Commit
•
1aaecd9
1
Parent(s):
15e190c
End of training
Browse files
all_results.json
CHANGED
|
@@ -1,7 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2000.0,
|
| 3 |
+
"eval_loss": 6.801175117492676,
|
| 4 |
+
"eval_runtime": 8.6897,
|
| 5 |
+
"eval_samples": 5,
|
| 6 |
+
"eval_samples_per_second": 0.575,
|
| 7 |
+
"eval_steps_per_second": 0.115,
|
| 8 |
+
"eval_wer": 100.0,
|
| 9 |
+
"train_loss": 0.10164999849759625,
|
| 10 |
+
"train_runtime": 1221.0979,
|
| 11 |
+
"train_samples_per_second": 104.824,
|
| 12 |
+
"train_steps_per_second": 1.638
|
| 13 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2000.0,
|
| 3 |
+
"eval_loss": 6.801175117492676,
|
| 4 |
+
"eval_runtime": 8.6897,
|
| 5 |
+
"eval_samples": 5,
|
| 6 |
+
"eval_samples_per_second": 0.575,
|
| 7 |
+
"eval_steps_per_second": 0.115,
|
| 8 |
+
"eval_wer": 100.0
|
| 9 |
+
}
|
runs/Dec25_15-57-57_129-213-85-198/events.out.tfevents.1671985223.129-213-85-198.71965.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dfacc0e460d4c92f158e375c72a33993fb2f825683cf77987f47dea65bf5c59
|
| 3 |
+
size 358
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 2000.0,
|
| 3 |
+
"train_loss": 0.10164999849759625,
|
| 4 |
+
"train_runtime": 1221.0979,
|
| 5 |
+
"train_samples_per_second": 104.824,
|
| 6 |
+
"train_steps_per_second": 1.638
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,265 +1,685 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
"learning_rate": 4.2000000000000006e-07,
|
| 13 |
-
"loss":
|
| 14 |
"step": 25
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch":
|
| 18 |
"learning_rate": 9.200000000000001e-07,
|
| 19 |
-
"loss": 2.
|
| 20 |
"step": 50
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch":
|
| 24 |
-
"learning_rate": 1.
|
| 25 |
-
"loss": 1.
|
| 26 |
"step": 75
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"learning_rate": 1.
|
| 31 |
-
"loss":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
"step": 100
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"learning_rate": 2.
|
| 37 |
-
"loss":
|
| 38 |
"step": 125
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate": 2.
|
| 43 |
-
"loss":
|
| 44 |
"step": 150
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"learning_rate": 3.
|
| 49 |
-
"loss":
|
| 50 |
"step": 175
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate": 3.
|
| 55 |
-
"loss":
|
| 56 |
"step": 200
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"
|
| 61 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
"step": 225
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch":
|
| 66 |
-
"learning_rate": 4.
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 250
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate": 5.
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 275
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"learning_rate": 5.
|
| 79 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
"step": 300
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
-
"learning_rate": 6.
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 325
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"learning_rate": 6.
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 350
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"learning_rate": 7.
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 375
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate": 7.
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 400
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"
|
| 109 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
"step": 425
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch":
|
| 114 |
-
"learning_rate": 8.
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 450
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"learning_rate": 9.
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 475
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"learning_rate": 9.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 500
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch":
|
| 132 |
-
"
|
| 133 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 134 |
"step": 525
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch":
|
| 138 |
-
"learning_rate": 9.
