results
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_HasAns_exact": 69.19611355371003,
|
| 4 |
+
"eval_HasAns_f1": 75.75383941256567,
|
| 5 |
+
"eval_HasAns_total": 18423,
|
| 6 |
+
"eval_NoAns_exact": 77.6109552879063,
|
| 7 |
+
"eval_NoAns_f1": 77.6109552879063,
|
| 8 |
+
"eval_NoAns_total": 6061,
|
| 9 |
+
"eval_best_exact": 71.27920274464957,
|
| 10 |
+
"eval_best_exact_thresh": 0.0,
|
| 11 |
+
"eval_best_f1": 76.21356737043324,
|
| 12 |
+
"eval_best_f1_thresh": 0.0,
|
| 13 |
+
"eval_exact": 71.27920274464957,
|
| 14 |
+
"eval_f1": 76.21356737043327,
|
| 15 |
+
"eval_samples": 44895,
|
| 16 |
+
"eval_total": 24484,
|
| 17 |
+
"train_loss": 1.0762882447665056,
|
| 18 |
+
"train_runtime": 1067.9056,
|
| 19 |
+
"train_samples": 317774,
|
| 20 |
+
"train_samples_per_second": 616.543,
|
| 21 |
+
"train_steps_per_second": 2.41
|
| 22 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_HasAns_exact": 69.19611355371003,
|
| 4 |
+
"eval_HasAns_f1": 75.75383941256567,
|
| 5 |
+
"eval_HasAns_total": 18423,
|
| 6 |
+
"eval_NoAns_exact": 77.6109552879063,
|
| 7 |
+
"eval_NoAns_f1": 77.6109552879063,
|
| 8 |
+
"eval_NoAns_total": 6061,
|
| 9 |
+
"eval_best_exact": 71.27920274464957,
|
| 10 |
+
"eval_best_exact_thresh": 0.0,
|
| 11 |
+
"eval_best_f1": 76.21356737043324,
|
| 12 |
+
"eval_best_f1_thresh": 0.0,
|
| 13 |
+
"eval_exact": 71.27920274464957,
|
| 14 |
+
"eval_f1": 76.21356737043327,
|
| 15 |
+
"eval_samples": 44895,
|
| 16 |
+
"eval_total": 24484
|
| 17 |
+
}
|
runs/Aug17_04-01-53_ip-172-31-85-26/events.out.tfevents.1660710268.ip-172-31-85-26.17194.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a98a28f90a85f1377e16391e5d5215b44eb933b959aba9db694f292426d048d
|
| 3 |
+
size 785
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.0762882447665056,
|
| 4 |
+
"train_runtime": 1067.9056,
|
| 5 |
+
"train_samples": 317774,
|
| 6 |
+
"train_samples_per_second": 616.543,
|
| 7 |
+
"train_steps_per_second": 2.41
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 2484,
|
| 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": 3.66,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.16,
|
| 18 |
+
"learning_rate": 8.032128514056225e-05,
|
| 19 |
+
"loss": 1.57,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"learning_rate": 9.771812080536913e-05,
|
| 25 |
+
"loss": 1.36,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.32,
|
| 30 |
+
"learning_rate": 9.324384787472036e-05,
|
| 31 |
+
"loss": 1.26,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.4,
|
| 36 |
+
"learning_rate": 8.876957494407159e-05,
|
| 37 |
+
"loss": 1.19,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.48,
|
| 42 |
+
"learning_rate": 8.429530201342283e-05,
|
| 43 |
+
"loss": 1.14,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.56,
|
| 48 |
+
"learning_rate": 7.982102908277405e-05,
|
| 49 |
+
"loss": 1.12,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.64,
|
| 54 |
+
"learning_rate": 7.534675615212528e-05,
|
| 55 |
+
"loss": 1.1,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.72,
|
| 60 |
+
"learning_rate": 7.087248322147651e-05,
|
| 61 |
+
"loss": 1.04,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.81,
|
| 66 |
+
"learning_rate": 6.639821029082774e-05,
|
| 67 |
+
"loss": 1.035,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.89,
|
| 72 |
+
"learning_rate": 6.192393736017897e-05,
|
| 73 |
+
"loss": 0.985,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.97,
|
| 78 |
+
"learning_rate": 5.7449664429530206e-05,
|
| 79 |
+
"loss": 0.97,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0,
|
| 84 |
+
"eval_HasAns_exact": 67.8608261412365,
