End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.6787810921669006,
|
| 4 |
+
"eval_runtime": 54.3949,
|
| 5 |
+
"eval_samples": 842,
|
| 6 |
+
"eval_samples_per_second": 15.479,
|
| 7 |
+
"eval_steps_per_second": 1.949,
|
| 8 |
+
"eval_wer": 0.3320341177569844,
|
| 9 |
+
"train_loss": 0.45776011664998273,
|
| 10 |
+
"train_runtime": 43219.7022,
|
| 11 |
+
"train_samples": 3350,
|
| 12 |
+
"train_samples_per_second": 3.876,
|
| 13 |
+
"train_steps_per_second": 0.485
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.6787810921669006,
|
| 4 |
+
"eval_runtime": 54.3949,
|
| 5 |
+
"eval_samples": 842,
|
| 6 |
+
"eval_samples_per_second": 15.479,
|
| 7 |
+
"eval_steps_per_second": 1.949,
|
| 8 |
+
"eval_wer": 0.3320341177569844
|
| 9 |
+
}
|
runs/Jul01_16-43-43_425a8a4a95c1/events.out.tfevents.1688273972.425a8a4a95c1.1452.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d6fcbf555b1dce2a4147563683ed2148871869c6f40fcd77d5ab6bca2a493ad
|
| 3 |
+
size 412
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 0.45776011664998273,
|
| 4 |
+
"train_runtime": 43219.7022,
|
| 5 |
+
"train_samples": 3350,
|
| 6 |
+
"train_samples_per_second": 3.876,
|
| 7 |
+
"train_steps_per_second": 0.485
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6787810921669006,
|
| 3 |
+
"best_model_checkpoint": "./wav2vec2-large-960h-lv60-self-paper/checkpoint-4190",
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 20950,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_loss": 3.3473238945007324,
|
| 13 |
+
"eval_runtime": 55.1245,
|
| 14 |
+
"eval_samples_per_second": 15.275,
|
| 15 |
+
"eval_steps_per_second": 1.923,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 419
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.19,
|
| 21 |
+
"learning_rate": 4.981977593765222e-05,
|
| 22 |
+
"loss": 5.8068,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_loss": 1.9190704822540283,
|
| 28 |
+
"eval_runtime": 55.4984,
|
| 29 |
+
"eval_samples_per_second": 15.172,
|
| 30 |
+
"eval_steps_per_second": 1.91,
|
| 31 |
+
"eval_wer": 0.8916934741113499,
|
| 32 |
+
"step": 838
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.39,
|
| 36 |
+
"learning_rate": 4.860204578665368e-05,
|
| 37 |
+
"loss": 2.5663,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_loss": 1.100569248199463,
|
| 43 |
+
"eval_runtime": 55.6905,
|
| 44 |
+
"eval_samples_per_second": 15.119,
|
| 45 |
+
"eval_steps_per_second": 1.903,
|
| 46 |
+
"eval_wer": 0.5802154384185165,
|
| 47 |
+
"step": 1257
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.58,
|
| 51 |
+
"learning_rate": 4.7384315635655144e-05,
|
| 52 |
+
"loss": 1.1433,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_loss": 0.9009209275245667,
|
| 58 |
+
"eval_runtime": 55.6736,
|
| 59 |
+
"eval_samples_per_second": 15.124,
|
| 60 |
+
"eval_steps_per_second": 1.904,
|
| 61 |
+
"eval_wer": 0.48139941535299063,
|
| 62 |
+
"step": 1676
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.77,
|
| 66 |
+
"learning_rate": 4.6166585484656604e-05,
|
| 67 |
+
"loss": 0.8522,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 5.0,
|
| 72 |
+
"eval_loss": 0.8214807510375977,
|
| 73 |
+
"eval_runtime": 55.5868,
|
| 74 |
+
"eval_samples_per_second": 15.147,
|
| 75 |
+
"eval_steps_per_second": 1.907,
|
| 76 |
+
"eval_wer": 0.42471001241373785,
|
| 77 |
+
"step": 2095
