All Dunn!!!
Browse files- all_results.json +7 -0
- train_results.json +7 -0
- trainer_state.json +367 -0
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.26616470564657185,
|
| 4 |
+
"train_runtime": 95644.4856,
|
| 5 |
+
"train_samples_per_second": 0.892,
|
| 6 |
+
"train_steps_per_second": 0.014
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.26616470564657185,
|
| 4 |
+
"train_runtime": 95644.4856,
|
| 5 |
+
"train_samples_per_second": 0.892,
|
| 6 |
+
"train_steps_per_second": 0.014
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,367 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8655209539834394,
|
| 3 |
+
"best_model_checkpoint": "fnet-large-Financial_Sentiment_Analysis_v3/checkpoint-670",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 1340,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.9985074626865674e-05,
|
| 13 |
+
"loss": 1.4558,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.37,
|
| 18 |
+
"learning_rate": 1.9253731343283585e-05,
|
| 19 |
+
"loss": 0.81,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.75,
|
| 24 |
+
"learning_rate": 1.8507462686567165e-05,
|
| 25 |
+
"loss": 0.6757,
|
| 26 |
+
"step": 100
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"eval_Macro F1": 0.36279759177569026,
|
| 31 |
+
"eval_Macro Precision": 0.5210381627879025,
|
| 32 |
+
"eval_Macro Recall": 0.4297578136174626,
|
| 33 |
+
"eval_Micro F1": 0.585480093676815,
|
| 34 |
+
"eval_Micro Precision": 0.585480093676815,
|
| 35 |
+
"eval_Micro Recall": 0.585480093676815,
|
| 36 |
+
"eval_Weighted F1": 0.4739290274173566,
|
| 37 |
+
"eval_Weighted Precision": 0.5912111905595777,
|
| 38 |
+
"eval_Weighted Recall": 0.585480093676815,
|
| 39 |
+
"eval_accuracy": 0.585480093676815,
|
| 40 |
+
"eval_loss": 0.5890011787414551,
|
| 41 |
+
"eval_runtime": 572.1521,
|
| 42 |
+
"eval_samples_per_second": 3.732,
|
| 43 |
+
"eval_steps_per_second": 0.059,
|
| 44 |
+
"step": 134
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.12,
|
| 48 |
+
"learning_rate": 1.7761194029850748e-05,
|
| 49 |
+
"loss": 0.615,
|
| 50 |
+
"step": 150
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.49,
|
| 54 |
+
"learning_rate": 1.701492537313433e-05,
|
| 55 |
+
"loss": 0.542,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.87,
|
| 60 |
+
"learning_rate": 1.626865671641791e-05,
|
| 61 |
+
"loss": 0.4815,
|
| 62 |
+
"step": 250
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.0,
|
| 66 |
+
"eval_Macro F1": 0.7155645405318029,
|
| 67 |
+
"eval_Macro Precision": 0.7388441683808017,
|
| 68 |
+
"eval_Macro Recall": 0.7039245533319153,
|
| 69 |
+
"eval_Micro F1": 0.7826697892271662,
|
| 70 |
+
"eval_Micro Precision": 0.7826697892271662,
|
| 71 |
+
"eval_Micro Recall": 0.7826697892271662,
|
| 72 |
+
"eval_Weighted F1": 0.778931131467011,
|
| 73 |
+
"eval_Weighted Precision": 0.7878024754296866,
|
| 74 |
+
"eval_Weighted Recall": 0.7826697892271662,
|
| 75 |
+
"eval_accuracy": 0.7826697892271662,
|
| 76 |
+
"eval_loss": 0.3994453251361847,
|
| 77 |
+
"eval_runtime": 570.0533,
|
| 78 |
+
"eval_samples_per_second": 3.745,
|
| 79 |
+
"eval_steps_per_second": 0.06,
|
| 80 |
+
"step": 268
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.24,
|
| 84 |
+
"learning_rate": 1.5522388059701494e-05,
|
| 85 |
+
"loss": 0.3774,
|
| 86 |
+
"step": 300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.61,
