End of training
Browse files- all_results.json +17 -0
- eval_results.json +12 -0
- train_results.json +8 -0
- trainer_state.json +229 -0
all_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.9810170943499085,
|
| 4 |
+
"eval_f1": 0.8787752724852317,
|
| 5 |
+
"eval_loss": 0.07104084640741348,
|
| 6 |
+
"eval_precision": 0.8690143162744776,
|
| 7 |
+
"eval_recall": 0.8887579939414338,
|
| 8 |
+
"eval_runtime": 21.7921,
|
| 9 |
+
"eval_samples": 3250,
|
| 10 |
+
"eval_samples_per_second": 149.137,
|
| 11 |
+
"eval_steps_per_second": 4.681,
|
| 12 |
+
"train_loss": 0.15424916956039117,
|
| 13 |
+
"train_runtime": 564.648,
|
| 14 |
+
"train_samples": 14041,
|
| 15 |
+
"train_samples_per_second": 24.867,
|
| 16 |
+
"train_steps_per_second": 0.777
|
| 17 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_accuracy": 0.9810170943499085,
|
| 4 |
+
"eval_f1": 0.8787752724852317,
|
| 5 |
+
"eval_loss": 0.07104084640741348,
|
| 6 |
+
"eval_precision": 0.8690143162744776,
|
| 7 |
+
"eval_recall": 0.8887579939414338,
|
| 8 |
+
"eval_runtime": 21.7921,
|
| 9 |
+
"eval_samples": 3250,
|
| 10 |
+
"eval_samples_per_second": 149.137,
|
| 11 |
+
"eval_steps_per_second": 4.681
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.15424916956039117,
|
| 4 |
+
"train_runtime": 564.648,
|
| 5 |
+
"train_samples": 14041,
|
| 6 |
+
"train_samples_per_second": 24.867,
|
| 7 |
+
"train_steps_per_second": 0.777
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 439,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"eval_accuracy": 0.9002375296912114,
|
| 13 |
+
"eval_f1": 0.3649465750020708,
|
| 14 |
+
"eval_loss": 0.41153180599212646,
|
| 15 |
+
"eval_precision": 0.3593214809982058,
|
| 16 |
+
"eval_recall": 0.37075058902726354,
|
| 17 |
+
"eval_runtime": 22.8743,
|
| 18 |
+
"eval_samples_per_second": 142.081,
|
| 19 |
+
"eval_steps_per_second": 4.459,
|
| 20 |
+
"step": 25
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.11,
|
| 24 |
+
"eval_accuracy": 0.9456407460768662,
|
| 25 |
+
"eval_f1": 0.6618228788245741,
|
| 26 |
+
"eval_loss": 0.22631964087486267,
|
| 27 |
+
"eval_precision": 0.6359968968192398,
|
| 28 |
+
"eval_recall": 0.6898350723662067,
|
| 29 |
+
"eval_runtime": 23.237,
|
| 30 |
+
"eval_samples_per_second": 139.863,
|
| 31 |
+
"eval_steps_per_second": 4.39,
|
| 32 |
+
"step": 50
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.17,
|
| 36 |
+
"eval_accuracy": 0.9564464000623029,
|
| 37 |
+
"eval_f1": 0.7411977624218493,
|
| 38 |
+
"eval_loss": 0.16604465246200562,
|
| 39 |
+
"eval_precision": 0.7249758609591246,
|
| 40 |
+
"eval_recall": 0.7581622349377314,
|
| 41 |
+
"eval_runtime": 22.7549,
|
| 42 |
+
"eval_samples_per_second": 142.827,
|
| 43 |
+
"eval_steps_per_second": 4.483,
|
| 44 |
+
"step": 75
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.23,
|
| 48 |
+
"eval_accuracy": 0.9596783614345236,
|
| 49 |
+
"eval_f1": 0.7599934199703898,
|
| 50 |
+
"eval_loss": 0.1520087569952011,
|
| 51 |
+
"eval_precision": 0.7432432432432432,
|
| 52 |
+
"eval_recall": 0.7775159878828677,
|
| 53 |
+
"eval_runtime": 22.7818,
|
| 54 |
+
"eval_samples_per_second": 142.658,
|
| 55 |
+
