paul
commited on
Commit
·
c34ef79
1
Parent(s):
7b7ca65
End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.99,
|
| 3 |
+
"total_flos": 1.832202236159447e+18,
|
| 4 |
+
"train_loss": 0.5447965228557586,
|
| 5 |
+
"train_runtime": 1430.1645,
|
| 6 |
+
"train_samples_per_second": 72.355,
|
| 7 |
+
"train_steps_per_second": 0.28
|
| 8 |
+
}
|
runs/Oct21_03-09-31_teesta/events.out.tfevents.1666301984.teesta.39935.4
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:b0b8d7cfcc5cb1b9648e0864beb520835d4aaba30d8ebf8467f51077658bfa5e
|
| 3 |
+
size 20622
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.99,
|
| 3 |
+
"total_flos": 1.832202236159447e+18,
|
| 4 |
+
"train_loss": 0.5447965228557586,
|
| 5 |
+
"train_runtime": 1430.1645,
|
| 6 |
+
"train_samples_per_second": 72.355,
|
| 7 |
+
"train_steps_per_second": 0.28
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8415765069551777,
|
| 3 |
+
"best_model_checkpoint": "cvt-13-384-22k-fv-finetuned-memes/checkpoint-380",
|
| 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": 1.6042,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.99,
|
| 18 |
+
"learning_rate": 6e-05,
|
| 19 |
+
"loss": 1.3821,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.99,
|
| 24 |
+
"eval_accuracy": 0.49690880989180836,
|
| 25 |
+
"eval_f1": 0.4458280336574581,
|
| 26 |
+
"eval_loss": 1.2779731750488281,
|
| 27 |
+
"eval_precision": 0.5083478748744594,
|
| 28 |
+
"eval_recall": 0.49690880989180836,
|
| 29 |
+
"eval_runtime": 11.7189,
|
| 30 |
+
"eval_samples_per_second": 110.42,
|
| 31 |
+
"eval_steps_per_second": 1.792,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.49,
|
| 36 |
+
"learning_rate": 9e-05,
|
| 37 |
+
"loss": 1.2697,
|
| 38 |
+
"step": 30
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.99,
|
| 42 |
+
"learning_rate": 0.00012,
|
| 43 |
+
"loss": 1.0785,
|
| 44 |
+
"step": 40
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.99,
|
| 48 |
+
"eval_accuracy": 0.6669242658423493,
|
| 49 |
+
"eval_f1": 0.6499601011830624,
|
| 50 |
+
"eval_loss": 0.8633419275283813,
|
| 51 |
+
"eval_precision": 0.6658463652527506,
|
| 52 |
+
"eval_recall": 0.6669242658423493,
|
| 53 |
+
"eval_runtime": 10.8339,
|
| 54 |
+
"eval_samples_per_second": 119.44,
|
| 55 |
+
"eval_steps_per_second": 1.938,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.49,
|
| 60 |
+
"learning_rate": 0.00011666666666666667,
|
| 61 |
+
"loss": 0.8908,
|
| 62 |
+
"step": 50
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.99,
|
| 66 |
+
"learning_rate": 0.00011333333333333333,
|
| 67 |
+
"loss": 0.8862,
|
| 68 |
+
"step": 60
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.99,
|
| 72 |
+
"eval_accuracy": 0.7217928902627512,
|
| 73 |
+
"eval_f1": 0.701310570825714,
|
| 74 |
+
"eval_loss": 0.71103435754776,
|
| 75 |
+
"eval_precision": 0.7257543548866834,
|
| 76 |
+
"eval_recall": 0.7217928902627512,
|
| 77 |
+
"eval_runtime": 11.1739,
|
| 78 |
+
"eval_samples_per_second": 115.806,
|
| 79 |
+
"eval_steps_per_second": 1.879,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.49,
|
| 84 |
+
"learning_rate": 0.00011,
|
| 85 |
+
"loss": 0.7375,
|
| 86 |
+
"step": 70
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.99,
|
| 90 |
+
"learning_rate": 0.00010666666666666667,
|
| 91 |
+
"loss": 0.665,
