End of training
Browse files- all_results.json +8 -0
- test_results.json +8 -0
- trainer_state.json +229 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.00044166212319396436,
|
| 5 |
+
"eval_runtime": 23.3044,
|
| 6 |
+
"eval_samples_per_second": 0.901,
|
| 7 |
+
"eval_steps_per_second": 0.257
|
| 8 |
+
}
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.00044166212319396436,
|
| 5 |
+
"eval_runtime": 23.3044,
|
| 6 |
+
"eval_samples_per_second": 0.901,
|
| 7 |
+
"eval_steps_per_second": 0.257
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-OKN-Test-V15\\checkpoint-92",
|
| 4 |
+
"epoch": 4.2,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 230,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 2.173913043478261e-05,
|
| 14 |
+
"loss": 0.6817,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.09,
|
| 19 |
+
"learning_rate": 4.347826086956522e-05,
|
| 20 |
+
"loss": 0.447,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.13,
|
| 25 |
+
"learning_rate": 4.830917874396135e-05,
|
| 26 |
+
"loss": 0.4195,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.17,
|
| 31 |
+
"learning_rate": 4.589371980676328e-05,
|
| 32 |
+
"loss": 0.465,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.2,
|
| 37 |
+
"eval_accuracy": 0.9047619047619048,
|
| 38 |
+
"eval_loss": 0.1457657516002655,
|
| 39 |
+
"eval_runtime": 22.0681,
|
| 40 |
+
"eval_samples_per_second": 0.952,
|
| 41 |
+
"eval_steps_per_second": 0.272,
|
| 42 |
+
"step": 46
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.02,
|
| 46 |
+
"learning_rate": 4.347826086956522e-05,
|
| 47 |
+
"loss": 0.2322,
|
| 48 |
+
"step": 50
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.06,
|
| 52 |
+
"learning_rate": 4.106280193236715e-05,
|
| 53 |
+
"loss": 0.0717,
|
| 54 |
+
"step": 60
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.1,
|
| 58 |
+
"learning_rate": 3.864734299516908e-05,
|
| 59 |
+
"loss": 0.0103,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.15,
|
| 64 |
+
"learning_rate": 3.6231884057971014e-05,
|
| 65 |
+
"loss": 0.001,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.19,
|
| 70 |
+
"learning_rate": 3.381642512077295e-05,
|
| 71 |
+
"loss": 0.0115,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.2,
|
| 76 |
+
"eval_accuracy": 1.0,
|
| 77 |
+
"eval_loss": 0.00043274767813272774,
|
| 78 |
+
"eval_runtime": 24.9569,
|
| 79 |
+
"eval_samples_per_second": 0.841,
|
| 80 |
+
"eval_steps_per_second": 0.24,
|
| 81 |
+
"step": 92
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.03,
|
| 85 |
+
"learning_rate": 3.140096618357488e-05,
|
| 86 |
+
"loss": 0.0004,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.08,
|
| 91 |
+
"learning_rate": 2.8985507246376814e-05,
|
| 92 |
+
"loss": 0.0004,
|
| 93 |
+
"step": 110
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.12,
|
| 97 |
+
"learning_rate": 2.6570048309178748e-05,
|
| 98 |
+
"loss": 0.0025,
|
| 99 |
+
"step": 120
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.17,
|
| 103 |
+
"learning_rate": 2.4154589371980676e-05,
|
| 104 |
+
"loss": 0.17,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.2,
|
| 109 |
+
"eval_accuracy": 0.9523809523809523,
|
| 110 |
+
"eval_loss": 0.09127208590507507,
|
| 111 |
+
"eval_runtime": 23.3382,
|
| 112 |
+
"eval_samples_per_second": 0.9,
|
