End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +535 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.86,
|
| 3 |
+
"eval_loss": 0.9210379123687744,
|
| 4 |
+
"eval_runtime": 58.4497,
|
| 5 |
+
"eval_samples": 842,
|
| 6 |
+
"eval_samples_per_second": 14.406,
|
| 7 |
+
"eval_steps_per_second": 0.907,
|
| 8 |
+
"eval_wer": 0.3900716793251198,
|
| 9 |
+
"train_loss": 0.11175713245685284,
|
| 10 |
+
"train_runtime": 33540.098,
|
| 11 |
+
"train_samples": 3350,
|
| 12 |
+
"train_samples_per_second": 4.994,
|
| 13 |
+
"train_steps_per_second": 0.155
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.86,
|
| 3 |
+
"eval_loss": 0.9210379123687744,
|
| 4 |
+
"eval_runtime": 58.4497,
|
| 5 |
+
"eval_samples": 842,
|
| 6 |
+
"eval_samples_per_second": 14.406,
|
| 7 |
+
"eval_steps_per_second": 0.907,
|
| 8 |
+
"eval_wer": 0.3900716793251198
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.86,
|
| 3 |
+
"train_loss": 0.11175713245685284,
|
| 4 |
+
"train_runtime": 33540.098,
|
| 5 |
+
"train_samples": 3350,
|
| 6 |
+
"train_samples_per_second": 4.994,
|
| 7 |
+
"train_steps_per_second": 0.155
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,535 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9210379123687744,
|
| 3 |
+
"best_model_checkpoint": "./wav2vec2-ver2.0/checkpoint-3538",
|
| 4 |
+
"epoch": 49.86396181384248,
|
| 5 |
+
"global_step": 5200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.99,
|
| 12 |
+
"eval_loss": 4.028111457824707,
|
| 13 |
+
"eval_runtime": 62.0842,
|
| 14 |
+
"eval_samples_per_second": 13.562,
|
| 15 |
+
"eval_steps_per_second": 0.854,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 104
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 2.0,
|
| 21 |
+
"eval_loss": 3.40583872795105,
|
| 22 |
+
"eval_runtime": 58.57,
|
| 23 |
+
"eval_samples_per_second": 14.376,
|
| 24 |
+
"eval_steps_per_second": 0.905,
|
| 25 |
+
"eval_wer": 1.0,
|
| 26 |
+
"step": 209
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.99,
|
| 30 |
+
"eval_loss": 3.345716953277588,
|
| 31 |
+
"eval_runtime": 62.5527,
|
| 32 |
+
"eval_samples_per_second": 13.461,
|
| 33 |
+
"eval_steps_per_second": 0.847,
|
| 34 |
+
"eval_wer": 1.0,
|
| 35 |
+
"step": 312
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 4.0,
|
| 39 |
+
"eval_loss": 3.3383560180664062,
|
| 40 |
+
"eval_runtime": 59.2148,
|
| 41 |
+
"eval_samples_per_second": 14.219,
|
| 42 |
+
"eval_steps_per_second": 0.895,
|
| 43 |
+
"eval_wer": 1.0,
|
| 44 |
+
"step": 417
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.79,
|
| 48 |
+
"learning_rate": 4.7e-05,
|
| 49 |
+
"loss": 3.351,
|
| 50 |
+
"step": 500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 5.0,
|
| 54 |
+
"eval_loss": 3.319535970687866,
|
| 55 |
+
"eval_runtime": 60.0386,
|
| 56 |
+
"eval_samples_per_second": 14.024,
|
| 57 |
+
"eval_steps_per_second": 0.883,
|
| 58 |
+
"eval_wer": 1.0,
|
| 59 |
+
"step": 522
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 6.0,
|
| 63 |
+
"eval_loss": 3.277388334274292,
|
| 64 |
+
"eval_runtime": 59.0991,
|
| 65 |
+