|
| 90 |
+
"learning_rate": 1.4776119402985077e-05,
|
| 91 |
+
"loss": 0.3366,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.99,
|
| 96 |
+
"learning_rate": 1.4029850746268658e-05,
|
| 97 |
+
"loss": 0.314,
|
| 98 |
+
"step": 400
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.0,
|
| 102 |
+
"eval_Macro F1": 0.736751489500019,
|
| 103 |
+
"eval_Macro Precision": 0.7612057314604446,
|
| 104 |
+
"eval_Macro Recall": 0.7252037377440934,
|
| 105 |
+
"eval_Micro F1": 0.7990632318501172,
|
| 106 |
+
"eval_Micro Precision": 0.7990632318501171,
|
| 107 |
+
"eval_Micro Recall": 0.7990632318501171,
|
| 108 |
+
"eval_Weighted F1": 0.7977313198767033,
|
| 109 |
+
"eval_Weighted Precision": 0.8100534851227623,
|
| 110 |
+
"eval_Weighted Recall": 0.7990632318501171,
|
| 111 |
+
"eval_accuracy": 0.7990632318501171,
|
| 112 |
+
"eval_loss": 0.3560428321361542,
|
| 113 |
+
"eval_runtime": 581.4066,
|
| 114 |
+
"eval_samples_per_second": 3.672,
|
| 115 |
+
"eval_steps_per_second": 0.058,
|
| 116 |
+
"step": 402
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.36,
|
| 120 |
+
"learning_rate": 1.328358208955224e-05,
|
| 121 |
+
"loss": 0.2486,
|
| 122 |
+
"step": 450
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.73,
|
| 126 |
+
"learning_rate": 1.2537313432835823e-05,
|
| 127 |
+
"loss": 0.235,
|
| 128 |
+
"step": 500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 4.0,
|
| 132 |
+
"eval_Macro F1": 0.7548578890974982,
|
| 133 |
+
"eval_Macro Precision": 0.7630930133664333,
|
| 134 |
+
"eval_Macro Recall": 0.7508943526446905,
|
| 135 |
+
"eval_Micro F1": 0.8201405152224824,
|
| 136 |
+
"eval_Micro Precision": 0.8201405152224824,
|
| 137 |
+
"eval_Micro Recall": 0.8201405152224824,
|
| 138 |
+
"eval_Weighted F1": 0.8217495227304409,
|
| 139 |
+
"eval_Weighted Precision": 0.8273969119402248,
|
| 140 |
+
"eval_Weighted Recall": 0.8201405152224824,
|
| 141 |
+
"eval_accuracy": 0.8201405152224824,
|
| 142 |
+
"eval_loss": 0.32777392864227295,
|
| 143 |
+
"eval_runtime": 571.7549,
|
| 144 |
+
"eval_samples_per_second": 3.734,
|
| 145 |
+
"eval_steps_per_second": 0.059,
|
| 146 |
+
"step": 536
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.1,
|
| 150 |
+
"learning_rate": 1.1791044776119405e-05,
|
| 151 |
+
"loss": 0.2309,
|
| 152 |
+
"step": 550
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 4.48,
|
| 156 |
+
"learning_rate": 1.1044776119402986e-05,
|
| 157 |
+
"loss": 0.188,
|
| 158 |
+
"step": 600
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.85,
|
| 162 |
+
"learning_rate": 1.029850746268657e-05,
|
| 163 |
+
"loss": 0.1986,
|
| 164 |
+
"step": 650
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 5.0,
|
| 168 |
+
"eval_Macro F1": 0.8208742913000978,
|
| 169 |
+
"eval_Macro Precision": 0.8083647050243598,
|
| 170 |
+
"eval_Macro Recall": 0.8400854990635674,
|
| 171 |
+
"eval_Micro F1": 0.8618266978922716,
|
| 172 |
+
"eval_Micro Precision": 0.8618266978922716,
|
| 173 |
+
"eval_Micro Recall": 0.8618266978922716,
|
| 174 |
+
"eval_Weighted F1": 0.8655209539834394,
|
| 175 |
+
"eval_Weighted Precision": 0.8723242107411118,
|
| 176 |
+
"eval_Weighted Recall": 0.8618266978922716,
|
| 177 |
+
"eval_accuracy": 0.8618266978922716,
|
| 178 |
+
"eval_loss": 0.3573662042617798,
|
| 179 |
+
"eval_runtime": 572.7753,
|
| 180 |
+
