paul
commited on
Commit
·
353a9d7
1
Parent(s):
6673261
End of training
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Oct20_17-16-04_teesta/events.out.tfevents.1666266382.teesta.4227.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +505 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.99,
|
| 3 |
+
"total_flos": 1.1809647563061068e+19,
|
| 4 |
+
"train_loss": 0.36638923436403276,
|
| 5 |
+
"train_runtime": 5624.3012,
|
| 6 |
+
"train_samples_per_second": 18.399,
|
| 7 |
+
"train_steps_per_second": 0.071
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 96918949
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbf06bef640245398ba513f818271955b18039be67272e7d37e6c0940ef5db53
|
| 3 |
size 96918949
|
runs/Oct20_17-16-04_teesta/events.out.tfevents.1666266382.teesta.4227.0
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 sha256:4129a8356191fe4cd6af930bab95f176d42c29ac35b70746590101268ddf6c3f
|
| 3 |
+
size 20366
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.99,
|
| 3 |
+
"total_flos": 1.1809647563061068e+19,
|
| 4 |
+
"train_loss": 0.36638923436403276,
|
| 5 |
+
"train_runtime": 5624.3012,
|
| 6 |
+
"train_samples_per_second": 18.399,
|
| 7 |
+
"train_steps_per_second": 0.071
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8361669242658424,
|
| 3 |
+
"best_model_checkpoint": "mit-b2-fv-finetuned-memes/checkpoint-180",
|
| 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": 1.6187,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.99,
|
| 18 |
+
"learning_rate": 6e-05,
|
| 19 |
+
"loss": 1.3683,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.99,
|
| 24 |
+
"eval_accuracy": 0.5703245749613601,
|
| 25 |
+
"eval_f1": 0.4915430460832317,
|
| 26 |
+
"eval_loss": 1.1798477172851562,
|
| 27 |
+
"eval_precision": 0.4913898246935893,
|
| 28 |
+
"eval_recall": 0.5703245749613601,
|
| 29 |
+
"eval_runtime": 25.7297,
|
| 30 |
+
"eval_samples_per_second": 50.292,
|
| 31 |
+
"eval_steps_per_second": 0.816,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.49,
|
| 36 |
+
"learning_rate": 9e-05,
|
| 37 |
+
"loss": 1.1618,
|
| 38 |
+
"step": 30
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.99,
|
| 42 |
+
"learning_rate": 0.00012,
|
| 43 |
+
"loss": 1.0113,
|
| 44 |
+
"step": 40
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.99,
|
| 48 |
+
"eval_accuracy": 0.615919629057187,
|
| 49 |
+
"eval_f1": 0.6273659431894075,
|
| 50 |
+
"eval_loss": 1.0383963584899902,
|
| 51 |
+
"eval_precision": 0.6812645697652936,
|
| 52 |
+
"eval_recall": 0.615919629057187,
|
| 53 |
+
"eval_runtime": 24.3501,
|
| 54 |
+
"eval_samples_per_second": 53.142,
|
| 55 |
+
"eval_steps_per_second": 0.862,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.49,
|
| 60 |
+
"learning_rate": 0.00011666666666666667,
|
| 61 |
+
"loss": 0.89,
|
| 62 |
+
"step": 50
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.99,
|
| 66 |
+
"learning_rate": 0.00011333333333333333,
|
| 67 |
+
"loss": 0.7581,
|
| 68 |
+
"step": 60
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.99,
|
| 72 |
+
"eval_accuracy": 0.6808346213292118,
|
| 73 |
+
"eval_f1": 0.6839700359928248,
|
| 74 |
+
"eval_loss": 0.834769070148468,
|
| 75 |
+
"eval_precision": 0.7376556278142583,
|
| 76 |
+
"eval_recall": 0.6808346213292118,
|
| 77 |
+
"eval_runtime": 25.9343,
|
| 78 |
+
"eval_samples_per_second": 49.895,
|
| 79 |
+