"eval_samples_per_second": 14.247,
|
| 66 |
+
"eval_steps_per_second": 0.897,
|
| 67 |
+
"eval_wer": 0.9999866518947635,
|
| 68 |
+
"step": 627
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.99,
|
| 72 |
+
"eval_loss": 2.7498323917388916,
|
| 73 |
+
"eval_runtime": 59.3674,
|
| 74 |
+
"eval_samples_per_second": 14.183,
|
| 75 |
+
"eval_steps_per_second": 0.893,
|
| 76 |
+
"eval_wer": 1.018353644700135,
|
| 77 |
+
"step": 731
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 8.0,
|
| 81 |
+
"eval_loss": 2.0694806575775146,
|
| 82 |
+
"eval_runtime": 59.1337,
|
| 83 |
+
"eval_samples_per_second": 14.239,
|
| 84 |
+
"eval_steps_per_second": 0.896,
|
| 85 |
+
"eval_wer": 0.9267989908832441,
|
| 86 |
+
"step": 836
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 9.0,
|
| 90 |
+
"eval_loss": 1.666611909866333,
|
| 91 |
+
"eval_runtime": 59.1057,
|
| 92 |
+
"eval_samples_per_second": 14.246,
|
| 93 |
+
"eval_steps_per_second": 0.897,
|
| 94 |
+
"eval_wer": 0.8102833802741701,
|
| 95 |
+
"step": 941
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 9.56,
|
| 99 |
+
"learning_rate": 4.2e-05,
|
| 100 |
+
"loss": 2.5482,
|
| 101 |
+
"step": 1000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 10.0,
|
| 105 |
+
"eval_loss": 1.4118962287902832,
|
| 106 |
+
"eval_runtime": 60.2006,
|
| 107 |
+
"eval_samples_per_second": 13.987,
|
| 108 |
+
"eval_steps_per_second": 0.88,
|
| 109 |
+
"eval_wer": 0.7014028858603522,
|
| 110 |
+
"step": 1046
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 10.99,
|
| 114 |
+
"eval_loss": 1.2479561567306519,
|
| 115 |
+
"eval_runtime": 59.1239,
|
| 116 |
+
"eval_samples_per_second": 14.241,
|
| 117 |
+
"eval_steps_per_second": 0.896,
|
| 118 |
+
"eval_wer": 0.6408024880868161,
|
| 119 |
+
"step": 1150
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 12.0,
|
| 123 |
+
"eval_loss": 1.1396839618682861,
|
| 124 |
+
"eval_runtime": 60.2391,
|
| 125 |
+
"eval_samples_per_second": 13.978,
|
| 126 |
+
"eval_steps_per_second": 0.88,
|
| 127 |
+
"eval_wer": 0.5814434641002709,
|
| 128 |
+
"step": 1255
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 13.0,
|
| 132 |
+
"eval_loss": 1.0593441724777222,
|
| 133 |
+
"eval_runtime": 59.2221,
|
| 134 |
+
"eval_samples_per_second": 14.218,
|
| 135 |
+
"eval_steps_per_second": 0.895,
|
| 136 |
+
"eval_wer": 0.5381155145027163,
|
| 137 |
+
"step": 1360
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 14.0,
|
| 141 |
+
"eval_loss": 1.0059597492218018,
|
| 142 |
+
"eval_runtime": 59.2878,
|
| 143 |
+
"eval_samples_per_second": 14.202,
|
| 144 |
+
"eval_steps_per_second": 0.894,
|
| 145 |
+
"eval_wer": 0.5098709238223634,
|
| 146 |
+
"step": 1465
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 14.33,
|
| 150 |
+
"learning_rate": 3.7e-05,
|
| 151 |
+
"loss": 1.1172,
|
| 152 |
+
"step": 1500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 14.99,
|
| 156 |
+
"eval_loss": 0.9677549600601196,
|
| 157 |
+
"eval_runtime": 59.2664,
|
| 158 |
+
"eval_samples_per_second": 14.207,
|
| 159 |
+
"eval_steps_per_second": 0.894,
|
| 160 |
+