| 113 |
+
"eval_steps_per_second": 0.257,
|
| 114 |
+
"step": 138
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.01,
|
| 118 |
+
"learning_rate": 2.173913043478261e-05,
|
| 119 |
+
"loss": 0.0005,
|
| 120 |
+
"step": 140
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.05,
|
| 124 |
+
"learning_rate": 1.932367149758454e-05,
|
| 125 |
+
"loss": 0.0004,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.1,
|
| 130 |
+
"learning_rate": 1.6908212560386476e-05,
|
| 131 |
+
"loss": 0.0004,
|
| 132 |
+
"step": 160
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 3.14,
|
| 136 |
+
"learning_rate": 1.4492753623188407e-05,
|
| 137 |
+
"loss": 0.0003,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 3.18,
|
| 142 |
+
"learning_rate": 1.2077294685990338e-05,
|
| 143 |
+
"loss": 0.0652,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.2,
|
| 148 |
+
"eval_accuracy": 1.0,
|
| 149 |
+
"eval_loss": 0.0002443942066747695,
|
| 150 |
+
"eval_runtime": 22.9752,
|
| 151 |
+
"eval_samples_per_second": 0.914,
|
| 152 |
+
"eval_steps_per_second": 0.261,
|
| 153 |
+
"step": 184
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.03,
|
| 157 |
+
"learning_rate": 9.66183574879227e-06,
|
| 158 |
+
"loss": 0.0003,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.07,
|
| 163 |
+
"learning_rate": 7.246376811594203e-06,
|
| 164 |
+
"loss": 0.0003,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.11,
|
| 169 |
+
"learning_rate": 4.830917874396135e-06,
|
| 170 |
+
"loss": 0.0002,
|
| 171 |
+
"step": 210
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 4.16,
|
| 175 |
+
"learning_rate": 2.4154589371980677e-06,
|
| 176 |
+
"loss": 0.0002,
|
| 177 |
+
"step": 220
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 4.2,
|
| 181 |
+
"learning_rate": 0.0,
|
| 182 |
+
"loss": 0.0002,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.2,
|
| 187 |
+
"eval_accuracy": 1.0,
|
| 188 |
+
"eval_loss": 0.00022312559303827584,
|
| 189 |
+
"eval_runtime": 24.2112,
|
| 190 |
+
"eval_samples_per_second": 0.867,
|
| 191 |
+
"eval_steps_per_second": 0.248,
|
| 192 |
+
"step": 230
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 4.2,
|
| 196 |
+
"step": 230,
|
| 197 |
+
"total_flos": 1.1463794223140045e+18,
|
| 198 |
+
"train_loss": 0.11223210689166317,
|
| 199 |
+
"train_runtime": 2573.7407,
|
| 200 |
+
"train_samples_per_second": 0.357,
|
| 201 |
+
"train_steps_per_second": 0.089
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 4.2,
|
| 205 |
+
"eval_accuracy": 1.0,
|
| 206 |
+
"eval_loss": 0.00043274767813272774,
|
| 207 |
+
"eval_runtime": 23.6483,
|
| 208 |
+
"eval_samples_per_second": 0.888,
|
| 209 |
+
"eval_steps_per_second": 0.254,
|
| 210 |
+
"step": 230
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 4.2,
|
| 214 |
+
"eval_accuracy": 1.0,
|
| 215 |
+
"eval_loss": 0.00044166212319396436,
|
| 216 |
+
"eval_runtime": 23.3044,
|
| 217 |
+
"eval_samples_per_second": 0.901,
|
| 218 |
+
"eval_steps_per_second": 0.257,
|
| 219 |
+
"step": 230
|
| 220 |
+
}
|
| 221 |
+
],
|
| 222 |
+
"logging_steps": 10,
|
| 223 |
+
"max_steps": 230,
|
| 224 |
+
"num_train_epochs": 9223372036854775807,
|
| 225 |
+
"save_steps": 500,
|
| 226 |
+
"total_flos": 1.1463794223140045e+18,
|
| 227 |
+
"trial_name": null,
|
| 228 |
+
"trial_params": null
|
| 229 |
+
}
|