End of training
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- train_results.json +5 -5
- trainer_state.json +323 -143
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 989,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 7914,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.97,
|
| 3 |
+
"eval_f1": 0.7058281501958075,
|
| 4 |
+
"eval_loss": 0.1904972940683365,
|
| 5 |
+
"eval_runtime": 42.3826,
|
| 6 |
"eval_samples": 989,
|
| 7 |
+
"eval_samples_per_second": 23.335,
|
| 8 |
+
"eval_steps_per_second": 1.463,
|
| 9 |
+
"train_loss": 0.2132105562745071,
|
| 10 |
+
"train_runtime": 4145.08,
|
| 11 |
"train_samples": 7914,
|
| 12 |
+
"train_samples_per_second": 9.546,
|
| 13 |
+
"train_steps_per_second": 0.148
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_f1": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
"eval_samples": 989,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.97,
|
| 3 |
+
"eval_f1": 0.7058281501958075,
|
| 4 |
+
"eval_loss": 0.1904972940683365,
|
| 5 |
+
"eval_runtime": 42.3826,
|
| 6 |
"eval_samples": 989,
|
| 7 |
+
"eval_samples_per_second": 23.335,
|
| 8 |
+
"eval_steps_per_second": 1.463
|
| 9 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 7914,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.97,
|
| 3 |
+
"train_loss": 0.2132105562745071,
|
| 4 |
+
"train_runtime": 4145.08,
|
| 5 |
"train_samples": 7914,
|
| 6 |
+
"train_samples_per_second": 9.546,
|
| 7 |
+
"train_steps_per_second": 0.148
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,259 +1,439 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"learning_rate": 1.
|
| 14 |
-
"loss": 0.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate": 1.
|
| 20 |
-
"loss": 0.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate": 1.
|
| 26 |
-
"loss": 0.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate": 1.
|
| 32 |
-
"loss": 0.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate": 1.
|
| 38 |
-
"loss": 0.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"learning_rate": 1.
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"eval_runtime": 1.9933,
|
| 52 |
-
"eval_samples_per_second": 496.167,
|
| 53 |
-
"eval_steps_per_second": 8.027,
|
| 54 |
-
"step": 62
|
| 55 |
-
},
|
| 56 |
-
{
|
| 57 |
-
"epoch": 1.13,
|
| 58 |
-
"learning_rate": 1.5483870967741936e-05,
|
| 59 |
-
"loss": 0.3319,
|
| 60 |
"step": 70
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch":
|
| 64 |
-
"learning_rate": 1.
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
-
"epoch":
|
| 70 |
-
"learning_rate": 1.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"learning_rate": 1.
|
| 77 |
-
"loss": 0.
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
-
"epoch":
|
| 82 |
-
"learning_rate": 1.
|
| 83 |
-
"loss": 0.
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"epoch":
|
| 88 |
-
"learning_rate": 1.
|
| 89 |
-
"loss": 0.
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"epoch":
|
| 94 |
-
"eval_f1": 0.
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_runtime":
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second":
|
| 99 |
-
"step":
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"learning_rate": 1.
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 130
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch":
|
| 109 |
-
"learning_rate": 1.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 140
|
| 112 |
},
|
| 113 |
{
|
| 114 |
-
"epoch":
|
| 115 |
-
"learning_rate": 1.
|
| 116 |
-
"loss": 0.
|
| 117 |
"step": 150
|
| 118 |
},
|
| 119 |
{
|
| 120 |
-
"epoch":
|
| 121 |
-
"learning_rate":
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 160
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch":
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 170
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch":
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
"eval_runtime": 1.8327,
|
| 142 |
-
"eval_samples_per_second": 539.642,
|
| 143 |
-
"eval_steps_per_second": 8.73,
|
| 144 |
-
"step": 186
|
| 145 |
-
},
|
| 146 |
-
{
|
| 147 |
-
"epoch": 3.06,
|
| 148 |
-
"learning_rate": 7.741935483870968e-06,
|
| 149 |
-
"loss": 0.2874,
|
| 150 |
"step": 190
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch":
|
| 154 |
-
"learning_rate":
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 200
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch":
|
| 160 |
-
"learning_rate":
|
| 161 |
-
"loss": 0.
|
| 162 |
"step": 210
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch":
|
| 166 |
-
"learning_rate":
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 220
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"epoch":
|
| 172 |
-
"learning_rate":
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 230
|
| 175 |
},
|
| 176 |
{
|
| 177 |
-
"epoch":
|
| 178 |
-
"learning_rate":
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 240
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch":
|
| 184 |
-
"eval_f1": 0.
|
| 185 |
-
"eval_loss": 0.
|
| 186 |
-
"eval_runtime":
|
| 187 |
-
"eval_samples_per_second":
|
| 188 |
-
"eval_steps_per_second":
|
| 189 |
-
"step":
|
| 190 |
},
|
| 191 |
{
|
| 192 |
-
"epoch":
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 250
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 260
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch":
|
| 211 |
-
"learning_rate": 1.