"eval_wer": 0.4830412322970754,
|
| 161 |
+
"step": 1569
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 16.0,
|
| 165 |
+
"eval_loss": 0.9378706812858582,
|
| 166 |
+
"eval_runtime": 59.4564,
|
| 167 |
+
"eval_samples_per_second": 14.162,
|
| 168 |
+
"eval_steps_per_second": 0.891,
|
| 169 |
+
"eval_wer": 0.46923929148257404,
|
| 170 |
+
"step": 1674
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 17.0,
|
| 174 |
+
"eval_loss": 0.9126999378204346,
|
| 175 |
+
"eval_runtime": 59.2107,
|
| 176 |
+
"eval_samples_per_second": 14.22,
|
| 177 |
+
"eval_steps_per_second": 0.895,
|
| 178 |
+
"eval_wer": 0.4618310930763378,
|
| 179 |
+
"step": 1779
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 18.0,
|
| 183 |
+
"eval_loss": 0.8923171758651733,
|
| 184 |
+
"eval_runtime": 59.2943,
|
| 185 |
+
"eval_samples_per_second": 14.2,
|
| 186 |
+
"eval_steps_per_second": 0.894,
|
| 187 |
+
"eval_wer": 0.43522831934006967,
|
| 188 |
+
"step": 1884
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 18.99,
|
| 192 |
+
"eval_loss": 0.8826682567596436,
|
| 193 |
+
"eval_runtime": 59.3015,
|
| 194 |
+
"eval_samples_per_second": 14.199,
|
| 195 |
+
"eval_steps_per_second": 0.894,
|
| 196 |
+
"eval_wer": 0.4254041138860339,
|
| 197 |
+
"step": 1988
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 19.11,
|
| 201 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 202 |
+
"loss": 0.7161,
|
| 203 |
+
"step": 2000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 20.0,
|
| 207 |
+
"eval_loss": 0.8722440600395203,
|
| 208 |
+
"eval_runtime": 59.4161,
|
| 209 |
+
"eval_samples_per_second": 14.171,
|
| 210 |
+
"eval_steps_per_second": 0.892,
|
| 211 |
+
"eval_wer": 0.43042300145494344,
|
| 212 |
+
"step": 2093
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 21.0,
|
| 216 |
+
"eval_loss": 0.8755246996879578,
|
| 217 |
+
"eval_runtime": 59.3074,
|
| 218 |
+
"eval_samples_per_second": 14.197,
|
| 219 |
+
"eval_steps_per_second": 0.894,
|
| 220 |
+
"eval_wer": 0.41415166117169666,
|
| 221 |
+
"step": 2198
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 22.0,
|
| 225 |
+
"eval_loss": 0.8679744601249695,
|
| 226 |
+
"eval_runtime": 59.2292,
|
| 227 |
+
"eval_samples_per_second": 14.216,
|
| 228 |
+
"eval_steps_per_second": 0.895,
|
| 229 |
+
"eval_wer": 0.4157400856948356,
|
| 230 |
+
"step": 2303
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 22.99,
|
| 234 |
+
"eval_loss": 0.8705059289932251,
|
| 235 |
+
"eval_runtime": 59.3713,
|
| 236 |
+
"eval_samples_per_second": 14.182,
|
| 237 |
+
"eval_steps_per_second": 0.893,
|
| 238 |
+
"eval_wer": 0.411588824966296,
|
| 239 |
+
"step": 2407
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 23.88,
|
| 243 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 244 |
+
"loss": 0.5338,
|
| 245 |
+
"step": 2500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 24.0,
|
| 249 |
+
"eval_loss": 0.8610785603523254,
|
| 250 |
+
"eval_runtime": 60.2932,
|
| 251 |
+
"eval_samples_per_second": 13.965,
|
| 252 |
+
"eval_steps_per_second": 0.879,
|
| 253 |
+
"eval_wer": 0.40391366445533056,
|
