Abdulwahab Sahyoun
commited on
Commit
•
e6e9e61
1
Parent(s):
63d6951
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +724 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_loss": 3.0463998317718506,
|
| 4 |
+
"eval_runtime": 175.3201,
|
| 5 |
+
"eval_samples": 4899,
|
| 6 |
+
"eval_samples_per_second": 27.943,
|
| 7 |
+
"eval_steps_per_second": 0.878,
|
| 8 |
+
"eval_wer": 1.0,
|
| 9 |
+
"train_loss": 3.233657403475996,
|
| 10 |
+
"train_runtime": 33798.1213,
|
| 11 |
+
"train_samples": 14730,
|
| 12 |
+
"train_samples_per_second": 13.075,
|
| 13 |
+
"train_steps_per_second": 0.204
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_loss": 3.0463998317718506,
|
| 4 |
+
"eval_runtime": 175.3201,
|
| 5 |
+
"eval_samples": 4899,
|
| 6 |
+
"eval_samples_per_second": 27.943,
|
| 7 |
+
"eval_steps_per_second": 0.878,
|
| 8 |
+
"eval_wer": 1.0
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"train_loss": 3.233657403475996,
|
| 4 |
+
"train_runtime": 33798.1213,
|
| 5 |
+
"train_samples": 14730,
|
| 6 |
+
"train_samples_per_second": 13.075,
|
| 7 |
+
"train_steps_per_second": 0.204
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,724 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 29.997830802603037,
|
| 5 |
+
"global_step": 6900,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.43,
|
| 12 |
+
"eval_loss": 3.3600032329559326,
|
| 13 |
+
"eval_runtime": 177.4912,
|
| 14 |
+
"eval_samples_per_second": 27.601,
|
| 15 |
+
"eval_steps_per_second": 0.868,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.87,
|
| 21 |
+
"eval_loss": 3.088737726211548,
|
| 22 |
+
"eval_runtime": 176.8112,
|
| 23 |
+
"eval_samples_per_second": 27.708,
|
| 24 |
+
"eval_steps_per_second": 0.871,
|
| 25 |
+
"eval_wer": 1.0,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.3,
|
| 30 |
+
"eval_loss": 3.0779149532318115,
|
| 31 |
+
"eval_runtime": 176.3294,
|
| 32 |
+
"eval_samples_per_second": 27.783,
|
| 33 |
+
"eval_steps_per_second": 0.873,
|
| 34 |
+
"eval_wer": 1.0,
|
| 35 |
+
"step": 300
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.74,
|
| 39 |
+
"eval_loss": 3.05513334274292,
|
| 40 |
+
"eval_runtime": 176.7029,
|
| 41 |
+
"eval_samples_per_second": 27.724,
|
| 42 |
+
"eval_steps_per_second": 0.872,
|
| 43 |
+
"eval_wer": 1.0,
|
| 44 |
+
"step": 400
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.17,
|
| 48 |
+
"learning_rate": 0.00029699999999999996,
|
| 49 |
+
"loss": 4.8553,
|
| 50 |
+
"step": 500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.17,
|
| 54 |
+
"eval_loss": 3.052617311477661,
|
| 55 |
+
"eval_runtime": 176.6413,
|
| 56 |
+
"eval_samples_per_second": 27.734,
|
| 57 |
+
"eval_steps_per_second": 0.872,
|
| 58 |
+
"eval_wer": 1.0,
|
| 59 |
+
"step": 500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.61,
|
| 63 |
+
"eval_loss": 3.0559935569763184,
|
| 64 |
+
"eval_runtime": 175.4042,
|
| 65 |
+
"eval_samples_per_second": 27.93,
|
| 66 |
+