"eval_steps_per_second": 0.81,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.49,
|
| 84 |
+
"learning_rate": 0.00011,
|
| 85 |
+
"loss": 0.706,
|
| 86 |
+
"step": 70
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.99,
|
| 90 |
+
"learning_rate": 0.00010666666666666667,
|
| 91 |
+
"loss": 0.6241,
|
| 92 |
+
"step": 80
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 3.99,
|
| 96 |
+
"eval_accuracy": 0.7712519319938176,
|
| 97 |
+
"eval_f1": 0.7734801228569064,
|
| 98 |
+
"eval_loss": 0.6034244894981384,
|
| 99 |
+
"eval_precision": 0.7864230813661904,
|
| 100 |
+
"eval_recall": 0.7712519319938176,
|
| 101 |
+
"eval_runtime": 24.0546,
|
| 102 |
+
"eval_samples_per_second": 53.794,
|
| 103 |
+
"eval_steps_per_second": 0.873,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.49,
|
| 108 |
+
"learning_rate": 0.00010333333333333334,
|
| 109 |
+
"loss": 0.574,
|
| 110 |
+
"step": 90
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.99,
|
| 114 |
+
"learning_rate": 0.0001,
|
| 115 |
+
"loss": 0.4999,
|
| 116 |
+
"step": 100
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 4.99,
|
| 120 |
+
"eval_accuracy": 0.794435857805255,
|
| 121 |
+
"eval_f1": 0.7908928134527277,
|
| 122 |
+
"eval_loss": 0.5480836033821106,
|
| 123 |
+
"eval_precision": 0.7999661256925431,
|
| 124 |
+
"eval_recall": 0.794435857805255,
|
| 125 |
+
"eval_runtime": 24.7472,
|
| 126 |
+
"eval_samples_per_second": 52.289,
|
| 127 |
+
"eval_steps_per_second": 0.849,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.49,
|
| 132 |
+
"learning_rate": 9.666666666666667e-05,
|
| 133 |
+
"loss": 0.4429,
|
| 134 |
+
"step": 110
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 5.99,
|
| 138 |
+
"learning_rate": 9.333333333333334e-05,
|
| 139 |
+
"loss": 0.3981,
|
| 140 |
+
"step": 120
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 5.99,
|
| 144 |
+
"eval_accuracy": 0.8021638330757341,
|
| 145 |
+
"eval_f1": 0.8000125861001945,
|
| 146 |
+
"eval_loss": 0.5253472328186035,
|
| 147 |
+
"eval_precision": 0.8090800980369639,
|
| 148 |
+
"eval_recall": 0.8021638330757341,
|
| 149 |
+
"eval_runtime": 24.5494,
|
| 150 |
+
"eval_samples_per_second": 52.71,
|
| 151 |
+
"eval_steps_per_second": 0.855,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.49,
|
| 156 |
+
"learning_rate": 9e-05,
|
| 157 |
+
"loss": 0.3603,
|
| 158 |
+
"step": 130
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 6.99,
|
| 162 |
+
"learning_rate": 8.666666666666667e-05,
|
| 163 |
+
"loss": 0.3484,
|
| 164 |
+
"step": 140
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.99,
|
| 168 |
+
"eval_accuracy": 0.8238021638330757,
|
| 169 |
+
"eval_f1": 0.8146387182540739,
|
| 170 |
+
"eval_loss": 0.46875712275505066,
|
| 171 |
+
"eval_precision": 0.8147156146167328,
|
| 172 |
+
"eval_recall": 0.8238021638330757,
|
| 173 |
+
"eval_runtime": 25.2779,
|
| 174 |
+
"eval_samples_per_second": 51.191,
|
| 175 |
+
"eval_steps_per_second": 0.831,
|
| 176 |
+
"step": 140
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 7.49,
|
| 180 |
+
"learning_rate": 8.333333333333333e-05,
|
| 181 |
+
"loss": 0.2789,
|
| 182 |
+
"step": 150
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 7.99,
|
| 186 |
+
"learning_rate": 7.999999999999999e-05,
|
| 187 |
+
"loss": 0.3142,
|
| 188 |
+
"step": 160
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 7.99,
|
| 192 |
+
"eval_accuracy": 0.7867078825347759,
