End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +610 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_loss": 8.827937126159668,
|
| 4 |
+
"eval_runtime": 223.6666,
|
| 5 |
+
"eval_samples": 4276,
|
| 6 |
+
"eval_samples_per_second": 19.118,
|
| 7 |
+
"eval_steps_per_second": 9.559,
|
| 8 |
+
"eval_wer": 1.0123093040005238,
|
| 9 |
+
"train_loss": 8.274780469063002,
|
| 10 |
+
"train_runtime": 14935.5952,
|
| 11 |
+
"train_samples": 10175,
|
| 12 |
+
"train_samples_per_second": 6.813,
|
| 13 |
+
"train_steps_per_second": 0.026
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"eval_loss": 8.827937126159668,
|
| 4 |
+
"eval_runtime": 223.6666,
|
| 5 |
+
"eval_samples": 4276,
|
| 6 |
+
"eval_samples_per_second": 19.118,
|
| 7 |
+
"eval_steps_per_second": 9.559,
|
| 8 |
+
"eval_wer": 1.0123093040005238
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.98,
|
| 3 |
+
"train_loss": 8.274780469063002,
|
| 4 |
+
"train_runtime": 14935.5952,
|
| 5 |
+
"train_samples": 10175,
|
| 6 |
+
"train_samples_per_second": 6.813,
|
| 7 |
+
"train_steps_per_second": 0.026
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,610 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.981132075471699,
|
| 5 |
+
"global_step": 390,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.25,
|
| 12 |
+
"learning_rate": 1e-08,
|
| 13 |
+
"loss": 8.1684,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.25,
|
| 18 |
+
"eval_loss": 8.85881519317627,
|
| 19 |
+
"eval_runtime": 219.4921,
|
| 20 |
+
"eval_samples_per_second": 19.481,
|
| 21 |
+
"eval_steps_per_second": 9.741,
|
| 22 |
+
"eval_wer": 1.0125384665750017,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5,
|
| 27 |
+
"learning_rate": 9.736842105263159e-09,
|
| 28 |
+
"loss": 8.1428,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.5,
|
| 33 |
+
"eval_loss": 8.856884956359863,
|
| 34 |
+
"eval_runtime": 224.2813,
|
| 35 |
+
"eval_samples_per_second": 19.065,
|
| 36 |
+
"eval_steps_per_second": 9.533,
|
| 37 |
+
"eval_wer": 1.012505729064362,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.75,
|
| 42 |
+
"learning_rate": 9.473684210526316e-09,
|
| 43 |
+
"loss": 8.1333,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.75,
|
| 48 |
+
"eval_loss": 8.855155944824219,
|
| 49 |
+
"eval_runtime": 226.0385,
|
| 50 |
+
"eval_samples_per_second": 18.917,
|
| 51 |
+
"eval_steps_per_second": 9.459,
|
| 52 |
+
"eval_wer": 1.0124075165324429,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.03,
|
| 57 |
+
"learning_rate": 9.210526315789473e-09,
|
| 58 |
+
"loss": 8.7873,
|
| 59 |
+
"step": 40
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.03,
|
| 63 |
+
"eval_loss": 8.85318660736084,
|
| 64 |
+
"eval_runtime": 220.4335,
|
| 65 |
+
"eval_samples_per_second": 19.398,
|
| 66 |
+
"eval_steps_per_second": 9.699,
|
| 67 |
+
"eval_wer": 1.0124075165324429,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.28,
|
| 72 |
+
"learning_rate": 8.947368421052632e-09,
|
| 73 |
+
"loss": 8.1298,
|
| 74 |
+
"step": 50
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.28,
|
| 78 |
+
"eval_loss": 8.851649284362793,
|
| 79 |
+
"eval_runtime": 224.7965,
|
