End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 87.01,
|
| 3 |
+
"eval_loss": 0.5686367750167847,
|
| 4 |
+
"eval_runtime": 638.1959,
|
| 5 |
+
"eval_samples_per_second": 1.938,
|
| 6 |
+
"eval_steps_per_second": 0.122,
|
| 7 |
+
"eval_wer": 18.863785917964464,
|
| 8 |
+
"train_loss": 0.07293392582147915,
|
| 9 |
+
"train_runtime": 12725.5944,
|
| 10 |
+
"train_samples_per_second": 3.52,
|
| 11 |
+
"train_steps_per_second": 0.11
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 87.01,
|
| 3 |
+
"eval_loss": 0.5686367750167847,
|
| 4 |
+
"eval_runtime": 638.1959,
|
| 5 |
+
"eval_samples_per_second": 1.938,
|
| 6 |
+
"eval_steps_per_second": 0.122,
|
| 7 |
+
"eval_wer": 18.863785917964464
|
| 8 |
+
}
|
runs/Dec19_22-12-33_129-146-48-110/events.out.tfevents.1671501538.129-146-48-110.3048972.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f777a6eff9950bb9679e918021e3dd899922b59534cf4cabb5810ca1f1cdb410
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 87.01,
|
| 3 |
+
"train_loss": 0.07293392582147915,
|
| 4 |
+
"train_runtime": 12725.5944,
|
| 5 |
+
"train_samples_per_second": 3.52,
|
| 6 |
+
"train_steps_per_second": 0.11
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 18.863785917964464,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint-400",
|
| 4 |
+
"epoch": 87.00571428571429,
|
| 5 |
+
"global_step": 1400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.01,
|
| 12 |
+
"learning_rate": 4.4e-07,
|
| 13 |
+
"loss": 1.9798,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 3.0,
|
| 18 |
+
"learning_rate": 9.400000000000001e-07,
|
| 19 |
+
"loss": 1.2092,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 4.01,
|
| 24 |
+
"learning_rate": 1.44e-06,
|
| 25 |
+
"loss": 0.4287,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 6.0,
|
| 30 |
+
"learning_rate": 1.94e-06,
|
| 31 |
+
"loss": 0.1862,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 7.01,
|
| 36 |
+
"learning_rate": 2.4400000000000004e-06,
|
| 37 |
+
"loss": 0.089,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 9.0,
|
| 42 |
+
"learning_rate": 2.9400000000000002e-06,
|
| 43 |
+
"loss": 0.0359,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 10.01,
|
| 48 |
+
"learning_rate": 3.44e-06,
|
| 49 |
+
"loss": 0.0119,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 12.01,
|
| 54 |
+
"learning_rate": 3.94e-06,
|
| 55 |
+
"loss": 0.0063,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 12.01,
|
| 60 |
+
"eval_loss": 0.5237645506858826,
|
| 61 |
+
"eval_runtime": 642.7046,
|
| 62 |
+
"eval_samples_per_second": 1.925,
|
| 63 |
+
"eval_steps_per_second": 0.121,
|
| 64 |
+
"eval_wer": 19.291511296336918,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 14.0,
|
| 69 |
+
"learning_rate": 4.440000000000001e-06,
|
| 70 |
+
"loss": 0.0044,
|
| 71 |
+
"step": 225
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 15.01,
|
| 75 |
+
"learning_rate": 4.94e-06,
|
| 76 |
+
"loss": 0.003,
|
| 77 |
+
"step": 250
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 17.0,
|
| 81 |
+
"learning_rate": 5.4400000000000004e-06,
|
| 82 |
+
"loss": 0.0051,
|
| 83 |
+
"step": 275
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 18.01,
|
| 87 |
+
"learning_rate": 5.94e-06,
|
| 88 |
+
"loss": 0.0044,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 20.0,
|
| 93 |
+
"learning_rate": 6.440000000000001e-06,
|
| 94 |
+
"loss": 0.0045,
|
| 95 |
+
"step": 325
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 21.01,
|
| 99 |
+
"learning_rate": 6.9400000000000005e-06,
|
| 100 |
+
"loss": 0.0041,
|
| 101 |
+
"step": 350
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 23.0,
|
| 105 |
+
"learning_rate": 7.440000000000001e-06,
|
| 106 |
+
"loss": 0.0042,
|
| 107 |
+
"step": 375
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 24.01,
|
| 111 |
+
"learning_rate": 7.94e-06,
|
| 112 |
+
"loss": 0.0046,
|
| 113 |
+
"step": 400
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 24.01,
|
| 117 |
+
"eval_loss": 0.5686367750167847,
|
| 118 |
+
"eval_runtime": 644.5254,
|
| 119 |
+
"eval_samples_per_second": 1.919,
|
| 120 |
+
"eval_steps_per_second": 0.121,
|
| 121 |
+
"eval_wer": 18.863785917964464,
|
| 122 |
+
"step": 400
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 26.01,
