End of training
Browse files
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 0.
|
| 7 |
-
"eval_wer":
|
| 8 |
-
"train_loss":
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second":
|
| 11 |
-
"train_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 71.43,
|
| 3 |
+
"eval_loss": 2.310106039047241,
|
| 4 |
+
"eval_runtime": 206.3711,
|
| 5 |
+
"eval_samples_per_second": 2.481,
|
| 6 |
+
"eval_steps_per_second": 0.078,
|
| 7 |
+
"eval_wer": 485.9866828087167,
|
| 8 |
+
"train_loss": 0.4595182914733887,
|
| 9 |
+
"train_runtime": 383.5233,
|
| 10 |
+
"train_samples_per_second": 83.437,
|
| 11 |
+
"train_steps_per_second": 1.304
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second": 0.
|
| 7 |
-
"eval_wer":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 71.43,
|
| 3 |
+
"eval_loss": 2.310106039047241,
|
| 4 |
+
"eval_runtime": 206.3711,
|
| 5 |
+
"eval_samples_per_second": 2.481,
|
| 6 |
+
"eval_steps_per_second": 0.078,
|
| 7 |
+
"eval_wer": 485.9866828087167
|
| 8 |
}
|
runs/Dec18_15-24-30_129-146-179-188/events.out.tfevents.1671377709.129-146-179-188.130712.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d048518c02c43ae90970320f92d48eb5c712ee9c34fa00c266118d3c77deb1c
|
| 3 |
+
size 358
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 71.43,
|
| 3 |
+
"train_loss": 0.4595182914733887,
|
| 4 |
+
"train_runtime": 383.5233,
|
| 5 |
+
"train_samples_per_second": 83.437,
|
| 6 |
+
"train_steps_per_second": 1.304
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,43 +1,370 @@
|
|
| 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 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
"
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
"
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"step":
|
| 27 |
-
},
|
| 28 |
-
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
}
|
| 37 |
],
|
| 38 |
-
"max_steps":
|
| 39 |
-
"num_train_epochs":
|
| 40 |
-
"total_flos":
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": null
|
| 43 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.310106039047241,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint-500",
|
| 4 |
+
"epoch": 71.42857142857143,
|
| 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": 1.43,
|
| 12 |
+
"learning_rate": 5.2499999999999994e-08,
|
| 13 |
+
"loss": 3.5252,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.86,
|
| 18 |
+
"learning_rate": 1.275e-07,
|
| 19 |
+
"loss": 3.509,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 4.29,
|
| 24 |
+
"learning_rate": 2.025e-07,
|
| 25 |
+
"loss": 3.481,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 5.71,
|
| 30 |
+
"learning_rate": 2.775e-07,
|
| 31 |
+
"loss": 3.4536,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 7.14,
|
| 36 |
+
"learning_rate": 2.86875e-07,
|
| 37 |
+
"loss": 3.3407,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 8.57,
|
| 42 |
+
"learning_rate": 2.6812500000000003e-07,
|
| 43 |
+
"loss": 3.1837,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 10.0,
|
| 48 |
+
"learning_rate": 2.49375e-07,
|
| 49 |
+
"loss": 3.1471,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 11.43,
|
| 54 |
+
"learning_rate": 2.3062500000000002e-07,
|
| 55 |
+
"loss": 3.0484,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 12.86,
|
| 60 |
+
"learning_rate": 2.11875e-07,
|
| 61 |
+
"loss": 2.9713,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 14.29,
|
| 66 |
+
"learning_rate": 1.93125e-07,
|
| 67 |
+
"loss": 2.9393,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 14.29,
|
| 72 |
+
"eval_loss": 2.902493715286255,
|
| 73 |
+
"eval_runtime": 131.7731,
|
| 74 |
+
"eval_samples_per_second": 3.885,
|
| 75 |
+
"eval_steps_per_second": 0.121,
|
| 76 |
+
"eval_wer": 369.26452784503635,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 15.71,
|
| 81 |
+
"learning_rate": 1.74375e-07,
|
| 82 |
+
"loss": 2.8874,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 17.14,