|
| 92 |
+
"step": 80
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.99,
|
| 96 |
+
"eval_accuracy": 0.8044822256568779,
|
| 97 |
+
"eval_f1": 0.805017946518536,
|
| 98 |
+
"eval_loss": 0.5514629483222961,
|
| 99 |
+
"eval_precision": 0.8136720242079513,
|
| 100 |
+
"eval_recall": 0.8044822256568779,
|
| 101 |
+
"eval_runtime": 10.847,
|
| 102 |
+
"eval_samples_per_second": 119.295,
|
| 103 |
+
"eval_steps_per_second": 1.936,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.49,
|
| 108 |
+
"learning_rate": 0.00010333333333333334,
|
| 109 |
+
"loss": 0.6256,
|
| 110 |
+
"step": 90
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.99,
|
| 114 |
+
"learning_rate": 0.0001,
|
| 115 |
+
"loss": 0.6056,
|
| 116 |
+
"step": 100
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.99,
|
| 120 |
+
"eval_accuracy": 0.7959814528593508,
|
| 121 |
+
"eval_f1": 0.7846029654723703,
|
| 122 |
+
"eval_loss": 0.5956416726112366,
|
| 123 |
+
"eval_precision": 0.8040705084962495,
|
| 124 |
+
"eval_recall": 0.7959814528593508,
|
| 125 |
+
"eval_runtime": 11.1412,
|
| 126 |
+
"eval_samples_per_second": 116.145,
|
| 127 |
+
"eval_steps_per_second": 1.885,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.49,
|
| 132 |
+
"learning_rate": 9.666666666666667e-05,
|
| 133 |
+
"loss": 0.5889,
|
| 134 |
+
"step": 110
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 5.99,
|
| 138 |
+
"learning_rate": 9.333333333333334e-05,
|
| 139 |
+
"loss": 0.4779,
|
| 140 |
+
"step": 120
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.99,
|
| 144 |
+
"eval_accuracy": 0.7936630602782071,
|
| 145 |
+
"eval_f1": 0.7856708002513016,
|
| 146 |
+
"eval_loss": 0.622891366481781,
|
| 147 |
+
"eval_precision": 0.7944777820954576,
|
| 148 |
+
"eval_recall": 0.7936630602782071,
|
| 149 |
+
"eval_runtime": 12.2285,
|
| 150 |
+
"eval_samples_per_second": 105.818,
|
| 151 |
+
"eval_steps_per_second": 1.717,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.49,
|
| 156 |
+
"learning_rate": 9e-05,
|
| 157 |
+
"loss": 0.4969,
|
| 158 |
+
"step": 130
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.99,
|
| 162 |
+
"learning_rate": 8.666666666666667e-05,
|
| 163 |
+
"loss": 0.4554,
|
| 164 |
+
"step": 140
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.99,
|
| 168 |
+
"eval_accuracy": 0.8098918083462133,
|
| 169 |
+
"eval_f1": 0.8086497823932973,
|
| 170 |
+
"eval_loss": 0.5355423092842102,
|
| 171 |
+
"eval_precision": 0.8125537937361387,
|
| 172 |
+
"eval_recall": 0.8098918083462133,
|
| 173 |
+
"eval_runtime": 11.0611,
|
| 174 |
+
"eval_samples_per_second": 116.986,
|
| 175 |
+
"eval_steps_per_second": 1.899,
|
| 176 |
+
"step": 140
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 7.49,
|
| 180 |
+
"learning_rate": 8.333333333333333e-05,
|
| 181 |
+
"loss": 0.475,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 7.99,
|
| 186 |
+
"learning_rate": 7.999999999999999e-05,
|
| 187 |
+
"loss": 0.4249,
|
| 188 |
+
"step": 160
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 7.99,
|
| 192 |
+
"eval_accuracy": 0.8268933539412674,
|
| 193 |
+
"eval_f1": 0.8235690575721668,
|
| 194 |
+
"eval_loss": 0.5447452664375305,
|
| 195 |
+
"eval_precision": 0.8274671013460899,
|
| 196 |
+
"eval_recall": 0.8268933539412674,
|
| 197 |
+
"eval_runtime": 10.9569,