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 280
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch":
|
| 217 |
-
"learning_rate": 1.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 290
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch":
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 0.
|
| 225 |
"step": 300
|
| 226 |
},
|
| 227 |
{
|
| 228 |
-
"epoch":
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 0.
|
| 231 |
"step": 310
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"epoch":
|
| 235 |
-
"
|
| 236 |
-
"
|
| 237 |
-
"
|
| 238 |
-
|
| 239 |
-
|
| 240 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch":
|
| 244 |
-
"step":
|
| 245 |
-
"total_flos":
|
| 246 |
-
"train_loss": 0.
|
| 247 |
-
"train_runtime":
|
| 248 |
-
"train_samples_per_second":
|
| 249 |
-
"train_steps_per_second":
|
| 250 |
}
|
| 251 |
],
|
| 252 |
"logging_steps": 10,
|
| 253 |
-
"max_steps":
|
| 254 |
"num_train_epochs": 5,
|
| 255 |
"save_steps": 500,
|
| 256 |
-
"total_flos":
|
| 257 |
"trial_name": null,
|
| 258 |
"trial_params": null
|
| 259 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.96969696969697,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 615,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"learning_rate": 1.9674796747967483e-05,
|
| 14 |
+
"loss": 0.6473,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.16,
|
| 19 |
+
"learning_rate": 1.934959349593496e-05,
|
| 20 |
+
"loss": 0.414,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.24,
|
| 25 |
+
"learning_rate": 1.902439024390244e-05,
|
| 26 |
+
"loss": 0.3542,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.32,
|
| 31 |
+
"learning_rate": 1.869918699186992e-05,
|
| 32 |
+
"loss": 0.3396,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.4,
|
| 37 |
+
"learning_rate": 1.83739837398374e-05,
|
| 38 |
+
"loss": 0.3274,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.48,
|
| 43 |
+
"learning_rate": 1.804878048780488e-05,
|
| 44 |
+
"loss": 0.3238,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.57,
|
| 49 |
+
"learning_rate": 1.772357723577236e-05,
|
| 50 |
+
"loss": 0.3495,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.65,
|
| 55 |
+
"learning_rate": 1.739837398373984e-05,
|
| 56 |
+
"loss": 0.3068,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.73,
|
| 61 |
+
"learning_rate": 1.7073170731707317e-05,
|
| 62 |
+
"loss": 0.3164,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.81,
|
| 67 |
+
"learning_rate": 1.6747967479674798e-05,
|
| 68 |
+
"loss": 0.2989,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 0.89,
|
| 73 |
+
"learning_rate": 1.642276422764228e-05,
|
| 74 |
+
"loss": 0.287,
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
+
"epoch": 0.97,
|
| 79 |
+
"learning_rate": 1.6097560975609757e-05,
|
| 80 |
+
"loss": 0.2903,
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 0.99,
|
| 85 |
+
"eval_f1": 0.40107752170008987,
|
| 86 |
+
"eval_loss": 0.26861757040023804,
|
| 87 |
+
"eval_runtime": 43.0151,
|
| 88 |
+
"eval_samples_per_second": 22.992,
|
| 89 |
+
"eval_steps_per_second": 1.441,
|
| 90 |
+
"step": 123
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"epoch": 1.05,
|
| 94 |
+
"learning_rate": 1.5772357723577235e-05,
|
| 95 |
+
"loss": 0.2869,
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 1.13,
|
| 100 |
+
"learning_rate": 1.5447154471544717e-05,
|
| 101 |
+
"loss": 0.2709,
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 1.21,
|
| 106 |
+
"learning_rate": 1.5121951219512196e-05,
|
| 107 |
+
"loss": 0.2599,
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 1.29,
|
| 112 |
+
"learning_rate": 1.4796747967479676e-05,
|
| 113 |
+
"loss": 0.2565,
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 1.37,
|
| 118 |
+
"learning_rate": 1.4471544715447157e-05,
|
| 119 |
+
"loss": 0.2597,
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"epoch": 1.45,
|
| 124 |
+
"learning_rate": 1.4146341463414635e-05,
|
| 125 |
+
"loss": 0.2525,
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
+
"epoch": 1.54,
|
| 130 |
+
"learning_rate": 1.3821138211382115e-05,
|
| 131 |
+
