End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +376 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.99,
|
| 3 |
+
"eval_loss": 0.35485121607780457,
|
| 4 |
+
"eval_runtime": 165.9954,
|
| 5 |
+
"eval_samples": 4843,
|
| 6 |
+
"eval_samples_per_second": 29.176,
|
| 7 |
+
"eval_steps_per_second": 0.916,
|
| 8 |
+
"eval_wer": 0.38265682656826566,
|
| 9 |
+
"train_loss": 2.1873197584885817,
|
| 10 |
+
"train_runtime": 245048.5131,
|
| 11 |
+
"train_samples": 11690,
|
| 12 |
+
"train_samples_per_second": 2.385,
|
| 13 |
+
"train_steps_per_second": 0.019
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.99,
|
| 3 |
+
"eval_loss": 0.35485121607780457,
|
| 4 |
+
"eval_runtime": 165.9954,
|
| 5 |
+
"eval_samples": 4843,
|
| 6 |
+
"eval_samples_per_second": 29.176,
|
| 7 |
+
"eval_steps_per_second": 0.916,
|
| 8 |
+
"eval_wer": 0.38265682656826566
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.99,
|
| 3 |
+
"train_loss": 2.1873197584885817,
|
| 4 |
+
"train_runtime": 245048.5131,
|
| 5 |
+
"train_samples": 11690,
|
| 6 |
+
"train_samples_per_second": 2.385,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.994535519125684,
|
| 5 |
+
"global_step": 4550,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.1,
|
| 12 |
+
"learning_rate": 3.7499999999999997e-06,
|
| 13 |
+
"loss": 14.8405,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.2,
|
| 18 |
+
"learning_rate": 7.499999999999999e-06,
|
| 19 |
+
"loss": 6.8597,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 3.3,
|
| 24 |
+
"learning_rate": 1.1249999999999999e-05,
|
| 25 |
+
"loss": 4.4132,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 4.39,
|
| 30 |
+
"learning_rate": 1.4999999999999999e-05,
|
| 31 |
+
"loss": 3.7795,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 5.49,
|
| 36 |
+
"learning_rate": 1.875e-05,
|
| 37 |
+
"loss": 3.4129,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 5.49,
|
| 42 |
+
"eval_loss": 3.3224499225616455,
|
| 43 |
+
"eval_runtime": 168.3653,
|
| 44 |
+
"eval_samples_per_second": 28.765,
|
| 45 |
+
"eval_steps_per_second": 0.903,
|
| 46 |
+
"eval_wer": 1.0,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 6.59,
|
| 51 |
+
"learning_rate": 2.2499999999999998e-05,
|
| 52 |
+
"loss": 3.2045,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 7.69,
|
| 57 |
+
"learning_rate": 2.6249999999999998e-05,
|
| 58 |
+
"loss": 3.142,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 8.79,
|
| 63 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 64 |
+
"loss": 3.0872,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 9.89,
|
| 69 |
+
"learning_rate": 3.375e-05,
|
| 70 |
+
"loss": 2.9848,
|
| 71 |
+
"step": 900
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 10.98,
|
| 75 |
+
"learning_rate": 3.75e-05,
|
| 76 |
+
"loss": 2.9323,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 10.98,
|
| 81 |
+
"eval_loss": 2.9127891063690186,
|
| 82 |
+
"eval_runtime": 166.7051,
|
| 83 |
+
"eval_samples_per_second": 29.051,
|
| 84 |
+
"eval_steps_per_second": 0.912,
|
| 85 |
+
"eval_wer": 1.0000283848992335,
|
| 86 |
+
"step": 1000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 12.09,
|
| 90 |
+
"learning_rate": 4.125e-05,
|
| 91 |
+
"loss": 2.9013,
|
| 92 |
+
"step": 1100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 13.19,
|
| 96 |
+
"learning_rate": 4.4999999999999996e-05,
|
| 97 |
+
"loss": 2.729,
|
| 98 |
+
"step": 1200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 14.28,
|
| 102 |
+
"learning_rate": 4.875e-05,
|
| 103 |
+
"loss": 2.1939,
|
| 104 |
+
"step": 1300
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 15.38,
|
| 108 |
+
"learning_rate": 5.2499999999999995e-05,
|
| 109 |
+
"loss": 1.8125,
|
| 110 |
+
"step": 1400