|
| 126 |
+
"learning_rate": 8.44e-06,
|
| 127 |
+
"loss": 0.0042,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 28.0,
|
| 132 |
+
"learning_rate": 8.94e-06,
|
| 133 |
+
"loss": 0.0078,
|
| 134 |
+
"step": 450
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 29.01,
|
| 138 |
+
"learning_rate": 9.440000000000001e-06,
|
| 139 |
+
"loss": 0.01,
|
| 140 |
+
"step": 475
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 31.0,
|
| 144 |
+
"learning_rate": 9.940000000000001e-06,
|
| 145 |
+
"loss": 0.0112,
|
| 146 |
+
"step": 500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 32.01,
|
| 150 |
+
"learning_rate": 9.755555555555556e-06,
|
| 151 |
+
"loss": 0.0147,
|
| 152 |
+
"step": 525
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 34.0,
|
| 156 |
+
"learning_rate": 9.47777777777778e-06,
|
| 157 |
+
"loss": 0.01,
|
| 158 |
+
"step": 550
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 35.01,
|
| 162 |
+
"learning_rate": 9.200000000000002e-06,
|
| 163 |
+
"loss": 0.0092,
|
| 164 |
+
"step": 575
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 37.01,
|
| 168 |
+
"learning_rate": 8.922222222222224e-06,
|
| 169 |
+
"loss": 0.0067,
|
| 170 |
+
"step": 600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 37.01,
|
| 174 |
+
"eval_loss": 0.5923575758934021,
|
| 175 |
+
"eval_runtime": 650.0985,
|
| 176 |
+
"eval_samples_per_second": 1.903,
|
| 177 |
+
"eval_steps_per_second": 0.12,
|
| 178 |
+
"eval_wer": 20.607589383636764,
|
| 179 |
+
"step": 600
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 39.0,
|
| 183 |
+
"learning_rate": 8.644444444444445e-06,
|
| 184 |
+
"loss": 0.0062,
|
| 185 |
+
"step": 625
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 40.01,
|
| 189 |
+
"learning_rate": 8.366666666666667e-06,
|
| 190 |
+
"loss": 0.0033,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 42.0,
|
| 195 |
+
"learning_rate": 8.08888888888889e-06,
|
| 196 |
+
"loss": 0.0017,
|
| 197 |
+
"step": 675
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 43.01,
|
| 201 |
+
"learning_rate": 7.811111111111111e-06,
|
| 202 |
+
"loss": 0.0078,
|
| 203 |
+
"step": 700
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 45.0,
|
| 207 |
+
"learning_rate": 7.533333333333334e-06,
|
| 208 |
+
"loss": 0.0014,
|
| 209 |
+
"step": 725
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 46.01,
|
| 213 |
+
"learning_rate": 7.255555555555556e-06,
|
| 214 |
+
"loss": 0.0017,
|
| 215 |
+
"step": 750
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 48.01,
|
| 219 |
+
"learning_rate": 6.977777777777779e-06,
|
| 220 |
+
"loss": 0.0004,
|
| 221 |
+
"step": 775
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 49.01,
|
| 225 |
+
"learning_rate": 6.700000000000001e-06,
|
| 226 |
+
"loss": 0.0004,
|
| 227 |
+
"step": 800
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 49.01,
|
| 231 |
+
"eval_loss": 0.6238680481910706,
|
| 232 |
+
"eval_runtime": 645.2778,
|
| 233 |
+
"eval_samples_per_second": 1.917,
|
| 234 |
+
"eval_steps_per_second": 0.121,
|
| 235 |
+
"eval_wer": 19.80697521386269,
|
| 236 |
+
"step": 800
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 51.01,
|
| 240 |
+
"learning_rate": 6.422222222222223e-06,
|
| 241 |
+
"loss": 0.0005,
|
| 242 |
+
"step": 825
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 53.0,
|
| 246 |
+
"learning_rate": 6.144444444444445e-06,
|
| 247 |
+
"loss": 0.0003,
|
| 248 |
+
"step": 850
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 54.01,
|
| 252 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 253 |
+
"loss": 0.0003,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 56.0,
|
| 258 |
+
"learning_rate": 5.588888888888889e-06,
|
| 259 |
+
"loss": 0.0002,
|
| 260 |
+
"step": 900
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 57.01,
|
| 264 |
+
"learning_rate": 5.311111111111111e-06,
|
| 265 |
+
"loss": 0.0003,
|
| 266 |
+
"step": 925
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 59.0,
|
| 270 |
+
"learning_rate": 5.033333333333333e-06,
|
| 271 |
+
"loss": 0.0005,
|
| 272 |
+
"step": 950
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 60.01,
|
| 276 |
+
"learning_rate": 4.755555555555556e-06,
|
| 277 |
+
"loss": 0.0008,
|
| 278 |
+
"step": 975
