End of training
Browse files- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +300 -0
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.0,
|
| 3 |
+
"total_flos": 5.459952374908416e+16,
|
| 4 |
+
"train_loss": 0.15556327351158078,
|
| 5 |
+
"train_runtime": 746.2434,
|
| 6 |
+
"train_samples": 10995,
|
| 7 |
+
"train_samples_per_second": 294.676,
|
| 8 |
+
"train_steps_per_second": 2.305
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.0,
|
| 3 |
+
"total_flos": 5.459952374908416e+16,
|
| 4 |
+
"train_loss": 0.15556327351158078,
|
| 5 |
+
"train_runtime": 746.2434,
|
| 6 |
+
"train_samples": 10995,
|
| 7 |
+
"train_samples_per_second": 294.676,
|
| 8 |
+
"train_steps_per_second": 2.305
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6313058518304987,
|
| 3 |
+
"best_model_checkpoint": "logs/indian_ner/roberta-base/seed_1/checkpoint-1376",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1634,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.7997455985661011,
|
| 14 |
+
"eval_f1": 0.14692321878650028,
|
| 15 |
+
"eval_loss": 0.35509759187698364,
|
| 16 |
+
"eval_precision": 0.08916579614982838,
|
| 17 |
+
"eval_recall": 0.41710296684118675,
|
| 18 |
+
"eval_runtime": 3.1945,
|
| 19 |
+
"eval_samples_per_second": 336.207,
|
| 20 |
+
"eval_steps_per_second": 2.817,
|
| 21 |
+
"step": 86
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.0,
|
| 25 |
+
"eval_accuracy": 0.8326539658678076,
|
| 26 |
+
"eval_f1": 0.2069869669160176,
|
| 27 |
+
"eval_loss": 0.23829466104507446,
|
| 28 |
+
"eval_precision": 0.1328449811918432,
|
| 29 |
+
"eval_recall": 0.46841186736474694,
|
| 30 |
+
"eval_runtime": 3.449,
|
| 31 |
+
"eval_samples_per_second": 311.39,
|
| 32 |
+
"eval_steps_per_second": 2.609,
|
| 33 |
+
"step": 172
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.8921588467134997,
|
| 38 |
+
"eval_f1": 0.29748962245503063,
|
| 39 |
+
"eval_loss": 0.21593649685382843,
|
| 40 |
+
"eval_precision": 0.20750034468495795,
|
| 41 |
+
"eval_recall": 0.525305410122164,
|
| 42 |
+
"eval_runtime": 2.5646,
|
| 43 |
+
"eval_samples_per_second": 418.778,
|
| 44 |
+
"eval_steps_per_second": 3.509,
|
| 45 |
+
"step": 258
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 4.0,
|
| 49 |
+
"eval_accuracy": 0.902517996010523,
|
| 50 |
+
"eval_f1": 0.325260250690461,
|
| 51 |
+
"eval_loss": 0.2013314664363861,
|
| 52 |
+
"eval_precision": 0.23377614903038632,
|
| 53 |
+
"eval_recall": 0.5343804537521815,
|
| 54 |
+
"eval_runtime": 2.5624,
|
| 55 |
+
"eval_samples_per_second": 419.138,
|
| 56 |
+
"eval_steps_per_second": 3.512,
|
| 57 |
+
"step": 344
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 5.0,
|
| 61 |
+
"eval_accuracy": 0.9131180557563142,
|
| 62 |
+
"eval_f1": 0.3645869640989892,
|
| 63 |
+
"eval_loss": 0.1926085650920868,
|
| 64 |
+
"eval_precision": 0.27324973876698017,
|
| 65 |
+
"eval_recall": 0.5476439790575917,
|
| 66 |
+
"eval_runtime": 2.6037,
|
| 67 |
+
"eval_samples_per_second": 412.492,
|
| 68 |
+
"eval_steps_per_second": 3.457,
|
| 69 |
+
"step": 430
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.813953488372093,
|
| 73 |
+
"grad_norm": 3.6987311840057373,
|
| 74 |
+
"learning_rate": 2.1313953488372093e-05,
|
| 75 |
+
"loss": 0.396,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 6.0,
|
| 80 |
+
"eval_accuracy": 0.9134071482948358,
|
| 81 |
+
"eval_f1": 0.37776752767527666,
|
| 82 |
+
"eval_loss": 0.20021429657936096,
|
| 83 |
+
"eval_precision": 0.28207335973824693,
|
| 84 |
+
"eval_recall": 0.5717277486910994,
|
| 85 |
+
"eval_runtime": 6.6862,
|
| 86 |
+
"eval_samples_per_second": 160.629,
|
| 87 |
+
"eval_steps_per_second": 1.346,
|
| 88 |
+
"step": 516
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 7.0,
