End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.7043963670730591,
|
| 4 |
+
"eval_runtime": 129.1286,
|
| 5 |
+
"eval_samples": 532,
|
| 6 |
+
"eval_samples_per_second": 4.12,
|
| 7 |
+
"eval_steps_per_second": 0.519,
|
| 8 |
+
"eval_wer": 0.47573439609179147,
|
| 9 |
+
"train_loss": 0.8933021876547071,
|
| 10 |
+
"train_runtime": 19496.7314,
|
| 11 |
+
"train_samples": 4617,
|
| 12 |
+
"train_samples_per_second": 2.368,
|
| 13 |
+
"train_steps_per_second": 0.037
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 0.7043963670730591,
|
| 4 |
+
"eval_runtime": 129.1286,
|
| 5 |
+
"eval_samples": 532,
|
| 6 |
+
"eval_samples_per_second": 4.12,
|
| 7 |
+
"eval_steps_per_second": 0.519,
|
| 8 |
+
"eval_wer": 0.47573439609179147
|
| 9 |
+
}
|
runs/Jul08_00-33-51_e43e87908b0c/events.out.tfevents.1657262667.e43e87908b0c.1852.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14aa9c626975f26cab5f8a12aed7c7620fd71fe3a990a8b332ef3480c10816c5
|
| 3 |
+
size 358
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.8933021876547071,
|
| 4 |
+
"train_runtime": 19496.7314,
|
| 5 |
+
"train_samples": 4617,
|
| 6 |
+
"train_samples_per_second": 2.368,
|
| 7 |
+
"train_steps_per_second": 0.037
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,547 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7043963670730591,
|
| 3 |
+
"best_model_checkpoint": "ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1/checkpoint-720",
|
| 4 |
+
"epoch": 9.996539792387543,
|
| 5 |
+
"global_step": 720,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.14,
|
| 12 |
+
"learning_rate": 7.000000000000001e-06,
|
| 13 |
+
"loss": 1.7072,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.28,
|
| 18 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 19 |
+
"loss": 1.3169,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.42,
|
| 24 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 25 |
+
"loss": 1.1845,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.55,
|
| 30 |
+
"learning_rate": 3.7e-05,
|
| 31 |
+
"loss": 1.1996,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.69,
|
| 36 |
+
"learning_rate": 4.7e-05,
|
| 37 |
+
"loss": 1.0979,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.83,
|
| 42 |
+
"learning_rate": 4.9477611940298504e-05,
|
| 43 |
+
"loss": 1.095,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.97,
|
| 48 |
+
"learning_rate": 4.8731343283582094e-05,
|
| 49 |
+
"loss": 1.0489,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_loss": 0.9701907634735107,
|
| 55 |
+
"eval_runtime": 131.7628,
|
| 56 |
+
"eval_samples_per_second": 4.038,
|
| 57 |
+
"eval_steps_per_second": 0.508,
|
| 58 |
+
"eval_wer": 0.6696021083756508,
|
| 59 |
+
"step": 72
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.11,
|
| 63 |
+
"learning_rate": 4.798507462686567e-05,
|
| 64 |
+
"loss": 1.0915,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.25,
|
| 69 |
+
"learning_rate": 4.723880597014926e-05,
|
| 70 |
+
"loss": 1.1852,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.39,
|
| 75 |
+
"learning_rate": 4.6492537313432837e-05,
|
| 76 |
+
"loss": 1.1105,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.53,
|
| 81 |
+
"learning_rate": 4.582089552238806e-05,
|
| 82 |
+
"loss": 1.052,
|
| 83 |
+
"step": 110
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.66,
|
| 87 |
+
"learning_rate": 4.5074626865671645e-05,
|
| 88 |
+
"loss": 1.0009,
|
| 89 |
+
"step": 120
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.8,
|
| 93 |
+
"learning_rate": 4.432835820895523e-05,
|
| 94 |
+
"loss": 1.0445,
|
| 95 |
+
"step": 130
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.94,
|
| 99 |
+
"learning_rate": 4.358208955223881e-05,
|
| 100 |
+
"loss": 0.9699,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.0,
|
| 105 |
+
"eval_loss": 0.9321106672286987,
|
| 106 |
+
"eval_runtime": 131.1021,
|
| 107 |
+
"eval_samples_per_second": 4.058,
|
| 108 |
+
"eval_steps_per_second": 0.511,
|
| 109 |
+
"eval_wer": 0.6595744680851063,
|