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.97,
|
| 81 |
+
"learning_rate": 4.4948855333658065e-05,
|
| 82 |
+
"loss": 0.7256,
|
| 83 |
+
"step": 2500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 6.0,
|
| 87 |
+
"eval_loss": 0.7522485256195068,
|
| 88 |
+
"eval_runtime": 55.6074,
|
| 89 |
+
"eval_samples_per_second": 15.142,
|
| 90 |
+
"eval_steps_per_second": 1.906,
|
| 91 |
+
"eval_wer": 0.39215398374200783,
|
| 92 |
+
"step": 2514
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.0,
|
| 96 |
+
"eval_loss": 0.7201786041259766,
|
| 97 |
+
"eval_runtime": 55.4815,
|
| 98 |
+
"eval_samples_per_second": 15.176,
|
| 99 |
+
"eval_steps_per_second": 1.911,
|
| 100 |
+
"eval_wer": 0.3653643365324292,
|
| 101 |
+
"step": 2933
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 7.16,
|
| 105 |
+
"learning_rate": 4.3731125182659525e-05,
|
| 106 |
+
"loss": 0.6239,
|
| 107 |
+
"step": 3000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_loss": 0.6909050941467285,
|
| 112 |
+
"eval_runtime": 55.6124,
|
| 113 |
+
"eval_samples_per_second": 15.14,
|
| 114 |
+
"eval_steps_per_second": 1.906,
|
| 115 |
+
"eval_wer": 0.3579427900209565,
|
| 116 |
+
"step": 3352
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 8.35,
|
| 120 |
+
"learning_rate": 4.2513395031660985e-05,
|
| 121 |
+
"loss": 0.5618,
|
| 122 |
+
"step": 3500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 9.0,
|
| 126 |
+
"eval_loss": 0.6887015700340271,
|
| 127 |
+
"eval_runtime": 56.9486,
|
| 128 |
+
"eval_samples_per_second": 14.785,
|
| 129 |
+
"eval_steps_per_second": 1.861,
|
| 130 |
+
"eval_wer": 0.340002936583152,
|
| 131 |
+
"step": 3771
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 9.55,
|
| 135 |
+
"learning_rate": 4.129566488066245e-05,
|
| 136 |
+
"loss": 0.4998,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 10.0,
|
| 141 |
+
"eval_loss": 0.6787810921669006,
|
| 142 |
+
"eval_runtime": 57.0323,
|
| 143 |
+
"eval_samples_per_second": 14.764,
|
| 144 |
+
"eval_steps_per_second": 1.859,
|
| 145 |
+
"eval_wer": 0.3320341177569844,
|
| 146 |
+
"step": 4190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 10.74,
|
| 150 |
+
"learning_rate": 4.0077934729663906e-05,
|
| 151 |
+
"loss": 0.4569,
|
| 152 |
+
"step": 4500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 11.0,
|
| 156 |
+
"eval_loss": 0.680539071559906,
|
| 157 |
+
"eval_runtime": 55.5776,
|
| 158 |
+
"eval_samples_per_second": 15.15,
|
| 159 |
+
"eval_steps_per_second": 1.907,
|
| 160 |
+
"eval_wer": 0.3351308781718435,
|
| 161 |
+
"step": 4609
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 11.93,
|
| 165 |
+
"learning_rate": 3.886020457866537e-05,
|
| 166 |
+
"loss": 0.4156,
|
| 167 |
+
"step": 5000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 12.0,
|
| 171 |
+
"eval_loss": 0.6909714937210083,
|
| 172 |
+
"eval_runtime": 55.4928,
|
| 173 |
+
"eval_samples_per_second": 15.173,
|
| 174 |
+
"eval_steps_per_second": 1.91,
|
| 175 |
+
"eval_wer": 0.3253066727178077,
|
| 176 |
+
"step": 5028
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 13.0,
|
| 180 |
+
"eval_loss": 0.6859297752380371,
|
| 181 |
+
"eval_runtime": 55.5121,
|
| 182 |
+
"eval_samples_per_second": 15.168,
|
| 183 |
+
"eval_steps_per_second": 1.909,
|
| 184 |
+
"eval_wer": 0.32790955323891774,
|
| 185 |
+
"step": 5447
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 13.13,