"eval_steps_per_second": 0.878,
|
| 67 |
+
"eval_wer": 1.0,
|
| 68 |
+
"step": 600
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.04,
|
| 72 |
+
"eval_loss": 3.125081777572632,
|
| 73 |
+
"eval_runtime": 174.6598,
|
| 74 |
+
"eval_samples_per_second": 28.049,
|
| 75 |
+
"eval_steps_per_second": 0.882,
|
| 76 |
+
"eval_wer": 1.0,
|
| 77 |
+
"step": 700
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.48,
|
| 81 |
+
"eval_loss": 3.087021589279175,
|
| 82 |
+
"eval_runtime": 177.8472,
|
| 83 |
+
"eval_samples_per_second": 27.546,
|
| 84 |
+
"eval_steps_per_second": 0.866,
|
| 85 |
+
"eval_wer": 1.0,
|
| 86 |
+
"step": 800
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 3.91,
|
| 90 |
+
"eval_loss": 3.08219575881958,
|
| 91 |
+
"eval_runtime": 180.0973,
|
| 92 |
+
"eval_samples_per_second": 27.202,
|
| 93 |
+
"eval_steps_per_second": 0.855,
|
| 94 |
+
"eval_wer": 1.0,
|
| 95 |
+
"step": 900
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 4.35,
|
| 99 |
+
"learning_rate": 0.00027679687499999997,
|
| 100 |
+
"loss": 3.1133,
|
| 101 |
+
"step": 1000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.35,
|
| 105 |
+
"eval_loss": 3.048403739929199,
|
| 106 |
+
"eval_runtime": 177.987,
|
| 107 |
+
"eval_samples_per_second": 27.524,
|
| 108 |
+
"eval_steps_per_second": 0.865,
|
| 109 |
+
"eval_wer": 1.0,
|
| 110 |
+
"step": 1000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 4.78,
|
| 114 |
+
"eval_loss": 3.0558109283447266,
|
| 115 |
+
"eval_runtime": 176.2514,
|
| 116 |
+
"eval_samples_per_second": 27.796,
|
| 117 |
+
"eval_steps_per_second": 0.874,
|
| 118 |
+
"eval_wer": 1.0,
|
| 119 |
+
"step": 1100
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 5.22,
|
| 123 |
+
"eval_loss": 3.1018614768981934,
|
| 124 |
+
"eval_runtime": 174.5505,
|
| 125 |
+
"eval_samples_per_second": 28.066,
|
| 126 |
+
"eval_steps_per_second": 0.882,
|
| 127 |
+
"eval_wer": 1.0,
|
| 128 |
+
"step": 1200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 5.65,
|
| 132 |
+
"eval_loss": 3.0914077758789062,
|
| 133 |
+
"eval_runtime": 174.0307,
|
| 134 |
+
"eval_samples_per_second": 28.15,
|
| 135 |
+
"eval_steps_per_second": 0.885,
|
| 136 |
+
"eval_wer": 1.0,
|
| 137 |
+
"step": 1300
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 6.09,
|
| 141 |
+
"eval_loss": 3.069120168685913,
|
| 142 |
+
"eval_runtime": 175.4381,
|
| 143 |
+
"eval_samples_per_second": 27.924,
|
| 144 |
+
"eval_steps_per_second": 0.878,
|
| 145 |
+
"eval_wer": 1.0,
|
| 146 |
+
"step": 1400
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.52,
|
| 150 |
+
"learning_rate": 0.00025335937499999995,
|
| 151 |
+
"loss": 3.109,
|
| 152 |
+
"step": 1500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 6.52,
|
| 156 |
+
"eval_loss": 3.0588901042938232,
|
| 157 |
+
"eval_runtime": 175.6572,
|
| 158 |
+
"eval_samples_per_second": 27.89,
|
| 159 |
+
"eval_steps_per_second": 0.877,
|
| 160 |
+
"eval_wer": 1.0,
|
| 161 |
+
