paul
commited on
Commit
·
c8b9e02
1
Parent(s):
36ef984
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.99,
|
| 3 |
+
"total_flos": 1.4224524590735456e+19,
|
| 4 |
+
"train_loss": 0.3359685759269371,
|
| 5 |
+
"train_runtime": 2345.2254,
|
| 6 |
+
"train_samples_per_second": 78.345,
|
| 7 |
+
"train_steps_per_second": 0.304
|
| 8 |
+
}
|
runs/Jan12_20-55-27_teesta/events.out.tfevents.1673537136.teesta.20755.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b74765ce4309a0ce4b92f9e6148210dfc4c71f451f9b19849938034833921ef
|
| 3 |
+
size 19249
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 7.99,
|
| 3 |
+
"total_flos": 1.4224524590735456e+19,
|
| 4 |
+
"train_loss": 0.3359685759269371,
|
| 5 |
+
"train_runtime": 2345.2254,
|
| 6 |
+
"train_samples_per_second": 78.345,
|
| 7 |
+
"train_steps_per_second": 0.304
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,547 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6960989202368513,
|
| 3 |
+
"best_model_checkpoint": "google-vit-base-patch16-224-face/checkpoint-712",
|
| 4 |
+
"epoch": 7.991643454038997,
|
| 5 |
+
"global_step": 712,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 13 |
+
"loss": 0.9691,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.22,
|
| 18 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 19 |
+
"loss": 0.9687,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.33,
|
| 24 |
+
"learning_rate": 5e-05,
|
| 25 |
+
"loss": 0.9727,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.45,
|
| 30 |
+
"learning_rate": 6.666666666666667e-05,
|
| 31 |
+
"loss": 0.9245,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.56,
|
| 36 |
+
"learning_rate": 8.333333333333333e-05,
|
| 37 |
+
"loss": 0.8955,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.67,
|
| 42 |
+
"learning_rate": 0.0001,
|
| 43 |
+
"loss": 0.8887,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.78,
|
| 48 |
+
"learning_rate": 0.00011666666666666667,
|
| 49 |
+
"loss": 0.8827,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.89,
|
| 54 |
+
"learning_rate": 0.00011850000000000001,
|
| 55 |
+
"loss": 0.8364,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.99,
|
| 60 |
+
"eval_accuracy": 0.648380355276907,
|
| 61 |
+
"eval_f1": 0.6385482827611145,
|
| 62 |
+
"eval_loss": 0.9452694654464722,
|
| 63 |
+
"eval_precision": 0.6461904026185493,
|
| 64 |
+
"eval_recall": 0.648380355276907,
|
| 65 |
+
"eval_runtime": 32.7545,
|
| 66 |
+
"eval_samples_per_second": 175.304,
|
| 67 |
+
"eval_steps_per_second": 2.748,
|
| 68 |
+
"step": 89
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.01,
|
| 72 |
+
"learning_rate": 0.000116625,
|
| 73 |
+
"loss": 0.9165,
|
| 74 |
+
"step": 90
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.12,
|
| 78 |
+
"learning_rate": 0.00011475000000000001,
|
| 79 |
+
"loss": 0.765,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.23,
|
| 84 |
+
"learning_rate": 0.000112875,
|
| 85 |
+
"loss": 0.7639,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.35,
|
| 90 |
+
"learning_rate": 0.00011100000000000001,
|
| 91 |
+
"loss": 0.7557,
|
| 92 |
+
"step": 120
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.46,
|
| 96 |
+
"learning_rate": 0.00010912500000000001,
|
| 97 |
+
"loss": 0.7494,
|
| 98 |
+
"step": 130
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.57,
|
| 102 |
+
"learning_rate": 0.00010725,
|
| 103 |
+
"loss": 0.7363,
|
| 104 |
+
"step": 140
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.68,
|
| 108 |
+
"learning_rate": 0.00010537500000000001,
|
| 109 |
+
"loss": 0.7147,
|
| 110 |
+
"step": 150
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.79,
|
| 114 |
+
"learning_rate": 0.00010350000000000001,
|
| 115 |
+
"loss": 0.7283,
|
| 116 |
+
"step": 160
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.9,
|
| 120 |
+
"learning_rate": 0.000101625,
|
| 121 |
+
"loss": 0.7433,
|
| 122 |
+
"step": 170