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 62.01,
|
| 282 |
+
"learning_rate": 4.477777777777778e-06,
|
| 283 |
+
"loss": 0.0005,
|
| 284 |
+
"step": 1000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 62.01,
|
| 288 |
+
"eval_loss": 0.6354185938835144,
|
| 289 |
+
"eval_runtime": 650.6168,
|
| 290 |
+
"eval_samples_per_second": 1.901,
|
| 291 |
+
"eval_steps_per_second": 0.12,
|
| 292 |
+
"eval_wer": 19.76310594428603,
|
| 293 |
+
"step": 1000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 64.0,
|
| 297 |
+
"learning_rate": 4.2000000000000004e-06,
|
| 298 |
+
"loss": 0.0002,
|
| 299 |
+
"step": 1025
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 65.01,
|
| 303 |
+
"learning_rate": 3.922222222222223e-06,
|
| 304 |
+
"loss": 0.0003,
|
| 305 |
+
"step": 1050
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 67.0,
|
| 309 |
+
"learning_rate": 3.644444444444445e-06,
|
| 310 |
+
"loss": 0.0002,
|
| 311 |
+
"step": 1075
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 68.01,
|
| 315 |
+
"learning_rate": 3.366666666666667e-06,
|
| 316 |
+
"loss": 0.0002,
|
| 317 |
+
"step": 1100
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 70.0,
|
| 321 |
+
"learning_rate": 3.088888888888889e-06,
|
| 322 |
+
"loss": 0.0002,
|
| 323 |
+
"step": 1125
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 71.01,
|
| 327 |
+
"learning_rate": 2.811111111111111e-06,
|
| 328 |
+
"loss": 0.0002,
|
| 329 |
+
"step": 1150
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 73.0,
|
| 333 |
+
"learning_rate": 2.5333333333333338e-06,
|
| 334 |
+
"loss": 0.0002,
|
| 335 |
+
"step": 1175
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 74.01,
|
| 339 |
+
"learning_rate": 2.2555555555555557e-06,
|
| 340 |
+
"loss": 0.0001,
|
| 341 |
+
"step": 1200
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 74.01,
|
| 345 |
+
"eval_loss": 0.6446589231491089,
|
| 346 |
+
"eval_runtime": 652.0364,
|
| 347 |
+
"eval_samples_per_second": 1.897,
|
| 348 |
+
"eval_steps_per_second": 0.12,
|
| 349 |
+
"eval_wer": 19.554726913796884,
|
| 350 |
+
"step": 1200
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 76.01,
|
| 354 |
+
"learning_rate": 1.977777777777778e-06,
|
| 355 |
+
"loss": 0.0001,
|
| 356 |
+
"step": 1225
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 78.0,
|
| 360 |
+
"learning_rate": 1.7000000000000002e-06,
|
| 361 |
+
"loss": 0.0001,
|
| 362 |
+
"step": 1250
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 79.01,
|
| 366 |
+
"learning_rate": 1.4222222222222223e-06,
|
| 367 |
+
"loss": 0.0001,
|
| 368 |
+
"step": 1275
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 81.0,
|
| 372 |
+
"learning_rate": 1.1444444444444446e-06,
|
| 373 |
+
"loss": 0.0001,
|
| 374 |
+
"step": 1300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 82.01,
|
| 378 |
+
"learning_rate": 8.666666666666668e-07,
|
| 379 |
+
"loss": 0.0001,
|
| 380 |
+
"step": 1325
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 84.0,
|
| 384 |
+
"learning_rate": 5.888888888888889e-07,
|
| 385 |
+
"loss": 0.0001,
|
| 386 |
+
"step": 1350
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 85.01,
|
| 390 |
+
"learning_rate": 3.111111111111111e-07,
|
| 391 |
+
"loss": 0.0001,
|
| 392 |
+
"step": 1375
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 87.01,
|
| 396 |
+
"learning_rate": 3.333333333333334e-08,
|
| 397 |
+
"loss": 0.0001,
|
| 398 |
+
"step": 1400
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 87.01,
|
| 402 |
+
"eval_loss": 0.6472771763801575,
|
| 403 |
+
"eval_runtime": 647.0101,
|
| 404 |
+
"eval_samples_per_second": 1.912,
|
| 405 |
+
"eval_steps_per_second": 0.121,
|
| 406 |
+
"eval_wer": 19.554726913796884,
|
| 407 |
+
"step": 1400
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 87.01,
|
| 411 |
+
"step": 1400,
|
| 412 |
+
"total_flos": 4.430241782562816e+19,
|
| 413 |
+
"train_loss": 0.07293392582147915,
|
| 414 |
+
"train_runtime": 12725.5944,
|
| 415 |
+
"train_samples_per_second": 3.52,
|
| 416 |
+
"train_steps_per_second": 0.11
|
| 417 |
+
}
|
| 418 |
+
],
|
| 419 |
+
"max_steps": 1400,
|
| 420 |
+
"num_train_epochs": 9223372036854775807,
|
| 421 |
+
"total_flos": 4.430241782562816e+19,
|
| 422 |
+
"trial_name": null,
|
| 423 |
+
"trial_params": null
|
| 424 |
+
}
|