|
| 193 |
+
"eval_f1": 0.7919733028920879,
|
| 194 |
+
"eval_loss": 0.6245487928390503,
|
| 195 |
+
"eval_precision": 0.820948058010093,
|
| 196 |
+
"eval_recall": 0.7867078825347759,
|
| 197 |
+
"eval_runtime": 24.2688,
|
| 198 |
+
"eval_samples_per_second": 53.32,
|
| 199 |
+
"eval_steps_per_second": 0.865,
|
| 200 |
+
"step": 160
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 8.49,
|
| 204 |
+
"learning_rate": 7.666666666666667e-05,
|
| 205 |
+
"loss": 0.2513,
|
| 206 |
+
"step": 170
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 8.99,
|
| 210 |
+
"learning_rate": 7.333333333333334e-05,
|
| 211 |
+
"loss": 0.2339,
|
| 212 |
+
"step": 180
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 8.99,
|
| 216 |
+
"eval_accuracy": 0.8361669242658424,
|
| 217 |
+
"eval_f1": 0.8354791396567843,
|
| 218 |
+
"eval_loss": 0.5053289532661438,
|
| 219 |
+
"eval_precision": 0.8426050546923035,
|
| 220 |
+
"eval_recall": 0.8361669242658424,
|
| 221 |
+
"eval_runtime": 24.696,
|
| 222 |
+
"eval_samples_per_second": 52.397,
|
| 223 |
+
"eval_steps_per_second": 0.85,
|
| 224 |
+
"step": 180
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 9.49,
|
| 228 |
+
"learning_rate": 7.000000000000001e-05,
|
| 229 |
+
"loss": 0.1999,
|
| 230 |
+
"step": 190
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 9.99,
|
| 234 |
+
"learning_rate": 6.666666666666667e-05,
|
| 235 |
+
"loss": 0.2284,
|
| 236 |
+
"step": 200
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 9.99,
|
| 240 |
+
"eval_accuracy": 0.8230293663060279,
|
| 241 |
+
"eval_f1": 0.8187153015149123,
|
| 242 |
+
"eval_loss": 0.5069507360458374,
|
| 243 |
+
"eval_precision": 0.822032270944375,
|
| 244 |
+
"eval_recall": 0.8230293663060279,
|
| 245 |
+
"eval_runtime": 23.6165,
|
| 246 |
+
"eval_samples_per_second": 54.792,
|
| 247 |
+
"eval_steps_per_second": 0.889,
|
| 248 |
+
"step": 200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 10.49,
|
| 252 |
+
"learning_rate": 6.333333333333333e-05,
|
| 253 |
+
"loss": 0.1861,
|
| 254 |
+
"step": 210
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 10.99,
|
| 258 |
+
"learning_rate": 6e-05,
|
| 259 |
+
"loss": 0.1824,
|
| 260 |
+
"step": 220
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 10.99,
|
| 264 |
+
"eval_accuracy": 0.8006182380216383,
|
| 265 |
+
"eval_f1": 0.8035059555919015,
|
| 266 |
+
"eval_loss": 0.5779785513877869,
|
| 267 |
+
"eval_precision": 0.8138172496848511,
|
| 268 |
+
"eval_recall": 0.8006182380216383,
|
| 269 |
+
"eval_runtime": 24.9222,
|
| 270 |
+
"eval_samples_per_second": 51.922,
|
| 271 |
+
"eval_steps_per_second": 0.843,
|
| 272 |
+
"step": 220
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 11.49,
|
| 276 |
+
"learning_rate": 5.6666666666666664e-05,
|
| 277 |
+
"loss": 0.1647,
|
| 278 |
+
"step": 230
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 11.99,
|
| 282 |
+
"learning_rate": 5.333333333333333e-05,
|
| 283 |
+
"loss": 0.1561,
|
| 284 |
+
"step": 240
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 11.99,
|
| 288 |
+
"eval_accuracy": 0.8253477588871716,
|
| 289 |
+
"eval_f1": 0.8217716611197545,
|
| 290 |
+
"eval_loss": 0.5429410338401794,
|
| 291 |
+
"eval_precision": 0.8196794558105368,
|
| 292 |
+
"eval_recall": 0.8253477588871716,
|
| 293 |
+
"eval_runtime": 23.8337,
|
| 294 |
+
"eval_samples_per_second": 54.293,
|
| 295 |
+