|
| 189 |
+
"learning_rate": 3.7642474427666826e-05,
|
| 190 |
+
"loss": 0.3763,
|
| 191 |
+
"step": 5500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.0,
|
| 195 |
+
"eval_loss": 0.7075064778327942,
|
| 196 |
+
"eval_runtime": 56.9008,
|
| 197 |
+
"eval_samples_per_second": 14.798,
|
| 198 |
+
"eval_steps_per_second": 1.863,
|
| 199 |
+
"eval_wer": 0.32066153209551906,
|
| 200 |
+
"step": 5866
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 14.32,
|
| 204 |
+
"learning_rate": 3.6424744276668293e-05,
|
| 205 |
+
"loss": 0.3473,
|
| 206 |
+
"step": 6000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 15.0,
|
| 210 |
+
"eval_loss": 0.7173970341682434,
|
| 211 |
+
"eval_runtime": 56.8103,
|
| 212 |
+
"eval_samples_per_second": 14.821,
|
| 213 |
+
"eval_steps_per_second": 1.866,
|
| 214 |
+
"eval_wer": 0.3151754608433333,
|
| 215 |
+
"step": 6285
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 15.51,
|
| 219 |
+
"learning_rate": 3.5207014125669754e-05,
|
| 220 |
+
"loss": 0.3141,
|
| 221 |
+
"step": 6500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 16.0,
|
| 225 |
+
"eval_loss": 0.7283802628517151,
|
| 226 |
+
"eval_runtime": 55.482,
|
| 227 |
+
"eval_samples_per_second": 15.176,
|
| 228 |
+
"eval_steps_per_second": 1.911,
|
| 229 |
+
"eval_wer": 0.31707089178691084,
|
| 230 |
+
"step": 6704
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 16.71,
|
| 234 |
+
"learning_rate": 3.3989283974671214e-05,
|
| 235 |
+
"loss": 0.2884,
|
| 236 |
+
"step": 7000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 17.0,
|
| 240 |
+
"eval_loss": 0.7537466883659363,
|
| 241 |
+
"eval_runtime": 55.5565,
|
| 242 |
+
"eval_samples_per_second": 15.156,
|
| 243 |
+
"eval_steps_per_second": 1.908,
|
| 244 |
+
"eval_wer": 0.3192332848352176,
|
| 245 |
+
"step": 7123
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 17.9,
|
| 249 |
+
"learning_rate": 3.277398928397467e-05,
|
| 250 |
+
"loss": 0.2771,
|
| 251 |
+
"step": 7500
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 18.0,
|
| 255 |
+
"eval_loss": 0.7311689853668213,
|
| 256 |
+
"eval_runtime": 55.4309,
|
| 257 |
+
"eval_samples_per_second": 15.19,
|
| 258 |
+
"eval_steps_per_second": 1.912,
|
| 259 |
+
"eval_wer": 0.31748468304924116,
|
| 260 |
+
"step": 7542
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 19.0,
|
| 264 |
+
"eval_loss": 0.7669196128845215,
|
| 265 |
+
"eval_runtime": 55.6417,
|
| 266 |
+
"eval_samples_per_second": 15.133,
|
| 267 |
+
"eval_steps_per_second": 1.905,
|
| 268 |
+
"eval_wer": 0.3138139541092142,
|
| 269 |
+
"step": 7961
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 19.09,
|
| 273 |
+
"learning_rate": 3.155625913297613e-05,
|
| 274 |
+
"loss": 0.2538,
|
| 275 |
+
"step": 8000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 20.0,
|
| 279 |
+
"eval_loss": 0.8143336772918701,
|
| 280 |
+
"eval_runtime": 55.4405,
|
| 281 |
+
"eval_samples_per_second": 15.187,
|
| 282 |
+
"eval_steps_per_second": 1.912,
|
| 283 |
+
"eval_wer": 0.30738016738523966,
|
| 284 |
+
"step": 8380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 20.29,
|
| 288 |
+
"learning_rate": 3.0338528981977592e-05,
|
| 289 |
+
"loss": 0.2319,
|
| 290 |
+
"step": 8500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 21.0,
|
| 294 |
+
"eval_loss": 0.8184694647789001,
|
| 295 |
+
"eval_runtime": 55.5569,
|
| 296 |