"eval_steps_per_second": 4.477,
|
| 56 |
+
"step": 100
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"eval_accuracy": 0.9644873641992134,
|
| 61 |
+
"eval_f1": 0.7887623884019985,
|
| 62 |
+
"eval_loss": 0.13425560295581818,
|
| 63 |
+
"eval_precision": 0.768310196266156,
|
| 64 |
+
"eval_recall": 0.810333221137664,
|
| 65 |
+
"eval_runtime": 23.077,
|
| 66 |
+
"eval_samples_per_second": 140.833,
|
| 67 |
+
"eval_steps_per_second": 4.42,
|
| 68 |
+
"step": 125
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.34,
|
| 72 |
+
"eval_accuracy": 0.9691406097893385,
|
| 73 |
+
"eval_f1": 0.8099378881987578,
|
| 74 |
+
"eval_loss": 0.12516255676746368,
|
| 75 |
+
"eval_precision": 0.7973259416272623,
|
| 76 |
+
"eval_recall": 0.8229552339279704,
|
| 77 |
+
"eval_runtime": 23.4305,
|
| 78 |
+
"eval_samples_per_second": 138.708,
|
| 79 |
+
"eval_steps_per_second": 4.353,
|
| 80 |
+
"step": 150
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.4,
|
| 84 |
+
"eval_accuracy": 0.9723725711615592,
|
| 85 |
+
"eval_f1": 0.8255438828687237,
|
| 86 |
+
"eval_loss": 0.1021428033709526,
|
| 87 |
+
"eval_precision": 0.811778103139743,
|
| 88 |
+
"eval_recall": 0.8397845843150454,
|
| 89 |
+
"eval_runtime": 23.3545,
|
| 90 |
+
"eval_samples_per_second": 139.16,
|
| 91 |
+
"eval_steps_per_second": 4.367,
|
| 92 |
+
"step": 175
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.46,
|
| 96 |
+
"eval_accuracy": 0.9727424944511507,
|
| 97 |
+
"eval_f1": 0.8280318091451293,
|
| 98 |
+
"eval_loss": 0.1055719405412674,
|
| 99 |
+
"eval_precision": 0.8153344208809136,
|
| 100 |
+
"eval_recall": 0.8411309323460114,
|
| 101 |
+
"eval_runtime": 22.8282,
|
| 102 |
+
"eval_samples_per_second": 142.368,
|
| 103 |
+
"eval_steps_per_second": 4.468,
|
| 104 |
+
"step": 200
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.51,
|
| 108 |
+
"eval_accuracy": 0.9754877146528562,
|
| 109 |
+
"eval_f1": 0.8469049983449188,
|
| 110 |
+
"eval_loss": 0.08719248324632645,
|
| 111 |
+
"eval_precision": 0.8331162487788993,
|
| 112 |
+
"eval_recall": 0.8611578593066308,
|
| 113 |
+
"eval_runtime": 22.3515,
|
| 114 |
+
"eval_samples_per_second": 145.404,
|
| 115 |
+
"eval_steps_per_second": 4.563,
|
| 116 |
+
"step": 225
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.57,
|
| 120 |
+
"eval_accuracy": 0.9724893890424827,
|
| 121 |
+
"eval_f1": 0.832071862263994,
|
| 122 |
+
"eval_loss": 0.10552600026130676,
|
| 123 |
+
"eval_precision": 0.8225620786054925,
|
| 124 |
+
"eval_recall": 0.8418041063614945,
|
| 125 |
+
"eval_runtime": 23.3713,
|
| 126 |
+
"eval_samples_per_second": 139.059,
|
| 127 |
+
"eval_steps_per_second": 4.364,
|
| 128 |
+
"step": 250
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.63,
|
| 132 |
+
"eval_accuracy": 0.9767337720493751,
|
| 133 |
+
"eval_f1": 0.8622774605307356,
|
| 134 |
+
"eval_loss": 0.09211930632591248,
|
| 135 |
+
"eval_precision": 0.86054307743882,
|
| 136 |
+
"eval_recall": 0.8640188488724335,
|
| 137 |
+
"eval_runtime": 22.1547,
|
| 138 |
+
"eval_samples_per_second": 146.696,
|
| 139 |
+
"eval_steps_per_second": 4.604,
|
| 140 |
+
"step": 275
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.68,