"step": 1500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 6.95,
|
| 165 |
+
"eval_loss": 3.050849199295044,
|
| 166 |
+
"eval_runtime": 175.685,
|
| 167 |
+
"eval_samples_per_second": 27.885,
|
| 168 |
+
"eval_steps_per_second": 0.877,
|
| 169 |
+
"eval_wer": 1.0,
|
| 170 |
+
"step": 1600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.39,
|
| 174 |
+
"eval_loss": 3.054013252258301,
|
| 175 |
+
"eval_runtime": 177.236,
|
| 176 |
+
"eval_samples_per_second": 27.641,
|
| 177 |
+
"eval_steps_per_second": 0.869,
|
| 178 |
+
"eval_wer": 1.0,
|
| 179 |
+
"step": 1700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 7.82,
|
| 183 |
+
"eval_loss": 3.0545613765716553,
|
| 184 |
+
"eval_runtime": 177.8822,
|
| 185 |
+
"eval_samples_per_second": 27.541,
|
| 186 |
+
"eval_steps_per_second": 0.866,
|
| 187 |
+
"eval_wer": 1.0,
|
| 188 |
+
"step": 1800
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 8.26,
|
| 192 |
+
"eval_loss": 3.0523643493652344,
|
| 193 |
+
"eval_runtime": 172.9222,
|
| 194 |
+
"eval_samples_per_second": 28.331,
|
| 195 |
+
"eval_steps_per_second": 0.891,
|
| 196 |
+
"eval_wer": 1.0,
|
| 197 |
+
"step": 1900
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 8.69,
|
| 201 |
+
"learning_rate": 0.00022992187499999996,
|
| 202 |
+
"loss": 3.1106,
|
| 203 |
+
"step": 2000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 8.69,
|
| 207 |
+
"eval_loss": 3.056912422180176,
|
| 208 |
+
"eval_runtime": 175.8694,
|
| 209 |
+
"eval_samples_per_second": 27.856,
|
| 210 |
+
"eval_steps_per_second": 0.876,
|
| 211 |
+
"eval_wer": 1.0,
|
| 212 |
+
"step": 2000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 9.13,
|
| 216 |
+
"eval_loss": 3.0621554851531982,
|
| 217 |
+
"eval_runtime": 175.7147,
|
| 218 |
+
"eval_samples_per_second": 27.88,
|
| 219 |
+
"eval_steps_per_second": 0.876,
|
| 220 |
+
"eval_wer": 1.0,
|
| 221 |
+
"step": 2100
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 9.56,
|
| 225 |
+
"eval_loss": 3.0517823696136475,
|
| 226 |
+
"eval_runtime": 174.9875,
|
| 227 |
+
"eval_samples_per_second": 27.996,
|
| 228 |
+
"eval_steps_per_second": 0.88,
|
| 229 |
+
"eval_wer": 1.0,
|
| 230 |
+
"step": 2200
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 10.0,
|
| 234 |
+
"eval_loss": 3.0749499797821045,
|
| 235 |
+
"eval_runtime": 176.3933,
|
| 236 |
+
"eval_samples_per_second": 27.773,
|
| 237 |
+
"eval_steps_per_second": 0.873,
|
| 238 |
+
"eval_wer": 1.0,
|
| 239 |
+
"step": 2300
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.43,
|
| 243 |
+
"eval_loss": 3.0697524547576904,
|
| 244 |
+
"eval_runtime": 175.8486,
|
| 245 |
+
"eval_samples_per_second": 27.859,
|
| 246 |
+
"eval_steps_per_second": 0.876,
|
| 247 |
+
"eval_wer": 1.0,
|
| 248 |
+
"step": 2400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 10.87,
|
| 252 |
+
"learning_rate": 0.00020648437499999996,
|
| 253 |
+
"loss": 3.1058,
|
| 254 |
+
"step": 2500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 10.87,