+
"eval_samples_per_second": 15.156,
|
| 297 |
+
"eval_steps_per_second": 1.908,
|
| 298 |
+
"eval_wer": 0.30880841464554104,
|
| 299 |
+
"step": 8799
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 21.48,
|
| 303 |
+
"learning_rate": 2.9120798830979056e-05,
|
| 304 |
+
"loss": 0.2206,
|
| 305 |
+
"step": 9000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 22.0,
|
| 309 |
+
"eval_loss": 0.8111276626586914,
|
| 310 |
+
"eval_runtime": 55.431,
|
| 311 |
+
"eval_samples_per_second": 15.19,
|
| 312 |
+
"eval_steps_per_second": 1.912,
|
| 313 |
+
"eval_wer": 0.30689963559672706,
|
| 314 |
+
"step": 9218
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 22.67,
|
| 318 |
+
"learning_rate": 2.7903068679980516e-05,
|
| 319 |
+
"loss": 0.2093,
|
| 320 |
+
"step": 9500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 23.0,
|
| 324 |
+
"eval_loss": 0.8248062133789062,
|
| 325 |
+
"eval_runtime": 55.4548,
|
| 326 |
+
"eval_samples_per_second": 15.184,
|
| 327 |
+
"eval_steps_per_second": 1.911,
|
| 328 |
+
"eval_wer": 0.30880841464554104,
|
| 329 |
+
"step": 9637
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 23.87,
|
| 333 |
+
"learning_rate": 2.668533852898198e-05,
|
| 334 |
+
"loss": 0.1979,
|
| 335 |
+
"step": 10000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 24.0,
|
| 339 |
+
"eval_loss": 0.8571637868881226,
|
| 340 |
+
"eval_runtime": 55.4105,
|
| 341 |
+
"eval_samples_per_second": 15.196,
|
| 342 |
+
"eval_steps_per_second": 1.913,
|
| 343 |
+
"eval_wer": 0.3067127621234166,
|
| 344 |
+
"step": 10056
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 25.0,
|
| 348 |
+
"eval_loss": 0.8709866404533386,
|
| 349 |
+
"eval_runtime": 55.5254,
|
| 350 |
+
"eval_samples_per_second": 15.164,
|
| 351 |
+
"eval_steps_per_second": 1.909,
|
| 352 |
+
"eval_wer": 0.3073935154904761,
|
| 353 |
+
"step": 10475
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 25.06,
|
| 357 |
+
"learning_rate": 2.5467608377983437e-05,
|
| 358 |
+
"loss": 0.1852,
|
| 359 |
+
"step": 10500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 26.0,
|
| 363 |
+
"eval_loss": 0.8921730518341064,
|
| 364 |
+
"eval_runtime": 55.3415,
|
| 365 |
+
"eval_samples_per_second": 15.215,
|
| 366 |
+
"eval_steps_per_second": 1.915,
|
| 367 |
+
"eval_wer": 0.3067394583338895,
|
| 368 |
+
"step": 10894
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 26.25,
|
| 372 |
+
"learning_rate": 2.42498782269849e-05,
|
| 373 |
+
"loss": 0.1742,
|
| 374 |
+
"step": 11000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 27.0,
|
| 378 |
+
"eval_loss": 0.9039767384529114,
|
| 379 |
+
"eval_runtime": 55.3805,
|
| 380 |
+
"eval_samples_per_second": 15.204,
|
| 381 |
+
"eval_steps_per_second": 1.914,
|
| 382 |
+
"eval_wer": 0.30679285075483537,
|
| 383 |
+
"step": 11313
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 27.45,
|
| 387 |
+
"learning_rate": 2.303214807598636e-05,
|
| 388 |
+
"loss": 0.1688,
|
| 389 |
+
"step": 11500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 28.0,
|
| 393 |
+
"eval_loss": 0.9143679738044739,
|
| 394 |
+
"eval_runtime": 55.4828,
|
| 395 |
+
"eval_samples_per_second": 15.176,
|
| 396 |
+
"eval_steps_per_second": 1.911,
|
| 397 |
+
"eval_wer": 0.30160043781785173,
|
| 398 |
+
"step": 11732
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 28.64,
|
| 402 |
+
"learning_rate": 2.1816853385289822e-05,