"eval_samples_per_second": 3.727,
|
| 181 |
+
"eval_steps_per_second": 0.059,
|
| 182 |
+
"step": 670
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 5.22,
|
| 186 |
+
"learning_rate": 9.552238805970149e-06,
|
| 187 |
+
"loss": 0.1838,
|
| 188 |
+
"step": 700
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.6,
|
| 192 |
+
"learning_rate": 8.805970149253732e-06,
|
| 193 |
+
"loss": 0.1485,
|
| 194 |
+
"step": 750
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.97,
|
| 198 |
+
"learning_rate": 8.059701492537314e-06,
|
| 199 |
+
"loss": 0.1605,
|
| 200 |
+
"step": 800
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.0,
|
| 204 |
+
"eval_Macro F1": 0.6588158445976257,
|
| 205 |
+
"eval_Macro Precision": 0.6987220074939374,
|
| 206 |
+
"eval_Macro Recall": 0.6469038522815648,
|
| 207 |
+
"eval_Micro F1": 0.7995316159250586,
|
| 208 |
+
"eval_Micro Precision": 0.7995316159250585,
|
| 209 |
+
"eval_Micro Recall": 0.7995316159250585,
|
| 210 |
+
"eval_Weighted F1": 0.7803428354754396,
|
| 211 |
+
"eval_Weighted Precision": 0.778138163263271,
|
| 212 |
+
"eval_Weighted Recall": 0.7995316159250585,
|
| 213 |
+
"eval_accuracy": 0.7995316159250585,
|
| 214 |
+
"eval_loss": 0.3885968029499054,
|
| 215 |
+
"eval_runtime": 571.7311,
|
| 216 |
+
"eval_samples_per_second": 3.734,
|
| 217 |
+
"eval_steps_per_second": 0.059,
|
| 218 |
+
"step": 804
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.34,
|
| 222 |
+
"learning_rate": 7.313432835820896e-06,
|
| 223 |
+
"loss": 0.1425,
|
| 224 |
+
"step": 850
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.72,
|
| 228 |
+
"learning_rate": 6.567164179104478e-06,
|
| 229 |
+
"loss": 0.1436,
|
| 230 |
+
"step": 900
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.0,
|
| 234 |
+
"eval_Macro F1": 0.7442069309467508,
|
| 235 |
+
"eval_Macro Precision": 0.7576208137220202,
|
| 236 |
+
"eval_Macro Recall": 0.7336057451045414,
|
| 237 |
+
"eval_Micro F1": 0.8229508196721311,
|
| 238 |
+
"eval_Micro Precision": 0.8229508196721311,
|
| 239 |
+
"eval_Micro Recall": 0.8229508196721311,
|
| 240 |
+
"eval_Weighted F1": 0.820676653014847,
|
| 241 |
+
"eval_Weighted Precision": 0.8209948655272054,
|
| 242 |
+
"eval_Weighted Recall": 0.8229508196721311,
|
| 243 |
+
"eval_accuracy": 0.8229508196721311,
|
| 244 |
+
"eval_loss": 0.4039975702762604,
|
| 245 |
+
"eval_runtime": 571.7322,
|
| 246 |
+
"eval_samples_per_second": 3.734,
|
| 247 |
+
"eval_steps_per_second": 0.059,
|
| 248 |
+
"step": 938
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 7.09,
|
| 252 |
+
"learning_rate": 5.820895522388061e-06,
|
| 253 |
+
"loss": 0.1368,
|
| 254 |
+
"step": 950
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 7.46,
|
| 258 |
+
"learning_rate": 5.074626865671642e-06,
|
| 259 |
+
"loss": 0.1253,
|
| 260 |
+
"step": 1000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 7.84,
|
| 264 |
+
"learning_rate": 4.3283582089552236e-06,
|
| 265 |
+
"loss": 0.1373,
|
| 266 |
+
"step": 1050
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 8.0,
|
| 270 |
+
"eval_Macro F1": 0.7123175103612404,
|
| 271 |
+
"eval_Macro Precision": 0.7322548905353868,
|
| 272 |
+
"eval_Macro Recall": 0.7019914283796879,
|
| 273 |
+
"eval_Micro F1": 0.8168618266978923,
|
| 274 |
+
"eval_Micro Precision": 0.8168618266978923,
|
| 275 |
+
"eval_Micro Recall": 0.8168618266978923,
|
| 276 |