|
| 258 |
+
"eval_loss": 3.0664749145507812,
|
| 259 |
+
"eval_runtime": 176.8396,
|
| 260 |
+
"eval_samples_per_second": 27.703,
|
| 261 |
+
"eval_steps_per_second": 0.871,
|
| 262 |
+
"eval_wer": 1.0,
|
| 263 |
+
"step": 2500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 11.3,
|
| 267 |
+
"eval_loss": 3.055528402328491,
|
| 268 |
+
"eval_runtime": 176.8954,
|
| 269 |
+
"eval_samples_per_second": 27.694,
|
| 270 |
+
"eval_steps_per_second": 0.871,
|
| 271 |
+
"eval_wer": 1.0,
|
| 272 |
+
"step": 2600
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 11.74,
|
| 276 |
+
"eval_loss": 3.0589022636413574,
|
| 277 |
+
"eval_runtime": 177.2054,
|
| 278 |
+
"eval_samples_per_second": 27.646,
|
| 279 |
+
"eval_steps_per_second": 0.869,
|
| 280 |
+
"eval_wer": 1.0,
|
| 281 |
+
"step": 2700
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 12.17,
|
| 285 |
+
"eval_loss": 3.061063051223755,
|
| 286 |
+
"eval_runtime": 176.5606,
|
| 287 |
+
"eval_samples_per_second": 27.747,
|
| 288 |
+
"eval_steps_per_second": 0.872,
|
| 289 |
+
"eval_wer": 1.0,
|
| 290 |
+
"step": 2800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 12.61,
|
| 294 |
+
"eval_loss": 3.056131601333618,
|
| 295 |
+
"eval_runtime": 175.9193,
|
| 296 |
+
"eval_samples_per_second": 27.848,
|
| 297 |
+
"eval_steps_per_second": 0.875,
|
| 298 |
+
"eval_wer": 1.0,
|
| 299 |
+
"step": 2900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 13.04,
|
| 303 |
+
"learning_rate": 0.00018304687499999997,
|
| 304 |
+
"loss": 3.1071,
|
| 305 |
+
"step": 3000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 13.04,
|
| 309 |
+
"eval_loss": 3.0480217933654785,
|
| 310 |
+
"eval_runtime": 175.6518,
|
| 311 |
+
"eval_samples_per_second": 27.89,
|
| 312 |
+
"eval_steps_per_second": 0.877,
|
| 313 |
+
"eval_wer": 1.0,
|
| 314 |
+
"step": 3000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 13.48,
|
| 318 |
+
"eval_loss": 3.0491693019866943,
|
| 319 |
+
"eval_runtime": 173.0223,
|
| 320 |
+
"eval_samples_per_second": 28.314,
|
| 321 |
+
"eval_steps_per_second": 0.89,
|
| 322 |
+
"eval_wer": 1.0,
|
| 323 |
+
"step": 3100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 13.91,
|
| 327 |
+
"eval_loss": 3.057448387145996,
|
| 328 |
+
"eval_runtime": 175.4684,
|
| 329 |
+
"eval_samples_per_second": 27.92,
|
| 330 |
+
"eval_steps_per_second": 0.878,
|
| 331 |
+
"eval_wer": 1.0,
|
| 332 |
+
"step": 3200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 14.35,
|
| 336 |
+
"eval_loss": 3.053784132003784,
|
| 337 |
+
"eval_runtime": 176.0074,
|
| 338 |
+
"eval_samples_per_second": 27.834,
|
| 339 |
+
"eval_steps_per_second": 0.875,
|
| 340 |
+
"eval_wer": 1.0,
|
| 341 |
+
"step": 3300
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 14.78,
|
| 345 |
+
"eval_loss": 3.050539016723633,
|
| 346 |
+
"eval_runtime": 175.3243,
|
| 347 |
+
"eval_samples_per_second": 27.943,
|
| 348 |
+
"eval_steps_per_second": 0.878,