| 80 |
+
"eval_samples_per_second": 19.022,
|
| 81 |
+
"eval_steps_per_second": 9.511,
|
| 82 |
+
"eval_wer": 1.0124075165324429,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.53,
|
| 87 |
+
"learning_rate": 8.68421052631579e-09,
|
| 88 |
+
"loss": 8.1445,
|
| 89 |
+
"step": 60
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.53,
|
| 93 |
+
"eval_loss": 8.84989070892334,
|
| 94 |
+
"eval_runtime": 220.475,
|
| 95 |
+
"eval_samples_per_second": 19.394,
|
| 96 |
+
"eval_steps_per_second": 9.697,
|
| 97 |
+
"eval_wer": 1.0123420415111635,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.78,
|
| 102 |
+
"learning_rate": 8.421052631578947e-09,
|
| 103 |
+
"loss": 8.1635,
|
| 104 |
+
"step": 70
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.78,
|
| 108 |
+
"eval_loss": 8.8483304977417,
|
| 109 |
+
"eval_runtime": 222.7151,
|
| 110 |
+
"eval_samples_per_second": 19.199,
|
| 111 |
+
"eval_steps_per_second": 9.6,
|
| 112 |
+
"eval_wer": 1.0124075165324429,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.05,
|
| 117 |
+
"learning_rate": 8.157894736842106e-09,
|
| 118 |
+
"loss": 8.7587,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.05,
|
| 123 |
+
"eval_loss": 8.846796989440918,
|
| 124 |
+
"eval_runtime": 221.1122,
|
| 125 |
+
"eval_samples_per_second": 19.339,
|
| 126 |
+
"eval_steps_per_second": 9.669,
|
| 127 |
+
"eval_wer": 1.0125384665750017,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.3,
|
| 132 |
+
"learning_rate": 7.894736842105263e-09,
|
| 133 |
+
"loss": 8.1424,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.3,
|
| 138 |
+
"eval_loss": 8.845438957214355,
|
| 139 |
+
"eval_runtime": 219.7737,
|
| 140 |
+
"eval_samples_per_second": 19.456,
|
| 141 |
+
"eval_steps_per_second": 9.728,
|
| 142 |
+
"eval_wer": 1.0124075165324429,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 2.55,
|
| 147 |
+
"learning_rate": 7.631578947368422e-09,
|
| 148 |
+
"loss": 8.1318,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.55,
|
| 153 |
+
"eval_loss": 8.844048500061035,
|
| 154 |
+
"eval_runtime": 222.4326,
|
| 155 |
+
"eval_samples_per_second": 19.224,
|
| 156 |
+
"eval_steps_per_second": 9.612,
|
| 157 |
+
"eval_wer": 1.0124402540430826,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.81,
|
| 162 |
+
"learning_rate": 7.368421052631579e-09,
|
| 163 |
+
"loss": 8.1469,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.81,
|
| 168 |
+
"eval_loss": 8.842790603637695,
|
| 169 |
+
"eval_runtime": 224.1044,
|
| 170 |
+
"eval_samples_per_second": 19.08,
|
| 171 |
+
"eval_steps_per_second": 9.54,
|
| 172 |
+
"eval_wer": 1.012505729064362,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.08,
|
| 177 |
+
"learning_rate": 7.105263157894737e-09,
|
| 178 |
+
"loss": 8.7602,
|
| 179 |
+
"step": 120
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.08,
|
| 183 |
+
"eval_loss": 8.841601371765137,
|
| 184 |
+
"eval_runtime": 222.7003,
|
| 185 |
+
"eval_samples_per_second": 19.201,
|
| 186 |
+
"eval_steps_per_second": 9.6,
|
| 187 |
+
"eval_wer": 1.0124729915537223,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.33,
|
| 192 |
+
"learning_rate": 6.842105263157895e-09,