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 550
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch":
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 575
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch":
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 600
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch":
|
| 156 |
-
"
|
| 157 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
"step": 625
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 650
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch":
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 675
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch":
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 700
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch":
|
| 180 |
-
"
|
| 181 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
"step": 725
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch":
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 750
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 775
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 800
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch":
|
| 204 |
-
"
|
| 205 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
"step": 825
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch":
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 850
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch":
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 875
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch":
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 900
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch":
|
| 228 |
-
"
|
| 229 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 230 |
"step": 925
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch":
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 950
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch":
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 975
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch":
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 1000
|
| 249 |
},
|
| 250 |
{
|
| 251 |
-
"epoch":
|
| 252 |
-
"
|
| 253 |
-
"
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
"
|
| 257 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 258 |
}
|
| 259 |
],
|
| 260 |
-
"max_steps":
|
| 261 |
-
"num_train_epochs":
|
| 262 |
-
"total_flos":
|
| 263 |
"trial_name": null,
|
| 264 |
"trial_params": null
|
| 265 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 100.0,
|
| 3 |
+
"best_model_checkpoint": "./whisper-small-amet/checkpoint-1100",
|
| 4 |
+
"epoch": 2000.0,
|
| 5 |
+
"global_step": 2000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 25.0,
|
| 12 |
"learning_rate": 4.2000000000000006e-07,
|
| 13 |
+
"loss": 2.9938,
|
| 14 |
"step": 25
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 50.0,
|
| 18 |
"learning_rate": 9.200000000000001e-07,
|
| 19 |
+
"loss": 2.2746,
|
| 20 |
"step": 50
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 75.0,
|
| 24 |
+
"learning_rate": 1.4000000000000001e-06,
|
| 25 |
+
"loss": 1.7055,
|
| 26 |
"step": 75
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 100.0,
|
| 30 |
+
"learning_rate": 1.9000000000000002e-06,
|
| 31 |
+
"loss": 0.9013,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 100.0,
|
| 36 |
+
"eval_loss": 2.7051408290863037,
|
| 37 |
+
"eval_runtime": 8.4302,
|
| 38 |
+
"eval_samples_per_second": 0.593,
|
| 39 |
+
"eval_steps_per_second": 0.119,
|
| 40 |
+
"eval_wer": 276.0,
|
| 41 |
"step": 100
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 125.0,
|
