End of training
Browse files- all_results.json +16 -0
- eval_results.json +11 -0
- train_results.json +8 -0
- trainer_state.json +271 -0
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.99,
|
| 3 |
+
"eval_accuracy": 0.9613120269133726,
|
| 4 |
+
"eval_f1": 0.9613120269133726,
|
| 5 |
+
"eval_loss": 0.1092575266957283,
|
| 6 |
+
"eval_precision": 0.9613120269133726,
|
| 7 |
+
"eval_recall": 0.9613120269133726,
|
| 8 |
+
"eval_runtime": 58.2407,
|
| 9 |
+
"eval_samples_per_second": 20.415,
|
| 10 |
+
"eval_steps_per_second": 0.652,
|
| 11 |
+
"total_flos": 1.061932048026071e+18,
|
| 12 |
+
"train_loss": 0.4249281358108463,
|
| 13 |
+
"train_runtime": 6173.988,
|
| 14 |
+
"train_samples_per_second": 6.932,
|
| 15 |
+
"train_steps_per_second": 0.054
|
| 16 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.99,
|
| 3 |
+
"eval_accuracy": 0.9613120269133726,
|
| 4 |
+
"eval_f1": 0.9613120269133726,
|
| 5 |
+
"eval_loss": 0.1092575266957283,
|
| 6 |
+
"eval_precision": 0.9613120269133726,
|
| 7 |
+
"eval_recall": 0.9613120269133726,
|
| 8 |
+
"eval_runtime": 58.2407,
|
| 9 |
+
"eval_samples_per_second": 20.415,
|
| 10 |
+
"eval_steps_per_second": 0.652
|
| 11 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.99,
|
| 3 |
+
"total_flos": 1.061932048026071e+18,
|
| 4 |
+
"train_loss": 0.4249281358108463,
|
| 5 |
+
"train_runtime": 6173.988,
|
| 6 |
+
"train_samples_per_second": 6.932,
|
| 7 |
+
"train_steps_per_second": 0.054
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9613120269133726,
|
| 3 |
+
"best_model_checkpoint": "Brain_Tumor_Classification/checkpoint-332",
|
| 4 |
+
"epoch": 3.991044776119403,
|
| 5 |
+
"global_step": 332,
|
| 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": 1.4705882352941177e-05,
|
| 13 |
+
"loss": 1.4267,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.24,
|
| 18 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 19 |
+
"loss": 1.2467,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.36,
|
| 24 |
+
"learning_rate": 4.411764705882353e-05,
|
| 25 |
+
"loss": 1.0154,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.48,
|
| 30 |
+
"learning_rate": 4.8993288590604034e-05,
|
| 31 |
+
"loss": 0.709,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.6,
|
| 36 |
+
"learning_rate": 4.731543624161074e-05,
|
| 37 |
+
"loss": 0.604,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.72,
|
| 42 |
+
"learning_rate": 4.5637583892617453e-05,
|
| 43 |
+
"loss": 0.5955,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.84,
|
| 48 |
+
"learning_rate": 4.395973154362416e-05,
|
| 49 |
+
"loss": 0.485,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.96,
|
| 54 |
+
"learning_rate": 4.228187919463087e-05,
|
| 55 |
+
"loss": 0.4369,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.99,
|
| 60 |
+
"eval_accuracy": 0.9091673675357443,
|
| 61 |
+
"eval_f1": 0.9091673675357443,
|
| 62 |
+
"eval_loss": 0.2500155568122864,
|
| 63 |
+
"eval_precision": 0.9091673675357443,
|
| 64 |
+
"eval_recall": 0.9091673675357443,
|
| 65 |
+
"eval_runtime": 64.8347,
|
| 66 |
+
"eval_samples_per_second": 18.339,
|
| 67 |
+
"eval_steps_per_second": 0.586,
|
| 68 |
+
"step": 83
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.08,
|
| 72 |
+
"learning_rate": 4.060402684563759e-05,
|
| 73 |
+
"loss": 0.4492,
|
| 74 |
+
"step": 90
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.2,
|
| 78 |
+
"learning_rate": 3.89261744966443e-05,
|
| 79 |
+
"loss": 0.3878,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.32,
|
| 84 |
+
"learning_rate": 3.724832214765101e-05,
|
| 85 |
+
"loss": 0.3951,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.44,
|
| 90 |
+
"learning_rate": 3.557046979865772e-05,
|
| 91 |
+
"loss": 0.3708,
|
| 92 |
+
"step": 120
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.56,
|
| 96 |
+
"learning_rate": 3.389261744966443e-05,
|
| 97 |
+
"loss": 0.342,
|
| 98 |
+
"step": 130
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.68,
|
| 102 |
+
"learning_rate": 3.221476510067114e-05,
|
| 103 |
+
"loss": 0.3343,
|
| 104 |
+
"step": 140
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.8,
|
| 108 |
+
"learning_rate": 3.0536912751677856e-05,
|
| 109 |
+
"loss": 0.314,
|
| 110 |
+
"step": 150
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.92,
|
| 114 |
+
"learning_rate": 2.885906040268457e-05,
|
| 115 |
+
"loss": 0.3777,
|
| 116 |
+
"step": 160
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.99,
|
| 120 |
