |
+
"eval_loss": 0.2553568482398987,
|
| 525 |
+
"eval_runtime": 31.773,
|
| 526 |
+
"eval_samples_per_second": 4.752,
|
| 527 |
+
"eval_steps_per_second": 4.752,
|
| 528 |
+
"step": 2728
|
| 529 |
+
}
|
| 530 |
+
],
|
| 531 |
+
"logging_steps": 80,
|
| 532 |
+
"max_steps": 2728,
|
| 533 |
+
"num_train_epochs": 9223372036854775807,
|
| 534 |
+
"save_steps": 500,
|
| 535 |
+
"total_flos": 2.719508368433401e+19,
|
| 536 |
+
"trial_name": null,
|
| 537 |
+
"trial_params": null
|
| 538 |
+
}
|