|
| 198 |
+
"eval_samples_per_second": 118.1,
|
| 199 |
+
"eval_steps_per_second": 1.917,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.49,
|
| 204 |
+
"learning_rate": 7.666666666666667e-05,
|
| 205 |
+
"loss": 0.4241,
|
| 206 |
+
"step": 170
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.99,
|
| 210 |
+
"learning_rate": 7.333333333333334e-05,
|
| 211 |
+
"loss": 0.4313,
|
| 212 |
+
"step": 180
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 8.99,
|
| 216 |
+
"eval_accuracy": 0.8153013910355487,
|
| 217 |
+
"eval_f1": 0.8132391167433421,
|
| 218 |
+
"eval_loss": 0.5530120730400085,
|
| 219 |
+
"eval_precision": 0.8139736548329274,
|
| 220 |
+
"eval_recall": 0.8153013910355487,
|
| 221 |
+
"eval_runtime": 10.8836,
|
| 222 |
+
"eval_samples_per_second": 118.895,
|
| 223 |
+
"eval_steps_per_second": 1.93,
|
| 224 |
+
"step": 180
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 9.49,
|
| 228 |
+
"learning_rate": 7.000000000000001e-05,
|
| 229 |
+
"loss": 0.4092,
|
| 230 |
+
"step": 190
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 9.99,
|
| 234 |
+
"learning_rate": 6.666666666666667e-05,
|
| 235 |
+
"loss": 0.423,
|
| 236 |
+
"step": 200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.99,
|
| 240 |
+
"eval_accuracy": 0.8238021638330757,
|
| 241 |
+
"eval_f1": 0.8222730304295096,
|
| 242 |
+
"eval_loss": 0.5345684885978699,
|
| 243 |
+
"eval_precision": 0.8230247813283141,
|
| 244 |
+
"eval_recall": 0.8238021638330757,
|
| 245 |
+
"eval_runtime": 10.942,
|
| 246 |
+
"eval_samples_per_second": 118.259,
|
| 247 |
+
"eval_steps_per_second": 1.919,
|
| 248 |
+
"step": 200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 10.49,
|
| 252 |
+
"learning_rate": 6.333333333333333e-05,
|
| 253 |
+
"loss": 0.3905,
|
| 254 |
+
"step": 210
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 10.99,
|
| 258 |
+
"learning_rate": 6e-05,
|
| 259 |
+
"loss": 0.3997,
|
| 260 |
+
"step": 220
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 10.99,
|
| 264 |
+
"eval_accuracy": 0.8338485316846986,
|
| 265 |
+
"eval_f1": 0.8338050888395913,
|
| 266 |
+
"eval_loss": 0.5413401126861572,
|
| 267 |
+
"eval_precision": 0.8346663333915662,
|
| 268 |
+
"eval_recall": 0.8338485316846986,
|
| 269 |
+
"eval_runtime": 11.954,
|
| 270 |
+
"eval_samples_per_second": 108.248,
|
| 271 |
+
"eval_steps_per_second": 1.757,
|
| 272 |
+
"step": 220
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 11.49,
|
| 276 |
+
"learning_rate": 5.6666666666666664e-05,
|
| 277 |
+
"loss": 0.3824,
|
| 278 |
+
"step": 230
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 11.99,
|
| 282 |
+
"learning_rate": 5.333333333333333e-05,
|
| 283 |
+
"loss": 0.4095,
|
| 284 |
+
"step": 240
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 11.99,
|
| 288 |
+
"eval_accuracy": 0.8207109737248841,
|
| 289 |
+
"eval_f1": 0.8177361362413736,
|
| 290 |
+
"eval_loss": 0.5999411344528198,
|
| 291 |
+
"eval_precision": 0.8230816829155458,
|
| 292 |
+
"eval_recall": 0.8207109737248841,
|
| 293 |
+
"eval_runtime": 11.094,
|
| 294 |
+
"eval_samples_per_second": 116.639,
|
| 295 |
+
"eval_steps_per_second": 1.893,
|
| 296 |
+
"step": 240
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 12.49,
|
| 300 |
+
"learning_rate": 5e-05,
|
| 301 |
+