| 45 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 46 |
+
"loss": 0.1244,
|
| 47 |
"step": 125
|
| 48 |
},
|
| 49 |
{
|
| 50 |
+
"epoch": 150.0,
|
| 51 |
+
"learning_rate": 2.9e-06,
|
| 52 |
+
"loss": 0.0031,
|
| 53 |
"step": 150
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 175.0,
|
| 57 |
+
"learning_rate": 3.4000000000000005e-06,
|
| 58 |
+
"loss": 0.0004,
|
| 59 |
"step": 175
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 200.0,
|
| 63 |
+
"learning_rate": 3.900000000000001e-06,
|
| 64 |
+
"loss": 0.0002,
|
| 65 |
"step": 200
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 200.0,
|
| 69 |
+
"eval_loss": 3.741528034210205,
|
| 70 |
+
"eval_runtime": 8.6419,
|
| 71 |
+
"eval_samples_per_second": 0.579,
|
| 72 |
+
"eval_steps_per_second": 0.116,
|
| 73 |
+
"eval_wer": 334.6666666666667,
|
| 74 |
+
"step": 200
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 225.0,
|
| 78 |
+
"learning_rate": 4.4e-06,
|
| 79 |
+
"loss": 0.0002,
|
| 80 |
"step": 225
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 250.0,
|
| 84 |
+
"learning_rate": 4.9000000000000005e-06,
|
| 85 |
+
"loss": 0.0001,
|
| 86 |
"step": 250
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 275.0,
|
| 90 |
+
"learning_rate": 5.400000000000001e-06,
|
| 91 |
+
"loss": 0.0001,
|
| 92 |
"step": 275
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 300.0,
|
| 96 |
+
"learning_rate": 5.9e-06,
|
| 97 |
+
"loss": 0.0001,
|
| 98 |
+
"step": 300
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 300.0,
|
| 102 |
+
"eval_loss": 3.840170383453369,
|
| 103 |
+
"eval_runtime": 1.5102,
|
| 104 |
+
"eval_samples_per_second": 3.311,
|
| 105 |
+
"eval_steps_per_second": 0.662,
|
| 106 |
+
"eval_wer": 117.33333333333333,
|
| 107 |
"step": 300
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 325.0,
|
| 111 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 112 |
+
"loss": 0.0001,
|
| 113 |
"step": 325
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 350.0,
|
| 117 |
+
"learning_rate": 6.9e-06,
|
| 118 |
+
"loss": 0.0001,
|
| 119 |
"step": 350
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 375.0,
|
| 123 |
+
"learning_rate": 7.4e-06,
|
| 124 |
+
"loss": 0.0001,
|
| 125 |
"step": 375
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 400.0,
|
| 129 |
+
"learning_rate": 7.9e-06,
|
| 130 |
+
"loss": 0.0001,
|
| 131 |
"step": 400
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 400.0,
|
| 135 |
+
"eval_loss": 3.8931400775909424,
|
| 136 |
+
"eval_runtime": 8.4556,
|
| 137 |
+
"eval_samples_per_second": 0.591,
|
| 138 |
+
"eval_steps_per_second": 0.118,
|
| 139 |
+
"eval_wer": 340.0,
|
| 140 |
+
"step": 400
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 425.0,
|
| 144 |
+
"learning_rate": 8.400000000000001e-06,
|
| 145 |
+
"loss": 0.0001,
|
| 146 |
"step": 425
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 450.0,
|
| 150 |
+
"learning_rate": 8.900000000000001e-06,
|
| 151 |
+
"loss": 0.0001,
|
| 152 |
"step": 450
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 475.0,
|
| 156 |
+
"learning_rate": 9.4e-06,
|
| 157 |
+
"loss": 0.0001,
|
| 158 |
"step": 475
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 500.0,
|
| 162 |
+
"learning_rate": 9.9e-06,
|
| 163 |
+
"loss": 0.0001,
|
| 164 |
"step": 500
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 500.0,
|
| 168 |
+
"eval_loss": 4.06705904006958,
|
| 169 |
+
"eval_runtime": 8.4836,
|
| 170 |
+
"eval_samples_per_second": 0.589,
|
| 171 |
+
"eval_steps_per_second": 0.118,
|
| 172 |
+
"eval_wer": 397.3333333333333,
|
| 173 |
+
"step": 500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 525.0,
|
| 177 |