|
| 92 |
+
"eval_accuracy": 0.9267054050668285,
|
| 93 |
+
"eval_f1": 0.440271772699197,
|
| 94 |
+
"eval_loss": 0.21028228104114532,
|
| 95 |
+
"eval_precision": 0.3407265774378585,
|
| 96 |
+
"eval_recall": 0.6219895287958115,
|
| 97 |
+
"eval_runtime": 2.6496,
|
| 98 |
+
"eval_samples_per_second": 405.343,
|
| 99 |
+
"eval_steps_per_second": 3.397,
|
| 100 |
+
"step": 602
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.0,
|
| 104 |
+
"eval_accuracy": 0.9255972170024959,
|
| 105 |
+
"eval_f1": 0.4397892931520274,
|
| 106 |
+
"eval_loss": 0.1943674236536026,
|
| 107 |
+
"eval_precision": 0.33880709701774253,
|
| 108 |
+
"eval_recall": 0.6265270506108203,
|
| 109 |
+
"eval_runtime": 2.5685,
|
| 110 |
+
"eval_samples_per_second": 418.146,
|
| 111 |
+
"eval_steps_per_second": 3.504,
|
| 112 |
+
"step": 688
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 9.0,
|
| 116 |
+
"eval_accuracy": 0.9290759638827055,
|
| 117 |
+
"eval_f1": 0.4493577075098814,
|
| 118 |
+
"eval_loss": 0.21183457970619202,
|
| 119 |
+
"eval_precision": 0.3477346587650545,
|
| 120 |
+
"eval_recall": 0.6349040139616056,
|
| 121 |
+
"eval_runtime": 6.3809,
|
| 122 |
+
"eval_samples_per_second": 168.314,
|
| 123 |
+
"eval_steps_per_second": 1.41,
|
| 124 |
+
"step": 774
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 10.0,
|
| 128 |
+
"eval_accuracy": 0.9396182051207925,
|
| 129 |
+
"eval_f1": 0.5092445853143158,
|
| 130 |
+
"eval_loss": 0.22744828462600708,
|
| 131 |
+
"eval_precision": 0.4096027193541534,
|
| 132 |
+
"eval_recall": 0.6729493891797557,
|
| 133 |
+
"eval_runtime": 2.6036,
|
| 134 |
+
"eval_samples_per_second": 412.506,
|
| 135 |
+
"eval_steps_per_second": 3.457,
|
| 136 |
+
"step": 860
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 11.0,
|
| 140 |
+
"eval_accuracy": 0.9450338720090968,
|
| 141 |
+
"eval_f1": 0.5512627986348123,
|
| 142 |
+
"eval_loss": 0.23177774250507355,
|
| 143 |
+
"eval_precision": 0.45269058295964126,
|
| 144 |
+
"eval_recall": 0.7047120418848167,
|
| 145 |
+
"eval_runtime": 2.5671,
|
| 146 |
+
"eval_samples_per_second": 418.363,
|
| 147 |
+
"eval_steps_per_second": 3.506,
|
| 148 |
+
"step": 946
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.627906976744185,
|
| 152 |
+
"grad_norm": 2.9459869861602783,
|
| 153 |
+
"learning_rate": 1.2593023255813954e-05,
|
| 154 |
+
"loss": 0.0715,
|
| 155 |
+
"step": 1000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 12.0,
|
| 159 |
+
"eval_accuracy": 0.9442533221550885,
|
| 160 |
+
"eval_f1": 0.541422935655013,
|
| 161 |
+
"eval_loss": 0.2438974231481552,
|
| 162 |
+
"eval_precision": 0.44360231832367364,
|
| 163 |
+
"eval_recall": 0.6945898778359512,
|
| 164 |
+
"eval_runtime": 2.5676,
|
| 165 |
+
"eval_samples_per_second": 418.287,
|
| 166 |
+
"eval_steps_per_second": 3.505,
|
| 167 |
+
"step": 1032
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 13.0,
|
| 171 |
+
"eval_accuracy": 0.9460360594759716,
|
| 172 |
+
"eval_f1": 0.5802113352545629,
|
| 173 |
+
"eval_loss": 0.2385331243276596,
|
| 174 |
+
"eval_precision": 0.47806422433288104,
|
| 175 |
+
"eval_recall": 0.737870855148342,
|
| 176 |
+
"eval_runtime": 2.5597,
|
| 177 |
+
"eval_samples_per_second": 419.581,
|
| 178 |
+
"eval_steps_per_second": 3.516,
|
| 179 |
+
"step": 1118
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 14.0,
|
| 183 |
+
"eval_accuracy": 0.9460071502221195,
|
| 184 |
+
"eval_f1": 0.5560439560439561,
|
| 185 |
+
"eval_loss": 0.24203675985336304,
|
| 186 |
+
"eval_precision": 0.45843714609286523,
|
| 187 |
+
"eval_recall": 0.706457242582897,
|
| 188 |
+
"eval_runtime": 2.5735,
|
| 189 |
+
"eval_samples_per_second": 417.328,
|
| 190 |
+
"eval_steps_per_second": 3.497,
|
| 191 |
+
"step": 1204