|
| 87 |
+
"learning_rate": 1.5562500000000002e-07,
|
| 88 |
+
"loss": 2.8192,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 18.57,
|
| 93 |
+
"learning_rate": 1.3687499999999999e-07,
|
| 94 |
+
"loss": 2.8025,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 20.0,
|
| 99 |
+
"learning_rate": 1.18125e-07,
|
| 100 |
+
"loss": 2.7738,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 21.43,
|
| 105 |
+
"learning_rate": 9.937499999999999e-08,
|
| 106 |
+
"loss": 2.7684,
|
| 107 |
+
"step": 150
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 22.86,
|
| 111 |
+
"learning_rate": 8.0625e-08,
|
| 112 |
+
"loss": 2.7294,
|
| 113 |
+
"step": 160
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 24.29,
|
| 117 |
+
"learning_rate": 6.187499999999999e-08,
|
| 118 |
+
"loss": 2.7318,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 25.71,
|
| 123 |
+
"learning_rate": 4.3125e-08,
|
| 124 |
+
"loss": 2.7239,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 27.14,
|
| 129 |
+
"learning_rate": 2.4374999999999998e-08,
|
| 130 |
+
"loss": 2.6988,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 28.57,
|
| 135 |
+
"learning_rate": 5.625e-09,
|
| 136 |
+
"loss": 2.7124,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 28.57,
|
| 141 |
+
"eval_loss": 2.716507911682129,
|
| 142 |
+
"eval_runtime": 138.682,
|
| 143 |
+
"eval_samples_per_second": 3.692,
|
| 144 |
+
"eval_steps_per_second": 0.115,
|
| 145 |
+
"eval_wer": 407.92221549636804,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 30.0,
|
| 150 |
+
"learning_rate": 1.9108695652173912e-07,
|
| 151 |
+
"loss": 2.6955,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 31.43,
|
| 156 |
+
"learning_rate": 1.8456521739130434e-07,
|
| 157 |
+
"loss": 2.6743,
|
| 158 |
+
"step": 220
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 32.86,
|
| 162 |
+
"learning_rate": 1.7804347826086957e-07,
|
| 163 |
+
"loss": 2.6255,
|
| 164 |
+
"step": 230
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 34.29,
|
| 168 |
+
"learning_rate": 1.715217391304348e-07,
|
| 169 |
+
"loss": 2.6113,
|
| 170 |
+
"step": 240
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 35.71,
|
| 174 |
+
"learning_rate": 1.65e-07,
|
| 175 |
+
"loss": 2.5752,
|
| 176 |
+
"step": 250
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 37.14,
|
| 180 |
+
"learning_rate": 1.584782608695652e-07,
|
| 181 |
+
"loss": 2.5542,
|
| 182 |
+
"step": 260
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 38.57,
|
| 186 |
+
"learning_rate": 1.5195652173913042e-07,
|
| 187 |
+
"loss": 2.514,
|
| 188 |
+
"step": 270
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 40.0,
|
| 192 |
+
"learning_rate": 1.4543478260869565e-07,
|
| 193 |
+
"loss": 2.5026,
|
| 194 |
+
"step": 280
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 41.43,
|
| 198 |
+
"learning_rate": 1.3891304347826087e-07,
|
| 199 |
+
"loss": 2.4645,
|
| 200 |
+
"step": 290
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 42.86,
|
| 204 |
+
"learning_rate": 1.323913043478261e-07,
|
| 205 |
+
"loss": 2.4773,
|
| 206 |
+
"step": 300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 42.86,
|
| 210 |
+
"eval_loss": 2.4649124145507812,
|
| 211 |
+
"eval_runtime": 248.4635,
|
| 212 |
+
"eval_samples_per_second": 2.061,
|
| 213 |
+
"eval_steps_per_second": 0.064,
|
| 214 |
+
"eval_wer": 449.50060532687655,
|
| 215 |
+
"step": 300
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 44.29,
|
| 219 |
+
"learning_rate": 1.258695652173913e-07,
|
| 220 |
+
"loss": 2.428,
|
| 221 |
+
"step": 310
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 45.71,
|
| 225 |
+
"learning_rate": 1.193478260869565e-07,
|
| 226 |
+
"loss": 2.4309,
|
| 227 |
+
"step": 320
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 47.14,
|
| 231 |
+
"learning_rate": 1.1282608695652174e-07,
|
| 232 |
+
"loss": 2.395,
|
| 233 |
+
"step": 330
