Commit
•
1d9a66d
1
Parent(s):
71cfa97
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +400 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.9613298177719116,
|
| 4 |
+
"eval_runtime": 17.9182,
|
| 5 |
+
"eval_samples": 341,
|
| 6 |
+
"eval_samples_per_second": 19.031,
|
| 7 |
+
"eval_steps_per_second": 2.4,
|
| 8 |
+
"eval_wer": 0.5376383763837639,
|
| 9 |
+
"train_loss": 1.0758988070020488,
|
| 10 |
+
"train_runtime": 4106.4423,
|
| 11 |
+
"train_samples": 810,
|
| 12 |
+
"train_samples_per_second": 9.863,
|
| 13 |
+
"train_steps_per_second": 0.621
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.9613298177719116,
|
| 4 |
+
"eval_runtime": 17.9182,
|
| 5 |
+
"eval_samples": 341,
|
| 6 |
+
"eval_samples_per_second": 19.031,
|
| 7 |
+
"eval_steps_per_second": 2.4,
|
| 8 |
+
"eval_wer": 0.5376383763837639
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 1.0758988070020488,
|
| 4 |
+
"train_runtime": 4106.4423,
|
| 5 |
+
"train_samples": 810,
|
| 6 |
+
"train_samples_per_second": 9.863,
|
| 7 |
+
"train_steps_per_second": 0.621
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 2550,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.96,
|
| 12 |
+
"learning_rate": 7.361999999999999e-05,
|
| 13 |
+
"loss": 5.3118,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.96,
|
| 18 |
+
"eval_loss": 2.9093422889709473,
|
| 19 |
+
"eval_runtime": 17.6486,
|
| 20 |
+
"eval_samples_per_second": 19.322,
|
| 21 |
+
"eval_steps_per_second": 2.436,
|
| 22 |
+
"eval_wer": 0.9981549815498155,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.92,
|
| 27 |
+
"learning_rate": 7.062e-05,
|
| 28 |
+
"loss": 2.2071,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 3.92,
|
| 33 |
+
"eval_loss": 1.1736845970153809,
|
| 34 |
+
"eval_runtime": 17.7952,
|
| 35 |
+
"eval_samples_per_second": 19.163,
|
| 36 |
+
"eval_steps_per_second": 2.416,
|
| 37 |
+
"eval_wer": 0.777859778597786,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 5.88,
|
| 42 |
+
"learning_rate": 6.761999999999999e-05,
|
| 43 |
+
"loss": 1.6098,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.88,
|
| 48 |
+
"eval_loss": 0.9983930587768555,
|
| 49 |
+
"eval_runtime": 17.6369,
|
| 50 |
+
"eval_samples_per_second": 19.334,
|
| 51 |
+
"eval_steps_per_second": 2.438,
|
| 52 |
+
"eval_wer": 0.7014760147601476,
|
| 53 |
+
"step": 300
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 7.84,
|
| 57 |
+
"learning_rate": 6.462e-05,
|
| 58 |
+
"loss": 1.4333,
|
| 59 |
+
"step": 400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 7.84,
|
| 63 |
+
"eval_loss": 0.9799550771713257,
|
| 64 |
+
"eval_runtime": 17.5884,
|
| 65 |
+
"eval_samples_per_second": 19.388,
|
| 66 |
+
"eval_steps_per_second": 2.445,
|
| 67 |
+
"eval_wer": 0.670479704797048,
|
| 68 |
+
"step": 400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 9.8,
|
| 72 |
+
"learning_rate": 6.162e-05,
|
| 73 |
+
"loss": 1.2859,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 9.8,
|
| 78 |
+
"eval_loss": 0.9582107067108154,
|
| 79 |
+
"eval_runtime": 17.5894,
|
| 80 |
+
"eval_samples_per_second": 19.387,
|
| 81 |
+
"eval_steps_per_second": 2.445,
|
| 82 |
+
