End of training
Browse files- all_results.json +22 -0
- eval_results.json +17 -0
- train_results.json +8 -0
- trainer_state.json +204 -0
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_HasAns_exact": 67.86625413884818,
|
| 4 |
+
"eval_HasAns_f1": 74.35217861420978,
|
| 5 |
+
"eval_HasAns_total": 18423,
|
| 6 |
+
"eval_NoAns_exact": 78.12242204256724,
|
| 7 |
+
"eval_NoAns_f1": 78.12242204256724,
|
| 8 |
+
"eval_NoAns_total": 6061,
|
| 9 |
+
"eval_best_exact": 70.40516255513805,
|
| 10 |
+
"eval_best_exact_thresh": 0.0,
|
| 11 |
+
"eval_best_f1": 75.28550018826877,
|
| 12 |
+
"eval_best_f1_thresh": 0.0,
|
| 13 |
+
"eval_exact": 70.40516255513805,
|
| 14 |
+
"eval_f1": 75.28550018826883,
|
| 15 |
+
"eval_samples": 44895,
|
| 16 |
+
"eval_total": 24484,
|
| 17 |
+
"train_loss": 1.0671158636125415,
|
| 18 |
+
"train_runtime": 2476.3519,
|
| 19 |
+
"train_samples": 317774,
|
| 20 |
+
"train_samples_per_second": 256.584,
|
| 21 |
+
"train_steps_per_second": 1.002
|
| 22 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_HasAns_exact": 67.86625413884818,
|
| 4 |
+
"eval_HasAns_f1": 74.35217861420978,
|
| 5 |
+
"eval_HasAns_total": 18423,
|
| 6 |
+
"eval_NoAns_exact": 78.12242204256724,
|
| 7 |
+
"eval_NoAns_f1": 78.12242204256724,
|
| 8 |
+
"eval_NoAns_total": 6061,
|
| 9 |
+
"eval_best_exact": 70.40516255513805,
|
| 10 |
+
"eval_best_exact_thresh": 0.0,
|
| 11 |
+
"eval_best_f1": 75.28550018826877,
|
| 12 |
+
"eval_best_f1_thresh": 0.0,
|
| 13 |
+
"eval_exact": 70.40516255513805,
|
| 14 |
+
"eval_f1": 75.28550018826883,
|
| 15 |
+
"eval_samples": 44895,
|
| 16 |
+
"eval_total": 24484
|
| 17 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.0671158636125415,
|
| 4 |
+
"train_runtime": 2476.3519,
|
| 5 |
+
"train_samples": 317774,
|
| 6 |
+
"train_samples_per_second": 256.584,
|
| 7 |
+
"train_steps_per_second": 1.002
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 2482,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 4.0160642570281125e-05,
|
| 13 |
+
"loss": 3.6101,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 8.032128514056225e-05,
|
| 19 |
+
"loss": 1.5644,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"learning_rate": 9.771607702642186e-05,
|
| 25 |
+
"loss": 1.4534,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.32,
|
| 30 |
+
"learning_rate": 9.323779668607256e-05,
|
| 31 |
+
"loss": 1.2308,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.4,
|
| 36 |
+
"learning_rate": 8.875951634572325e-05,
|
| 37 |
+
"loss": 1.0461,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.48,
|
| 42 |
+
"learning_rate": 8.428123600537394e-05,
|
| 43 |
+
"loss": 1.2082,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.56,
|
| 48 |
+
"learning_rate": 7.980295566502463e-05,
|
| 49 |
+
"loss": 1.1456,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.64,
|
| 54 |
+
"learning_rate": 7.532467532467533e-05,
|
| 55 |
+
"loss": 1.0767,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.73,
|
| 60 |
+
"learning_rate": 7.084639498432603e-05,
|
| 61 |
+
"loss": 1.136,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.81,
|
| 66 |
+
"learning_rate": 6.636811464397672e-05,
|
| 67 |
+
"loss": 1.041,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.89,
|
| 72 |
+
"learning_rate": 6.188983430362741e-05,
|
| 73 |
+
"loss": 1.1013,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.97,
|
| 78 |
+
"learning_rate": 5.741155396327811e-05,
|
| 79 |
+
"loss": 0.9227,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_HasAns_exact": 68.0616620528687,
|
| 85 |
+
"eval_HasAns_f1": 74.92241418708792,
|
| 86 |
+