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 48.57,
|
| 237 |
+
"learning_rate": 1.0630434782608696e-07,
|
| 238 |
+
"loss": 2.3836,
|
| 239 |
+
"step": 340
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 50.0,
|
| 243 |
+
"learning_rate": 9.978260869565218e-08,
|
| 244 |
+
"loss": 2.3801,
|
| 245 |
+
"step": 350
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 51.43,
|
| 249 |
+
"learning_rate": 9.326086956521739e-08,
|
| 250 |
+
"loss": 2.3529,
|
| 251 |
+
"step": 360
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 52.86,
|
| 255 |
+
"learning_rate": 8.673913043478261e-08,
|
| 256 |
+
"loss": 2.3635,
|
| 257 |
+
"step": 370
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 54.29,
|
| 261 |
+
"learning_rate": 8.021739130434783e-08,
|
| 262 |
+
"loss": 2.3338,
|
| 263 |
+
"step": 380
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 55.71,
|
| 267 |
+
"learning_rate": 7.369565217391304e-08,
|
| 268 |
+
"loss": 2.3501,
|
| 269 |
+
"step": 390
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 57.14,
|
| 273 |
+
"learning_rate": 6.717391304347826e-08,
|
| 274 |
+
"loss": 2.3142,
|
| 275 |
+
"step": 400
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 57.14,
|
| 279 |
+
"eval_loss": 2.346592664718628,
|
| 280 |
+
"eval_runtime": 217.0162,
|
| 281 |
+
"eval_samples_per_second": 2.359,
|
| 282 |
+
"eval_steps_per_second": 0.074,
|
| 283 |
+
"eval_wer": 473.600181598063,
|
| 284 |
+
"step": 400
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 58.57,
|
| 288 |
+
"learning_rate": 6.065217391304348e-08,
|
| 289 |
+
"loss": 2.3374,
|
| 290 |
+
"step": 410
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 60.0,
|
| 294 |
+
"learning_rate": 5.4130434782608695e-08,
|
| 295 |
+
"loss": 2.2977,
|
| 296 |
+
"step": 420
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 61.43,
|
| 300 |
+
"learning_rate": 4.760869565217391e-08,
|
| 301 |
+
"loss": 2.3,
|
| 302 |
+
"step": 430
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 62.86,
|
| 306 |
+
"learning_rate": 4.1086956521739124e-08,
|
| 307 |
+
"loss": 2.2979,
|
| 308 |
+
"step": 440
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 64.29,
|
| 312 |
+
"learning_rate": 3.4565217391304345e-08,
|
| 313 |
+
"loss": 2.2983,
|
| 314 |
+
"step": 450
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 65.71,
|
| 318 |
+
"learning_rate": 2.8043478260869563e-08,
|
| 319 |
+
"loss": 2.3046,
|
| 320 |
+
"step": 460
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 67.14,
|
| 324 |
+
"learning_rate": 2.152173913043478e-08,
|
| 325 |
+
"loss": 2.2772,
|
| 326 |
+
"step": 470
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 68.57,
|
| 330 |
+
"learning_rate": 1.5e-08,
|
| 331 |
+
"loss": 2.2866,
|
| 332 |
+
"step": 480
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 70.0,
|
| 336 |
+
"learning_rate": 8.478260869565216e-09,
|
| 337 |
+
"loss": 2.2822,
|
| 338 |
+
"step": 490
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 71.43,
|
| 342 |
+
"learning_rate": 1.9565217391304347e-09,
|
| 343 |
+
"loss": 2.2942,
|
| 344 |
+
"step": 500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 71.43,
|
| 348 |
+
"eval_loss": 2.310106039047241,
|
| 349 |
+
"eval_runtime": 207.4467,
|
| 350 |
+
"eval_samples_per_second": 2.468,
|
| 351 |
+
"eval_steps_per_second": 0.077,
|
| 352 |
+
"eval_wer": 485.9866828087167,
|
| 353 |
+
"step": 500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 71.43,
|
| 357 |
+
"step": 500,
|
| 358 |
+
"total_flos": 7.5808932950016e+17,
|
| 359 |
+
"train_loss": 0.4595182914733887,
|
| 360 |
+
"train_runtime": 383.5233,
|
| 361 |
+
"train_samples_per_second": 83.437,
|
| 362 |
+
"train_steps_per_second": 1.304
|
| 363 |
}
|
| 364 |
],
|
| 365 |
+
"max_steps": 500,
|
| 366 |
+
"num_train_epochs": 72,
|
| 367 |
+
"total_flos": 7.5808932950016e+17,
|
| 368 |
"trial_name": null,
|
| 369 |
"trial_params": null
|
| 370 |
}
|