"loss": 0.2519,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 1.62,
|
| 136 |
+
"learning_rate": 1.3495934959349594e-05,
|
| 137 |
+
"loss": 0.2366,
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 1.7,
|
| 142 |
+
"learning_rate": 1.3170731707317076e-05,
|
| 143 |
+
"loss": 0.2292,
|
| 144 |
"step": 210
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.78,
|
| 148 |
+
"learning_rate": 1.2845528455284555e-05,
|
| 149 |
+
"loss": 0.2214,
|
| 150 |
"step": 220
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 1.86,
|
| 154 |
+
"learning_rate": 1.2520325203252033e-05,
|
| 155 |
+
"loss": 0.2193,
|
| 156 |
"step": 230
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 1.94,
|
| 160 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 161 |
+
"loss": 0.2171,
|
| 162 |
"step": 240
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 2.0,
|
| 166 |
+
"eval_f1": 0.6493130874909617,
|
| 167 |
+
"eval_loss": 0.2168290913105011,
|
| 168 |
+
"eval_runtime": 43.1471,
|
| 169 |
+
"eval_samples_per_second": 22.922,
|
| 170 |
+
"eval_steps_per_second": 1.437,
|
| 171 |
+
"step": 247
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 2.02,
|
| 175 |
+
"learning_rate": 1.1869918699186992e-05,
|
| 176 |
+
"loss": 0.1994,
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 2.1,
|
| 181 |
+
"learning_rate": 1.1544715447154474e-05,
|
| 182 |
+
"loss": 0.204,
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 2.18,
|
| 187 |
+
"learning_rate": 1.1219512195121953e-05,
|
| 188 |
+
"loss": 0.1909,
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 2.26,
|
| 193 |
+
"learning_rate": 1.0894308943089431e-05,
|
| 194 |
+
"loss": 0.1906,
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 2.34,
|
| 199 |
+
"learning_rate": 1.0569105691056911e-05,
|
| 200 |
+
"loss": 0.1919,
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 2.42,
|
| 205 |
+
"learning_rate": 1.024390243902439e-05,
|
| 206 |
+
"loss": 0.1825,
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 2.51,
|
| 211 |
+
"learning_rate": 9.91869918699187e-06,
|
| 212 |
+
"loss": 0.1839,
|
| 213 |
"step": 310
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 2.59,
|
| 217 |
+
"learning_rate": 9.59349593495935e-06,
|
| 218 |
+
"loss": 0.189,
|
| 219 |
+
"step": 320
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.67,
|
| 223 |
+
"learning_rate": 9.268292682926831e-06,
|
| 224 |
+
"loss": 0.178,
|
| 225 |
+
"step": 330
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.75,
|
| 229 |
+
"learning_rate": 8.94308943089431e-06,
|
| 230 |
+
"loss": 0.1903,
|
| 231 |
+
"step": 340
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.83,
|
| 235 |
+
"learning_rate": 8.617886178861789e-06,
|
| 236 |
+
"loss": 0.1835,
|
| 237 |
+
"step": 350
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.91,
|
| 241 |
+
"learning_rate": 8.292682926829268e-06,
|
| 242 |
+
"loss": 0.1722,
|
| 243 |
+
"step": 360
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.99,
|
| 247 |
+
"learning_rate": 7.967479674796748e-06,
|
| 248 |
+
"loss": 0.1879,
|
| 249 |
+
"step": 370
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.0,
|
| 253 |
+
"eval_f1": 0.6612224696857214,
|
| 254 |
+
"eval_loss": 0.19899873435497284,
|
| 255 |
+
"eval_runtime": 43.1679,
|
| 256 |
+
"eval_samples_per_second": 22.911,
|
| 257 |
+
"eval_steps_per_second": 1.436,
|
| 258 |
+
"step": 371
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.07,
|
| 262 |
+
"learning_rate": 7.64227642276423e-06,
|
| 263 |
+
"loss": 0.1593,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.15,
|
| 268 |
+
"learning_rate": 7.317073170731707e-06,
|
| 269 |
+
"loss": 0.1553,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.23,
|
| 274 |
+
"learning_rate": 6.991869918699188e-06,
|
| 275 |
+
"loss": 0.1529,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.31,
|
| 280 |
+
"learning_rate": 6.666666666666667e-06,
|
| 281 |
+
"loss": 0.1589,
|
| 282 |
+
"step": 410
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.39,
|
| 286 |
+
"learning_rate": 6.341463414634147e-06,
|
| 287 |
+
"loss": 0.1514,
|
| 288 |
+
"step": 420
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.47,
|
| 292 |
+