|
| 193 |
+
"loss": 8.1584,
|
| 194 |
+
"step": 130
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.33,
|
| 198 |
+
"eval_loss": 8.840473175048828,
|
| 199 |
+
"eval_runtime": 220.9442,
|
| 200 |
+
"eval_samples_per_second": 19.353,
|
| 201 |
+
"eval_steps_per_second": 9.677,
|
| 202 |
+
"eval_wer": 1.0125712040856414,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.58,
|
| 207 |
+
"learning_rate": 6.578947368421054e-09,
|
| 208 |
+
"loss": 8.142,
|
| 209 |
+
"step": 140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.58,
|
| 213 |
+
"eval_loss": 8.839417457580566,
|
| 214 |
+
"eval_runtime": 223.4762,
|
| 215 |
+
"eval_samples_per_second": 19.134,
|
| 216 |
+
"eval_steps_per_second": 9.567,
|
| 217 |
+
"eval_wer": 1.0125712040856414,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.83,
|
| 222 |
+
"learning_rate": 6.31578947368421e-09,
|
| 223 |
+
"loss": 8.1285,
|
| 224 |
+
"step": 150
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.83,
|
| 228 |
+
"eval_loss": 8.838351249694824,
|
| 229 |
+
"eval_runtime": 225.8637,
|
| 230 |
+
"eval_samples_per_second": 18.932,
|
| 231 |
+
"eval_steps_per_second": 9.466,
|
| 232 |
+
"eval_wer": 1.0124075165324429,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 4.1,
|
| 237 |
+
"learning_rate": 6.052631578947369e-09,
|
| 238 |
+
"loss": 8.7756,
|
| 239 |
+
"step": 160
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 4.1,
|
| 243 |
+
"eval_loss": 8.837142944335938,
|
| 244 |
+
"eval_runtime": 224.8527,
|
| 245 |
+
"eval_samples_per_second": 19.017,
|
| 246 |
+
"eval_steps_per_second": 9.508,
|
| 247 |
+
"eval_wer": 1.0124075165324429,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.35,
|
| 252 |
+
"learning_rate": 5.789473684210527e-09,
|
| 253 |
+
"loss": 8.0991,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.35,
|
| 258 |
+
"eval_loss": 8.83634090423584,
|
| 259 |
+
"eval_runtime": 220.3123,
|
| 260 |
+
"eval_samples_per_second": 19.409,
|
| 261 |
+
"eval_steps_per_second": 9.704,
|
| 262 |
+
"eval_wer": 1.0124729915537223,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 4.6,
|
| 267 |
+
"learning_rate": 5.526315789473685e-09,
|
| 268 |
+
"loss": 8.1442,
|
| 269 |
+
"step": 180
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.6,
|
| 273 |
+
"eval_loss": 8.83536434173584,
|
| 274 |
+
"eval_runtime": 224.5432,
|
| 275 |
+
"eval_samples_per_second": 19.043,
|
| 276 |
+
"eval_steps_per_second": 9.522,
|
| 277 |
+
"eval_wer": 1.0124402540430826,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.86,
|
| 282 |
+
"learning_rate": 5.263157894736842e-09,
|
| 283 |
+
"loss": 8.1294,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.86,
|
| 288 |
+
"eval_loss": 8.834578514099121,
|
| 289 |
+
"eval_runtime": 220.0402,
|
| 290 |
+
"eval_samples_per_second": 19.433,
|
| 291 |
+
"eval_steps_per_second": 9.716,
|
| 292 |
+
"eval_wer": 1.0124075165324429,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 5.13,
|
| 297 |
+
"learning_rate": 5e-09,
|
| 298 |
+
"loss": 8.7276,
|
| 299 |
+
"step": 200
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.13,
|
| 303 |
+
"eval_loss": 8.833772659301758,
|
| 304 |
+
