paul
commited on
Commit
·
42f7b4f
1
Parent(s):
5122322
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.99,
|
| 3 |
+
"total_flos": 2.1968670326740623e+18,
|
| 4 |
+
"train_loss": 1.0949385786056518,
|
| 5 |
+
"train_runtime": 1181.8167,
|
| 6 |
+
"train_samples_per_second": 87.56,
|
| 7 |
+
"train_steps_per_second": 0.338
|
| 8 |
+
}
|
runs/Oct22_02-45-45_teesta/events.out.tfevents.1666386960.teesta.11575.2
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 sha256:799bc81386cbe6d6ad61ea6afe45d9328111f01ded8ca2cd7b9d50d8dce61774
|
| 3 |
+
size 19829
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.99,
|
| 3 |
+
"total_flos": 2.1968670326740623e+18,
|
| 4 |
+
"train_loss": 1.0949385786056518,
|
| 5 |
+
"train_runtime": 1181.8167,
|
| 6 |
+
"train_samples_per_second": 87.56,
|
| 7 |
+
"train_steps_per_second": 0.338
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6452859350850078,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-FV2-finetuned-memes/checkpoint-400",
|
| 4 |
+
"epoch": 19.987654320987655,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.49,
|
| 12 |
+
"learning_rate": 3e-05,
|
| 13 |
+
"loss": 1.5967,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.99,
|
| 18 |
+
"learning_rate": 6e-05,
|
| 19 |
+
"loss": 1.5763,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.99,
|
| 24 |
+
"eval_accuracy": 0.4281298299845441,
|
| 25 |
+
"eval_f1": 0.26687554630409566,
|
| 26 |
+
"eval_loss": 1.5574817657470703,
|
| 27 |
+
"eval_precision": 0.29655663588874154,
|
| 28 |
+
"eval_recall": 0.4281298299845441,
|
| 29 |
+
"eval_runtime": 11.3953,
|
| 30 |
+
"eval_samples_per_second": 113.556,
|
| 31 |
+
"eval_steps_per_second": 1.843,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.49,
|
| 36 |
+
"learning_rate": 9e-05,
|
| 37 |
+
"loss": 1.5775,
|
| 38 |
+
"step": 30
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.99,
|
| 42 |
+
"learning_rate": 0.00012,
|
| 43 |
+
"loss": 1.4761,
|
| 44 |
+
"step": 40
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.99,
|
| 48 |
+
"eval_accuracy": 0.43431221020092736,
|
| 49 |
+
"eval_f1": 0.2630209721259926,
|
| 50 |
+
"eval_loss": 1.4423725605010986,
|
| 51 |
+
"eval_precision": 0.18862709592961452,
|
| 52 |
+
"eval_recall": 0.43431221020092736,
|
| 53 |
+
"eval_runtime": 10.1591,
|
| 54 |
+
"eval_samples_per_second": 127.373,
|
| 55 |
+
"eval_steps_per_second": 2.067,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.49,
|
| 60 |
+
"learning_rate": 0.00011666666666666667,
|
| 61 |
+
"loss": 1.444,
|
| 62 |
+
"step": 50
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.99,
|
| 66 |
+
"learning_rate": 0.00011333333333333333,
|
| 67 |
+
"loss": 1.3563,
|
| 68 |
+
"step": 60
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.99,
|
| 72 |
+
"eval_accuracy": 0.43431221020092736,
|
| 73 |
+
"eval_f1": 0.2630209721259926,
|
| 74 |
+
"eval_loss": 1.3240060806274414,
|
| 75 |
+
"eval_precision": 0.18862709592961452,
|
| 76 |
+
"eval_recall": 0.43431221020092736,
|
| 77 |
+
"eval_runtime": 10.039,
|
| 78 |
+
"eval_samples_per_second": 128.897,
|
| 79 |
+
"eval_steps_per_second": 2.092,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.49,
|
| 84 |
+
"learning_rate": 0.00011,
|
| 85 |
+
"loss": 1.3356,
|
| 86 |
+
"step": 70
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.99,
