End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.33,
|
| 3 |
+
"eval_cer": 0.9545736113978939,
|
| 4 |
+
"eval_loss": 4.904029369354248,
|
| 5 |
+
"eval_runtime": 53.4856,
|
| 6 |
+
"eval_samples": 481,
|
| 7 |
+
"eval_samples_per_second": 8.993,
|
| 8 |
+
"eval_steps_per_second": 1.14,
|
| 9 |
+
"eval_wer": 0.9322987721691678,
|
| 10 |
+
"train_loss": 6.457582977294922,
|
| 11 |
+
"train_runtime": 2324.152,
|
| 12 |
+
"train_samples": 2528,
|
| 13 |
+
"train_samples_per_second": 6.884,
|
| 14 |
+
"train_steps_per_second": 0.215
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.33,
|
| 3 |
+
"eval_cer": 0.9545736113978939,
|
| 4 |
+
"eval_loss": 4.904029369354248,
|
| 5 |
+
"eval_runtime": 53.4856,
|
| 6 |
+
"eval_samples": 481,
|
| 7 |
+
"eval_samples_per_second": 8.993,
|
| 8 |
+
"eval_steps_per_second": 1.14,
|
| 9 |
+
"eval_wer": 0.9322987721691678
|
| 10 |
+
}
|
runs/Dec18_16-45-22_129-146-179-188/events.out.tfevents.1671384689.129-146-179-188.139020.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a127794760c295e59532d86517572bcfa40362a9312c8a3df1195f9ca7daeb8b
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.33,
|
| 3 |
+
"train_loss": 6.457582977294922,
|
| 4 |
+
"train_runtime": 2324.152,
|
| 5 |
+
"train_samples": 2528,
|
| 6 |
+
"train_samples_per_second": 6.884,
|
| 7 |
+
"train_steps_per_second": 0.215
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 4.904029369354248,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint-500",
|
| 4 |
+
"epoch": 6.329113924050633,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 7.500000000000001e-09,
|
| 13 |
+
"loss": 22.5894,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.25,
|
| 18 |
+
"learning_rate": 1.5000000000000002e-08,
|
| 19 |
+
"loss": 20.4369,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.38,
|
| 24 |
+
"learning_rate": 2.25e-08,
|
| 25 |
+
"loss": 22.056,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.51,
|
| 30 |
+
"learning_rate": 3.0000000000000004e-08,
|
| 31 |
+
"loss": 19.983,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.63,
|
| 36 |
+
"learning_rate": 3.7500000000000005e-08,
|
| 37 |
+
"loss": 21.5341,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.76,
|
| 42 |
+
"learning_rate": 4.4249999999999996e-08,
|
| 43 |
+
"loss": 20.8669,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.89,
|
| 48 |
+
"learning_rate": 5.1750000000000003e-08,
|
| 49 |
+
"loss": 21.3542,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.01,
|
| 54 |
+
"learning_rate": 5.9250000000000004e-08,
|
| 55 |
+
"loss": 20.587,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.14,
|
| 60 |
+
"learning_rate": 6.675e-08,
|
| 61 |
+
"loss": 21.7896,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.27,
|
| 66 |
+
"learning_rate": 7.425e-08,
|
| 67 |
+
"loss": 19.9558,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.27,
|
| 72 |
+
"eval_cer": 3.2660447130816737,
|
| 73 |
+
"eval_loss": 20.919719696044922,
|
| 74 |
+
"eval_runtime": 51.6953,
|
| 75 |
+
"eval_samples_per_second": 9.305,
|
| 76 |
+
"eval_steps_per_second": 2.341,
|
| 77 |
+
"eval_wer": 1.0,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.39,
|
| 82 |
+
"learning_rate": 8.175e-08,
|
| 83 |
+
"loss": 21.8368,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.52,
|
| 88 |
+
"learning_rate": 8.925e-08,
|
| 89 |
+
"loss": 20.2781,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.65,
|
| 94 |
+
"learning_rate": 9.675e-08,
|
| 95 |
+
"loss": 20.5284,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.77,
|
| 100 |
+
"learning_rate": 1.0425000000000001e-07,
|
| 101 |
+
