paul
commited on
Commit
•
ae82612
1
Parent(s):
a9e3c03
End of training
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Jan23_01-00-26_teesta/events.out.tfevents.1674415839.teesta.12792.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +361 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.97,
|
| 3 |
+
"total_flos": 3.206521023309693e+18,
|
| 4 |
+
"train_loss": 0.16520703649148344,
|
| 5 |
+
"train_runtime": 938.1956,
|
| 6 |
+
"train_samples_per_second": 44.127,
|
| 7 |
+
"train_steps_per_second": 0.171
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343274861
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47633b06ce778902fb75f10ac1b0dac5363cd40f1d6f6d43ae5496ffa2aa8a24
|
| 3 |
size 343274861
|
runs/Jan23_01-00-26_teesta/events.out.tfevents.1674415839.teesta.12792.0
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 sha256:3cca0b87a25a00e6adff2cc51be1fdc9f6d20a69b42eca57a39b5158c3427b20
|
| 3 |
+
size 15658
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.97,
|
| 3 |
+
"total_flos": 3.206521023309693e+18,
|
| 4 |
+
"train_loss": 0.16520703649148344,
|
| 5 |
+
"train_runtime": 938.1956,
|
| 6 |
+
"train_samples_per_second": 44.127,
|
| 7 |
+
"train_steps_per_second": 0.171
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.908256880733945,
|
| 3 |
+
"best_model_checkpoint": "google-vit-base-patch16-224-cartoon-emotion-detection/checkpoint-128",
|
| 4 |
+
"epoch": 19.96969696969697,
|
| 5 |
+
"global_step": 160,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.97,
|
| 12 |
+
"eval_accuracy": 0.5779816513761468,
|
| 13 |
+
"eval_f1": 0.5496044478283086,
|
| 14 |
+
"eval_loss": 1.0942180156707764,
|
| 15 |
+
"eval_precision": 0.6101578737429934,
|
| 16 |
+
"eval_recall": 0.5779816513761468,
|
| 17 |
+
"eval_runtime": 6.1545,
|
| 18 |
+
"eval_samples_per_second": 17.711,
|
| 19 |
+
"eval_steps_per_second": 0.325,
|
| 20 |
+
"step": 8
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.24,
|
| 24 |
+
"learning_rate": 7.500000000000001e-05,
|
| 25 |
+
"loss": 1.3198,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.97,
|
| 30 |
+
"eval_accuracy": 0.7614678899082569,
|
| 31 |
+
"eval_f1": 0.7493394355240011,
|
| 32 |
+
"eval_loss": 0.6914369463920593,
|
| 33 |
+
"eval_precision": 0.7497958611640302,
|
| 34 |
+
"eval_recall": 0.7614678899082569,
|
| 35 |
+
"eval_runtime": 4.6109,
|
| 36 |
+
"eval_samples_per_second": 23.64,
|
| 37 |
+
"eval_steps_per_second": 0.434,
|
| 38 |
+
"step": 16
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.48,
|
| 42 |
+
"learning_rate": 0.00011666666666666667,
|
| 43 |
+
"loss": 0.6694,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.97,
|
| 48 |
+
"eval_accuracy": 0.7889908256880734,
|
| 49 |
+
"eval_f1": 0.7780956547838787,
|
| 50 |
+
"eval_loss": 0.47017431259155273,
|
| 51 |
+
"eval_precision": 0.7808396335677842,
|
| 52 |
+
"eval_recall": 0.7889908256880734,
|
| 53 |
+
"eval_runtime": 5.0072,
|
| 54 |
+
"eval_samples_per_second": 21.769,
|
| 55 |
+
"eval_steps_per_second": 0.399,
|
| 56 |
+
"step": 24
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.73,
|
| 60 |
+
"learning_rate": 0.00010833333333333334,
|
| 61 |
+
"loss": 0.2725,
|
| 62 |
+
"step": 30
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.97,
|
| 66 |
+
"eval_accuracy": 0.8532110091743119,
|
| 67 |
+
"eval_f1": 0.852182928635528,