"loss": 0.3849,
|
| 302 |
+
"step": 250
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 12.99,
|
| 306 |
+
"learning_rate": 4.666666666666667e-05,
|
| 307 |
+
"loss": 0.3979,
|
| 308 |
+
"step": 260
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 12.99,
|
| 312 |
+
"eval_accuracy": 0.8284389489953632,
|
| 313 |
+
"eval_f1": 0.825049010410594,
|
| 314 |
+
"eval_loss": 0.563246488571167,
|
| 315 |
+
"eval_precision": 0.8254511686180086,
|
| 316 |
+
"eval_recall": 0.8284389489953632,
|
| 317 |
+
"eval_runtime": 11.1372,
|
| 318 |
+
"eval_samples_per_second": 116.187,
|
| 319 |
+
"eval_steps_per_second": 1.886,
|
| 320 |
+
"step": 260
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 13.49,
|
| 324 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 325 |
+
"loss": 0.3571,
|
| 326 |
+
"step": 270
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 13.99,
|
| 330 |
+
"learning_rate": 3.9999999999999996e-05,
|
| 331 |
+
"loss": 0.3408,
|
| 332 |
+
"step": 280
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 13.99,
|
| 336 |
+
"eval_accuracy": 0.8207109737248841,
|
| 337 |
+
"eval_f1": 0.819562228886707,
|
| 338 |
+
"eval_loss": 0.5724937319755554,
|
| 339 |
+
"eval_precision": 0.8198440242244688,
|
| 340 |
+
"eval_recall": 0.8207109737248841,
|
| 341 |
+
"eval_runtime": 10.994,
|
| 342 |
+
"eval_samples_per_second": 117.7,
|
| 343 |
+
"eval_steps_per_second": 1.91,
|
| 344 |
+
"step": 280
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 14.49,
|
| 348 |
+
"learning_rate": 3.666666666666667e-05,
|
| 349 |
+
"loss": 0.3746,
|
| 350 |
+
"step": 290
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 14.99,
|
| 354 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 355 |
+
"loss": 0.3828,
|
| 356 |
+
"step": 300
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 14.99,
|
| 360 |
+
"eval_accuracy": 0.8276661514683153,
|
| 361 |
+
"eval_f1": 0.8260480131366693,
|
| 362 |
+
"eval_loss": 0.5630865693092346,
|
| 363 |
+
"eval_precision": 0.8257927020758725,
|
| 364 |
+
"eval_recall": 0.8276661514683153,
|
| 365 |
+
"eval_runtime": 10.9146,
|
| 366 |
+
"eval_samples_per_second": 118.557,
|
| 367 |
+
"eval_steps_per_second": 1.924,
|
| 368 |
+
"step": 300
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 15.49,
|
| 372 |
+
"learning_rate": 3e-05,
|
| 373 |
+
"loss": 0.3506,
|
| 374 |
+
"step": 310
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 15.99,
|
| 378 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 379 |
+
"loss": 0.3595,
|
| 380 |
+
"step": 320
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 15.99,
|
| 384 |
+
"eval_accuracy": 0.8307573415765069,
|
| 385 |
+
"eval_f1": 0.8275327108334436,
|
| 386 |
+
"eval_loss": 0.6005313396453857,
|
| 387 |
+
"eval_precision": 0.8296678468094887,
|
| 388 |
+
"eval_recall": 0.8307573415765069,
|
| 389 |
+
"eval_runtime": 11.7668,
|
| 390 |
+
"eval_samples_per_second": 109.971,
|
| 391 |
+
"eval_steps_per_second": 1.785,
|
| 392 |
+
"step": 320
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 16.49,
|
| 396 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 397 |
+
"loss": 0.3535,
|
| 398 |
+
"step": 330
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 16.99,
|
| 402 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 403 |
+
"loss": 0.3789,