"loss": 20.2507,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.9,
|
| 106 |
+
"learning_rate": 1.1174999999999999e-07,
|
| 107 |
+
"loss": 20.063,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.03,
|
| 112 |
+
"learning_rate": 1.1925e-07,
|
| 113 |
+
"loss": 20.3082,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.15,
|
| 118 |
+
"learning_rate": 1.2675000000000002e-07,
|
| 119 |
+
"loss": 20.5946,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.28,
|
| 124 |
+
"learning_rate": 1.3425e-07,
|
| 125 |
+
"loss": 19.3427,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.41,
|
| 130 |
+
"learning_rate": 1.4175e-07,
|
| 131 |
+
"loss": 19.4337,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.53,
|
| 136 |
+
"learning_rate": 1.4925000000000002e-07,
|
| 137 |
+
"loss": 19.7186,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.53,
|
| 142 |
+
"eval_cer": 1.1691851406904061,
|
| 143 |
+
"eval_loss": 19.244659423828125,
|
| 144 |
+
"eval_runtime": 51.3422,
|
| 145 |
+
"eval_samples_per_second": 9.369,
|
| 146 |
+
"eval_steps_per_second": 2.357,
|
| 147 |
+
"eval_wer": 1.0,
|
| 148 |
+
"step": 200
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.66,
|
| 152 |
+
"learning_rate": 1.56e-07,
|
| 153 |
+
"loss": 19.3518,
|
| 154 |
+
"step": 210
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.78,
|
| 158 |
+
"learning_rate": 1.635e-07,
|
| 159 |
+
"loss": 18.8406,
|
| 160 |
+
"step": 220
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.91,
|
| 164 |
+
"learning_rate": 1.71e-07,
|
| 165 |
+
"loss": 18.1267,
|
| 166 |
+
"step": 230
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.04,
|
| 170 |
+
"learning_rate": 1.785e-07,
|
| 171 |
+
"loss": 18.2315,
|
| 172 |
+
"step": 240
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 3.16,
|
| 176 |
+
"learning_rate": 1.86e-07,
|
| 177 |
+
"loss": 17.8997,
|
| 178 |
+
"step": 250
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 3.29,
|
| 182 |
+
"learning_rate": 1.935e-07,
|
| 183 |
+
"loss": 17.5011,
|
| 184 |
+
"step": 260
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.42,
|
| 188 |
+
"learning_rate": 2.01e-07,
|
| 189 |
+
"loss": 16.8782,
|
| 190 |
+
"step": 270
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.54,
|
| 194 |
+
"learning_rate": 2.0850000000000002e-07,
|
| 195 |
+
"loss": 16.628,
|
| 196 |
+
"step": 280
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.67,
|
| 200 |
+
"learning_rate": 2.16e-07,
|
| 201 |
+
"loss": 15.2879,
|
| 202 |
+
"step": 290
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 3.8,
|
| 206 |
+
"learning_rate": 2.2349999999999998e-07,
|
| 207 |
+
"loss": 15.203,
|
| 208 |
+
"step": 300
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.8,
|
| 212 |
+
"eval_cer": 0.9687083513224335,
|
| 213 |
+
"eval_loss": 15.005261421203613,
|
| 214 |
+
"eval_runtime": 54.4312,
|
| 215 |
+
"eval_samples_per_second": 8.837,
|
| 216 |
+
"eval_steps_per_second": 1.121,
|
| 217 |
+
"eval_wer": 0.9998294679399727,
|
| 218 |
+
"step": 300
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.92,
|
| 222 |
+
"learning_rate": 2.31e-07,
|
| 223 |
+
"loss": 13.8484,
|
| 224 |
+
"step": 310
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.05,
|
| 228 |
+
"learning_rate": 2.385e-07,
|
| 229 |
+
"loss": 13.6877,
|
| 230 |
+
"step": 320
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.18,
|
| 234 |
+
"learning_rate": 2.46e-07,
|
| 235 |
+
"loss": 12.1026,
|
| 236 |
+
"step": 330
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.3,
|
| 240 |
+
"learning_rate": 2.5350000000000004e-07,
|
| 241 |
+
"loss": 11.1649,
|
| 242 |
+
"step": 340
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.43,