+
"learning_rate": 9.866666666666668e-06,
|
| 178 |
+
"loss": 0.0001,
|
| 179 |
"step": 525
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 550.0,
|
| 183 |
+
"learning_rate": 9.7e-06,
|
| 184 |
+
"loss": 0.0001,
|
| 185 |
"step": 550
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 575.0,
|
| 189 |
+
"learning_rate": 9.533333333333334e-06,
|
| 190 |
+
"loss": 0.0001,
|
| 191 |
"step": 575
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 600.0,
|
| 195 |
+
"learning_rate": 9.366666666666668e-06,
|
| 196 |
+
"loss": 0.0001,
|
| 197 |
"step": 600
|
| 198 |
},
|
| 199 |
{
|
| 200 |
+
"epoch": 600.0,
|
| 201 |
+
"eval_loss": 4.284416675567627,
|
| 202 |
+
"eval_runtime": 1.5895,
|
| 203 |
+
"eval_samples_per_second": 3.146,
|
| 204 |
+
"eval_steps_per_second": 0.629,
|
| 205 |
+
"eval_wer": 137.33333333333334,
|
| 206 |
+
"step": 600
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 625.0,
|
| 210 |
+
"learning_rate": 9.200000000000002e-06,
|
| 211 |
+
"loss": 0.0001,
|
| 212 |
"step": 625
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 650.0,
|
| 216 |
+
"learning_rate": 9.033333333333334e-06,
|
| 217 |
+
"loss": 0.0,
|
| 218 |
"step": 650
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 675.0,
|
| 222 |
+
"learning_rate": 8.866666666666668e-06,
|
| 223 |
+
"loss": 0.0,
|
| 224 |
"step": 675
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 700.0,
|
| 228 |
+
"learning_rate": 8.700000000000001e-06,
|
| 229 |
+
"loss": 0.0,
|
| 230 |
"step": 700
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 700.0,
|
| 234 |
+
"eval_loss": 4.469689846038818,
|
| 235 |
+
"eval_runtime": 4.8142,
|
| 236 |
+
"eval_samples_per_second": 1.039,
|
| 237 |
+
"eval_steps_per_second": 0.208,
|
| 238 |
+
"eval_wer": 289.33333333333337,
|
| 239 |
+
"step": 700
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 725.0,
|
| 243 |
+
"learning_rate": 8.533333333333335e-06,
|
| 244 |
+
"loss": 0.0,
|
| 245 |
"step": 725
|
| 246 |
},
|
| 247 |
{
|
| 248 |
+
"epoch": 750.0,
|
| 249 |
+
"learning_rate": 8.366666666666667e-06,
|
| 250 |
+
"loss": 0.0,
|
| 251 |
"step": 750
|
| 252 |
},
|
| 253 |
{
|
| 254 |
+
"epoch": 775.0,
|
| 255 |
+
"learning_rate": 8.2e-06,
|
| 256 |
+
"loss": 0.0,
|
| 257 |
"step": 775
|
| 258 |
},
|
| 259 |
{
|
| 260 |
+
"epoch": 800.0,
|
| 261 |
+
"learning_rate": 8.033333333333335e-06,
|
| 262 |
+
"loss": 0.0,
|
| 263 |
"step": 800
|
| 264 |
},
|
| 265 |
{
|
| 266 |
+
"epoch": 800.0,
|
| 267 |
+
"eval_loss": 4.627803325653076,
|
| 268 |
+
"eval_runtime": 8.4484,
|
| 269 |
+
"eval_samples_per_second": 0.592,
|
| 270 |
+
"eval_steps_per_second": 0.118,
|
| 271 |
+
"eval_wer": 449.3333333333333,
|
| 272 |
+
"step": 800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 825.0,
|
| 276 |
+
"learning_rate": 7.866666666666667e-06,
|
| 277 |
+
"loss": 0.0,
|
| 278 |
"step": 825
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 850.0,
|
| 282 |
+
"learning_rate": 7.7e-06,
|
| 283 |
+
"loss": 0.0,
|
| 284 |
"step": 850
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 875.0,
|
| 288 |
+
"learning_rate": 7.533333333333334e-06,
|
| 289 |
+
"loss": 0.0,
|
| 290 |
"step": 875
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 900.0,
|
| 294 |
+
"learning_rate": 7.3666666666666676e-06,
|
| 295 |
+
"loss": 0.0,
|
| 296 |
"step": 900
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 900.0,
|
| 300 |
+
"eval_loss": 4.779428005218506,
|
| 301 |
+
"eval_runtime": 8.432,
|
| 302 |
+
"eval_samples_per_second": 0.593,
|
| 303 |
+
"eval_steps_per_second": 0.119,
|
| 304 |
+
"eval_wer": 678.6666666666667,
|
| 305 |
+