|
| 403 |
+
"loss": 0.1578,
|
| 404 |
+
"step": 12000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 29.0,
|
| 408 |
+
"eval_loss": 0.8989725112915039,
|
| 409 |
+
"eval_runtime": 55.3269,
|
| 410 |
+
"eval_samples_per_second": 15.219,
|
| 411 |
+
"eval_steps_per_second": 1.916,
|
| 412 |
+
"eval_wer": 0.310917415272902,
|
| 413 |
+
"step": 12151
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 29.83,
|
| 417 |
+
"learning_rate": 2.0599123234291282e-05,
|
| 418 |
+
"loss": 0.1557,
|
| 419 |
+
"step": 12500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 30.0,
|
| 423 |
+
"eval_loss": 0.9465027451515198,
|
| 424 |
+
"eval_runtime": 55.5076,
|
| 425 |
+
"eval_samples_per_second": 15.169,
|
| 426 |
+
"eval_steps_per_second": 1.91,
|
| 427 |
+
"eval_wer": 0.30042580455704315,
|
| 428 |
+
"step": 12570
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 31.0,
|
| 432 |
+
"eval_loss": 0.9480117559432983,
|
| 433 |
+
"eval_runtime": 56.1121,
|
| 434 |
+
"eval_samples_per_second": 15.006,
|
| 435 |
+
"eval_steps_per_second": 1.889,
|
| 436 |
+
"eval_wer": 0.3024680646582218,
|
| 437 |
+
"step": 12989
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 31.03,
|
| 441 |
+
"learning_rate": 1.9381393083292742e-05,
|
| 442 |
+
"loss": 0.1456,
|
| 443 |
+
"step": 13000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 32.0,
|
| 447 |
+
"eval_loss": 0.9730611443519592,
|
| 448 |
+
"eval_runtime": 55.4397,
|
| 449 |
+
"eval_samples_per_second": 15.188,
|
| 450 |
+
"eval_steps_per_second": 1.912,
|
| 451 |
+
"eval_wer": 0.3016538302387976,
|
| 452 |
+
"step": 13408
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 32.22,
|
| 456 |
+
"learning_rate": 1.81660983925962e-05,
|
| 457 |
+
"loss": 0.1398,
|
| 458 |
+
"step": 13500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 33.0,
|
| 462 |
+
"eval_loss": 0.9633293151855469,
|
| 463 |
+
"eval_runtime": 55.4286,
|
| 464 |
+
"eval_samples_per_second": 15.191,
|
| 465 |
+
"eval_steps_per_second": 1.912,
|
| 466 |
+
"eval_wer": 0.30380287518186794,
|
| 467 |
+
"step": 13827
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 33.41,
|
| 471 |
+
"learning_rate": 1.6948368241597664e-05,
|
| 472 |
+
"loss": 0.1343,
|
| 473 |
+
"step": 14000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 34.0,
|
| 477 |
+
"eval_loss": 0.9843713045120239,
|
| 478 |
+
"eval_runtime": 55.4228,
|
| 479 |
+
"eval_samples_per_second": 15.192,
|
| 480 |
+
"eval_steps_per_second": 1.913,
|
| 481 |
+
"eval_wer": 0.30114660223981204,
|
| 482 |
+
"step": 14246
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 34.61,
|
| 486 |
+
"learning_rate": 1.5730638090599124e-05,
|
| 487 |
+
"loss": 0.1275,
|
| 488 |
+
"step": 14500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 35.0,
|
| 492 |
+
"eval_loss": 1.007832407951355,
|
| 493 |
+
"eval_runtime": 55.4358,
|
| 494 |
+
"eval_samples_per_second": 15.189,
|
| 495 |
+
"eval_steps_per_second": 1.912,
|
| 496 |
+
"eval_wer": 0.2996783106638013,
|
| 497 |
+
"step": 14665
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 35.8,
|
| 501 |
+
"learning_rate": 1.4512907939600584e-05,
|
| 502 |
+
"loss": 0.1266,
|
| 503 |
+
"step": 15000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 36.0,
|
| 507 |
+
"eval_loss": 1.0066460371017456,
|
| 508 |
+
"eval_runtime": 55.4803,
|
| 509 |
+
"eval_samples_per_second": 15.177,