|
| 85 |
+
"eval_HasAns_f1": 74.52685937888027,
|
| 86 |
+
"eval_HasAns_total": 18423,
|
| 87 |
+
"eval_NoAns_exact": 67.53011054281471,
|
| 88 |
+
"eval_NoAns_f1": 67.53011054281471,
|
| 89 |
+
"eval_NoAns_total": 6061,
|
| 90 |
+
"eval_best_exact": 67.7789576866525,
|
| 91 |
+
"eval_best_exact_thresh": 0.0,
|
| 92 |
+
"eval_best_f1": 72.79481826242022,
|
| 93 |
+
"eval_best_f1_thresh": 0.0,
|
| 94 |
+
"eval_exact": 67.7789576866525,
|
| 95 |
+
"eval_f1": 72.79481826242029,
|
| 96 |
+
"eval_total": 24484,
|
| 97 |
+
"step": 1242
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.05,
|
| 101 |
+
"learning_rate": 5.297539149888143e-05,
|
| 102 |
+
"loss": 0.885,
|
| 103 |
+
"step": 1300
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.13,
|
| 107 |
+
"learning_rate": 4.850111856823266e-05,
|
| 108 |
+
"loss": 0.82,
|
| 109 |
+
"step": 1400
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.21,
|
| 113 |
+
"learning_rate": 4.40268456375839e-05,
|
| 114 |
+
"loss": 0.83,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.29,
|
| 119 |
+
"learning_rate": 3.955257270693513e-05,
|
| 120 |
+
"loss": 0.835,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.37,
|
| 125 |
+
"learning_rate": 3.507829977628635e-05,
|
| 126 |
+
"loss": 0.82,
|
| 127 |
+
"step": 1700
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.45,
|
| 131 |
+
"learning_rate": 3.0604026845637584e-05,
|
| 132 |
+
"loss": 0.805,
|
| 133 |
+
"step": 1800
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.53,
|
| 137 |
+
"learning_rate": 2.6129753914988815e-05,
|
| 138 |
+
"loss": 0.8,
|
| 139 |
+
"step": 1900
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 1.61,
|
| 143 |
+
"learning_rate": 2.1655480984340046e-05,
|
| 144 |
+
"loss": 0.795,
|
| 145 |
+
"step": 2000
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.69,
|
| 149 |
+
"learning_rate": 1.7181208053691277e-05,
|
| 150 |
+
"loss": 0.795,
|
| 151 |
+
"step": 2100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.77,
|
| 155 |
+
"learning_rate": 1.2706935123042507e-05,
|
| 156 |
+
"loss": 0.76,
|
| 157 |
+
"step": 2200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.85,
|
| 161 |
+
"learning_rate": 8.232662192393737e-06,
|
| 162 |
+
"loss": 0.76,
|
| 163 |
+
"step": 2300
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.93,
|
| 167 |
+
"learning_rate": 3.7583892617449665e-06,
|
| 168 |
+
"loss": 0.76,
|
| 169 |
+
"step": 2400
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 2.0,
|
| 173 |
+
"eval_HasAns_exact": 69.19611355371003,
|
| 174 |
+
"eval_HasAns_f1": 75.75383941256567,
|
| 175 |
+
"eval_HasAns_total": 18423,
|
| 176 |
+
"eval_NoAns_exact": 77.6109552879063,
|
| 177 |
+
"eval_NoAns_f1": 77.6109552879063,
|
| 178 |
+
"eval_NoAns_total": 6061,
|
| 179 |
+
"eval_best_exact": 71.27920274464957,
|
| 180 |
+
"eval_best_exact_thresh": 0.0,
|
| 181 |
+
"eval_best_f1": 76.21356737043324,
|
| 182 |
+
"eval_best_f1_thresh": 0.0,
|
| 183 |
+
"eval_exact": 71.27920274464957,
|
| 184 |
+
"eval_f1": 76.21356737043327,
|
| 185 |
+
"eval_total": 24484,
|
| 186 |
+
"step": 2484
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.0,
|
| 190 |
+
"step": 2484,
|
| 191 |
+
"total_flos": 1.2455075452551168e+17,
|
| 192 |
+
"train_loss": 1.0762882447665056,
|
| 193 |
+
"train_runtime": 1067.9056,
|
| 194 |
+
"train_samples_per_second": 616.543,
|
| 195 |
+
"train_steps_per_second": 2.41
|
| 196 |
+
}
|
| 197 |
+
],
|
| 198 |
+
"max_steps": 2484,
|
| 199 |
+
"num_train_epochs": 2,
|
| 200 |
+
"total_flos": 1.2455075452551168e+17,
|
| 201 |
+
"trial_name": null,
|
| 202 |
+
"trial_params": null
|
| 203 |
+
}
|