"step": 900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 925.0,
|
| 309 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 310 |
+
"loss": 0.0,
|
| 311 |
"step": 925
|
| 312 |
},
|
| 313 |
{
|
| 314 |
+
"epoch": 950.0,
|
| 315 |
+
"learning_rate": 7.033333333333334e-06,
|
| 316 |
+
"loss": 0.0,
|
| 317 |
"step": 950
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 975.0,
|
| 321 |
+
"learning_rate": 6.886666666666667e-06,
|
| 322 |
+
"loss": 0.0753,
|
| 323 |
"step": 975
|
| 324 |
},
|
| 325 |
{
|
| 326 |
+
"epoch": 1000.0,
|
| 327 |
+
"learning_rate": 6.720000000000001e-06,
|
| 328 |
+
"loss": 0.0405,
|
| 329 |
"step": 1000
|
| 330 |
},
|
| 331 |
{
|
| 332 |
+
"epoch": 1000.0,
|
| 333 |
+
"eval_loss": 4.676939487457275,
|
| 334 |
+
"eval_runtime": 8.4726,
|
| 335 |
+
"eval_samples_per_second": 0.59,
|
| 336 |
+
"eval_steps_per_second": 0.118,
|
| 337 |
+
"eval_wer": 261.3333333333333,
|
| 338 |
+
"step": 1000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1025.0,
|
| 342 |
+
"learning_rate": 6.553333333333334e-06,
|
| 343 |
+
"loss": 0.0057,
|
| 344 |
+
"step": 1025
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1050.0,
|
| 348 |
+
"learning_rate": 6.386666666666668e-06,
|
| 349 |
+
"loss": 0.0001,
|
| 350 |
+
"step": 1050
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1075.0,
|
| 354 |
+
"learning_rate": 6.220000000000001e-06,
|
| 355 |
+
"loss": 0.0001,
|
| 356 |
+
"step": 1075
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1100.0,
|
| 360 |
+
"learning_rate": 6.0533333333333335e-06,
|
| 361 |
+
"loss": 0.0002,
|
| 362 |
+
"step": 1100
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1100.0,
|
| 366 |
+
"eval_loss": 5.499487400054932,
|
| 367 |
+
"eval_runtime": 8.5264,
|
| 368 |
+
"eval_samples_per_second": 0.586,
|
| 369 |
+
"eval_steps_per_second": 0.117,
|
| 370 |
+
"eval_wer": 100.0,
|
| 371 |
+
"step": 1100
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1125.0,
|
| 375 |
+
"learning_rate": 5.886666666666667e-06,
|
| 376 |
+
"loss": 0.0002,
|
| 377 |
+
"step": 1125
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1150.0,
|
| 381 |
+
"learning_rate": 5.72e-06,
|
| 382 |
+
"loss": 0.0002,
|
| 383 |
+
"step": 1150
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1175.0,
|
| 387 |
+
"learning_rate": 5.553333333333334e-06,
|
| 388 |
+
"loss": 0.0002,
|
| 389 |
+
"step": 1175
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1200.0,
|
| 393 |
+
"learning_rate": 5.386666666666667e-06,
|
| 394 |
+
"loss": 0.0002,
|
| 395 |
+
"step": 1200
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1200.0,
|
| 399 |
+
"eval_loss": 6.003348350524902,
|
| 400 |
+
"eval_runtime": 8.4985,
|
| 401 |
+
"eval_samples_per_second": 0.588,
|
| 402 |
+
"eval_steps_per_second": 0.118,
|
| 403 |
+
"eval_wer": 100.0,
|
| 404 |
+
"step": 1200
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1225.0,
|
| 408 |
+
"learning_rate": 5.220000000000001e-06,
|
| 409 |
+
"loss": 0.0002,
|
| 410 |
+
"step": 1225
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1250.0,
|
| 414 |
+
"learning_rate": 5.053333333333334e-06,
|
| 415 |
+
"loss": 0.0002,
|
| 416 |
+
"step": 1250
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1275.0,
|
| 420 |
+
"learning_rate": 4.886666666666668e-06,
|
| 421 |
+
"loss": 0.0002,
|
| 422 |
+
"step": 1275
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1300.0,
|
| 426 |
+
"learning_rate": 4.7200000000000005e-06,
|
| 427 |
+
"loss": 0.0002,
|
| 428 |
+
"step": 1300
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1300.0,
|
| 432 |
+
"eval_loss": 6.288400650024414,
|
| 433 |
+
"eval_runtime": 8.612,
|
| 434 |
+