"learning_rate": 6.016260162601627e-06,
|
| 293 |
+
"loss": 0.1524,
|
| 294 |
+
"step": 430
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.56,
|
| 298 |
+
"learning_rate": 5.691056910569106e-06,
|
| 299 |
+
"loss": 0.1577,
|
| 300 |
+
"step": 440
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.64,
|
| 304 |
+
"learning_rate": 5.365853658536586e-06,
|
| 305 |
+
"loss": 0.1504,
|
| 306 |
+
"step": 450
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 3.72,
|
| 310 |
+
"learning_rate": 5.040650406504065e-06,
|
| 311 |
+
"loss": 0.151,
|
| 312 |
+
"step": 460
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 3.8,
|
| 316 |
+
"learning_rate": 4.715447154471545e-06,
|
| 317 |
+
"loss": 0.1539,
|
| 318 |
+
"step": 470
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.88,
|
| 322 |
+
"learning_rate": 4.390243902439025e-06,
|
| 323 |
+
"loss": 0.1575,
|
| 324 |
+
"step": 480
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.96,
|
| 328 |
+
"learning_rate": 4.0650406504065046e-06,
|
| 329 |
+
"loss": 0.1476,
|
| 330 |
+
"step": 490
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 4.0,
|
| 334 |
+
"eval_f1": 0.7060445874511607,
|
| 335 |
+
"eval_loss": 0.18790604174137115,
|
| 336 |
+
"eval_runtime": 43.1492,
|
| 337 |
+
"eval_samples_per_second": 22.92,
|
| 338 |
+
"eval_steps_per_second": 1.437,
|
| 339 |
+
"step": 495
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.04,
|
| 343 |
+
"learning_rate": 3.7398373983739838e-06,
|
| 344 |
+
"loss": 0.1412,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.12,
|
| 349 |
+
"learning_rate": 3.414634146341464e-06,
|
| 350 |
+
"loss": 0.1274,
|
| 351 |
+
"step": 510
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.2,
|
| 355 |
+
"learning_rate": 3.0894308943089435e-06,
|
| 356 |
+
"loss": 0.1266,
|
| 357 |
+
"step": 520
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.28,
|
| 361 |
+
"learning_rate": 2.764227642276423e-06,
|
| 362 |
+
"loss": 0.1275,
|
| 363 |
+
"step": 530
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.36,
|
| 367 |
+
"learning_rate": 2.4390243902439027e-06,
|
| 368 |
+
"loss": 0.1222,
|
| 369 |
+
"step": 540
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.44,
|
| 373 |
+
"learning_rate": 2.1138211382113824e-06,
|
| 374 |
+
"loss": 0.1275,
|
| 375 |
+
"step": 550
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.53,
|
| 379 |
+
"learning_rate": 1.788617886178862e-06,
|
| 380 |
+
"loss": 0.1248,
|
| 381 |
+
"step": 560
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.61,
|
| 385 |
+
"learning_rate": 1.4634146341463414e-06,
|
| 386 |
+
"loss": 0.1308,
|
| 387 |
+
"step": 570
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.69,
|
| 391 |
+
"learning_rate": 1.1382113821138213e-06,
|
| 392 |
+
"loss": 0.1272,
|
| 393 |
+
"step": 580
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.77,
|
| 397 |
+
"learning_rate": 8.130081300813009e-07,
|
| 398 |
+
"loss": 0.1261,
|
| 399 |
+
"step": 590
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.85,
|
| 403 |
+
"learning_rate": 4.878048780487805e-07,
|
| 404 |
+
"loss": 0.1289,
|
| 405 |
+
"step": 600
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.93,
|
| 409 |
+
"learning_rate": 1.6260162601626018e-07,
|
| 410 |
+
"loss": 0.1279,
|
| 411 |
+
"step": 610
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.97,
|
| 415 |
+
"eval_f1": 0.7058281501958075,
|
| 416 |
+
"eval_loss": 0.1904972940683365,
|
| 417 |
+
"eval_runtime": 43.1284,
|
| 418 |
+
"eval_samples_per_second": 22.932,
|
| 419 |
+
"eval_steps_per_second": 1.438,
|
| 420 |
+
"step": 615
|
| 421 |
},
|
| 422 |
{
|
| 423 |
+
"epoch": 4.97,
|
| 424 |
+
"step": 615,
|
| 425 |
+
"total_flos": 2.6435427934519296e+16,
|
| 426 |
+
"train_loss": 0.2132105562745071,
|
| 427 |
+
"train_runtime": 4145.08,
|
| 428 |
+
"train_samples_per_second": 9.546,
|
| 429 |
+
"train_steps_per_second": 0.148
|
| 430 |
}
|
| 431 |
],
|
| 432 |
"logging_steps": 10,
|
| 433 |
+
"max_steps": 615,
|
| 434 |
"num_train_epochs": 5,
|
| 435 |
"save_steps": 500,
|
| 436 |
+
"total_flos": 2.6435427934519296e+16,
|
| 437 |
"trial_name": null,
|
| 438 |
"trial_params": null
|
| 439 |
}
|