|
| 68 |
+
"eval_loss": 0.3957468569278717,
|
| 69 |
+
"eval_precision": 0.8513973454558302,
|
| 70 |
+
"eval_recall": 0.8532110091743119,
|
| 71 |
+
"eval_runtime": 5.1072,
|
| 72 |
+
"eval_samples_per_second": 21.342,
|
| 73 |
+
"eval_steps_per_second": 0.392,
|
| 74 |
+
"step": 32
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.97,
|
| 78 |
+
"learning_rate": 0.0001,
|
| 79 |
+
"loss": 0.1116,
|
| 80 |
+
"step": 40
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.97,
|
| 84 |
+
"eval_accuracy": 0.8715596330275229,
|
| 85 |
+
"eval_f1": 0.8693196656152253,
|
| 86 |
+
"eval_loss": 0.3428177833557129,
|
| 87 |
+
"eval_precision": 0.8696674261696613,
|
| 88 |
+
"eval_recall": 0.8715596330275229,
|
| 89 |
+
"eval_runtime": 4.6559,
|
| 90 |
+
"eval_samples_per_second": 23.411,
|
| 91 |
+
"eval_steps_per_second": 0.43,
|
| 92 |
+
"step": 40
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 5.97,
|
| 96 |
+
"eval_accuracy": 0.8532110091743119,
|
| 97 |
+
"eval_f1": 0.852182928635528,
|
| 98 |
+
"eval_loss": 0.38648203015327454,
|
| 99 |
+
"eval_precision": 0.8513973454558302,
|
| 100 |
+
"eval_recall": 0.8532110091743119,
|
| 101 |
+
"eval_runtime": 4.7748,
|
| 102 |
+
"eval_samples_per_second": 22.828,
|
| 103 |
+
"eval_steps_per_second": 0.419,
|
| 104 |
+
"step": 48
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.24,
|
| 108 |
+
"learning_rate": 9.166666666666667e-05,
|
| 109 |
+
"loss": 0.0486,
|
| 110 |
+
"step": 50
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 6.97,
|
| 114 |
+
"eval_accuracy": 0.8532110091743119,
|
| 115 |
+
"eval_f1": 0.8506716755357531,
|
| 116 |
+
"eval_loss": 0.3445301055908203,
|
| 117 |
+
"eval_precision": 0.8494739768520552,
|
| 118 |
+
"eval_recall": 0.8532110091743119,
|
| 119 |
+
"eval_runtime": 4.611,
|
| 120 |
+
"eval_samples_per_second": 23.639,
|
| 121 |
+
"eval_steps_per_second": 0.434,
|
| 122 |
+
"step": 56
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 7.48,
|
| 126 |
+
"learning_rate": 8.333333333333333e-05,
|
| 127 |
+
"loss": 0.0346,
|
| 128 |
+
"step": 60
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.97,
|
| 132 |
+
"eval_accuracy": 0.8807339449541285,
|
| 133 |
+
"eval_f1": 0.8831061019446504,
|
| 134 |
+
"eval_loss": 0.35539454221725464,
|
| 135 |
+
"eval_precision": 0.8921137072355041,
|
| 136 |
+
"eval_recall": 0.8807339449541285,
|
| 137 |
+
"eval_runtime": 5.4806,
|
| 138 |
+
"eval_samples_per_second": 19.888,
|
| 139 |
+
"eval_steps_per_second": 0.365,
|
| 140 |
+
"step": 64
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 8.73,
|
| 144 |
+
"learning_rate": 7.500000000000001e-05,
|
| 145 |
+
"loss": 0.0304,
|
| 146 |
+
"step": 70
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 8.97,
|
| 150 |
+
"eval_accuracy": 0.8623853211009175,
|
| 151 |
+
"eval_f1": 0.8605019312208758,
|
| 152 |
+
"eval_loss": 0.3100130259990692,
|
| 153 |
+
"eval_precision": 0.859227121302747,
|
| 154 |
+
"eval_recall": 0.8623853211009175,
|
| 155 |
+
"eval_runtime": 4.4858,
|
| 156 |
+
"eval_samples_per_second": 24.299,
|
| 157 |
+
"eval_steps_per_second": 0.446,
|
| 158 |
+
"step": 72
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 9.97,
|
| 162 |
+
"learning_rate": 6.666666666666667e-05,
|
| 163 |
+
"loss": 0.0215,
|
| 164 |
+
"step": 80
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 9.97,