|
| 349 |
+
"eval_wer": 1.0,
|
| 350 |
+
"step": 3400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 15.22,
|
| 354 |
+
"learning_rate": 0.00015960937499999997,
|
| 355 |
+
"loss": 3.1061,
|
| 356 |
+
"step": 3500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 15.22,
|
| 360 |
+
"eval_loss": 3.059952735900879,
|
| 361 |
+
"eval_runtime": 176.5589,
|
| 362 |
+
"eval_samples_per_second": 27.747,
|
| 363 |
+
"eval_steps_per_second": 0.872,
|
| 364 |
+
"eval_wer": 1.0,
|
| 365 |
+
"step": 3500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 15.65,
|
| 369 |
+
"eval_loss": 3.0595669746398926,
|
| 370 |
+
"eval_runtime": 177.5778,
|
| 371 |
+
"eval_samples_per_second": 27.588,
|
| 372 |
+
"eval_steps_per_second": 0.867,
|
| 373 |
+
"eval_wer": 1.0,
|
| 374 |
+
"step": 3600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 16.09,
|
| 378 |
+
"eval_loss": 3.0623462200164795,
|
| 379 |
+
"eval_runtime": 174.5228,
|
| 380 |
+
"eval_samples_per_second": 28.071,
|
| 381 |
+
"eval_steps_per_second": 0.882,
|
| 382 |
+
"eval_wer": 1.0,
|
| 383 |
+
"step": 3700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 16.52,
|
| 387 |
+
"eval_loss": 3.079986095428467,
|
| 388 |
+
"eval_runtime": 175.7994,
|
| 389 |
+
"eval_samples_per_second": 27.867,
|
| 390 |
+
"eval_steps_per_second": 0.876,
|
| 391 |
+
"eval_wer": 1.0,
|
| 392 |
+
"step": 3800
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 16.95,
|
| 396 |
+
"eval_loss": 3.0583465099334717,
|
| 397 |
+
"eval_runtime": 176.6021,
|
| 398 |
+
"eval_samples_per_second": 27.74,
|
| 399 |
+
"eval_steps_per_second": 0.872,
|
| 400 |
+
"eval_wer": 1.0,
|
| 401 |
+
"step": 3900
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 17.39,
|
| 405 |
+
"learning_rate": 0.00013617187499999998,
|
| 406 |
+
"loss": 3.1036,
|
| 407 |
+
"step": 4000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 17.39,
|
| 411 |
+
"eval_loss": 3.053365468978882,
|
| 412 |
+
"eval_runtime": 175.9714,
|
| 413 |
+
"eval_samples_per_second": 27.84,
|
| 414 |
+
"eval_steps_per_second": 0.875,
|
| 415 |
+
"eval_wer": 1.0,
|
| 416 |
+
"step": 4000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 17.82,
|
| 420 |
+
"eval_loss": 3.0563225746154785,
|
| 421 |
+
"eval_runtime": 175.7204,
|
| 422 |
+
"eval_samples_per_second": 27.88,
|
| 423 |
+
"eval_steps_per_second": 0.876,
|
| 424 |
+
"eval_wer": 1.0,
|
| 425 |
+
"step": 4100
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 18.26,
|
| 429 |
+
"eval_loss": 3.0481250286102295,
|
| 430 |
+
"eval_runtime": 175.8171,
|
| 431 |
+
"eval_samples_per_second": 27.864,
|
| 432 |
+
"eval_steps_per_second": 0.876,
|
| 433 |
+
"eval_wer": 1.0,
|
| 434 |
+
"step": 4200
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 18.69,
|
| 438 |
+
"eval_loss": 3.0476744174957275,
|
| 439 |
+
"eval_runtime": 175.2697,
|
| 440 |
+
"eval_samples_per_second": 27.951,
|
| 441 |
+
"eval_steps_per_second": 0.879,
|
| 442 |
+