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.99,
|
| 126 |
+
"eval_accuracy": 0.6778126088470916,
|
| 127 |
+
"eval_f1": 0.672969661980768,
|
| 128 |
+
"eval_loss": 0.8876001834869385,
|
| 129 |
+
"eval_precision": 0.679362397138447,
|
| 130 |
+
"eval_recall": 0.6778126088470916,
|
| 131 |
+
"eval_runtime": 37.9557,
|
| 132 |
+
"eval_samples_per_second": 151.282,
|
| 133 |
+
"eval_steps_per_second": 2.371,
|
| 134 |
+
"step": 178
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.02,
|
| 138 |
+
"learning_rate": 9.975000000000001e-05,
|
| 139 |
+
"loss": 0.7192,
|
| 140 |
+
"step": 180
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.13,
|
| 144 |
+
"learning_rate": 9.787500000000001e-05,
|
| 145 |
+
"loss": 0.5258,
|
| 146 |
+
"step": 190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.25,
|
| 150 |
+
"learning_rate": 9.6e-05,
|
| 151 |
+
"loss": 0.5159,
|
| 152 |
+
"step": 200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.36,
|
| 156 |
+
"learning_rate": 9.412500000000001e-05,
|
| 157 |
+
"loss": 0.5151,
|
| 158 |
+
"step": 210
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.47,
|
| 162 |
+
"learning_rate": 9.225e-05,
|
| 163 |
+
"loss": 0.5134,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.58,
|
| 168 |
+
"learning_rate": 9.0375e-05,
|
| 169 |
+
"loss": 0.4776,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.69,
|
| 174 |
+
"learning_rate": 8.850000000000001e-05,
|
| 175 |
+
"loss": 0.5188,
|
| 176 |
+
"step": 240
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.8,
|
| 180 |
+
"learning_rate": 8.6625e-05,
|
| 181 |
+
"loss": 0.5312,
|
| 182 |
+
"step": 250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.91,
|
| 186 |
+
"learning_rate": 8.475000000000001e-05,
|
| 187 |
+
"loss": 0.4732,
|
| 188 |
+
"step": 260
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.99,
|
| 192 |
+
"eval_accuracy": 0.6872169975618252,
|
| 193 |
+
"eval_f1": 0.6840932939913709,
|
| 194 |
+
"eval_loss": 0.9042980670928955,
|
| 195 |
+
"eval_precision": 0.6906579200512205,
|
| 196 |
+
"eval_recall": 0.6872169975618252,
|
| 197 |
+
"eval_runtime": 32.8137,
|
| 198 |
+
"eval_samples_per_second": 174.988,
|
| 199 |
+
"eval_steps_per_second": 2.743,
|
| 200 |
+
"step": 267
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.03,
|
| 204 |
+
"learning_rate": 8.287500000000001e-05,
|
| 205 |
+
"loss": 0.4772,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.14,
|
| 210 |
+
"learning_rate": 8.1e-05,
|
| 211 |
+
"loss": 0.299,
|
| 212 |
+
"step": 280
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.26,
|
| 216 |
+
"learning_rate": 7.912500000000001e-05,
|
| 217 |
+
"loss": 0.2614,
|
| 218 |
+
"step": 290
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.37,
|
| 222 |
+
"learning_rate": 7.725000000000001e-05,
|
| 223 |
+
"loss": 0.2679,
|
| 224 |
+
"step": 300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.48,
|
| 228 |
+
"learning_rate": 7.5375e-05,
|
| 229 |
+
"loss": 0.2992,
|
| 230 |
+
"step": 310
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.59,
|
| 234 |
+
"learning_rate": 7.350000000000001e-05,
|
| 235 |
+
"loss": 0.2835,
|
| 236 |
+
"step": 320
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.7,
|
| 240 |
+
"learning_rate": 7.1625e-05,
|
| 241 |
+
"loss": 0.2752,
|
| 242 |
+
"step": 330
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.81,
|
| 246 |
+
"learning_rate": 6.975e-05,
|
| 247 |
+
"loss": 0.27,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.92,
|
| 252 |
+
"learning_rate": 6.787500000000001e-05,
|
| 253 |
+
"loss": 0.2861,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.99,
|
| 258 |
+
"eval_accuracy": 0.6847788227098572,
|
| 259 |
+
"eval_f1": 0.6813474424826861,
|
| 260 |
+
"eval_loss": 0.9865238666534424,
|
| 261 |
+
"eval_precision": 0.6808262458026351,
|
| 262 |
+
"eval_recall": 0.6847788227098572,
|
| 263 |
+
"eval_runtime": 34.0061,