| 110 |
+
"step": 144
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.08,
|
| 114 |
+
"learning_rate": 4.283582089552239e-05,
|
| 115 |
+
"loss": 1.0048,
|
| 116 |
+
"step": 150
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.22,
|
| 120 |
+
"learning_rate": 4.208955223880597e-05,
|
| 121 |
+
"loss": 0.9799,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.36,
|
| 126 |
+
"learning_rate": 4.1343283582089554e-05,
|
| 127 |
+
"loss": 1.034,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.5,
|
| 132 |
+
"learning_rate": 4.059701492537314e-05,
|
| 133 |
+
"loss": 0.9303,
|
| 134 |
+
"step": 180
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.64,
|
| 138 |
+
"learning_rate": 3.985074626865672e-05,
|
| 139 |
+
"loss": 0.9381,
|
| 140 |
+
"step": 190
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.78,
|
| 144 |
+
"learning_rate": 3.9104477611940296e-05,
|
| 145 |
+
"loss": 0.9386,
|
| 146 |
+
"step": 200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.91,
|
| 150 |
+
"learning_rate": 3.8358208955223886e-05,
|
| 151 |
+
"loss": 0.9074,
|
| 152 |
+
"step": 210
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.0,
|
| 156 |
+
"eval_loss": 0.854228138923645,
|
| 157 |
+
"eval_runtime": 129.803,
|
| 158 |
+
"eval_samples_per_second": 4.099,
|
| 159 |
+
"eval_steps_per_second": 0.516,
|
| 160 |
+
"eval_wer": 0.6138715690685865,
|
| 161 |
+
"step": 216
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.06,
|
| 165 |
+
"learning_rate": 3.761194029850746e-05,
|
| 166 |
+
"loss": 0.9405,
|
| 167 |
+
"step": 220
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.19,
|
| 171 |
+
"learning_rate": 3.6865671641791046e-05,
|
| 172 |
+
"loss": 0.9118,
|
| 173 |
+
"step": 230
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.33,
|
| 177 |
+
"learning_rate": 3.611940298507463e-05,
|
| 178 |
+
"loss": 0.9953,
|
| 179 |
+
"step": 240
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.47,
|
| 183 |
+
"learning_rate": 3.537313432835821e-05,
|
| 184 |
+
"loss": 0.9019,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.61,
|
| 189 |
+
"learning_rate": 3.4626865671641795e-05,
|
| 190 |
+
"loss": 0.8914,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.75,
|
| 195 |
+
"learning_rate": 3.388059701492537e-05,
|
| 196 |
+
"loss": 0.9089,
|
| 197 |
+
"step": 270
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.89,
|
| 201 |
+
"learning_rate": 3.3134328358208955e-05,
|
| 202 |
+
"loss": 0.8979,
|
| 203 |
+
"step": 280
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 4.0,
|
| 207 |
+
"eval_loss": 0.8186684846878052,
|
| 208 |
+
"eval_runtime": 131.2574,
|
| 209 |
+
"eval_samples_per_second": 4.053,
|
| 210 |
+
"eval_steps_per_second": 0.51,
|
| 211 |
+
"eval_wer": 0.5776820723789934,
|
| 212 |
+
"step": 288
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.03,
|
| 216 |
+
"learning_rate": 3.238805970149254e-05,
|
| 217 |
+
"loss": 0.9317,
|
| 218 |
+
"step": 290
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.17,
|
| 222 |
+
"learning_rate": 3.164179104477612e-05,
|
| 223 |
+
"loss": 0.887,
|
| 224 |
+
"step": 300
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.3,
|
| 228 |
+
"learning_rate": 3.0895522388059704e-05,
|
| 229 |
+
"loss": 0.8859,
|
| 230 |
+
"step": 310
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 4.44,
|
| 234 |
+
"learning_rate": 3.0149253731343284e-05,
|
| 235 |
+
"loss": 0.8687,
|
| 236 |
+
"step": 320
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.58,
|
| 240 |
+
"learning_rate": 2.9402985074626864e-05,
|
| 241 |
+
"loss": 0.9075,
|
| 242 |
+
"step": 330
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.72,
|
| 246 |
+
"learning_rate": 2.865671641791045e-05,
|
| 247 |
+
"loss": 0.8513,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.86,
|
| 252 |
+
"learning_rate": 2.791044776119403e-05,
|
| 253 |
+
"loss": 0.8585,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.0,
|
| 258 |
+
"learning_rate": 2.716417910447761e-05,
|
| 259 |
+
"loss": 0.8363,