|
| 168 |
+
"eval_accuracy": 0.8715596330275229,
|
| 169 |
+
"eval_f1": 0.8706535281458829,
|
| 170 |
+
"eval_loss": 0.3717760443687439,
|
| 171 |
+
"eval_precision": 0.8700050641259672,
|
| 172 |
+
"eval_recall": 0.8715596330275229,
|
| 173 |
+
"eval_runtime": 4.4596,
|
| 174 |
+
"eval_samples_per_second": 24.442,
|
| 175 |
+
"eval_steps_per_second": 0.448,
|
| 176 |
+
"step": 80
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.97,
|
| 180 |
+
"eval_accuracy": 0.8899082568807339,
|
| 181 |
+
"eval_f1": 0.8896213803351865,
|
| 182 |
+
"eval_loss": 0.3945842683315277,
|
| 183 |
+
"eval_precision": 0.8901151962474995,
|
| 184 |
+
"eval_recall": 0.8899082568807339,
|
| 185 |
+
"eval_runtime": 4.3806,
|
| 186 |
+
"eval_samples_per_second": 24.882,
|
| 187 |
+
"eval_steps_per_second": 0.457,
|
| 188 |
+
"step": 88
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 11.24,
|
| 192 |
+
"learning_rate": 5.833333333333333e-05,
|
| 193 |
+
"loss": 0.0201,
|
| 194 |
+
"step": 90
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 11.97,
|
| 198 |
+
"eval_accuracy": 0.8532110091743119,
|
| 199 |
+
"eval_f1": 0.8523968233405174,
|
| 200 |
+
"eval_loss": 0.45045793056488037,
|
| 201 |
+
"eval_precision": 0.8557594291539246,
|
| 202 |
+
"eval_recall": 0.8532110091743119,
|
| 203 |
+
"eval_runtime": 4.5094,
|
| 204 |
+
"eval_samples_per_second": 24.172,
|
| 205 |
+
"eval_steps_per_second": 0.444,
|
| 206 |
+
"step": 96
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 12.48,
|
| 210 |
+
"learning_rate": 5e-05,
|
| 211 |
+
"loss": 0.02,
|
| 212 |
+
"step": 100
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 12.97,
|
| 216 |
+
"eval_accuracy": 0.8715596330275229,
|
| 217 |
+
"eval_f1": 0.8718071382402676,
|
| 218 |
+
"eval_loss": 0.45429742336273193,
|
| 219 |
+
"eval_precision": 0.8734266859810075,
|
| 220 |
+
"eval_recall": 0.8715596330275229,
|
| 221 |
+
"eval_runtime": 4.3136,
|
| 222 |
+
"eval_samples_per_second": 25.269,
|
| 223 |
+
"eval_steps_per_second": 0.464,
|
| 224 |
+
"step": 104
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.73,
|
| 228 |
+
"learning_rate": 4.1666666666666665e-05,
|
| 229 |
+
"loss": 0.0181,
|
| 230 |
+
"step": 110
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 13.97,
|
| 234 |
+
"eval_accuracy": 0.8899082568807339,
|
| 235 |
+
"eval_f1": 0.8884082118557669,
|
| 236 |
+
"eval_loss": 0.38368093967437744,
|
| 237 |
+
"eval_precision": 0.887776250789288,
|
| 238 |
+
"eval_recall": 0.8899082568807339,
|
| 239 |
+
"eval_runtime": 5.0241,
|
| 240 |
+
"eval_samples_per_second": 21.695,
|
| 241 |
+
"eval_steps_per_second": 0.398,
|
| 242 |
+
"step": 112
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 14.97,
|
| 246 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 247 |
+
"loss": 0.0158,
|
| 248 |
+
"step": 120
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 14.97,
|
| 252 |
+
"eval_accuracy": 0.8715596330275229,
|
| 253 |
+
"eval_f1": 0.8690629924501888,
|
| 254 |
+
"eval_loss": 0.39043566584587097,
|
| 255 |
+
"eval_precision": 0.8676131770089379,
|
| 256 |
+
"eval_recall": 0.8715596330275229,
|
| 257 |
+
"eval_runtime": 4.6243,
|
| 258 |
+
"eval_samples_per_second": 23.571,
|
| 259 |
+
"eval_steps_per_second": 0.432,
|
| 260 |
+
"step": 120
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 15.97,
|