|
| 264 |
+
"eval_samples_per_second": 168.852,
|
| 265 |
+
"eval_steps_per_second": 2.647,
|
| 266 |
+
"step": 356
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.04,
|
| 270 |
+
"learning_rate": 6.6e-05,
|
| 271 |
+
"loss": 0.2485,
|
| 272 |
+
"step": 360
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.16,
|
| 276 |
+
"learning_rate": 6.412500000000001e-05,
|
| 277 |
+
"loss": 0.1212,
|
| 278 |
+
"step": 370
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.27,
|
| 282 |
+
"learning_rate": 6.225000000000001e-05,
|
| 283 |
+
"loss": 0.121,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.38,
|
| 288 |
+
"learning_rate": 6.0375000000000004e-05,
|
| 289 |
+
"loss": 0.131,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.49,
|
| 294 |
+
"learning_rate": 5.85e-05,
|
| 295 |
+
"loss": 0.1192,
|
| 296 |
+
"step": 400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.6,
|
| 300 |
+
"learning_rate": 5.6625e-05,
|
| 301 |
+
"loss": 0.1137,
|
| 302 |
+
"step": 410
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.71,
|
| 306 |
+
"learning_rate": 5.475e-05,
|
| 307 |
+
"loss": 0.1334,
|
| 308 |
+
"step": 420
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.82,
|
| 312 |
+
"learning_rate": 5.2875e-05,
|
| 313 |
+
"loss": 0.1285,
|
| 314 |
+
"step": 430
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.94,
|
| 318 |
+
"learning_rate": 5.1e-05,
|
| 319 |
+
"loss": 0.1234,
|
| 320 |
+
"step": 440
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.99,
|
| 324 |
+
"eval_accuracy": 0.6853012887495646,
|
| 325 |
+
"eval_f1": 0.6871627462072427,
|
| 326 |
+
"eval_loss": 1.1047998666763306,
|
| 327 |
+
"eval_precision": 0.6907009316583976,
|
| 328 |
+
"eval_recall": 0.6853012887495646,
|
| 329 |
+
"eval_runtime": 32.6937,
|
| 330 |
+
"eval_samples_per_second": 175.63,
|
| 331 |
+
"eval_steps_per_second": 2.753,
|
| 332 |
+
"step": 445
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 5.06,
|
| 336 |
+
"learning_rate": 4.9125e-05,
|
| 337 |
+
"loss": 0.1018,
|
| 338 |
+
"step": 450
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.17,
|
| 342 |
+
"learning_rate": 4.7249999999999997e-05,
|
| 343 |
+
"loss": 0.053,
|
| 344 |
+
"step": 460
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 5.28,
|
| 348 |
+
"learning_rate": 4.5375e-05,
|
| 349 |
+
"loss": 0.0495,
|
| 350 |
+
"step": 470
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 5.39,
|
| 354 |
+
"learning_rate": 4.35e-05,
|
| 355 |
+
"loss": 0.052,
|
| 356 |
+
"step": 480
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 5.5,
|
| 360 |
+
"learning_rate": 4.1625e-05,
|
| 361 |
+
"loss": 0.0597,
|
| 362 |
+
"step": 490
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 5.61,
|
| 366 |
+
"learning_rate": 3.975e-05,
|
| 367 |
+
"loss": 0.0548,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 5.72,
|
| 372 |
+
"learning_rate": 3.7875e-05,
|
| 373 |
+
"loss": 0.0619,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.84,
|
| 378 |
+
"learning_rate": 3.6e-05,
|
| 379 |
+
"loss": 0.0627,
|
| 380 |
+
"step": 520
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.95,
|
| 384 |
+
"learning_rate": 3.4125e-05,
|
| 385 |
+
"loss": 0.0599,
|
| 386 |
+
"step": 530
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.99,
|
| 390 |
+
"eval_accuracy": 0.6889585510275166,
|
| 391 |
+
"eval_f1": 0.6876003709723829,
|
| 392 |
+
"eval_loss": 1.2361745834350586,
|
| 393 |
+
"eval_precision": 0.6897347831759311,
|
| 394 |
+
"eval_recall": 0.6889585510275166,
|
| 395 |
+
"eval_runtime": 34.0898,
|
| 396 |
+
"eval_samples_per_second": 168.437,
|
| 397 |
+
"eval_steps_per_second": 2.64,
|
| 398 |
+
"step": 534
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.07,
|
| 402 |
+
"learning_rate": 3.225e-05,
|
| 403 |
+
"loss": 0.0431,
|
| 404 |
+
"step": 540
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 6.18,
|
| 408 |
+
"learning_rate": 3.0375e-05,