|
| 246 |
+
"learning_rate": 2.6099999999999997e-07,
|
| 247 |
+
"loss": 9.5398,
|
| 248 |
+
"step": 350
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.56,
|
| 252 |
+
"learning_rate": 2.6775e-07,
|
| 253 |
+
"loss": 8.7484,
|
| 254 |
+
"step": 360
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.68,
|
| 258 |
+
"learning_rate": 2.7525e-07,
|
| 259 |
+
"loss": 7.7766,
|
| 260 |
+
"step": 370
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.81,
|
| 264 |
+
"learning_rate": 2.8275e-07,
|
| 265 |
+
"loss": 7.2303,
|
| 266 |
+
"step": 380
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.94,
|
| 270 |
+
"learning_rate": 2.9025e-07,
|
| 271 |
+
"loss": 6.5927,
|
| 272 |
+
"step": 390
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.06,
|
| 276 |
+
"learning_rate": 2.9775000000000003e-07,
|
| 277 |
+
"loss": 6.4303,
|
| 278 |
+
"step": 400
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 5.06,
|
| 282 |
+
"eval_cer": 0.9911212058641338,
|
| 283 |
+
"eval_loss": 6.543659687042236,
|
| 284 |
+
"eval_runtime": 55.4335,
|
| 285 |
+
"eval_samples_per_second": 8.677,
|
| 286 |
+
"eval_steps_per_second": 1.1,
|
| 287 |
+
"eval_wer": 0.9631650750341064,
|
| 288 |
+
"step": 400
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 5.19,
|
| 292 |
+
"learning_rate": 3.0525e-07,
|
| 293 |
+
"loss": 5.9555,
|
| 294 |
+
"step": 410
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.32,
|
| 298 |
+
"learning_rate": 3.1275e-07,
|
| 299 |
+
"loss": 5.9212,
|
| 300 |
+
"step": 420
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 5.44,
|
| 304 |
+
"learning_rate": 3.2025e-07,
|
| 305 |
+
"loss": 5.4995,
|
| 306 |
+
"step": 430
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.57,
|
| 310 |
+
"learning_rate": 3.2775e-07,
|
| 311 |
+
"loss": 5.5903,
|
| 312 |
+
"step": 440
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 5.7,
|
| 316 |
+
"learning_rate": 3.3525000000000004e-07,
|
| 317 |
+
"loss": 5.1376,
|
| 318 |
+
"step": 450
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 5.82,
|
| 322 |
+
"learning_rate": 3.4275e-07,
|
| 323 |
+
"loss": 4.9402,
|
| 324 |
+
"step": 460
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 5.95,
|
| 328 |
+
"learning_rate": 3.5025e-07,
|
| 329 |
+
"loss": 4.9112,
|
| 330 |
+
"step": 470
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 6.08,
|
| 334 |
+
"learning_rate": 3.5775e-07,
|
| 335 |
+
"loss": 4.8001,
|
| 336 |
+
"step": 480
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 6.2,
|
| 340 |
+
"learning_rate": 3.6525e-07,
|
| 341 |
+
"loss": 4.482,
|
| 342 |
+
"step": 490
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 6.33,
|
| 346 |
+
"learning_rate": 3.7275e-07,
|
| 347 |
+
"loss": 4.5712,
|
| 348 |
+
"step": 500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 6.33,
|
| 352 |
+
"eval_cer": 0.9545736113978939,
|
| 353 |
+
"eval_loss": 4.904029369354248,
|
| 354 |
+
"eval_runtime": 64.6266,
|
| 355 |
+
"eval_samples_per_second": 7.443,
|
| 356 |
+
"eval_steps_per_second": 0.944,
|
| 357 |
+
"eval_wer": 0.9322987721691678,
|
| 358 |
+
"step": 500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 6.33,
|
| 362 |
+
"step": 500,
|
| 363 |
+
"total_flos": 1.7609861732211995e+19,
|
| 364 |
+
"train_loss": 6.457582977294922,
|
| 365 |
+
"train_runtime": 2324.152,
|
| 366 |
+
"train_samples_per_second": 6.884,
|
| 367 |
+
"train_steps_per_second": 0.215
|
| 368 |
+
}
|
| 369 |
+
],
|
| 370 |
+
"max_steps": 500,
|
| 371 |
+
"num_train_epochs": 7,
|
| 372 |
+
"total_flos": 1.7609861732211995e+19,
|
| 373 |
+
"trial_name": null,
|
| 374 |
+
"trial_params": null
|
| 375 |
+
}
|