"eval_runtime": 224.0823,
|
| 305 |
+
"eval_samples_per_second": 19.082,
|
| 306 |
+
"eval_steps_per_second": 9.541,
|
| 307 |
+
"eval_wer": 1.0125384665750017,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.38,
|
| 312 |
+
"learning_rate": 4.736842105263158e-09,
|
| 313 |
+
"loss": 8.1439,
|
| 314 |
+
"step": 210
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.38,
|
| 318 |
+
"eval_loss": 8.832892417907715,
|
| 319 |
+
"eval_runtime": 220.6908,
|
| 320 |
+
"eval_samples_per_second": 19.376,
|
| 321 |
+
"eval_steps_per_second": 9.688,
|
| 322 |
+
"eval_wer": 1.0124402540430826,
|
| 323 |
+
"step": 210
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 5.63,
|
| 327 |
+
"learning_rate": 4.473684210526316e-09,
|
| 328 |
+
"loss": 8.1115,
|
| 329 |
+
"step": 220
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 5.63,
|
| 333 |
+
"eval_loss": 8.832157135009766,
|
| 334 |
+
"eval_runtime": 221.8649,
|
| 335 |
+
"eval_samples_per_second": 19.273,
|
| 336 |
+
"eval_steps_per_second": 9.636,
|
| 337 |
+
"eval_wer": 1.0124402540430826,
|
| 338 |
+
"step": 220
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.88,
|
| 342 |
+
"learning_rate": 4.210526315789473e-09,
|
| 343 |
+
"loss": 8.1501,
|
| 344 |
+
"step": 230
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 5.88,
|
| 348 |
+
"eval_loss": 8.831602096557617,
|
| 349 |
+
"eval_runtime": 223.55,
|
| 350 |
+
"eval_samples_per_second": 19.128,
|
| 351 |
+
"eval_steps_per_second": 9.564,
|
| 352 |
+
"eval_wer": 1.0125384665750017,
|
| 353 |
+
"step": 230
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 6.15,
|
| 357 |
+
"learning_rate": 3.947368421052631e-09,
|
| 358 |
+
"loss": 8.7143,
|
| 359 |
+
"step": 240
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 6.15,
|
| 363 |
+
"eval_loss": 8.830825805664062,
|
| 364 |
+
"eval_runtime": 224.3279,
|
| 365 |
+
"eval_samples_per_second": 19.061,
|
| 366 |
+
"eval_steps_per_second": 9.531,
|
| 367 |
+
"eval_wer": 1.0124075165324429,
|
| 368 |
+
"step": 240
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.4,
|
| 372 |
+
"learning_rate": 3.6842105263157894e-09,
|
| 373 |
+
"loss": 8.143,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.4,
|
| 378 |
+
"eval_loss": 8.830228805541992,
|
| 379 |
+
"eval_runtime": 225.4738,
|
| 380 |
+
"eval_samples_per_second": 18.965,
|
| 381 |
+
"eval_steps_per_second": 9.482,
|
| 382 |
+
"eval_wer": 1.0123747790218032,
|
| 383 |
+
"step": 250
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 6.65,
|
| 387 |
+
"learning_rate": 3.4210526315789474e-09,
|
| 388 |
+
"loss": 8.1528,
|
| 389 |
+
"step": 260
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 6.65,
|
| 393 |
+
"eval_loss": 8.829960823059082,
|
| 394 |
+
"eval_runtime": 222.8802,
|
| 395 |
+
"eval_samples_per_second": 19.185,
|
| 396 |
+
"eval_steps_per_second": 9.593,
|
| 397 |
+
"eval_wer": 1.0124729915537223,
|
| 398 |
+
"step": 260
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.91,
|
| 402 |
+
"learning_rate": 3.1842105263157894e-09,
|
| 403 |
+
"loss": 8.1293,
|
| 404 |
+
"step": 270
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 6.91,
|
| 408 |
+
"eval_loss": 8.829716682434082,