|
| 90 |
+
"learning_rate": 0.00010666666666666667,
|
| 91 |
+
"loss": 1.2824,
|
| 92 |
+
"step": 80
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.99,
|
| 96 |
+
"eval_accuracy": 0.43894899536321486,
|
| 97 |
+
"eval_f1": 0.27337332937410136,
|
| 98 |
+
"eval_loss": 1.263592004776001,
|
| 99 |
+
"eval_precision": 0.3097252114961456,
|
| 100 |
+
"eval_recall": 0.43894899536321486,
|
| 101 |
+
"eval_runtime": 10.0514,
|
| 102 |
+
"eval_samples_per_second": 128.739,
|
| 103 |
+
"eval_steps_per_second": 2.089,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.49,
|
| 108 |
+
"learning_rate": 0.00010333333333333334,
|
| 109 |
+
"loss": 1.2695,
|
| 110 |
+
"step": 90
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.99,
|
| 114 |
+
"learning_rate": 0.0001,
|
| 115 |
+
"loss": 1.2315,
|
| 116 |
+
"step": 100
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.99,
|
| 120 |
+
"eval_accuracy": 0.4528593508500773,
|
| 121 |
+
"eval_f1": 0.30415713999389604,
|
| 122 |
+
"eval_loss": 1.2118711471557617,
|
| 123 |
+
"eval_precision": 0.3235903479528001,
|
| 124 |
+
"eval_recall": 0.4528593508500773,
|
| 125 |
+
"eval_runtime": 10.1242,
|
| 126 |
+
"eval_samples_per_second": 127.813,
|
| 127 |
+
"eval_steps_per_second": 2.074,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.49,
|
| 132 |
+
"learning_rate": 9.666666666666667e-05,
|
| 133 |
+
"loss": 1.2096,
|
| 134 |
+
"step": 110
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 5.99,
|
| 138 |
+
"learning_rate": 9.333333333333334e-05,
|
| 139 |
+
"loss": 1.1956,
|
| 140 |
+
"step": 120
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.99,
|
| 144 |
+
"eval_accuracy": 0.4899536321483771,
|
| 145 |
+
"eval_f1": 0.3692247614974613,
|
| 146 |
+
"eval_loss": 1.1763864755630493,
|
| 147 |
+
"eval_precision": 0.3730719437429542,
|
| 148 |
+
"eval_recall": 0.4899536321483771,
|
| 149 |
+
"eval_runtime": 10.0285,
|
| 150 |
+
"eval_samples_per_second": 129.033,
|
| 151 |
+
"eval_steps_per_second": 2.094,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.49,
|
| 156 |
+
"learning_rate": 9e-05,
|
| 157 |
+
"loss": 1.1727,
|
| 158 |
+
"step": 130
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.99,
|
| 162 |
+
"learning_rate": 8.666666666666667e-05,
|
| 163 |
+
"loss": 1.1452,
|
| 164 |
+
"step": 140
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.99,
|
| 168 |
+
"eval_accuracy": 0.5146831530139103,
|
| 169 |
+
"eval_f1": 0.4090229013083186,
|
| 170 |
+
"eval_loss": 1.1424295902252197,
|
| 171 |
+
"eval_precision": 0.396316505367188,
|
| 172 |
+
"eval_recall": 0.5146831530139103,
|
| 173 |
+
"eval_runtime": 11.1,
|
| 174 |
+
"eval_samples_per_second": 116.577,
|
| 175 |
+
"eval_steps_per_second": 1.892,
|
| 176 |
+
"step": 140
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 7.49,
|
| 180 |
+
"learning_rate": 8.333333333333333e-05,
|
| 181 |
+
"loss": 1.1455,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 7.99,
|
| 186 |
+
"learning_rate": 7.999999999999999e-05,
|
| 187 |
+
"loss": 1.1076,
|
| 188 |
+
"step": 160
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 7.99,
|
| 192 |
+
"eval_accuracy": 0.5370942812982998,
|
| 193 |
+
"eval_f1": 0.4392356918841944,
|
| 194 |
+
"eval_loss": 1.1189799308776855,
|
| 195 |
+
"eval_precision": 0.41207140655215574,
|
| 196 |