|
| 144 |
+
"eval_accuracy": 0.9788364939060006,
|
| 145 |
+
"eval_f1": 0.8692250062432365,
|
| 146 |
+
"eval_loss": 0.08241179585456848,
|
| 147 |
+
"eval_precision": 0.8599901169494317,
|
| 148 |
+
"eval_recall": 0.8786603837091889,
|
| 149 |
+
"eval_runtime": 21.7226,
|
| 150 |
+
"eval_samples_per_second": 149.614,
|
| 151 |
+
"eval_steps_per_second": 4.696,
|
| 152 |
+
"step": 300
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.74,
|
| 156 |
+
"eval_accuracy": 0.9787196760250769,
|
| 157 |
+
"eval_f1": 0.8649186856953203,
|
| 158 |
+
"eval_loss": 0.08343011140823364,
|
| 159 |
+
"eval_precision": 0.8530278232405892,
|
| 160 |
+
"eval_recall": 0.877145742174352,
|
| 161 |
+
"eval_runtime": 21.4988,
|
| 162 |
+
"eval_samples_per_second": 151.171,
|
| 163 |
+
"eval_steps_per_second": 4.744,
|
| 164 |
+
"step": 325
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.8,
|
| 168 |
+
"eval_accuracy": 0.9800436120088781,
|
| 169 |
+
"eval_f1": 0.8759342301943199,
|
| 170 |
+
"eval_loss": 0.07576573640108109,
|
| 171 |
+
"eval_precision": 0.8645901639344262,
|
| 172 |
+
"eval_recall": 0.8875799394143387,
|
| 173 |
+
"eval_runtime": 21.2722,
|
| 174 |
+
"eval_samples_per_second": 152.782,
|
| 175 |
+
"eval_steps_per_second": 4.795,
|
| 176 |
+
"step": 350
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.85,
|
| 180 |
+
"eval_accuracy": 0.9809781550562673,
|
| 181 |
+
"eval_f1": 0.8784392196098049,
|
| 182 |
+
"eval_loss": 0.07266835123300552,
|
| 183 |
+
"eval_precision": 0.8704560475875743,
|
| 184 |
+
"eval_recall": 0.8865701783911141,
|
| 185 |
+
"eval_runtime": 20.8328,
|
| 186 |
+
"eval_samples_per_second": 156.004,
|
| 187 |
+
"eval_steps_per_second": 4.896,
|
| 188 |
+
"step": 375
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.91,
|
| 192 |
+
"eval_accuracy": 0.9811339122308321,
|
| 193 |
+
"eval_f1": 0.8807461692205196,
|
| 194 |
+
"eval_loss": 0.07344163954257965,
|
| 195 |
+
"eval_precision": 0.8717441477085394,
|
| 196 |
+
"eval_recall": 0.8899360484685291,
|
| 197 |
+
"eval_runtime": 21.8636,
|
| 198 |
+
"eval_samples_per_second": 148.649,
|
| 199 |
+
"eval_steps_per_second": 4.665,
|
| 200 |
+
"step": 400
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.97,
|
| 204 |
+
"eval_accuracy": 0.9809781550562673,
|
| 205 |
+
"eval_f1": 0.8785031185031185,
|
| 206 |
+
"eval_loss": 0.07130375504493713,
|
| 207 |
+
"eval_precision": 0.8683215518658557,
|
| 208 |
+
"eval_recall": 0.8889262874453047,
|
| 209 |
+
"eval_runtime": 21.7613,
|
| 210 |
+
"eval_samples_per_second": 149.348,
|
| 211 |
+
"eval_steps_per_second": 4.687,
|
| 212 |
+
"step": 425
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.0,
|
| 216 |
+
"step": 439,
|
| 217 |
+
"total_flos": 456920583926760.0,
|
| 218 |
+
"train_loss": 0.15424916956039117,
|
| 219 |
+
"train_runtime": 564.648,
|
| 220 |
+
"train_samples_per_second": 24.867,
|
| 221 |
+
"train_steps_per_second": 0.777
|
| 222 |
+
}
|
| 223 |
+
],
|
| 224 |
+
"max_steps": 439,
|
| 225 |
+
"num_train_epochs": 1,
|
| 226 |
+
"total_flos": 456920583926760.0,
|
| 227 |
+
"trial_name": null,
|
| 228 |
+
"trial_params": null
|
| 229 |
+
}
|