"eval_steps_per_second": 0.881,
|
| 296 |
+
"step": 240
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 12.49,
|
| 300 |
+
"learning_rate": 5e-05,
|
| 301 |
+
"loss": 0.1551,
|
| 302 |
+
"step": 250
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 12.99,
|
| 306 |
+
"learning_rate": 4.666666666666667e-05,
|
| 307 |
+
"loss": 0.1229,
|
| 308 |
+
"step": 260
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 12.99,
|
| 312 |
+
"eval_accuracy": 0.8330757341576507,
|
| 313 |
+
"eval_f1": 0.8303358084478046,
|
| 314 |
+
"eval_loss": 0.5324836373329163,
|
| 315 |
+
"eval_precision": 0.8296069273511578,
|
| 316 |
+
"eval_recall": 0.8330757341576507,
|
| 317 |
+
"eval_runtime": 25.348,
|
| 318 |
+
"eval_samples_per_second": 51.049,
|
| 319 |
+
"eval_steps_per_second": 0.828,
|
| 320 |
+
"step": 260
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 13.49,
|
| 324 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 325 |
+
"loss": 0.1208,
|
| 326 |
+
"step": 270
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 13.99,
|
| 330 |
+
"learning_rate": 3.9999999999999996e-05,
|
| 331 |
+
"loss": 0.1232,
|
| 332 |
+
"step": 280
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 13.99,
|
| 336 |
+
"eval_accuracy": 0.8276661514683153,
|
| 337 |
+
"eval_f1": 0.8273115902224707,
|
| 338 |
+
"eval_loss": 0.5595067143440247,
|
| 339 |
+
"eval_precision": 0.8290015047050906,
|
| 340 |
+
"eval_recall": 0.8276661514683153,
|
| 341 |
+
"eval_runtime": 23.6014,
|
| 342 |
+
"eval_samples_per_second": 54.827,
|
| 343 |
+
"eval_steps_per_second": 0.89,
|
| 344 |
+
"step": 280
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 14.49,
|
| 348 |
+
"learning_rate": 3.666666666666667e-05,
|
| 349 |
+
"loss": 0.1204,
|
| 350 |
+
"step": 290
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 14.99,
|
| 354 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 355 |
+
"loss": 0.118,
|
| 356 |
+
"step": 300
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 14.99,
|
| 360 |
+
"eval_accuracy": 0.8292117465224111,
|
| 361 |
+
"eval_f1": 0.8298744039909668,
|
| 362 |
+
"eval_loss": 0.5973792672157288,
|
| 363 |
+
"eval_precision": 0.8344810455815268,
|
| 364 |
+
"eval_recall": 0.8292117465224111,
|
| 365 |
+
"eval_runtime": 24.4918,
|
| 366 |
+
"eval_samples_per_second": 52.834,
|
| 367 |
+
"eval_steps_per_second": 0.857,
|
| 368 |
+
"step": 300
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 15.49,
|
| 372 |
+
"learning_rate": 3e-05,
|
| 373 |
+
"loss": 0.1015,
|
| 374 |
+
"step": 310
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 15.99,
|
| 378 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 379 |
+
"loss": 0.11,
|
| 380 |
+
"step": 320
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 15.99,
|
| 384 |
+
"eval_accuracy": 0.8253477588871716,
|
| 385 |
+
"eval_f1": 0.8230916961516846,
|
| 386 |
+
"eval_loss": 0.579598069190979,
|
| 387 |
+
"eval_precision": 0.8228234989922505,
|
| 388 |
+
"eval_recall": 0.8253477588871716,
|
| 389 |
+
"eval_runtime": 23.8333,
|
| 390 |
+
"eval_samples_per_second": 54.294,
|
| 391 |
+
"eval_steps_per_second": 0.881,
|
| 392 |
+
"step": 320
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 16.49,
|
| 396 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 397 |
+
"loss": 0.1037,
|
| 398 |
+
"step": 330
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 16.99,
|
| 402 |