|
| 404 |
+
"step": 340
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 16.99,
|
| 408 |
+
"eval_accuracy": 0.8299845440494591,
|
| 409 |
+
"eval_f1": 0.8273370558566532,
|
| 410 |
+
"eval_loss": 0.5840371251106262,
|
| 411 |
+
"eval_precision": 0.827140388432744,
|
| 412 |
+
"eval_recall": 0.8299845440494591,
|
| 413 |
+
"eval_runtime": 10.837,
|
| 414 |
+
"eval_samples_per_second": 119.405,
|
| 415 |
+
"eval_steps_per_second": 1.938,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 17.49,
|
| 420 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 421 |
+
"loss": 0.389,
|
| 422 |
+
"step": 350
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 17.99,
|
| 426 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 427 |
+
"loss": 0.3545,
|
| 428 |
+
"step": 360
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 17.99,
|
| 432 |
+
"eval_accuracy": 0.8245749613601236,
|
| 433 |
+
"eval_f1": 0.8222146970644545,
|
| 434 |
+
"eval_loss": 0.5983098745346069,
|
| 435 |
+
"eval_precision": 0.8226259868849637,
|
| 436 |
+
"eval_recall": 0.8245749613601236,
|
| 437 |
+
"eval_runtime": 10.7069,
|
| 438 |
+
"eval_samples_per_second": 120.857,
|
| 439 |
+
"eval_steps_per_second": 1.961,
|
| 440 |
+
"step": 360
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 18.49,
|
| 444 |
+
"learning_rate": 9.999999999999999e-06,
|
| 445 |
+
"loss": 0.3661,
|
| 446 |
+
"step": 370
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 18.99,
|
| 450 |
+
"learning_rate": 6.666666666666667e-06,
|
| 451 |
+
"loss": 0.3472,
|
| 452 |
+
"step": 380
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 18.99,
|
| 456 |
+
"eval_accuracy": 0.8415765069551777,
|
| 457 |
+
"eval_f1": 0.8390361807029366,
|
| 458 |
+
"eval_loss": 0.5795101523399353,
|
| 459 |
+
"eval_precision": 0.838184001941316,
|
| 460 |
+
"eval_recall": 0.8415765069551777,
|
| 461 |
+
"eval_runtime": 10.7681,
|
| 462 |
+
"eval_samples_per_second": 120.17,
|
| 463 |
+
"eval_steps_per_second": 1.95,
|
| 464 |
+
"step": 380
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 19.49,
|
| 468 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 469 |
+
"loss": 0.3654,
|
| 470 |
+
"step": 390
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 19.99,
|
| 474 |
+
"learning_rate": 0.0,
|
| 475 |
+
"loss": 0.355,
|
| 476 |
+
"step": 400
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 19.99,
|
| 480 |
+
"eval_accuracy": 0.8315301391035549,
|
| 481 |
+
"eval_f1": 0.8292026505769348,
|
| 482 |
+
"eval_loss": 0.5761234760284424,
|
| 483 |
+
"eval_precision": 0.8302128280229624,
|
| 484 |
+
"eval_recall": 0.8315301391035549,
|
| 485 |
+
"eval_runtime": 11.7079,
|
| 486 |
+
"eval_samples_per_second": 110.524,
|
| 487 |
+
"eval_steps_per_second": 1.794,
|
| 488 |
+
"step": 400
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 19.99,
|
| 492 |
+
"step": 400,
|
| 493 |
+
"total_flos": 1.832202236159447e+18,
|
| 494 |
+
"train_loss": 0.5447965228557586,
|
| 495 |
+
"train_runtime": 1430.1645,
|
| 496 |
+
"train_samples_per_second": 72.355,
|
| 497 |
+
"train_steps_per_second": 0.28
|
| 498 |
+
}
|
| 499 |
+
],
|
| 500 |
+
"max_steps": 400,
|
| 501 |
+
"num_train_epochs": 20,
|
| 502 |
+
"total_flos": 1.832202236159447e+18,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|