|
| 260 |
+
"step": 360
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.0,
|
| 264 |
+
"eval_loss": 0.7735126614570618,
|
| 265 |
+
"eval_runtime": 129.316,
|
| 266 |
+
"eval_samples_per_second": 4.114,
|
| 267 |
+
"eval_steps_per_second": 0.518,
|
| 268 |
+
"eval_wer": 0.5551198817252684,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.14,
|
| 273 |
+
"learning_rate": 2.6417910447761197e-05,
|
| 274 |
+
"loss": 0.8316,
|
| 275 |
+
"step": 370
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 5.28,
|
| 279 |
+
"learning_rate": 2.5671641791044776e-05,
|
| 280 |
+
"loss": 0.8286,
|
| 281 |
+
"step": 380
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 5.42,
|
| 285 |
+
"learning_rate": 2.492537313432836e-05,
|
| 286 |
+
"loss": 0.8229,
|
| 287 |
+
"step": 390
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 5.55,
|
| 291 |
+
"learning_rate": 2.4179104477611943e-05,
|
| 292 |
+
"loss": 0.8304,
|
| 293 |
+
"step": 400
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 5.69,
|
| 297 |
+
"learning_rate": 2.3432835820895522e-05,
|
| 298 |
+
"loss": 0.8113,
|
| 299 |
+
"step": 410
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.83,
|
| 303 |
+
"learning_rate": 2.2686567164179106e-05,
|
| 304 |
+
"loss": 0.8642,
|
| 305 |
+
"step": 420
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 5.97,
|
| 309 |
+
"learning_rate": 2.1940298507462685e-05,
|
| 310 |
+
"loss": 0.802,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 6.0,
|
| 315 |
+
"eval_loss": 0.7765986919403076,
|
| 316 |
+
"eval_runtime": 128.8303,
|
| 317 |
+
"eval_samples_per_second": 4.129,
|
| 318 |
+
"eval_steps_per_second": 0.52,
|
| 319 |
+
"eval_wer": 0.5402069807803561,
|
| 320 |
+
"step": 432
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.11,
|
| 324 |
+
"learning_rate": 2.119402985074627e-05,
|
| 325 |
+
"loss": 0.8724,
|
| 326 |
+
"step": 440
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.25,
|
| 330 |
+
"learning_rate": 2.0447761194029852e-05,
|
| 331 |
+
"loss": 0.7674,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.39,
|
| 336 |
+
"learning_rate": 1.9701492537313435e-05,
|
| 337 |
+
"loss": 0.7822,
|
| 338 |
+
"step": 460
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.53,
|
| 342 |
+
"learning_rate": 1.8955223880597015e-05,
|
| 343 |
+
"loss": 0.8182,
|
| 344 |
+
"step": 470
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.66,
|
| 348 |
+
"learning_rate": 1.8208955223880598e-05,
|
| 349 |
+
"loss": 0.8082,
|
| 350 |
+
"step": 480
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.8,
|
| 354 |
+
"learning_rate": 1.746268656716418e-05,
|
| 355 |
+
"loss": 0.8026,
|
| 356 |
+
"step": 490
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.94,
|
| 360 |
+
"learning_rate": 1.6716417910447764e-05,
|
| 361 |
+
"loss": 0.7702,
|
| 362 |
+
"step": 500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 7.0,
|
| 366 |
+
"eval_loss": 0.7470704317092896,
|
| 367 |
+
"eval_runtime": 130.8433,
|
| 368 |
+
"eval_samples_per_second": 4.066,
|
| 369 |
+
"eval_steps_per_second": 0.512,
|
| 370 |
+
"eval_wer": 0.49713955132737675,
|
| 371 |
+
"step": 504
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 7.08,
|
| 375 |
+
"learning_rate": 1.5970149253731344e-05,
|
| 376 |
+
"loss": 0.8414,
|
| 377 |
+
"step": 510
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 7.22,
|
| 381 |
+
"learning_rate": 1.5223880597014925e-05,
|
| 382 |
+
"loss": 0.7644,
|
| 383 |
+
"step": 520
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 7.36,
|
| 387 |
+
"learning_rate": 1.4477611940298509e-05,
|
| 388 |
+
"loss": 0.7924,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 7.5,
|
| 393 |
+
"learning_rate": 1.373134328358209e-05,
|
| 394 |
+
"loss": 0.7678,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 7.64,
|
| 399 |
+
"learning_rate": 1.2985074626865673e-05,
|
| 400 |
+
"loss": 0.7541,
|
| 401 |
+
"step": 550
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.78,
|
| 405 |
+
"learning_rate": 1.2238805970149255e-05,