| 264 |
+
"eval_accuracy": 0.908256880733945,
|
| 265 |
+
"eval_f1": 0.9076765848444429,
|
| 266 |
+
"eval_loss": 0.38814032077789307,
|
| 267 |
+
"eval_precision": 0.9077606207554442,
|
| 268 |
+
"eval_recall": 0.908256880733945,
|
| 269 |
+
"eval_runtime": 4.4737,
|
| 270 |
+
"eval_samples_per_second": 24.364,
|
| 271 |
+
"eval_steps_per_second": 0.447,
|
| 272 |
+
"step": 128
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 16.24,
|
| 276 |
+
"learning_rate": 2.5e-05,
|
| 277 |
+
"loss": 0.0147,
|
| 278 |
+
"step": 130
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 16.97,
|
| 282 |
+
"eval_accuracy": 0.8807339449541285,
|
| 283 |
+
"eval_f1": 0.8785402173459473,
|
| 284 |
+
"eval_loss": 0.4233301281929016,
|
| 285 |
+
"eval_precision": 0.877296042811741,
|
| 286 |
+
"eval_recall": 0.8807339449541285,
|
| 287 |
+
"eval_runtime": 5.5943,
|
| 288 |
+
"eval_samples_per_second": 19.484,
|
| 289 |
+
"eval_steps_per_second": 0.358,
|
| 290 |
+
"step": 136
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 17.48,
|
| 294 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 295 |
+
"loss": 0.0138,
|
| 296 |
+
"step": 140
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 17.97,
|
| 300 |
+
"eval_accuracy": 0.8715596330275229,
|
| 301 |
+
"eval_f1": 0.8706535281458829,
|
| 302 |
+
"eval_loss": 0.4334617853164673,
|
| 303 |
+
"eval_precision": 0.8700050641259672,
|
| 304 |
+
"eval_recall": 0.8715596330275229,
|
| 305 |
+
"eval_runtime": 4.4249,
|
| 306 |
+
"eval_samples_per_second": 24.634,
|
| 307 |
+
"eval_steps_per_second": 0.452,
|
| 308 |
+
"step": 144
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 18.73,
|
| 312 |
+
"learning_rate": 8.333333333333334e-06,
|
| 313 |
+
"loss": 0.0166,
|
| 314 |
+
"step": 150
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 18.97,
|
| 318 |
+
"eval_accuracy": 0.8715596330275229,
|
| 319 |
+
"eval_f1": 0.8701110574601642,
|
| 320 |
+
"eval_loss": 0.44918692111968994,
|
| 321 |
+
"eval_precision": 0.8689788374764814,
|
| 322 |
+
"eval_recall": 0.8715596330275229,
|
| 323 |
+
"eval_runtime": 4.6129,
|
| 324 |
+
"eval_samples_per_second": 23.629,
|
| 325 |
+
"eval_steps_per_second": 0.434,
|
| 326 |
+
"step": 152
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 19.97,
|
| 330 |
+
"learning_rate": 0.0,
|
| 331 |
+
"loss": 0.016,
|
| 332 |
+
"step": 160
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 19.97,
|
| 336 |
+
"eval_accuracy": 0.8715596330275229,
|
| 337 |
+
"eval_f1": 0.871683140929764,
|
| 338 |
+
"eval_loss": 0.4169996976852417,
|
| 339 |
+
"eval_precision": 0.8725197999744695,
|
| 340 |
+
"eval_recall": 0.8715596330275229,
|
| 341 |
+
"eval_runtime": 4.5712,
|
| 342 |
+
"eval_samples_per_second": 23.845,
|
| 343 |
+
"eval_steps_per_second": 0.438,
|
| 344 |
+
"step": 160
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 19.97,
|
| 348 |
+
"step": 160,
|
| 349 |
+
"total_flos": 3.206521023309693e+18,
|
| 350 |
+
"train_loss": 0.16520703649148344,
|
| 351 |
+
"train_runtime": 938.1956,
|
| 352 |
+
"train_samples_per_second": 44.127,
|
| 353 |
+
"train_steps_per_second": 0.171
|
| 354 |
+
}
|
| 355 |
+
],
|
| 356 |
+
"max_steps": 160,
|
| 357 |
+
"num_train_epochs": 20,
|
| 358 |
+
"total_flos": 3.206521023309693e+18,
|
| 359 |
+
"trial_name": null,
|
| 360 |
+
"trial_params": null
|
| 361 |
+
}
|