"eval_wer": 0.6487084870848708,
|
| 83 |
+
"step": 500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 11.76,
|
| 87 |
+
"learning_rate": 5.861999999999999e-05,
|
| 88 |
+
"loss": 1.2073,
|
| 89 |
+
"step": 600
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 11.76,
|
| 93 |
+
"eval_loss": 0.8841160535812378,
|
| 94 |
+
"eval_runtime": 17.5809,
|
| 95 |
+
"eval_samples_per_second": 19.396,
|
| 96 |
+
"eval_steps_per_second": 2.446,
|
| 97 |
+
"eval_wer": 0.6077490774907749,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 13.73,
|
| 102 |
+
"learning_rate": 5.562e-05,
|
| 103 |
+
"loss": 1.1417,
|
| 104 |
+
"step": 700
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 13.73,
|
| 108 |
+
"eval_loss": 0.9118468165397644,
|
| 109 |
+
"eval_runtime": 17.5423,
|
| 110 |
+
"eval_samples_per_second": 19.439,
|
| 111 |
+
"eval_steps_per_second": 2.451,
|
| 112 |
+
"eval_wer": 0.6343173431734317,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 15.69,
|
| 117 |
+
"learning_rate": 5.2619999999999994e-05,
|
| 118 |
+
"loss": 1.0988,
|
| 119 |
+
"step": 800
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 15.69,
|
| 123 |
+
"eval_loss": 0.9216808080673218,
|
| 124 |
+
"eval_runtime": 17.5542,
|
| 125 |
+
"eval_samples_per_second": 19.426,
|
| 126 |
+
"eval_steps_per_second": 2.45,
|
| 127 |
+
"eval_wer": 0.6195571955719558,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 17.65,
|
| 132 |
+
"learning_rate": 4.9619999999999996e-05,
|
| 133 |
+
"loss": 1.0279,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 17.65,
|
| 138 |
+
"eval_loss": 0.9165470600128174,
|
| 139 |
+
"eval_runtime": 17.6001,
|
| 140 |
+
"eval_samples_per_second": 19.375,
|
| 141 |
+
"eval_steps_per_second": 2.443,
|
| 142 |
+
"eval_wer": 0.5867158671586716,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 19.61,
|
| 147 |
+
"learning_rate": 4.662e-05,
|
| 148 |
+
"loss": 0.9765,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 19.61,
|
| 153 |
+
"eval_loss": 0.9305969476699829,
|
| 154 |
+
"eval_runtime": 17.6088,
|
| 155 |
+
"eval_samples_per_second": 19.365,
|
| 156 |
+
"eval_steps_per_second": 2.442,
|
| 157 |
+
"eval_wer": 0.5977859778597786,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 21.57,
|
| 162 |
+
"learning_rate": 4.362e-05,
|
| 163 |
+
"loss": 0.9161,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 21.57,
|
| 168 |
+
"eval_loss": 0.9304590225219727,
|
| 169 |
+
"eval_runtime": 17.4967,
|
| 170 |
+
"eval_samples_per_second": 19.489,
|
| 171 |
+
"eval_steps_per_second": 2.458,
|
| 172 |
+
"eval_wer": 0.5767527675276752,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 23.53,
|
| 177 |
+
"learning_rate": 4.0619999999999994e-05,
|
| 178 |
+
"loss": 0.8395,
|
| 179 |
+
"step": 1200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 23.53,
|
| 183 |
+
"eval_loss": 0.982844889163971,
|
| 184 |
+
"eval_runtime": 17.7044,
|
| 185 |
+
"eval_samples_per_second": 19.261,
|
| 186 |
+
"eval_steps_per_second": 2.429,
|
| 187 |
+
"eval_wer": 0.5819188191881919,
|
| 188 |
+
"step": 1200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 25.49,
|
| 192 |
+
"learning_rate": 3.762e-05,
|