+
"eval_recall": 0.5370942812982998,
|
| 197 |
+
"eval_runtime": 10.2542,
|
| 198 |
+
"eval_samples_per_second": 126.192,
|
| 199 |
+
"eval_steps_per_second": 2.048,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.49,
|
| 204 |
+
"learning_rate": 7.666666666666667e-05,
|
| 205 |
+
"loss": 1.1204,
|
| 206 |
+
"step": 170
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.99,
|
| 210 |
+
"learning_rate": 7.333333333333334e-05,
|
| 211 |
+
"loss": 1.0679,
|
| 212 |
+
"step": 180
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 8.99,
|
| 216 |
+
"eval_accuracy": 0.5718701700154559,
|
| 217 |
+
"eval_f1": 0.48309150932194556,
|
| 218 |
+
"eval_loss": 1.0824542045593262,
|
| 219 |
+
"eval_precision": 0.44653696889067535,
|
| 220 |
+
"eval_recall": 0.5718701700154559,
|
| 221 |
+
"eval_runtime": 10.0099,
|
| 222 |
+
"eval_samples_per_second": 129.272,
|
| 223 |
+
"eval_steps_per_second": 2.098,
|
| 224 |
+
"step": 180
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 9.49,
|
| 228 |
+
"learning_rate": 7.000000000000001e-05,
|
| 229 |
+
"loss": 1.0551,
|
| 230 |
+
"step": 190
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 9.99,
|
| 234 |
+
"learning_rate": 6.666666666666667e-05,
|
| 235 |
+
"loss": 1.0432,
|
| 236 |
+
"step": 200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.99,
|
| 240 |
+
"eval_accuracy": 0.5749613601236476,
|
| 241 |
+
"eval_f1": 0.4930062944584295,
|
| 242 |
+
"eval_loss": 1.0481715202331543,
|
| 243 |
+
"eval_precision": 0.5404301068833355,
|
| 244 |
+
"eval_recall": 0.5749613601236476,
|
| 245 |
+
"eval_runtime": 19.2474,
|
| 246 |
+
"eval_samples_per_second": 67.23,
|
| 247 |
+
"eval_steps_per_second": 1.091,
|
| 248 |
+
"step": 200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 10.49,
|
| 252 |
+
"learning_rate": 6.333333333333333e-05,
|
| 253 |
+
"loss": 1.0465,
|
| 254 |
+
"step": 210
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 10.99,
|
| 258 |
+
"learning_rate": 6e-05,
|
| 259 |
+
"loss": 0.9903,
|
| 260 |
+
"step": 220
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 10.99,
|
| 264 |
+
"eval_accuracy": 0.5958268933539412,
|
| 265 |
+
"eval_f1": 0.5240773887363929,
|
| 266 |
+
"eval_loss": 1.0275342464447021,
|
| 267 |
+
"eval_precision": 0.545875829974407,
|
| 268 |
+
"eval_recall": 0.5958268933539412,
|
| 269 |
+
"eval_runtime": 9.9464,
|
| 270 |
+
"eval_samples_per_second": 130.097,
|
| 271 |
+
"eval_steps_per_second": 2.111,
|
| 272 |
+
"step": 220
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 11.49,
|
| 276 |
+
"learning_rate": 5.6666666666666664e-05,
|
| 277 |
+
"loss": 1.0046,
|
| 278 |
+
"step": 230
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 11.99,
|
| 282 |
+
"learning_rate": 5.333333333333333e-05,
|
| 283 |
+
"loss": 0.9675,
|
| 284 |
+
"step": 240
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 11.99,
|
| 288 |
+
"eval_accuracy": 0.6051004636785162,
|
| 289 |
+
"eval_f1": 0.5379053813016494,
|
| 290 |
+
"eval_loss": 1.0145165920257568,
|
| 291 |
+
"eval_precision": 0.5349771722020813,
|
| 292 |
+
"eval_recall": 0.6051004636785162,
|
| 293 |
+
"eval_runtime": 10.1612,
|
| 294 |
+
"eval_samples_per_second": 127.347,
|
| 295 |
+
"eval_steps_per_second": 2.067,
|
| 296 |
+
"step": 240
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 12.49,
|
| 300 |