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 16.48,
|
| 114 |
+
"learning_rate": 5.625e-05,
|
| 115 |
+
"loss": 1.6839,
|
| 116 |
+
"step": 1500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 16.48,
|
| 120 |
+
"eval_loss": 0.7740097641944885,
|
| 121 |
+
"eval_runtime": 167.3266,
|
| 122 |
+
"eval_samples_per_second": 28.943,
|
| 123 |
+
"eval_steps_per_second": 0.908,
|
| 124 |
+
"eval_wer": 0.685381776894692,
|
| 125 |
+
"step": 1500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 17.58,
|
| 129 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 130 |
+
"loss": 1.6194,
|
| 131 |
+
"step": 1600
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 18.68,
|
| 135 |
+
"learning_rate": 6.374999999999999e-05,
|
| 136 |
+
"loss": 1.5613,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 19.78,
|
| 141 |
+
"learning_rate": 6.75e-05,
|
| 142 |
+
"loss": 1.5197,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 20.87,
|
| 147 |
+
"learning_rate": 7.1175e-05,
|
| 148 |
+
"loss": 1.5009,
|
| 149 |
+
"step": 1900
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 21.97,
|
| 153 |
+
"learning_rate": 7.492499999999999e-05,
|
| 154 |
+
"loss": 1.485,
|
| 155 |
+
"step": 2000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 21.97,
|
| 159 |
+
"eval_loss": 0.5829736590385437,
|
| 160 |
+
"eval_runtime": 166.3956,
|
| 161 |
+
"eval_samples_per_second": 29.105,
|
| 162 |
+
"eval_steps_per_second": 0.913,
|
| 163 |
+
"eval_wer": 0.597615668464377,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 23.08,
|
| 168 |
+
"learning_rate": 7.211764705882351e-05,
|
| 169 |
+
"loss": 1.4606,
|
| 170 |
+
"step": 2100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 24.17,
|
| 174 |
+
"learning_rate": 6.920588235294117e-05,
|
| 175 |
+
"loss": 1.4257,
|
| 176 |
+
"step": 2200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 25.27,
|
| 180 |
+
"learning_rate": 6.626470588235294e-05,
|
| 181 |
+
"loss": 1.4002,
|
| 182 |
+
"step": 2300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 26.37,
|
| 186 |
+
"learning_rate": 6.33235294117647e-05,
|
| 187 |
+
"loss": 1.3856,
|
| 188 |
+
"step": 2400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 27.47,
|
| 192 |
+
"learning_rate": 6.038235294117646e-05,
|
| 193 |
+
"loss": 1.362,
|
| 194 |
+
"step": 2500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 27.47,
|
| 198 |
+
"eval_loss": 0.48657190799713135,
|
| 199 |
+
"eval_runtime": 166.2387,
|
| 200 |
+
"eval_samples_per_second": 29.133,
|
| 201 |
+
"eval_steps_per_second": 0.914,
|
| 202 |
+
"eval_wer": 0.490519443655975,
|
| 203 |
+
"step": 2500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 28.57,
|
| 207 |
+
"learning_rate": 5.744117647058823e-05,
|
| 208 |
+
"loss": 1.3342,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 29.67,
|
| 213 |
+
"learning_rate": 5.4499999999999997e-05,
|
| 214 |
+
"loss": 1.318,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 30.77,
|
| 219 |
+
"learning_rate": 5.155882352941176e-05,
|
| 220 |
+
"loss": 1.3013,
|
| 221 |
+
"step": 2800
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 31.86,
|
| 225 |
+
"learning_rate": 4.861764705882352e-05,
|
| 226 |
+
"loss": 1.2849,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 32.96,
|
| 231 |
+
"learning_rate": 4.567647058823529e-05,
|
| 232 |
+
"loss": 1.2752,
|
| 233 |
+
"step": 3000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 32.96,
|
| 237 |
+
"eval_loss": 0.42398178577423096,
|
| 238 |
+
"eval_runtime": 167.0219,
|
| 239 |
+
"eval_samples_per_second": 28.996,
|
| 240 |
+
"eval_steps_per_second": 0.91,
|
| 241 |
+
"eval_wer": 0.4966789667896679,
|
| 242 |
+
"step": 3000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 34.07,
|
| 246 |