| 193 |
+
"loss": 0.8306,
|
| 194 |
+
"step": 1300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 25.49,
|
| 198 |
+
"eval_loss": 0.9397062063217163,
|
| 199 |
+
"eval_runtime": 17.6627,
|
| 200 |
+
"eval_samples_per_second": 19.306,
|
| 201 |
+
"eval_steps_per_second": 2.435,
|
| 202 |
+
"eval_wer": 0.5760147601476014,
|
| 203 |
+
"step": 1300
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 27.45,
|
| 207 |
+
"learning_rate": 3.462e-05,
|
| 208 |
+
"loss": 0.7819,
|
| 209 |
+
"step": 1400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 27.45,
|
| 213 |
+
"eval_loss": 0.9543871283531189,
|
| 214 |
+
"eval_runtime": 17.6517,
|
| 215 |
+
"eval_samples_per_second": 19.318,
|
| 216 |
+
"eval_steps_per_second": 2.436,
|
| 217 |
+
"eval_wer": 0.574169741697417,
|
| 218 |
+
"step": 1400
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 29.41,
|
| 222 |
+
"learning_rate": 3.161999999999999e-05,
|
| 223 |
+
"loss": 0.7509,
|
| 224 |
+
"step": 1500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 29.41,
|
| 228 |
+
"eval_loss": 0.9278193712234497,
|
| 229 |
+
"eval_runtime": 17.4199,
|
| 230 |
+
"eval_samples_per_second": 19.575,
|
| 231 |
+
"eval_steps_per_second": 2.468,
|
| 232 |
+
"eval_wer": 0.5690036900369003,
|
| 233 |
+
"step": 1500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 31.37,
|
| 237 |
+
"learning_rate": 2.8619999999999997e-05,
|
| 238 |
+
"loss": 0.7218,
|
| 239 |
+
"step": 1600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 31.37,
|
| 243 |
+
"eval_loss": 0.9002724289894104,
|
| 244 |
+
"eval_runtime": 17.4813,
|
| 245 |
+
"eval_samples_per_second": 19.507,
|
| 246 |
+
"eval_steps_per_second": 2.46,
|
| 247 |
+
"eval_wer": 0.5586715867158671,
|
| 248 |
+
"step": 1600
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 33.33,
|
| 252 |
+
"learning_rate": 2.562e-05,
|
| 253 |
+
"loss": 0.6725,
|
| 254 |
+
"step": 1700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 33.33,
|
| 258 |
+
"eval_loss": 0.9659368395805359,
|
| 259 |
+
"eval_runtime": 17.6287,
|
| 260 |
+
"eval_samples_per_second": 19.343,
|
| 261 |
+
"eval_steps_per_second": 2.439,
|
| 262 |
+
"eval_wer": 0.5553505535055351,
|
| 263 |
+
"step": 1700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 35.29,
|
| 267 |
+
"learning_rate": 2.2619999999999997e-05,
|
| 268 |
+
"loss": 0.6287,
|
| 269 |
+
"step": 1800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 35.29,
|
| 273 |
+
"eval_loss": 0.9521807432174683,
|
| 274 |
+
"eval_runtime": 17.6153,
|
| 275 |
+
"eval_samples_per_second": 19.358,
|
| 276 |
+
"eval_steps_per_second": 2.441,
|
| 277 |
+
"eval_wer": 0.5560885608856089,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 37.25,
|
| 282 |
+
"learning_rate": 1.962e-05,
|
| 283 |
+
"loss": 0.6077,
|
| 284 |
+
"step": 1900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 37.25,
|
| 288 |
+
"eval_loss": 0.9153698086738586,
|
| 289 |
+
"eval_runtime": 17.5781,
|
| 290 |
+
"eval_samples_per_second": 19.399,
|
| 291 |
+
"eval_steps_per_second": 2.446,
|
| 292 |
+
"eval_wer": 0.5464944649446495,
|
| 293 |
+
"step": 1900
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 39.22,