+
"learning_rate": 5e-05,
|
| 301 |
+
"loss": 0.997,
|
| 302 |
+
"step": 250
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 12.99,
|
| 306 |
+
"learning_rate": 4.666666666666667e-05,
|
| 307 |
+
"loss": 0.9335,
|
| 308 |
+
"step": 260
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 12.99,
|
| 312 |
+
"eval_accuracy": 0.6174652241112828,
|
| 313 |
+
"eval_f1": 0.552720253591733,
|
| 314 |
+
"eval_loss": 0.9859771728515625,
|
| 315 |
+
"eval_precision": 0.5536990181229813,
|
| 316 |
+
"eval_recall": 0.6174652241112828,
|
| 317 |
+
"eval_runtime": 11.4078,
|
| 318 |
+
"eval_samples_per_second": 113.431,
|
| 319 |
+
"eval_steps_per_second": 1.841,
|
| 320 |
+
"step": 260
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 13.49,
|
| 324 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 325 |
+
"loss": 0.9501,
|
| 326 |
+
"step": 270
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 13.99,
|
| 330 |
+
"learning_rate": 3.9999999999999996e-05,
|
| 331 |
+
"loss": 0.9157,
|
| 332 |
+
"step": 280
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 13.99,
|
| 336 |
+
"eval_accuracy": 0.6105100463678517,
|
| 337 |
+
"eval_f1": 0.5504384069346341,
|
| 338 |
+
"eval_loss": 0.9683175683021545,
|
| 339 |
+
"eval_precision": 0.5386397521561105,
|
| 340 |
+
"eval_recall": 0.6105100463678517,
|
| 341 |
+
"eval_runtime": 10.0837,
|
| 342 |
+
"eval_samples_per_second": 128.326,
|
| 343 |
+
"eval_steps_per_second": 2.083,
|
| 344 |
+
"step": 280
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 14.49,
|
| 348 |
+
"learning_rate": 3.666666666666667e-05,
|
| 349 |
+
"loss": 0.9324,
|
| 350 |
+
"step": 290
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 14.99,
|
| 354 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 355 |
+
"loss": 0.8901,
|
| 356 |
+
"step": 300
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 14.99,
|
| 360 |
+
"eval_accuracy": 0.6352395672333848,
|
| 361 |
+
"eval_f1": 0.5833124251549139,
|
| 362 |
+
"eval_loss": 0.95584636926651,
|
| 363 |
+
"eval_precision": 0.5686172096380677,
|
| 364 |
+
"eval_recall": 0.6352395672333848,
|
| 365 |
+
"eval_runtime": 11.1778,
|
| 366 |
+
"eval_samples_per_second": 115.766,
|
| 367 |
+
"eval_steps_per_second": 1.879,
|
| 368 |
+
"step": 300
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 15.49,
|
| 372 |
+
"learning_rate": 3e-05,
|
| 373 |
+
"loss": 0.9157,
|
| 374 |
+
"step": 310
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 15.99,
|
| 378 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 379 |
+
"loss": 0.8722,
|
| 380 |
+
"step": 320
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 15.99,
|
| 384 |
+
"eval_accuracy": 0.634466769706337,
|
| 385 |
+
"eval_f1": 0.5807225066585998,
|
| 386 |
+
"eval_loss": 0.9381548762321472,
|
| 387 |
+
"eval_precision": 0.5656504472537988,
|
| 388 |
+
"eval_recall": 0.634466769706337,
|
| 389 |
+
"eval_runtime": 10.0783,
|
| 390 |
+
"eval_samples_per_second": 128.395,
|
| 391 |
+
"eval_steps_per_second": 2.084,
|
| 392 |
+
"step": 320
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 16.49,
|
| 396 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 397 |
+
"loss": 0.9132,
|
| 398 |
+
"step": 330
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 16.99,
|
| 402 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 403 |