|
| 406 |
+
"loss": 0.7677,
|
| 407 |
+
"step": 560
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 7.91,
|
| 411 |
+
"learning_rate": 1.1492537313432836e-05,
|
| 412 |
+
"loss": 0.7483,
|
| 413 |
+
"step": 570
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 8.0,
|
| 417 |
+
"eval_loss": 0.7225961089134216,
|
| 418 |
+
"eval_runtime": 129.9737,
|
| 419 |
+
"eval_samples_per_second": 4.093,
|
| 420 |
+
"eval_steps_per_second": 0.515,
|
| 421 |
+
"eval_wer": 0.49810374750915987,
|
| 422 |
+
"step": 576
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 8.06,
|
| 426 |
+
"learning_rate": 1.0746268656716418e-05,
|
| 427 |
+
"loss": 0.7906,
|
| 428 |
+
"step": 580
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 8.19,
|
| 432 |
+
"learning_rate": 1e-05,
|
| 433 |
+
"loss": 0.7329,
|
| 434 |
+
"step": 590
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 8.33,
|
| 438 |
+
"learning_rate": 9.253731343283582e-06,
|
| 439 |
+
"loss": 0.7563,
|
| 440 |
+
"step": 600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 8.47,
|
| 444 |
+
"learning_rate": 8.507462686567165e-06,
|
| 445 |
+
"loss": 0.7423,
|
| 446 |
+
"step": 610
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 8.61,
|
| 450 |
+
"learning_rate": 7.761194029850747e-06,
|
| 451 |
+
"loss": 0.7615,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.75,
|
| 456 |
+
"learning_rate": 7.014925373134329e-06,
|
| 457 |
+
"loss": 0.7527,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 8.89,
|
| 462 |
+
"learning_rate": 6.26865671641791e-06,
|
| 463 |
+
"loss": 0.7196,
|
| 464 |
+
"step": 640
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 9.0,
|
| 468 |
+
"eval_loss": 0.709452748298645,
|
| 469 |
+
"eval_runtime": 130.8637,
|
| 470 |
+
"eval_samples_per_second": 4.065,
|
| 471 |
+
"eval_steps_per_second": 0.512,
|
| 472 |
+
"eval_wer": 0.4842193224914829,
|
| 473 |
+
"step": 648
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 9.03,
|
| 477 |
+
"learning_rate": 5.522388059701493e-06,
|
| 478 |
+
"loss": 0.7642,
|
| 479 |
+
"step": 650
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 9.17,
|
| 483 |
+
"learning_rate": 4.7761194029850745e-06,
|
| 484 |
+
"loss": 0.7204,
|
| 485 |
+
"step": 660
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 9.3,
|
| 489 |
+
"learning_rate": 4.029850746268657e-06,
|
| 490 |
+
"loss": 0.7626,
|
| 491 |
+
"step": 670
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 9.44,
|
| 495 |
+
"learning_rate": 3.2835820895522387e-06,
|
| 496 |
+
"loss": 0.7175,
|
| 497 |
+
"step": 680
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 9.58,
|
| 501 |
+
"learning_rate": 2.537313432835821e-06,
|
| 502 |
+
"loss": 0.7452,
|
| 503 |
+
"step": 690
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.72,
|
| 507 |
+
"learning_rate": 1.7910447761194032e-06,
|
| 508 |
+
"loss": 0.7173,
|
| 509 |
+
"step": 700
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 9.86,
|
| 513 |
+
"learning_rate": 1.0447761194029853e-06,
|
| 514 |
+
"loss": 0.743,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 10.0,
|
| 519 |
+
"learning_rate": 2.9850746268656716e-07,
|
| 520 |
+
"loss": 0.731,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 10.0,
|
| 525 |
+
"eval_loss": 0.7043963670730591,
|
| 526 |
+
"eval_runtime": 129.9462,
|
| 527 |
+
"eval_samples_per_second": 4.094,
|
| 528 |
+
"eval_steps_per_second": 0.516,
|
| 529 |
+
"eval_wer": 0.47573439609179147,
|
| 530 |
+
"step": 720
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 10.0,
|
| 534 |
+
"step": 720,
|
| 535 |
+
"total_flos": 2.7197958559499194e+19,
|
| 536 |
+
"train_loss": 0.8933021876547071,
|
| 537 |
+
"train_runtime": 19496.7314,
|
| 538 |
+
"train_samples_per_second": 2.368,
|
| 539 |
+
"train_steps_per_second": 0.037
|
| 540 |
+
}
|
| 541 |
+
],
|
| 542 |
+
"max_steps": 720,
|
| 543 |
+
"num_train_epochs": 10,
|
| 544 |
+
"total_flos": 2.7197958559499194e+19,
|
| 545 |
+
"trial_name": null,
|
| 546 |
+
"trial_params": null
|
| 547 |
+
}
|