|
| 510 |
+
"eval_steps_per_second": 1.911,
|
| 511 |
+
"eval_wer": 0.2996382663480919,
|
| 512 |
+
"step": 15084
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 36.99,
|
| 516 |
+
"learning_rate": 1.3295177788602044e-05,
|
| 517 |
+
"loss": 0.1243,
|
| 518 |
+
"step": 15500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 37.0,
|
| 522 |
+
"eval_loss": 1.0132853984832764,
|
| 523 |
+
"eval_runtime": 55.3704,
|
| 524 |
+
"eval_samples_per_second": 15.207,
|
| 525 |
+
"eval_steps_per_second": 1.914,
|
| 526 |
+
"eval_wer": 0.3014135643445413,
|
| 527 |
+
"step": 15503
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 38.0,
|
| 531 |
+
"eval_loss": 1.0387077331542969,
|
| 532 |
+
"eval_runtime": 55.3084,
|
| 533 |
+
"eval_samples_per_second": 15.224,
|
| 534 |
+
"eval_steps_per_second": 1.917,
|
| 535 |
+
"eval_wer": 0.2971822149845829,
|
| 536 |
+
"step": 15922
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 38.19,
|
| 540 |
+
"learning_rate": 1.2077447637603508e-05,
|
| 541 |
+
"loss": 0.1182,
|
| 542 |
+
"step": 16000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 39.0,
|
| 546 |
+
"eval_loss": 1.0173468589782715,
|
| 547 |
+
"eval_runtime": 55.2898,
|
| 548 |
+
"eval_samples_per_second": 15.229,
|
| 549 |
+
"eval_steps_per_second": 1.917,
|
| 550 |
+
"eval_wer": 0.3026015457105864,
|
| 551 |
+
"step": 16341
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 39.38,
|
| 555 |
+
"learning_rate": 1.0859717486604968e-05,
|
| 556 |
+
"loss": 0.1152,
|
| 557 |
+
"step": 16500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 40.0,
|
| 561 |
+
"eval_loss": 1.0526808500289917,
|
| 562 |
+
"eval_runtime": 55.2419,
|
| 563 |
+
"eval_samples_per_second": 15.242,
|
| 564 |
+
"eval_steps_per_second": 1.919,
|
| 565 |
+
"eval_wer": 0.2977161391940414,
|
| 566 |
+
"step": 16760
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 40.57,
|
| 570 |
+
"learning_rate": 9.644422795908426e-06,
|
| 571 |
+
"loss": 0.1134,
|
| 572 |
+
"step": 17000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 41.0,
|
| 576 |
+
"eval_loss": 1.0490872859954834,
|
| 577 |
+
"eval_runtime": 56.6858,
|
| 578 |
+
"eval_samples_per_second": 14.854,
|
| 579 |
+
"eval_steps_per_second": 1.87,
|
| 580 |
+
"eval_wer": 0.29776953161498726,
|
| 581 |
+
"step": 17179
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 41.77,
|
| 585 |
+
"learning_rate": 8.426692644909888e-06,
|
| 586 |
+
"loss": 0.1101,
|
| 587 |
+
"step": 17500
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 42.0,
|
| 591 |
+
"eval_loss": 1.0661942958831787,
|
| 592 |
+
"eval_runtime": 56.702,
|
| 593 |
+
"eval_samples_per_second": 14.85,
|
| 594 |
+
"eval_steps_per_second": 1.869,
|
| 595 |
+
"eval_wer": 0.2975693100364403,
|
| 596 |
+
"step": 17598
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 42.96,
|
| 600 |
+
"learning_rate": 7.208962493911349e-06,
|
| 601 |
+
"loss": 0.1083,
|
| 602 |
+
"step": 18000
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 43.0,
|
| 606 |
+
"eval_loss": 1.0543538331985474,
|
| 607 |
+
"eval_runtime": 55.2662,
|
| 608 |
+
"eval_samples_per_second": 15.235,
|
| 609 |
+
"eval_steps_per_second": 1.918,
|
| 610 |
+
"eval_wer": 0.29790301266735186,
|
| 611 |
+
"step": 18017
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 44.0,
|
| 615 |
+
"eval_loss": 1.0599024295806885,
|
| 616 |
+