"eval_wer": 1.0,
|
| 443 |
+
"step": 4300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 19.13,
|
| 447 |
+
"eval_loss": 3.0504729747772217,
|
| 448 |
+
"eval_runtime": 175.8225,
|
| 449 |
+
"eval_samples_per_second": 27.863,
|
| 450 |
+
"eval_steps_per_second": 0.876,
|
| 451 |
+
"eval_wer": 1.0,
|
| 452 |
+
"step": 4400
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 19.56,
|
| 456 |
+
"learning_rate": 0.00011273437499999999,
|
| 457 |
+
"loss": 3.1086,
|
| 458 |
+
"step": 4500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 19.56,
|
| 462 |
+
"eval_loss": 3.0484793186187744,
|
| 463 |
+
"eval_runtime": 176.184,
|
| 464 |
+
"eval_samples_per_second": 27.806,
|
| 465 |
+
"eval_steps_per_second": 0.874,
|
| 466 |
+
"eval_wer": 1.0,
|
| 467 |
+
"step": 4500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 20.0,
|
| 471 |
+
"eval_loss": 3.0480639934539795,
|
| 472 |
+
"eval_runtime": 175.5218,
|
| 473 |
+
"eval_samples_per_second": 27.911,
|
| 474 |
+
"eval_steps_per_second": 0.877,
|
| 475 |
+
"eval_wer": 1.0,
|
| 476 |
+
"step": 4600
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 20.43,
|
| 480 |
+
"eval_loss": 3.061495780944824,
|
| 481 |
+
"eval_runtime": 176.4313,
|
| 482 |
+
"eval_samples_per_second": 27.767,
|
| 483 |
+
"eval_steps_per_second": 0.873,
|
| 484 |
+
"eval_wer": 1.0,
|
| 485 |
+
"step": 4700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 20.87,
|
| 489 |
+
"eval_loss": 3.0657691955566406,
|
| 490 |
+
"eval_runtime": 175.5853,
|
| 491 |
+
"eval_samples_per_second": 27.901,
|
| 492 |
+
"eval_steps_per_second": 0.877,
|
| 493 |
+
"eval_wer": 1.0,
|
| 494 |
+
"step": 4800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 21.3,
|
| 498 |
+
"eval_loss": 3.050532341003418,
|
| 499 |
+
"eval_runtime": 176.2169,
|
| 500 |
+
"eval_samples_per_second": 27.801,
|
| 501 |
+
"eval_steps_per_second": 0.874,
|
| 502 |
+
"eval_wer": 1.0,
|
| 503 |
+
"step": 4900
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 21.74,
|
| 507 |
+
"learning_rate": 8.9296875e-05,
|
| 508 |
+
"loss": 3.1028,
|
| 509 |
+
"step": 5000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 21.74,
|
| 513 |
+
"eval_loss": 3.0491702556610107,
|
| 514 |
+
"eval_runtime": 175.9502,
|
| 515 |
+
"eval_samples_per_second": 27.843,
|
| 516 |
+
"eval_steps_per_second": 0.875,
|
| 517 |
+
"eval_wer": 1.0,
|
| 518 |
+
"step": 5000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 22.17,
|
| 522 |
+
"eval_loss": 3.048527479171753,
|
| 523 |
+
"eval_runtime": 174.9586,
|
| 524 |
+
"eval_samples_per_second": 28.001,
|
| 525 |
+
"eval_steps_per_second": 0.88,
|
| 526 |
+
"eval_wer": 1.0,
|
| 527 |
+
"step": 5100
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 22.61,
|
| 531 |
+
"eval_loss": 3.0482711791992188,
|
| 532 |
+
"eval_runtime": 176.76,
|
| 533 |
+
"eval_samples_per_second": 27.716,
|
| 534 |
+
"eval_steps_per_second": 0.871,
|
| 535 |
+
"eval_wer": 1.0,
|
| 536 |
+
"step": 5200