|
| 297 |
+
"learning_rate": 1.6619999999999997e-05,
|
| 298 |
+
"loss": 0.5873,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 39.22,
|
| 303 |
+
"eval_loss": 0.9330592751502991,
|
| 304 |
+
"eval_runtime": 17.6281,
|
| 305 |
+
"eval_samples_per_second": 19.344,
|
| 306 |
+
"eval_steps_per_second": 2.439,
|
| 307 |
+
"eval_wer": 0.5468634686346864,
|
| 308 |
+
"step": 2000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 41.18,
|
| 312 |
+
"learning_rate": 1.362e-05,
|
| 313 |
+
"loss": 0.5621,
|
| 314 |
+
"step": 2100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 41.18,
|
| 318 |
+
"eval_loss": 0.9334675669670105,
|
| 319 |
+
"eval_runtime": 17.5009,
|
| 320 |
+
"eval_samples_per_second": 19.485,
|
| 321 |
+
"eval_steps_per_second": 2.457,
|
| 322 |
+
"eval_wer": 0.5490774907749078,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 43.14,
|
| 327 |
+
"learning_rate": 1.062e-05,
|
| 328 |
+
"loss": 0.5168,
|
| 329 |
+
"step": 2200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 43.14,
|
| 333 |
+
"eval_loss": 0.9632032513618469,
|
| 334 |
+
"eval_runtime": 17.6433,
|
| 335 |
+
"eval_samples_per_second": 19.327,
|
| 336 |
+
"eval_steps_per_second": 2.437,
|
| 337 |
+
"eval_wer": 0.5457564575645757,
|
| 338 |
+
"step": 2200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 45.1,
|
| 342 |
+
"learning_rate": 7.619999999999999e-06,
|
| 343 |
+
"loss": 0.5114,
|
| 344 |
+
"step": 2300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 45.1,
|
| 348 |
+
"eval_loss": 0.9349461793899536,
|
| 349 |
+
"eval_runtime": 17.5705,
|
| 350 |
+
"eval_samples_per_second": 19.407,
|
| 351 |
+
"eval_steps_per_second": 2.447,
|
| 352 |
+
"eval_wer": 0.5387453874538746,
|
| 353 |
+
"step": 2300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 47.06,
|
| 357 |
+
"learning_rate": 4.62e-06,
|
| 358 |
+
"loss": 0.4986,
|
| 359 |
+
"step": 2400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 47.06,
|
| 363 |
+
"eval_loss": 0.9364362955093384,
|
| 364 |
+
"eval_runtime": 17.6211,
|
| 365 |
+
"eval_samples_per_second": 19.352,
|
| 366 |
+
"eval_steps_per_second": 2.44,
|
| 367 |
+
"eval_wer": 0.5380073800738008,
|
| 368 |
+
"step": 2400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 49.02,
|
| 372 |
+
"learning_rate": 1.62e-06,
|
| 373 |
+
"loss": 0.4761,
|
| 374 |
+
"step": 2500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 49.02,
|
| 378 |
+
"eval_loss": 0.9584243297576904,
|
| 379 |
+
"eval_runtime": 17.5152,
|
| 380 |
+
"eval_samples_per_second": 19.469,
|
| 381 |
+
"eval_steps_per_second": 2.455,
|
| 382 |
+
"eval_wer": 0.5391143911439115,
|
| 383 |
+
"step": 2500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 50.0,
|
| 387 |
+
"step": 2550,
|
| 388 |
+
"total_flos": 1.5012316680494998e+19,
|
| 389 |
+
"train_loss": 1.0758988070020488,
|
| 390 |
+
"train_runtime": 4106.4423,
|
| 391 |
+
"train_samples_per_second": 9.863,
|
| 392 |
+
"train_steps_per_second": 0.621
|
| 393 |
+
}
|
| 394 |
+
],
|
| 395 |
+
"max_steps": 2550,
|
| 396 |
+
"num_train_epochs": 50,
|
| 397 |
+
"total_flos": 1.5012316680494998e+19,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|