|
| 409 |
+
"eval_runtime": 223.7307,
|
| 410 |
+
"eval_samples_per_second": 19.112,
|
| 411 |
+
"eval_steps_per_second": 9.556,
|
| 412 |
+
"eval_wer": 1.0124075165324429,
|
| 413 |
+
"step": 270
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 7.18,
|
| 417 |
+
"learning_rate": 2.9210526315789475e-09,
|
| 418 |
+
"loss": 8.7519,
|
| 419 |
+
"step": 280
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 7.18,
|
| 423 |
+
"eval_loss": 8.829301834106445,
|
| 424 |
+
"eval_runtime": 223.0404,
|
| 425 |
+
"eval_samples_per_second": 19.171,
|
| 426 |
+
"eval_steps_per_second": 9.586,
|
| 427 |
+
"eval_wer": 1.0124729915537223,
|
| 428 |
+
"step": 280
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 7.43,
|
| 432 |
+
"learning_rate": 2.657894736842105e-09,
|
| 433 |
+
"loss": 8.1153,
|
| 434 |
+
"step": 290
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 7.43,
|
| 438 |
+
"eval_loss": 8.828947067260742,
|
| 439 |
+
"eval_runtime": 219.8129,
|
| 440 |
+
"eval_samples_per_second": 19.453,
|
| 441 |
+
"eval_steps_per_second": 9.726,
|
| 442 |
+
"eval_wer": 1.0124075165324429,
|
| 443 |
+
"step": 290
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 7.68,
|
| 447 |
+
"learning_rate": 2.394736842105263e-09,
|
| 448 |
+
"loss": 8.1292,
|
| 449 |
+
"step": 300
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 7.68,
|
| 453 |
+
"eval_loss": 8.828753471374512,
|
| 454 |
+
"eval_runtime": 222.9513,
|
| 455 |
+
"eval_samples_per_second": 19.179,
|
| 456 |
+
"eval_steps_per_second": 9.59,
|
| 457 |
+
"eval_wer": 1.0124402540430826,
|
| 458 |
+
"step": 300
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 7.93,
|
| 462 |
+
"learning_rate": 2.131578947368421e-09,
|
| 463 |
+
"loss": 8.0904,
|
| 464 |
+
"step": 310
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 7.93,
|
| 468 |
+
"eval_loss": 8.828449249267578,
|
| 469 |
+
"eval_runtime": 224.0134,
|
| 470 |
+
"eval_samples_per_second": 19.088,
|
| 471 |
+
"eval_steps_per_second": 9.544,
|
| 472 |
+
"eval_wer": 1.0124075165324429,
|
| 473 |
+
"step": 310
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 8.2,
|
| 477 |
+
"learning_rate": 1.868421052631579e-09,
|
| 478 |
+
"loss": 8.7425,
|
| 479 |
+
"step": 320
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 8.2,
|
| 483 |
+
"eval_loss": 8.828290939331055,
|
| 484 |
+
"eval_runtime": 219.9475,
|
| 485 |
+
"eval_samples_per_second": 19.441,
|
| 486 |
+
"eval_steps_per_second": 9.721,
|
| 487 |
+
"eval_wer": 1.0125384665750017,
|
| 488 |
+
"step": 320
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 8.45,
|
| 492 |
+
"learning_rate": 1.605263157894737e-09,
|
| 493 |
+
"loss": 8.0963,
|
| 494 |
+
"step": 330
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 8.45,
|
| 498 |
+
"eval_loss": 8.828081130981445,
|
| 499 |
+
"eval_runtime": 222.5212,
|
| 500 |
+
"eval_samples_per_second": 19.216,
|
| 501 |
+
"eval_steps_per_second": 9.608,
|
| 502 |
+
"eval_wer": 1.0124075165324429,
|
| 503 |
+
"step": 330
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 8.7,
|
| 507 |
+
"learning_rate": 1.3421052631578948e-09,
|
| 508 |
+
"loss": 8.1112,
|
| 509 |
+
"step": 340