"eval_samples_per_second": 0.581,
|
| 435 |
+
"eval_steps_per_second": 0.116,
|
| 436 |
+
"eval_wer": 100.0,
|
| 437 |
+
"step": 1300
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1325.0,
|
| 441 |
+
"learning_rate": 4.5533333333333335e-06,
|
| 442 |
+
"loss": 0.0002,
|
| 443 |
+
"step": 1325
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1350.0,
|
| 447 |
+
"learning_rate": 4.3866666666666665e-06,
|
| 448 |
+
"loss": 0.0002,
|
| 449 |
+
"step": 1350
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1375.0,
|
| 453 |
+
"learning_rate": 4.22e-06,
|
| 454 |
+
"loss": 0.0002,
|
| 455 |
+
"step": 1375
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1400.0,
|
| 459 |
+
"learning_rate": 4.053333333333333e-06,
|
| 460 |
+
"loss": 0.0002,
|
| 461 |
+
"step": 1400
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1400.0,
|
| 465 |
+
"eval_loss": 6.474369049072266,
|
| 466 |
+
"eval_runtime": 8.436,
|
| 467 |
+
"eval_samples_per_second": 0.593,
|
| 468 |
+
"eval_steps_per_second": 0.119,
|
| 469 |
+
"eval_wer": 100.0,
|
| 470 |
+
"step": 1400
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1425.0,
|
| 474 |
+
"learning_rate": 3.886666666666667e-06,
|
| 475 |
+
"loss": 0.0002,
|
| 476 |
+
"step": 1425
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1450.0,
|
| 480 |
+
"learning_rate": 3.7200000000000004e-06,
|
| 481 |
+
"loss": 0.0002,
|
| 482 |
+
"step": 1450
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1475.0,
|
| 486 |
+
"learning_rate": 3.5533333333333338e-06,
|
| 487 |
+
"loss": 0.0002,
|
| 488 |
+
"step": 1475
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1500.0,
|
| 492 |
+
"learning_rate": 3.386666666666667e-06,
|
| 493 |
+
"loss": 0.0002,
|
| 494 |
+
"step": 1500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1500.0,
|
| 498 |
+
"eval_loss": 6.596408843994141,
|
| 499 |
+
"eval_runtime": 8.5317,
|
| 500 |
+
"eval_samples_per_second": 0.586,
|
| 501 |
+
"eval_steps_per_second": 0.117,
|
| 502 |
+
"eval_wer": 100.0,
|
| 503 |
+
"step": 1500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1525.0,
|
| 507 |
+
"learning_rate": 3.2200000000000005e-06,
|
| 508 |
+
"loss": 0.0002,
|
| 509 |
+
"step": 1525
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1550.0,
|
| 513 |
+
"learning_rate": 3.053333333333334e-06,
|
| 514 |
+
"loss": 0.0001,
|
| 515 |
+
"step": 1550
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1575.0,
|
| 519 |
+
"learning_rate": 2.8866666666666673e-06,
|
| 520 |
+
"loss": 0.0001,
|
| 521 |
+
"step": 1575
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1600.0,
|
| 525 |
+
"learning_rate": 2.7200000000000002e-06,
|
| 526 |
+
"loss": 0.0001,
|
| 527 |
+
"step": 1600
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1600.0,
|
| 531 |
+
"eval_loss": 6.679154872894287,
|
| 532 |
+
"eval_runtime": 8.5665,
|
| 533 |
+
"eval_samples_per_second": 0.584,
|
| 534 |
+
"eval_steps_per_second": 0.117,
|
| 535 |
+
"eval_wer": 100.0,
|
| 536 |
+
"step": 1600
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1625.0,
|
| 540 |
+
"learning_rate": 2.5533333333333336e-06,
|
| 541 |
+
"loss": 0.0001,
|
| 542 |
+
"step": 1625
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1650.0,
|
| 546 |
+
"learning_rate": 2.386666666666667e-06,
|
| 547 |
+
"loss": 0.0001,
|
| 548 |
+
"step": 1650
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1675.0,
|
| 552 |
+
"learning_rate": 2.2200000000000003e-06,
|
| 553 |
+
"loss": 0.0001,
|
| 554 |
+
"step": 1675
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1700.0,
|
| 558 |
+
"learning_rate": 2.0533333333333337e-06,
|
| 559 |
+
"loss": 0.0001,
|
| 560 |
+
"step": 1700