|
| 409 |
+
"loss": 0.033,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 6.29,
|
| 414 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 415 |
+
"loss": 0.0332,
|
| 416 |
+
"step": 560
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 6.4,
|
| 420 |
+
"learning_rate": 2.6625e-05,
|
| 421 |
+
"loss": 0.0315,
|
| 422 |
+
"step": 570
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.51,
|
| 426 |
+
"learning_rate": 2.475e-05,
|
| 427 |
+
"loss": 0.0305,
|
| 428 |
+
"step": 580
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 6.62,
|
| 432 |
+
"learning_rate": 2.2875e-05,
|
| 433 |
+
"loss": 0.0243,
|
| 434 |
+
"step": 590
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 6.74,
|
| 438 |
+
"learning_rate": 2.1e-05,
|
| 439 |
+
"loss": 0.0241,
|
| 440 |
+
"step": 600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 6.85,
|
| 444 |
+
"learning_rate": 1.9125e-05,
|
| 445 |
+
"loss": 0.0206,
|
| 446 |
+
"step": 610
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 6.96,
|
| 450 |
+
"learning_rate": 1.725e-05,
|
| 451 |
+
"loss": 0.0289,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 6.99,
|
| 456 |
+
"eval_accuracy": 0.6931382793451759,
|
| 457 |
+
"eval_f1": 0.6921150248707686,
|
| 458 |
+
"eval_loss": 1.3140767812728882,
|
| 459 |
+
"eval_precision": 0.6925717262836596,
|
| 460 |
+
"eval_recall": 0.6931382793451759,
|
| 461 |
+
"eval_runtime": 33.0395,
|
| 462 |
+
"eval_samples_per_second": 173.792,
|
| 463 |
+
"eval_steps_per_second": 2.724,
|
| 464 |
+
"step": 623
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 7.08,
|
| 468 |
+
"learning_rate": 1.5374999999999998e-05,
|
| 469 |
+
"loss": 0.0185,
|
| 470 |
+
"step": 630
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 7.19,
|
| 474 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 475 |
+
"loss": 0.0132,
|
| 476 |
+
"step": 640
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 7.3,
|
| 480 |
+
"learning_rate": 1.1625000000000001e-05,
|
| 481 |
+
"loss": 0.014,
|
| 482 |
+
"step": 650
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 7.41,
|
| 486 |
+
"learning_rate": 9.75e-06,
|
| 487 |
+
"loss": 0.0121,
|
| 488 |
+
"step": 660
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 7.52,
|
| 492 |
+
"learning_rate": 7.875e-06,
|
| 493 |
+
"loss": 0.0203,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 7.64,
|
| 498 |
+
"learning_rate": 6e-06,
|
| 499 |
+
"loss": 0.0103,
|
| 500 |
+
"step": 680
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 7.75,
|
| 504 |
+
"learning_rate": 4.125e-06,
|
| 505 |
+
"loss": 0.0178,
|
| 506 |
+
"step": 690
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.86,
|
| 510 |
+
"learning_rate": 2.25e-06,
|
| 511 |
+
"loss": 0.0126,
|
| 512 |
+
"step": 700
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 7.97,
|
| 516 |
+
"learning_rate": 3.75e-07,
|
| 517 |
+
"loss": 0.0134,
|
| 518 |
+
"step": 710
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 7.99,
|
| 522 |
+
"eval_accuracy": 0.6960989202368513,
|
| 523 |
+
"eval_f1": 0.6957934361657124,
|
| 524 |
+
"eval_loss": 1.3257348537445068,
|
| 525 |
+
"eval_precision": 0.6966334506335445,
|
| 526 |
+
"eval_recall": 0.6960989202368513,
|
| 527 |
+
"eval_runtime": 37.8195,
|
| 528 |
+
"eval_samples_per_second": 151.827,
|
| 529 |
+
"eval_steps_per_second": 2.38,
|
| 530 |
+
"step": 712
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 7.99,
|
| 534 |
+
"step": 712,
|
| 535 |
+
"total_flos": 1.4224524590735456e+19,
|
| 536 |
+
"train_loss": 0.3359685759269371,
|
| 537 |
+
"train_runtime": 2345.2254,
|
| 538 |
+
"train_samples_per_second": 78.345,
|
| 539 |
+
"train_steps_per_second": 0.304
|
| 540 |
+
}
|
| 541 |
+
],
|
| 542 |
+
"max_steps": 712,
|
| 543 |
+
"num_train_epochs": 8,
|
| 544 |
+
"total_flos": 1.4224524590735456e+19,
|
| 545 |
+
"trial_name": null,
|
| 546 |
+
"trial_params": null
|
| 547 |
+
}
|