| 254 |
+
"step": 2512
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 25.0,
|
| 258 |
+
"eval_loss": 0.8716456294059753,
|
| 259 |
+
"eval_runtime": 59.4195,
|
| 260 |
+
"eval_samples_per_second": 14.17,
|
| 261 |
+
"eval_steps_per_second": 0.892,
|
| 262 |
+
"eval_wer": 0.3995087897272982,
|
| 263 |
+
"step": 2617
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 26.0,
|
| 267 |
+
"eval_loss": 0.8720651865005493,
|
| 268 |
+
"eval_runtime": 60.3407,
|
| 269 |
+
"eval_samples_per_second": 13.954,
|
| 270 |
+
"eval_steps_per_second": 0.878,
|
| 271 |
+
"eval_wer": 0.40370009477154717,
|
| 272 |
+
"step": 2722
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 26.99,
|
| 276 |
+
"eval_loss": 0.8809343576431274,
|
| 277 |
+
"eval_runtime": 59.2643,
|
| 278 |
+
"eval_samples_per_second": 14.208,
|
| 279 |
+
"eval_steps_per_second": 0.894,
|
| 280 |
+
"eval_wer": 0.39733304857375495,
|
| 281 |
+
"step": 2826
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 28.0,
|
| 285 |
+
"eval_loss": 0.9036707878112793,
|
| 286 |
+
"eval_runtime": 60.3075,
|
| 287 |
+
"eval_samples_per_second": 13.962,
|
| 288 |
+
"eval_steps_per_second": 0.879,
|
| 289 |
+
"eval_wer": 0.393835845001802,
|
| 290 |
+
"step": 2931
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 28.65,
|
| 294 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 295 |
+
"loss": 0.4299,
|
| 296 |
+
"step": 3000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 29.0,
|
| 300 |
+
"eval_loss": 0.9118879437446594,
|
| 301 |
+
"eval_runtime": 59.2709,
|
| 302 |
+
"eval_samples_per_second": 14.206,
|
| 303 |
+
"eval_steps_per_second": 0.894,
|
| 304 |
+
"eval_wer": 0.39029859711413967,
|
| 305 |
+
"step": 3036
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 30.0,
|
| 309 |
+
"eval_loss": 0.9117182493209839,
|
| 310 |
+
"eval_runtime": 59.2026,
|
| 311 |
+
"eval_samples_per_second": 14.222,
|
| 312 |
+
"eval_steps_per_second": 0.895,
|
| 313 |
+
"eval_wer": 0.3911929201649826,
|
| 314 |
+
"step": 3141
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 30.99,
|
| 318 |
+
"eval_loss": 0.9027386903762817,
|
| 319 |
+
"eval_runtime": 59.2101,
|
| 320 |
+
"eval_samples_per_second": 14.221,
|
| 321 |
+
"eval_steps_per_second": 0.895,
|
| 322 |
+
"eval_wer": 0.39296821816143196,
|
| 323 |
+
"step": 3245
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 31.99,
|
| 327 |
+
"eval_loss": 0.923963189125061,
|
| 328 |
+
"eval_runtime": 61.8239,
|
| 329 |
+
"eval_samples_per_second": 13.619,
|
| 330 |
+
"eval_steps_per_second": 0.857,
|
| 331 |
+
"eval_wer": 0.38977802100991765,
|
| 332 |
+
"step": 3328
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 33.0,
|
| 336 |
+
"eval_loss": 0.9336917400360107,
|
| 337 |
+
"eval_runtime": 58.5975,
|
| 338 |
+
"eval_samples_per_second": 14.369,
|
| 339 |
+
"eval_steps_per_second": 0.904,
|
| 340 |
+
"eval_wer": 0.3872418810149899,
|
| 341 |
+
"step": 3433
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 33.63,
|
| 345 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 346 |
+
"loss": 0.3491,
|
| 347 |
+