"eval_runtime": 55.6295,
|
| 617 |
+
"eval_samples_per_second": 15.136,
|
| 618 |
+
"eval_steps_per_second": 1.905,
|
| 619 |
+
"eval_wer": 0.29568722719809926,
|
| 620 |
+
"step": 18436
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 44.15,
|
| 624 |
+
"learning_rate": 5.991232342912811e-06,
|
| 625 |
+
"loss": 0.1073,
|
| 626 |
+
"step": 18500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 45.0,
|
| 630 |
+
"eval_loss": 1.0766526460647583,
|
| 631 |
+
"eval_runtime": 55.4679,
|
| 632 |
+
"eval_samples_per_second": 15.18,
|
| 633 |
+
"eval_steps_per_second": 1.911,
|
| 634 |
+
"eval_wer": 0.2959141449871191,
|
| 635 |
+
"step": 18855
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 45.35,
|
| 639 |
+
"learning_rate": 4.773502191914271e-06,
|
| 640 |
+
"loss": 0.1045,
|
| 641 |
+
"step": 19000
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 46.0,
|
| 645 |
+
"eval_loss": 1.0773001909255981,
|
| 646 |
+
"eval_runtime": 55.3004,
|
| 647 |
+
"eval_samples_per_second": 15.226,
|
| 648 |
+
"eval_steps_per_second": 1.917,
|
| 649 |
+
"eval_wer": 0.29592749309235555,
|
| 650 |
+
"step": 19274
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 46.54,
|
| 654 |
+
"learning_rate": 3.5557720409157334e-06,
|
| 655 |
+
"loss": 0.1024,
|
| 656 |
+
"step": 19500
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 47.0,
|
| 660 |
+
"eval_loss": 1.0730717182159424,
|
| 661 |
+
"eval_runtime": 55.5009,
|
| 662 |
+
"eval_samples_per_second": 15.171,
|
| 663 |
+
"eval_steps_per_second": 1.91,
|
| 664 |
+
"eval_wer": 0.2952600878305325,
|
| 665 |
+
"step": 19693
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 47.73,
|
| 669 |
+
"learning_rate": 2.3380418899171945e-06,
|
| 670 |
+
"loss": 0.1015,
|
| 671 |
+
"step": 20000
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 48.0,
|
| 675 |
+
"eval_loss": 1.0823478698730469,
|
| 676 |
+
"eval_runtime": 55.423,
|
| 677 |
+
"eval_samples_per_second": 15.192,
|
| 678 |
+
"eval_steps_per_second": 1.913,
|
| 679 |
+
"eval_wer": 0.2965682021437057,
|
| 680 |
+
"step": 20112
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 48.93,
|
| 684 |
+
"learning_rate": 1.1203117389186556e-06,
|
| 685 |
+
"loss": 0.1016,
|
| 686 |
+
"step": 20500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 49.0,
|
| 690 |
+
"eval_loss": 1.08854079246521,
|
| 691 |
+
"eval_runtime": 55.6127,
|
| 692 |
+
"eval_samples_per_second": 15.14,
|
| 693 |
+
"eval_steps_per_second": 1.906,
|
| 694 |
+
"eval_wer": 0.29445920151634475,
|
| 695 |
+
"step": 20531
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 50.0,
|
| 699 |
+
"eval_loss": 1.0854156017303467,
|
| 700 |
+
"eval_runtime": 55.4189,
|
| 701 |
+
"eval_samples_per_second": 15.193,
|
| 702 |
+
"eval_steps_per_second": 1.913,
|
| 703 |
+
"eval_wer": 0.2950331700415126,
|
| 704 |
+
"step": 20950
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 50.0,
|
| 708 |
+
"step": 20950,
|
| 709 |
+
"total_flos": 1.40587009875955e+20,
|
| 710 |
+
"train_loss": 0.45776011664998273,
|
| 711 |
+
"train_runtime": 43219.7022,
|
| 712 |
+
"train_samples_per_second": 3.876,
|
| 713 |
+
"train_steps_per_second": 0.485
|
| 714 |
+
}
|
| 715 |
+
],
|
| 716 |
+
"max_steps": 20950,
|
| 717 |
+
"num_train_epochs": 50,
|
| 718 |
+
"total_flos": 1.40587009875955e+20,
|
| 719 |
+
"trial_name": null,
|
| 720 |
+
"trial_params": null
|
| 721 |
+
}
|