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 23.04,
|
| 540 |
+
"eval_loss": 3.0478527545928955,
|
| 541 |
+
"eval_runtime": 174.8893,
|
| 542 |
+
"eval_samples_per_second": 28.012,
|
| 543 |
+
"eval_steps_per_second": 0.881,
|
| 544 |
+
"eval_wer": 1.0,
|
| 545 |
+
"step": 5300
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 23.48,
|
| 549 |
+
"eval_loss": 3.05094313621521,
|
| 550 |
+
"eval_runtime": 175.0794,
|
| 551 |
+
"eval_samples_per_second": 27.982,
|
| 552 |
+
"eval_steps_per_second": 0.88,
|
| 553 |
+
"eval_wer": 1.0,
|
| 554 |
+
"step": 5400
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 23.91,
|
| 558 |
+
"learning_rate": 6.5859375e-05,
|
| 559 |
+
"loss": 3.1087,
|
| 560 |
+
"step": 5500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 23.91,
|
| 564 |
+
"eval_loss": 3.0529990196228027,
|
| 565 |
+
"eval_runtime": 176.1904,
|
| 566 |
+
"eval_samples_per_second": 27.805,
|
| 567 |
+
"eval_steps_per_second": 0.874,
|
| 568 |
+
"eval_wer": 1.0,
|
| 569 |
+
"step": 5500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 24.35,
|
| 573 |
+
"eval_loss": 3.048621654510498,
|
| 574 |
+
"eval_runtime": 175.2104,
|
| 575 |
+
"eval_samples_per_second": 27.961,
|
| 576 |
+
"eval_steps_per_second": 0.879,
|
| 577 |
+
"eval_wer": 1.0,
|
| 578 |
+
"step": 5600
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 24.78,
|
| 582 |
+
"eval_loss": 3.051391124725342,
|
| 583 |
+
"eval_runtime": 175.9351,
|
| 584 |
+
"eval_samples_per_second": 27.845,
|
| 585 |
+
"eval_steps_per_second": 0.875,
|
| 586 |
+
"eval_wer": 1.0,
|
| 587 |
+
"step": 5700
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 25.22,
|
| 591 |
+
"eval_loss": 3.050508499145508,
|
| 592 |
+
"eval_runtime": 175.1722,
|
| 593 |
+
"eval_samples_per_second": 27.967,
|
| 594 |
+
"eval_steps_per_second": 0.879,
|
| 595 |
+
"eval_wer": 1.0,
|
| 596 |
+
"step": 5800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 25.65,
|
| 600 |
+
"eval_loss": 3.050753355026245,
|
| 601 |
+
"eval_runtime": 175.581,
|
| 602 |
+
"eval_samples_per_second": 27.902,
|
| 603 |
+
"eval_steps_per_second": 0.877,
|
| 604 |
+
"eval_wer": 1.0,
|
| 605 |
+
"step": 5900
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 26.09,
|
| 609 |
+
"learning_rate": 4.2421875e-05,
|
| 610 |
+
"loss": 3.1043,
|
| 611 |
+
"step": 6000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 26.09,
|
| 615 |
+
"eval_loss": 3.050074815750122,
|
| 616 |
+
"eval_runtime": 175.9337,
|
| 617 |
+
"eval_samples_per_second": 27.846,
|
| 618 |
+
"eval_steps_per_second": 0.875,
|
| 619 |
+
"eval_wer": 1.0,
|
| 620 |
+
"step": 6000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 26.52,
|
| 624 |
+
"eval_loss": 3.046748638153076,
|
| 625 |
+
"eval_runtime": 176.2651,
|
| 626 |
+
"eval_samples_per_second": 27.793,
|
| 627 |
+
"eval_steps_per_second": 0.874,
|
| 628 |
+
"eval_wer": 1.0,
|
| 629 |
+
"step": 6100
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 26.95,