"step": 3500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 34.0,
|
| 351 |
+
"eval_loss": 0.9210379123687744,
|
| 352 |
+
"eval_runtime": 58.5611,
|
| 353 |
+
"eval_samples_per_second": 14.378,
|
| 354 |
+
"eval_steps_per_second": 0.905,
|
| 355 |
+
"eval_wer": 0.3900716793251198,
|
| 356 |
+
"step": 3538
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 35.0,
|
| 360 |
+
"eval_loss": 0.9308741092681885,
|
| 361 |
+
"eval_runtime": 58.496,
|
| 362 |
+
"eval_samples_per_second": 14.394,
|
| 363 |
+
"eval_steps_per_second": 0.906,
|
| 364 |
+
"eval_wer": 0.39053886300839596,
|
| 365 |
+
"step": 3643
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 35.99,
|
| 369 |
+
"eval_loss": 0.9527643918991089,
|
| 370 |
+
"eval_runtime": 58.33,
|
| 371 |
+
"eval_samples_per_second": 14.435,
|
| 372 |
+
"eval_steps_per_second": 0.909,
|
| 373 |
+
"eval_wer": 0.3906322997450512,
|
| 374 |
+
"step": 3747
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 37.0,
|
| 378 |
+
"eval_loss": 0.9505965113639832,
|
| 379 |
+
"eval_runtime": 58.5212,
|
| 380 |
+
"eval_samples_per_second": 14.388,
|
| 381 |
+
"eval_steps_per_second": 0.906,
|
| 382 |
+
"eval_wer": 0.3880160711187047,
|
| 383 |
+
"step": 3852
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 38.0,
|
| 387 |
+
"eval_loss": 0.9606704711914062,
|
| 388 |
+
"eval_runtime": 58.4358,
|
| 389 |
+
"eval_samples_per_second": 14.409,
|
| 390 |
+
"eval_steps_per_second": 0.907,
|
| 391 |
+
"eval_wer": 0.3853197538609394,
|
| 392 |
+
"step": 3957
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 38.41,
|
| 396 |
+
"learning_rate": 1.2e-05,
|
| 397 |
+
"loss": 0.3195,
|
| 398 |
+
"step": 4000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 39.0,
|
| 402 |
+
"eval_loss": 0.9566919803619385,
|
| 403 |
+
"eval_runtime": 58.6525,
|
| 404 |
+
"eval_samples_per_second": 14.356,
|
| 405 |
+
"eval_steps_per_second": 0.904,
|
| 406 |
+
"eval_wer": 0.3905655592188689,
|
| 407 |
+
"step": 4062
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 39.99,
|
| 411 |
+
"eval_loss": 0.9631790518760681,
|
| 412 |
+
"eval_runtime": 58.5685,
|
| 413 |
+
"eval_samples_per_second": 14.376,
|
| 414 |
+
"eval_steps_per_second": 0.905,
|
| 415 |
+
"eval_wer": 0.38928414111616855,
|
| 416 |
+
"step": 4166
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 41.0,
|
| 420 |
+
"eval_loss": 0.9797289371490479,
|
| 421 |
+
"eval_runtime": 58.522,
|
| 422 |
+
"eval_samples_per_second": 14.388,
|
| 423 |
+
"eval_steps_per_second": 0.906,
|
| 424 |
+
"eval_wer": 0.38385146228492867,
|
| 425 |
+
"step": 4271
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 42.0,
|
| 429 |
+
"eval_loss": 0.9818938970565796,
|
| 430 |
+
"eval_runtime": 58.7742,
|
| 431 |
+
"eval_samples_per_second": 14.326,
|
| 432 |
+
"eval_steps_per_second": 0.902,
|
| 433 |
+
"eval_wer": 0.38535979817664884,
|
| 434 |
+
"step": 4376
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 43.0,
|
| 438 |
+
"eval_loss": 0.9686055779457092,
|
| 439 |
+
"eval_runtime": 58.9453,
|
| 440 |
+
"eval_samples_per_second": 14.284,
|
| 441 |
+