+
"eval_accuracy": 0.9301934398654331,
|
| 121 |
+
"eval_f1": 0.9301934398654331,
|
| 122 |
+
"eval_loss": 0.17629508674144745,
|
| 123 |
+
"eval_precision": 0.9301934398654331,
|
| 124 |
+
"eval_recall": 0.9301934398654331,
|
| 125 |
+
"eval_runtime": 69.6074,
|
| 126 |
+
"eval_samples_per_second": 17.082,
|
| 127 |
+
"eval_steps_per_second": 0.546,
|
| 128 |
+
"step": 166
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.05,
|
| 132 |
+
"learning_rate": 2.7181208053691276e-05,
|
| 133 |
+
"loss": 0.3736,
|
| 134 |
+
"step": 170
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.17,
|
| 138 |
+
"learning_rate": 2.550335570469799e-05,
|
| 139 |
+
"loss": 0.3141,
|
| 140 |
+
"step": 180
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.29,
|
| 144 |
+
"learning_rate": 2.38255033557047e-05,
|
| 145 |
+
"loss": 0.3334,
|
| 146 |
+
"step": 190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.41,
|
| 150 |
+
"learning_rate": 2.2147651006711412e-05,
|
| 151 |
+
"loss": 0.3104,
|
| 152 |
+
"step": 200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.53,
|
| 156 |
+
"learning_rate": 2.0469798657718122e-05,
|
| 157 |
+
"loss": 0.266,
|
| 158 |
+
"step": 210
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.64,
|
| 162 |
+
"learning_rate": 1.8791946308724835e-05,
|
| 163 |
+
"loss": 0.2586,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.76,
|
| 168 |
+
"learning_rate": 1.7114093959731545e-05,
|
| 169 |
+
"loss": 0.2747,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.88,
|
| 174 |
+
"learning_rate": 1.5436241610738255e-05,
|
| 175 |
+
"loss": 0.2684,
|
| 176 |
+
"step": 240
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.99,
|
| 180 |
+
"eval_accuracy": 0.9512195121951219,
|
| 181 |
+
"eval_f1": 0.9512195121951219,
|
| 182 |
+
"eval_loss": 0.12147016078233719,
|
| 183 |
+
"eval_precision": 0.9512195121951219,
|
| 184 |
+
"eval_recall": 0.9512195121951219,
|
| 185 |
+
"eval_runtime": 62.5572,
|
| 186 |
+
"eval_samples_per_second": 19.007,
|
| 187 |
+
"eval_steps_per_second": 0.607,
|
| 188 |
+
"step": 249
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.01,
|
| 192 |
+
"learning_rate": 1.3758389261744966e-05,
|
| 193 |
+
"loss": 0.2589,
|
| 194 |
+
"step": 250
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.13,
|
| 198 |
+
"learning_rate": 1.208053691275168e-05,
|
| 199 |
+
"loss": 0.2467,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.25,
|
| 204 |
+
"learning_rate": 1.040268456375839e-05,
|
| 205 |
+
"loss": 0.2406,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.37,
|
| 210 |
+
"learning_rate": 8.724832214765101e-06,
|
| 211 |
+
"loss": 0.2289,
|
| 212 |
+
"step": 280
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.49,
|
| 216 |
+
"learning_rate": 7.046979865771812e-06,
|
| 217 |
+
"loss": 0.2812,
|
| 218 |
+
"step": 290
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.61,
|
| 222 |
+
"learning_rate": 5.3691275167785235e-06,
|
| 223 |
+
"loss": 0.2478,
|
| 224 |
+
"step": 300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.73,
|
| 228 |
+
"learning_rate": 3.6912751677852355e-06,
|
| 229 |
+
"loss": 0.2235,
|
| 230 |
+
"step": 310
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.85,
|
| 234 |
+
"learning_rate": 2.013422818791946e-06,
|
| 235 |
+
"loss": 0.207,
|
| 236 |
+
"step": 320
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.97,
|
| 240 |
+
"learning_rate": 3.355704697986577e-07,
|
| 241 |
+
"loss": 0.2363,
|
| 242 |
+
"step": 330
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.99,
|
| 246 |
+
"eval_accuracy": 0.9613120269133726,
|
| 247 |
+
"eval_f1": 0.9613120269133726,
|
| 248 |
+
"eval_loss": 0.1092575266957283,
|
| 249 |
+
"eval_precision": 0.9613120269133726,
|
| 250 |
+
"eval_recall": 0.9613120269133726,
|
| 251 |
+
"eval_runtime": 64.3459,
|
| 252 |
+
"eval_samples_per_second": 18.478,
|
| 253 |
+
"eval_steps_per_second": 0.591,
|
| 254 |
+
"step": 332
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.99,
|
| 258 |
+
"step": 332,
|
| 259 |
+
"total_flos": 1.061932048026071e+18,
|
| 260 |
+
"train_loss": 0.4249281358108463,
|
| 261 |
+
"train_runtime": 6173.988,
|
| 262 |
+
"train_samples_per_second": 6.932,
|
| 263 |
+
"train_steps_per_second": 0.054
|
| 264 |
+
}
|
| 265 |
+
],
|
| 266 |
+
"max_steps": 332,
|
| 267 |
+
"num_train_epochs": 4,
|
| 268 |
+
"total_flos": 1.061932048026071e+18,
|
| 269 |
+
"trial_name": null,
|
| 270 |
+
"trial_params": null
|
| 271 |
+
}
|