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1700.0,
|
| 564 |
+
"eval_loss": 6.7370285987854,
|
| 565 |
+
"eval_runtime": 8.4426,
|
| 566 |
+
"eval_samples_per_second": 0.592,
|
| 567 |
+
"eval_steps_per_second": 0.118,
|
| 568 |
+
"eval_wer": 100.0,
|
| 569 |
+
"step": 1700
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1725.0,
|
| 573 |
+
"learning_rate": 1.8866666666666669e-06,
|
| 574 |
+
"loss": 0.0001,
|
| 575 |
+
"step": 1725
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1750.0,
|
| 579 |
+
"learning_rate": 1.72e-06,
|
| 580 |
+
"loss": 0.0001,
|
| 581 |
+
"step": 1750
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1775.0,
|
| 585 |
+
"learning_rate": 1.5533333333333334e-06,
|
| 586 |
+
"loss": 0.0001,
|
| 587 |
+
"step": 1775
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1800.0,
|
| 591 |
+
"learning_rate": 1.3866666666666668e-06,
|
| 592 |
+
"loss": 0.0001,
|
| 593 |
+
"step": 1800
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1800.0,
|
| 597 |
+
"eval_loss": 6.773484230041504,
|
| 598 |
+
"eval_runtime": 8.4858,
|
| 599 |
+
"eval_samples_per_second": 0.589,
|
| 600 |
+
"eval_steps_per_second": 0.118,
|
| 601 |
+
"eval_wer": 100.0,
|
| 602 |
+
"step": 1800
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1825.0,
|
| 606 |
+
"learning_rate": 1.2200000000000002e-06,
|
| 607 |
+
"loss": 0.0001,
|
| 608 |
+
"step": 1825
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1850.0,
|
| 612 |
+
"learning_rate": 1.0533333333333333e-06,
|
| 613 |
+
"loss": 0.0001,
|
| 614 |
+
"step": 1850
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1875.0,
|
| 618 |
+
"learning_rate": 8.866666666666668e-07,
|
| 619 |
+
"loss": 0.0001,
|
| 620 |
+
"step": 1875
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 1900.0,
|
| 624 |
+
"learning_rate": 7.2e-07,
|
| 625 |
+
"loss": 0.0001,
|
| 626 |
+
"step": 1900
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1900.0,
|
| 630 |
+
"eval_loss": 6.795783042907715,
|
| 631 |
+
"eval_runtime": 8.5107,
|
| 632 |
+
"eval_samples_per_second": 0.587,
|
| 633 |
+
"eval_steps_per_second": 0.117,
|
| 634 |
+
"eval_wer": 100.0,
|
| 635 |
+
"step": 1900
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 1925.0,
|
| 639 |
+
"learning_rate": 5.533333333333334e-07,
|
| 640 |
+
"loss": 0.0001,
|
| 641 |
+
"step": 1925
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 1950.0,
|
| 645 |
+
"learning_rate": 3.8666666666666674e-07,
|
| 646 |
+
"loss": 0.0001,
|
| 647 |
+
"step": 1950
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1975.0,
|
| 651 |
+
"learning_rate": 2.2e-07,
|
| 652 |
+
"loss": 0.0001,
|
| 653 |
+
"step": 1975
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2000.0,
|
| 657 |
+
"learning_rate": 5.3333333333333334e-08,
|
| 658 |
+
"loss": 0.0001,
|
| 659 |
+
"step": 2000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2000.0,
|
| 663 |
+
"eval_loss": 6.801175117492676,
|
| 664 |
+
"eval_runtime": 8.5138,
|
| 665 |
+
"eval_samples_per_second": 0.587,
|
| 666 |
+
"eval_steps_per_second": 0.117,
|
| 667 |
+
"eval_wer": 100.0,
|
| 668 |
+
"step": 2000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2000.0,
|
| 672 |
+
"step": 2000,
|
| 673 |
+
"total_flos": 5.7717080064e+17,
|
| 674 |
+
"train_loss": 0.10164999849759625,
|
| 675 |
+
"train_runtime": 1221.0979,
|
| 676 |
+
"train_samples_per_second": 104.824,
|
| 677 |
+
"train_steps_per_second": 1.638
|
| 678 |
}
|
| 679 |
],
|
| 680 |
+
"max_steps": 2000,
|
| 681 |
+
"num_train_epochs": 2000,
|
| 682 |
+
"total_flos": 5.7717080064e+17,
|
| 683 |
"trial_name": null,
|
| 684 |
"trial_params": null
|
| 685 |
}
|