"eval_HasAns_total": 18423,
|
| 87 |
+
"eval_NoAns_exact": 72.74377165484243,
|
| 88 |
+
"eval_NoAns_f1": 72.74377165484243,
|
| 89 |
+
"eval_NoAns_total": 6061,
|
| 90 |
+
"eval_best_exact": 69.22071556935141,
|
| 91 |
+
"eval_best_exact_thresh": 0.0,
|
| 92 |
+
"eval_best_f1": 74.3830924917785,
|
| 93 |
+
"eval_best_f1_thresh": 0.0,
|
| 94 |
+
"eval_exact": 69.22071556935141,
|
| 95 |
+
"eval_f1": 74.38309249177856,
|
| 96 |
+
"eval_total": 24484,
|
| 97 |
+
"step": 1241
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.05,
|
| 101 |
+
"learning_rate": 5.29332736229288e-05,
|
| 102 |
+
"loss": 0.9157,
|
| 103 |
+
"step": 1300
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.13,
|
| 107 |
+
"learning_rate": 4.845499328257949e-05,
|
| 108 |
+
"loss": 0.7482,
|
| 109 |
+
"step": 1400
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.21,
|
| 113 |
+
"learning_rate": 4.397671294223019e-05,
|
| 114 |
+
"loss": 0.7523,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.29,
|
| 119 |
+
"learning_rate": 3.949843260188088e-05,
|
| 120 |
+
"loss": 0.8341,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.37,
|
| 125 |
+
"learning_rate": 3.5020152261531576e-05,
|
| 126 |
+
"loss": 0.7643,
|
| 127 |
+
"step": 1700
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.45,
|
| 131 |
+
"learning_rate": 3.0541871921182266e-05,
|
| 132 |
+
"loss": 0.7429,
|
| 133 |
+
"step": 1800
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.53,
|
| 137 |
+
"learning_rate": 2.6063591580832963e-05,
|
| 138 |
+
"loss": 0.7005,
|
| 139 |
+
"step": 1900
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.61,
|
| 143 |
+
"learning_rate": 2.1585311240483657e-05,
|
| 144 |
+
"loss": 0.7959,
|
| 145 |
+
"step": 2000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.69,
|
| 149 |
+
"learning_rate": 1.710703090013435e-05,
|
| 150 |
+
"loss": 0.838,
|
| 151 |
+
"step": 2100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.77,
|
| 155 |
+
"learning_rate": 1.2628750559785044e-05,
|
| 156 |
+
"loss": 0.6559,
|
| 157 |
+
"step": 2200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.85,
|
| 161 |
+
"learning_rate": 8.150470219435737e-06,
|
| 162 |
+
"loss": 0.7658,
|
| 163 |
+
"step": 2300
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.93,
|
| 167 |
+
"learning_rate": 3.672189879086431e-06,
|
| 168 |
+
"loss": 0.7433,
|
| 169 |
+
"step": 2400
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.0,
|
| 173 |
+
"eval_HasAns_exact": 67.86625413884818,
|
| 174 |
+
"eval_HasAns_f1": 74.35217861420978,
|
| 175 |
+
"eval_HasAns_total": 18423,
|
| 176 |
+
"eval_NoAns_exact": 78.12242204256724,
|
| 177 |
+
"eval_NoAns_f1": 78.12242204256724,
|
| 178 |
+
"eval_NoAns_total": 6061,
|
| 179 |
+
"eval_best_exact": 70.40516255513805,
|
| 180 |
+
"eval_best_exact_thresh": 0.0,
|
| 181 |
+
"eval_best_f1": 75.28550018826877,
|
| 182 |
+
"eval_best_f1_thresh": 0.0,
|
| 183 |
+
"eval_exact": 70.40516255513805,
|
| 184 |
+
"eval_f1": 75.28550018826883,
|
| 185 |
+
"eval_total": 24484,
|
| 186 |
+
"step": 2482
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0,
|
| 190 |
+
"step": 2482,
|
| 191 |
+
"total_flos": 7.969241705088025e+18,
|
| 192 |
+
"train_loss": 1.0671158636125415,
|
| 193 |
+
"train_runtime": 2476.3519,
|
| 194 |
+
"train_samples_per_second": 256.584,
|
| 195 |
+
"train_steps_per_second": 1.002
|
| 196 |
+
}
|
| 197 |
+
],
|
| 198 |
+
"max_steps": 2482,
|
| 199 |
+
"num_train_epochs": 2,
|
| 200 |
+
"start_time": 1661273831.2880511,
|
| 201 |
+
"total_flos": 7.969241705088025e+18,
|
| 202 |
+
"trial_name": null,
|
| 203 |
+
"trial_params": null
|
| 204 |
+
}
|