+
"learning_rate": 4.2735294117647056e-05,
|
| 247 |
+
"loss": 1.2682,
|
| 248 |
+
"step": 3100
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 35.16,
|
| 252 |
+
"learning_rate": 3.979411764705882e-05,
|
| 253 |
+
"loss": 1.2428,
|
| 254 |
+
"step": 3200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 36.26,
|
| 258 |
+
"learning_rate": 3.6852941176470586e-05,
|
| 259 |
+
"loss": 1.2282,
|
| 260 |
+
"step": 3300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 37.36,
|
| 264 |
+
"learning_rate": 3.391176470588235e-05,
|
| 265 |
+
"loss": 1.2198,
|
| 266 |
+
"step": 3400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 38.46,
|
| 270 |
+
"learning_rate": 3.0970588235294116e-05,
|
| 271 |
+
"loss": 1.1957,
|
| 272 |
+
"step": 3500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 38.46,
|
| 276 |
+
"eval_loss": 0.38985687494277954,
|
| 277 |
+
"eval_runtime": 166.2154,
|
| 278 |
+
"eval_samples_per_second": 29.137,
|
| 279 |
+
"eval_steps_per_second": 0.914,
|
| 280 |
+
"eval_wer": 0.42577348850411584,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 39.56,
|
| 285 |
+
"learning_rate": 2.8029411764705878e-05,
|
| 286 |
+
"loss": 1.1891,
|
| 287 |
+
"step": 3600
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 40.66,
|
| 291 |
+
"learning_rate": 2.5088235294117646e-05,
|
| 292 |
+
"loss": 1.1847,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 41.75,
|
| 297 |
+
"learning_rate": 2.2147058823529408e-05,
|
| 298 |
+
"loss": 1.1779,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 42.85,
|
| 303 |
+
"learning_rate": 1.9205882352941176e-05,
|
| 304 |
+
"loss": 1.1654,
|
| 305 |
+
"step": 3900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 43.95,
|
| 309 |
+
"learning_rate": 1.626470588235294e-05,
|
| 310 |
+
"loss": 1.1646,
|
| 311 |
+
"step": 4000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 43.95,
|
| 315 |
+
"eval_loss": 0.3597247898578644,
|
| 316 |
+
"eval_runtime": 165.7161,
|
| 317 |
+
"eval_samples_per_second": 29.225,
|
| 318 |
+
"eval_steps_per_second": 0.917,
|
| 319 |
+
"eval_wer": 0.401447629860914,
|
| 320 |
+
"step": 4000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 45.05,
|
| 324 |
+
"learning_rate": 1.3323529411764704e-05,
|
| 325 |
+
"loss": 1.1574,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 46.15,
|
| 330 |
+
"learning_rate": 1.0411764705882353e-05,
|
| 331 |
+
"loss": 1.1513,
|
| 332 |
+
"step": 4200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 47.25,
|
| 336 |
+
"learning_rate": 7.470588235294117e-06,
|
| 337 |
+
"loss": 1.1412,
|
| 338 |
+
"step": 4300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 48.35,
|
| 342 |
+
"learning_rate": 4.529411764705882e-06,
|
| 343 |
+
"loss": 1.1383,
|
| 344 |
+
"step": 4400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 49.45,
|
| 348 |
+
"learning_rate": 1.5882352941176468e-06,
|
| 349 |
+
"loss": 1.1265,
|
| 350 |
+
"step": 4500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 49.45,
|
| 354 |
+
"eval_loss": 0.35590532422065735,
|
| 355 |
+
"eval_runtime": 165.6811,
|
| 356 |
+
"eval_samples_per_second": 29.231,
|
| 357 |
+
"eval_steps_per_second": 0.917,
|
| 358 |
+
"eval_wer": 0.38288390576213455,
|
| 359 |
+
"step": 4500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 49.99,
|
| 363 |
+
"step": 4550,
|
| 364 |
+
"total_flos": 7.032770514539837e+19,
|
| 365 |
+
"train_loss": 2.1873197584885817,
|
| 366 |
+
"train_runtime": 245048.5131,
|
| 367 |
+
"train_samples_per_second": 2.385,
|
| 368 |
+
"train_steps_per_second": 0.019
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 4550,
|
| 372 |
+
"num_train_epochs": 50,
|
| 373 |
+
"total_flos": 7.032770514539837e+19,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|