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 8.7,
|
| 513 |
+
"eval_loss": 8.828051567077637,
|
| 514 |
+
"eval_runtime": 222.696,
|
| 515 |
+
"eval_samples_per_second": 19.201,
|
| 516 |
+
"eval_steps_per_second": 9.601,
|
| 517 |
+
"eval_wer": 1.0124402540430826,
|
| 518 |
+
"step": 340
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 8.96,
|
| 522 |
+
"learning_rate": 1.0789473684210528e-09,
|
| 523 |
+
"loss": 8.124,
|
| 524 |
+
"step": 350
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 8.96,
|
| 528 |
+
"eval_loss": 8.828123092651367,
|
| 529 |
+
"eval_runtime": 222.2122,
|
| 530 |
+
"eval_samples_per_second": 19.243,
|
| 531 |
+
"eval_steps_per_second": 9.621,
|
| 532 |
+
"eval_wer": 1.012505729064362,
|
| 533 |
+
"step": 350
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 9.23,
|
| 537 |
+
"learning_rate": 8.157894736842106e-10,
|
| 538 |
+
"loss": 8.7327,
|
| 539 |
+
"step": 360
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.23,
|
| 543 |
+
"eval_loss": 8.827865600585938,
|
| 544 |
+
"eval_runtime": 222.5189,
|
| 545 |
+
"eval_samples_per_second": 19.216,
|
| 546 |
+
"eval_steps_per_second": 9.608,
|
| 547 |
+
"eval_wer": 1.0123420415111635,
|
| 548 |
+
"step": 360
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 9.48,
|
| 552 |
+
"learning_rate": 5.526315789473684e-10,
|
| 553 |
+
"loss": 8.1261,
|
| 554 |
+
"step": 370
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 9.48,
|
| 558 |
+
"eval_loss": 8.827857971191406,
|
| 559 |
+
"eval_runtime": 224.6034,
|
| 560 |
+
"eval_samples_per_second": 19.038,
|
| 561 |
+
"eval_steps_per_second": 9.519,
|
| 562 |
+
"eval_wer": 1.012603941596281,
|
| 563 |
+
"step": 370
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 9.73,
|
| 567 |
+
"learning_rate": 2.894736842105263e-10,
|
| 568 |
+
"loss": 8.1259,
|
| 569 |
+
"step": 380
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 9.73,
|
| 573 |
+
"eval_loss": 8.827925682067871,
|
| 574 |
+
"eval_runtime": 223.0189,
|
| 575 |
+
"eval_samples_per_second": 19.173,
|
| 576 |
+
"eval_steps_per_second": 9.587,
|
| 577 |
+
"eval_wer": 1.0123747790218032,
|
| 578 |
+
"step": 380
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 9.98,
|
| 582 |
+
"learning_rate": 2.631578947368421e-11,
|
| 583 |
+
"loss": 8.1116,
|
| 584 |
+
"step": 390
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 9.98,
|
| 588 |
+
"eval_loss": 8.827937126159668,
|
| 589 |
+
"eval_runtime": 224.7494,
|
| 590 |
+
"eval_samples_per_second": 19.026,
|
| 591 |
+
"eval_steps_per_second": 9.513,
|
| 592 |
+
"eval_wer": 1.0123093040005238,
|
| 593 |
+
"step": 390
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 9.98,
|
| 597 |
+
"step": 390,
|
| 598 |
+
"total_flos": 1.7181016563618468e+19,
|
| 599 |
+
"train_loss": 8.274780469063002,
|
| 600 |
+
"train_runtime": 14935.5952,
|
| 601 |
+
"train_samples_per_second": 6.813,
|
| 602 |
+
"train_steps_per_second": 0.026
|
| 603 |
+
}
|
| 604 |
+
],
|
| 605 |
+
"max_steps": 390,
|
| 606 |
+
"num_train_epochs": 10,
|
| 607 |
+
"total_flos": 1.7181016563618468e+19,
|
| 608 |
+
"trial_name": null,
|
| 609 |
+
"trial_params": null
|
| 610 |
+
}
|