|
| 633 |
+
"eval_loss": 3.046581268310547,
|
| 634 |
+
"eval_runtime": 175.4906,
|
| 635 |
+
"eval_samples_per_second": 27.916,
|
| 636 |
+
"eval_steps_per_second": 0.878,
|
| 637 |
+
"eval_wer": 1.0,
|
| 638 |
+
"step": 6200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 27.39,
|
| 642 |
+
"eval_loss": 3.0465457439422607,
|
| 643 |
+
"eval_runtime": 174.3257,
|
| 644 |
+
"eval_samples_per_second": 28.103,
|
| 645 |
+
"eval_steps_per_second": 0.883,
|
| 646 |
+
"eval_wer": 1.0,
|
| 647 |
+
"step": 6300
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 27.82,
|
| 651 |
+
"eval_loss": 3.0464954376220703,
|
| 652 |
+
"eval_runtime": 174.3395,
|
| 653 |
+
"eval_samples_per_second": 28.1,
|
| 654 |
+
"eval_steps_per_second": 0.883,
|
| 655 |
+
"eval_wer": 1.0,
|
| 656 |
+
"step": 6400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 28.26,
|
| 660 |
+
"learning_rate": 1.8984375e-05,
|
| 661 |
+
"loss": 3.1175,
|
| 662 |
+
"step": 6500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 28.26,
|
| 666 |
+
"eval_loss": 3.046614170074463,
|
| 667 |
+
"eval_runtime": 174.756,
|
| 668 |
+
"eval_samples_per_second": 28.033,
|
| 669 |
+
"eval_steps_per_second": 0.881,
|
| 670 |
+
"eval_wer": 1.0,
|
| 671 |
+
"step": 6500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 28.69,
|
| 675 |
+
"eval_loss": 3.046605110168457,
|
| 676 |
+
"eval_runtime": 174.8316,
|
| 677 |
+
"eval_samples_per_second": 28.021,
|
| 678 |
+
"eval_steps_per_second": 0.881,
|
| 679 |
+
"eval_wer": 1.0,
|
| 680 |
+
"step": 6600
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 29.13,
|
| 684 |
+
"eval_loss": 3.0464911460876465,
|
| 685 |
+
"eval_runtime": 174.5543,
|
| 686 |
+
"eval_samples_per_second": 28.066,
|
| 687 |
+
"eval_steps_per_second": 0.882,
|
| 688 |
+
"eval_wer": 1.0,
|
| 689 |
+
"step": 6700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 29.56,
|
| 693 |
+
"eval_loss": 3.046463966369629,
|
| 694 |
+
"eval_runtime": 175.0973,
|
| 695 |
+
"eval_samples_per_second": 27.979,
|
| 696 |
+
"eval_steps_per_second": 0.88,
|
| 697 |
+
"eval_wer": 1.0,
|
| 698 |
+
"step": 6800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 30.0,
|
| 702 |
+
"eval_loss": 3.0463998317718506,
|
| 703 |
+
"eval_runtime": 174.6633,
|
| 704 |
+
"eval_samples_per_second": 28.048,
|
| 705 |
+
"eval_steps_per_second": 0.882,
|
| 706 |
+
"eval_wer": 1.0,
|
| 707 |
+
"step": 6900
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 30.0,
|
| 711 |
+
"step": 6900,
|
| 712 |
+
"total_flos": 1.7654566052477592e+19,
|
| 713 |
+
"train_loss": 3.233657403475996,
|
| 714 |
+
"train_runtime": 33798.1213,
|
| 715 |
+
"train_samples_per_second": 13.075,
|
| 716 |
+
"train_steps_per_second": 0.204
|
| 717 |
+
}
|
| 718 |
+
],
|
| 719 |
+
"max_steps": 6900,
|
| 720 |
+
"num_train_epochs": 30,
|
| 721 |
+
"total_flos": 1.7654566052477592e+19,
|
| 722 |
+
"trial_name": null,
|
| 723 |
+
"trial_params": null
|
| 724 |
+
}
|