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 15.0,
|
| 195 |
+
"eval_accuracy": 0.9501604463588795,
|
| 196 |
+
"eval_f1": 0.5943502824858757,
|
| 197 |
+
"eval_loss": 0.245487779378891,
|
| 198 |
+
"eval_precision": 0.4991696322657177,
|
| 199 |
+
"eval_recall": 0.7343804537521815,
|
| 200 |
+
"eval_runtime": 2.5639,
|
| 201 |
+
"eval_samples_per_second": 418.898,
|
| 202 |
+
"eval_steps_per_second": 3.51,
|
| 203 |
+
"step": 1290
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 16.0,
|
| 207 |
+
"eval_accuracy": 0.9571950314629046,
|
| 208 |
+
"eval_f1": 0.6313058518304987,
|
| 209 |
+
"eval_loss": 0.25131794810295105,
|
| 210 |
+
"eval_precision": 0.537687208445863,
|
| 211 |
+
"eval_recall": 0.7643979057591623,
|
| 212 |
+
"eval_runtime": 2.5566,
|
| 213 |
+
"eval_samples_per_second": 420.083,
|
| 214 |
+
"eval_steps_per_second": 3.52,
|
| 215 |
+
"step": 1376
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 17.0,
|
| 219 |
+
"eval_accuracy": 0.9557784780241488,
|
| 220 |
+
"eval_f1": 0.6291390728476821,
|
| 221 |
+
"eval_loss": 0.26701298356056213,
|
| 222 |
+
"eval_precision": 0.5354079882381769,
|
| 223 |
+
"eval_recall": 0.7626527050610821,
|
| 224 |
+
"eval_runtime": 2.5575,
|
| 225 |
+
"eval_samples_per_second": 419.947,
|
| 226 |
+
"eval_steps_per_second": 3.519,
|
| 227 |
+
"step": 1462
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 17.441860465116278,
|
| 231 |
+
"grad_norm": 0.8599265813827515,
|
| 232 |
+
"learning_rate": 3.8720930232558145e-06,
|
| 233 |
+
"loss": 0.0344,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 18.0,
|
| 238 |
+
"eval_accuracy": 0.9505266302410068,
|
| 239 |
+
"eval_f1": 0.596600566572238,
|
| 240 |
+
"eval_loss": 0.26870501041412354,
|
| 241 |
+
"eval_precision": 0.5020262216924911,
|
| 242 |
+
"eval_recall": 0.7350785340314137,
|
| 243 |
+
"eval_runtime": 4.3379,
|
| 244 |
+
"eval_samples_per_second": 247.585,
|
| 245 |
+
"eval_steps_per_second": 2.075,
|
| 246 |
+
"step": 1548
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 19.0,
|
| 250 |
+
"eval_accuracy": 0.9547473813034218,
|
| 251 |
+
"eval_f1": 0.619456366237482,
|
| 252 |
+
"eval_loss": 0.2665688395500183,
|
| 253 |
+
"eval_precision": 0.5248484848484849,
|
| 254 |
+
"eval_recall": 0.7556719022687609,
|
| 255 |
+
"eval_runtime": 2.5569,
|
| 256 |
+
"eval_samples_per_second": 420.037,
|
| 257 |
+
"eval_steps_per_second": 3.52,
|
| 258 |
+
"step": 1634
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 19.0,
|
| 262 |
+
"step": 1634,
|
| 263 |
+
"total_flos": 5.459952374908416e+16,
|
| 264 |
+
"train_loss": 0.15556327351158078,
|
| 265 |
+
"train_runtime": 746.2434,
|
| 266 |
+
"train_samples_per_second": 294.676,
|
| 267 |
+
"train_steps_per_second": 2.305
|
| 268 |
+
}
|
| 269 |
+
],
|
| 270 |
+
"logging_steps": 500,
|
| 271 |
+
"max_steps": 1720,
|
| 272 |
+
"num_input_tokens_seen": 0,
|
| 273 |
+
"num_train_epochs": 20,
|
| 274 |
+
"save_steps": 500,
|
| 275 |
+
"stateful_callbacks": {
|
| 276 |
+
"EarlyStoppingCallback": {
|
| 277 |
+
"args": {
|
| 278 |
+
"early_stopping_patience": 3,
|
| 279 |
+
"early_stopping_threshold": 0.0
|
| 280 |
+
},
|
| 281 |
+
"attributes": {
|
| 282 |
+
"early_stopping_patience_counter": 0
|
| 283 |
+
}
|
| 284 |
+
},
|
| 285 |
+
"TrainerControl": {
|
| 286 |
+
"args": {
|
| 287 |
+
"should_epoch_stop": false,
|
| 288 |
+
"should_evaluate": false,
|
| 289 |
+
"should_log": false,
|
| 290 |
+
"should_save": true,
|
| 291 |
+
"should_training_stop": true
|
| 292 |
+
},
|
| 293 |
+
"attributes": {}
|
| 294 |
+
}
|
| 295 |
+
},
|
| 296 |
+
"total_flos": 5.459952374908416e+16,
|
| 297 |
+
"train_batch_size": 128,
|
| 298 |
+
"trial_name": null,
|
| 299 |
+
"trial_params": null
|
| 300 |
+
}
|