+
"eval_Weighted F1": 0.807557064029797,
|
| 277 |
+
"eval_Weighted Precision": 0.8030050439721781,
|
| 278 |
+
"eval_Weighted Recall": 0.8168618266978923,
|
| 279 |
+
"eval_accuracy": 0.8168618266978923,
|
| 280 |
+
"eval_loss": 0.4517393112182617,
|
| 281 |
+
"eval_runtime": 571.7202,
|
| 282 |
+
"eval_samples_per_second": 3.734,
|
| 283 |
+
"eval_steps_per_second": 0.059,
|
| 284 |
+
"step": 1072
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 8.21,
|
| 288 |
+
"learning_rate": 3.582089552238806e-06,
|
| 289 |
+
"loss": 0.1206,
|
| 290 |
+
"step": 1100
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 8.58,
|
| 294 |
+
"learning_rate": 2.835820895522388e-06,
|
| 295 |
+
"loss": 0.1141,
|
| 296 |
+
"step": 1150
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 8.96,
|
| 300 |
+
"learning_rate": 2.08955223880597e-06,
|
| 301 |
+
"loss": 0.1271,
|
| 302 |
+
"step": 1200
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 9.0,
|
| 306 |
+
"eval_Macro F1": 0.6891590047543085,
|
| 307 |
+
"eval_Macro Precision": 0.7169021915882458,
|
| 308 |
+
"eval_Macro Recall": 0.6768345177275865,
|
| 309 |
+
"eval_Micro F1": 0.8070257611241218,
|
| 310 |
+
"eval_Micro Precision": 0.8070257611241218,
|
| 311 |
+
"eval_Micro Recall": 0.8070257611241218,
|
| 312 |
+
"eval_Weighted F1": 0.7944945373911929,
|
| 313 |
+
"eval_Weighted Precision": 0.790593845937712,
|
| 314 |
+
"eval_Weighted Recall": 0.8070257611241218,
|
| 315 |
+
"eval_accuracy": 0.8070257611241218,
|
| 316 |
+
"eval_loss": 0.45325130224227905,
|
| 317 |
+
"eval_runtime": 593.452,
|
| 318 |
+
"eval_samples_per_second": 3.598,
|
| 319 |
+
"eval_steps_per_second": 0.057,
|
| 320 |
+
"step": 1206
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 9.33,
|
| 324 |
+
"learning_rate": 1.3432835820895524e-06,
|
| 325 |
+
"loss": 0.1171,
|
| 326 |
+
"step": 1250
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 9.7,
|
| 330 |
+
"learning_rate": 5.970149253731343e-07,
|
| 331 |
+
"loss": 0.1199,
|
| 332 |
+
"step": 1300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 10.0,
|
| 336 |
+
"eval_Macro F1": 0.7368644623841439,
|
| 337 |
+
"eval_Macro Precision": 0.7514878901301887,
|
| 338 |
+
"eval_Macro Recall": 0.726942967276122,
|
| 339 |
+
"eval_Micro F1": 0.824824355971897,
|
| 340 |
+
"eval_Micro Precision": 0.824824355971897,
|
| 341 |
+
"eval_Micro Recall": 0.824824355971897,
|
| 342 |
+
"eval_Weighted F1": 0.8193666524247488,
|
| 343 |
+
"eval_Weighted Precision": 0.8163202759848958,
|
| 344 |
+
"eval_Weighted Recall": 0.824824355971897,
|
| 345 |
+
"eval_accuracy": 0.824824355971897,
|
| 346 |
+
"eval_loss": 0.474141001701355,
|
| 347 |
+
"eval_runtime": 569.2941,
|
| 348 |
+
"eval_samples_per_second": 3.75,
|
| 349 |
+
"eval_steps_per_second": 0.06,
|
| 350 |
+
"step": 1340
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 10.0,
|
| 354 |
+
"step": 1340,
|
| 355 |
+
"total_flos": 1.105606065652704e+16,
|
| 356 |
+
"train_loss": 0.26616470564657185,
|
| 357 |
+
"train_runtime": 95644.4856,
|
| 358 |
+
"train_samples_per_second": 0.892,
|
| 359 |
+
"train_steps_per_second": 0.014
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"max_steps": 1340,
|
| 363 |
+
"num_train_epochs": 10,
|
| 364 |
+
"total_flos": 1.105606065652704e+16,
|
| 365 |
+
"trial_name": null,
|
| 366 |
+
"trial_params": null
|
| 367 |
+
}
|