"eval_steps_per_second": 0.899,
|
| 442 |
+
"eval_wer": 0.38696157080502425,
|
| 443 |
+
"step": 4481
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 43.18,
|
| 447 |
+
"learning_rate": 7.000000000000001e-06,
|
| 448 |
+
"loss": 0.2892,
|
| 449 |
+
"step": 4500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 43.99,
|
| 453 |
+
"eval_loss": 0.9807793498039246,
|
| 454 |
+
"eval_runtime": 58.7863,
|
| 455 |
+
"eval_samples_per_second": 14.323,
|
| 456 |
+
"eval_steps_per_second": 0.902,
|
| 457 |
+
"eval_wer": 0.38953775511566135,
|
| 458 |
+
"step": 4585
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 45.0,
|
| 462 |
+
"eval_loss": 0.9857133626937866,
|
| 463 |
+
"eval_runtime": 58.8468,
|
| 464 |
+
"eval_samples_per_second": 14.308,
|
| 465 |
+
"eval_steps_per_second": 0.901,
|
| 466 |
+
"eval_wer": 0.3892440968004592,
|
| 467 |
+
"step": 4690
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 46.0,
|
| 471 |
+
"eval_loss": 0.9959315657615662,
|
| 472 |
+
"eval_runtime": 58.8414,
|
| 473 |
+
"eval_samples_per_second": 14.31,
|
| 474 |
+
"eval_steps_per_second": 0.901,
|
| 475 |
+
"eval_wer": 0.3831039683916868,
|
| 476 |
+
"step": 4795
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 47.0,
|
| 480 |
+
"eval_loss": 0.9959281086921692,
|
| 481 |
+
"eval_runtime": 58.7339,
|
| 482 |
+
"eval_samples_per_second": 14.336,
|
| 483 |
+
"eval_steps_per_second": 0.902,
|
| 484 |
+
"eval_wer": 0.387041659436443,
|
| 485 |
+
"step": 4900
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 47.95,
|
| 489 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 490 |
+
"loss": 0.2705,
|
| 491 |
+
"step": 5000
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 47.99,
|
| 495 |
+
"eval_loss": 1.0028016567230225,
|
| 496 |
+
"eval_runtime": 58.7024,
|
| 497 |
+
"eval_samples_per_second": 14.344,
|
| 498 |
+
"eval_steps_per_second": 0.903,
|
| 499 |
+
"eval_wer": 0.38601385533323546,
|
| 500 |
+
"step": 5004
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 49.0,
|
| 504 |
+
"eval_loss": 1.001922845840454,
|
| 505 |
+
"eval_runtime": 59.7161,
|
| 506 |
+
"eval_samples_per_second": 14.1,
|
| 507 |
+
"eval_steps_per_second": 0.888,
|
| 508 |
+
"eval_wer": 0.386868134068369,
|
| 509 |
+
"step": 5109
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 49.86,
|
| 513 |
+
"eval_loss": 1.004983901977539,
|
| 514 |
+
"eval_runtime": 58.7107,
|
| 515 |
+
"eval_samples_per_second": 14.342,
|
| 516 |
+
"eval_steps_per_second": 0.903,
|
| 517 |
+
"eval_wer": 0.3856801527023239,
|
| 518 |
+
"step": 5200
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 49.86,
|
| 522 |
+
"step": 5200,
|
| 523 |
+
"total_flos": 4.179442576708594e+19,
|
| 524 |
+
"train_loss": 0.11175713245685284,
|
| 525 |
+
"train_runtime": 33540.098,
|
| 526 |
+
"train_samples_per_second": 4.994,
|
| 527 |
+
"train_steps_per_second": 0.155
|
| 528 |
+
}
|
| 529 |
+
],
|
| 530 |
+
"max_steps": 5200,
|
| 531 |
+
"num_train_epochs": 50,
|
| 532 |
+
"total_flos": 4.179442576708594e+19,
|
| 533 |
+
"trial_name": null,
|
| 534 |
+
"trial_params": null
|
| 535 |
+
}
|