+
"loss": 0.854,
|
| 404 |
+
"step": 340
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 16.99,
|
| 408 |
+
"eval_accuracy": 0.6375579598145286,
|
| 409 |
+
"eval_f1": 0.5855599844273062,
|
| 410 |
+
"eval_loss": 0.9322208166122437,
|
| 411 |
+
"eval_precision": 0.5622591012744048,
|
| 412 |
+
"eval_recall": 0.6375579598145286,
|
| 413 |
+
"eval_runtime": 10.1911,
|
| 414 |
+
"eval_samples_per_second": 126.973,
|
| 415 |
+
"eval_steps_per_second": 2.061,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 17.49,
|
| 420 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 421 |
+
"loss": 0.8979,
|
| 422 |
+
"step": 350
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 17.99,
|
| 426 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 427 |
+
"loss": 0.8494,
|
| 428 |
+
"step": 360
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 17.99,
|
| 432 |
+
"eval_accuracy": 0.6421947449768161,
|
| 433 |
+
"eval_f1": 0.5918308732628852,
|
| 434 |
+
"eval_loss": 0.9286540746688843,
|
| 435 |
+
"eval_precision": 0.6675486262621129,
|
| 436 |
+
"eval_recall": 0.6421947449768161,
|
| 437 |
+
"eval_runtime": 11.41,
|
| 438 |
+
"eval_samples_per_second": 113.409,
|
| 439 |
+
"eval_steps_per_second": 1.84,
|
| 440 |
+
"step": 360
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 18.49,
|
| 444 |
+
"learning_rate": 9.999999999999999e-06,
|
| 445 |
+
"loss": 0.8649,
|
| 446 |
+
"step": 370
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 18.99,
|
| 450 |
+
"learning_rate": 6.666666666666667e-06,
|
| 451 |
+
"loss": 0.8652,
|
| 452 |
+
"step": 380
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 18.99,
|
| 456 |
+
"eval_accuracy": 0.6398763523956723,
|
| 457 |
+
"eval_f1": 0.586308244884445,
|
| 458 |
+
"eval_loss": 0.9211938977241516,
|
| 459 |
+
"eval_precision": 0.5640414016020209,
|
| 460 |
+
"eval_recall": 0.6398763523956723,
|
| 461 |
+
"eval_runtime": 10.0413,
|
| 462 |
+
"eval_samples_per_second": 128.867,
|
| 463 |
+
"eval_steps_per_second": 2.091,
|
| 464 |
+
"step": 380
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 19.49,
|
| 468 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 469 |
+
"loss": 0.8826,
|
| 470 |
+
"step": 390
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 19.99,
|
| 474 |
+
"learning_rate": 0.0,
|
| 475 |
+
"loss": 0.846,
|
| 476 |
+
"step": 400
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 19.99,
|
| 480 |
+
"eval_accuracy": 0.6452859350850078,
|
| 481 |
+
"eval_f1": 0.5963647629954705,
|
| 482 |
+
"eval_loss": 0.9262650012969971,
|
| 483 |
+
"eval_precision": 0.5727919568038408,
|
| 484 |
+
"eval_recall": 0.6452859350850078,
|
| 485 |
+
"eval_runtime": 10.2246,
|
| 486 |
+
"eval_samples_per_second": 126.557,
|
| 487 |
+
"eval_steps_per_second": 2.054,
|
| 488 |
+
"step": 400
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 19.99,
|
| 492 |
+
"step": 400,
|
| 493 |
+
"total_flos": 2.1968670326740623e+18,
|
| 494 |
+
"train_loss": 1.0949385786056518,
|
| 495 |
+
"train_runtime": 1181.8167,
|
| 496 |
+
"train_samples_per_second": 87.56,
|
| 497 |
+
"train_steps_per_second": 0.338
|
| 498 |
+
}
|
| 499 |
+
],
|
| 500 |
+
"max_steps": 400,
|
| 501 |
+
"num_train_epochs": 20,
|
| 502 |
+
"total_flos": 2.1968670326740623e+18,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|