+
"learning_rate": 1.9999999999999998e-05,
|
| 403 |
+
"loss": 0.0948,
|
| 404 |
+
"step": 340
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 16.99,
|
| 408 |
+
"eval_accuracy": 0.8346213292117465,
|
| 409 |
+
"eval_f1": 0.8348916431445179,
|
| 410 |
+
"eval_loss": 0.5581147074699402,
|
| 411 |
+
"eval_precision": 0.8357545769977985,
|
| 412 |
+
"eval_recall": 0.8346213292117465,
|
| 413 |
+
"eval_runtime": 24.5732,
|
| 414 |
+
"eval_samples_per_second": 52.659,
|
| 415 |
+
"eval_steps_per_second": 0.855,
|
| 416 |
+
"step": 340
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 17.49,
|
| 420 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 421 |
+
"loss": 0.0933,
|
| 422 |
+
"step": 350
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 17.99,
|
| 426 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 427 |
+
"loss": 0.0985,
|
| 428 |
+
"step": 360
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 17.99,
|
| 432 |
+
"eval_accuracy": 0.8338485316846986,
|
| 433 |
+
"eval_f1": 0.8318239397011512,
|
| 434 |
+
"eval_loss": 0.569961428642273,
|
| 435 |
+
"eval_precision": 0.830062297595451,
|
| 436 |
+
"eval_recall": 0.8338485316846986,
|
| 437 |
+
"eval_runtime": 24.4249,
|
| 438 |
+
"eval_samples_per_second": 52.979,
|
| 439 |
+
"eval_steps_per_second": 0.86,
|
| 440 |
+
"step": 360
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 18.49,
|
| 444 |
+
"learning_rate": 9.999999999999999e-06,
|
| 445 |
+
"loss": 0.0877,
|
| 446 |
+
"step": 370
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 18.99,
|
| 450 |
+
"learning_rate": 6.666666666666667e-06,
|
| 451 |
+
"loss": 0.0821,
|
| 452 |
+
"step": 380
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 18.99,
|
| 456 |
+
"eval_accuracy": 0.8330757341576507,
|
| 457 |
+
"eval_f1": 0.833525849625881,
|
| 458 |
+
"eval_loss": 0.5755681395530701,
|
| 459 |
+
"eval_precision": 0.8342801097840022,
|
| 460 |
+
"eval_recall": 0.8330757341576507,
|
| 461 |
+
"eval_runtime": 23.5787,
|
| 462 |
+
"eval_samples_per_second": 54.88,
|
| 463 |
+
"eval_steps_per_second": 0.891,
|
| 464 |
+
"step": 380
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 19.49,
|
| 468 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 469 |
+
"loss": 0.0843,
|
| 470 |
+
"step": 390
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 19.99,
|
| 474 |
+
"learning_rate": 0.0,
|
| 475 |
+
"loss": 0.0813,
|
| 476 |
+
"step": 400
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 19.99,
|
| 480 |
+
"eval_accuracy": 0.8323029366306027,
|
| 481 |
+
"eval_f1": 0.831492653119617,
|
| 482 |
+
"eval_loss": 0.5984169840812683,
|
| 483 |
+
"eval_precision": 0.831217385971583,
|
| 484 |
+
"eval_recall": 0.8323029366306027,
|
| 485 |
+
"eval_runtime": 24.9692,
|
| 486 |
+
"eval_samples_per_second": 51.824,
|
| 487 |
+
"eval_steps_per_second": 0.841,
|
| 488 |
+
"step": 400
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 19.99,
|
| 492 |
+
"step": 400,
|
| 493 |
+
"total_flos": 1.1809647563061068e+19,
|
| 494 |
+
"train_loss": 0.36638923436403276,
|
| 495 |
+
"train_runtime": 5624.3012,
|
| 496 |
+
"train_samples_per_second": 18.399,
|
| 497 |
+
"train_steps_per_second": 0.071
|
| 498 |
+
}
|
| 499 |
+
],
|
| 500 |
+
"max_steps": 400,
|
| 501 |
+
"num_train_epochs": 20,
|
| 502 |
+
"total_flos": 1.1809647563061068e+19,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|