Abdulwahab Sahyoun
commited on
Commit
•
3637072
1
Parent(s):
49583eb
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +715 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.78,
|
| 3 |
+
"eval_loss": 0.717069685459137,
|
| 4 |
+
"eval_runtime": 202.6594,
|
| 5 |
+
"eval_samples": 4899,
|
| 6 |
+
"eval_samples_per_second": 24.174,
|
| 7 |
+
"eval_steps_per_second": 0.76,
|
| 8 |
+
"eval_wer": 0.333567605557658,
|
| 9 |
+
"train_loss": 0.0,
|
| 10 |
+
"train_runtime": 70.228,
|
| 11 |
+
"train_samples": 14730,
|
| 12 |
+
"train_samples_per_second": 4194.91,
|
| 13 |
+
"train_steps_per_second": 65.501
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.78,
|
| 3 |
+
"eval_loss": 0.717069685459137,
|
| 4 |
+
"eval_runtime": 202.6594,
|
| 5 |
+
"eval_samples": 4899,
|
| 6 |
+
"eval_samples_per_second": 24.174,
|
| 7 |
+
"eval_steps_per_second": 0.76,
|
| 8 |
+
"eval_wer": 0.333567605557658
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 14.78,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 70.228,
|
| 5 |
+
"train_samples": 14730,
|
| 6 |
+
"train_samples_per_second": 4194.91,
|
| 7 |
+
"train_steps_per_second": 65.501
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,715 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.781758957654723,
|
| 5 |
+
"global_step": 6800,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.22,
|
| 12 |
+
"eval_loss": 5.188871383666992,
|
| 13 |
+
"eval_runtime": 204.5528,
|
| 14 |
+
"eval_samples_per_second": 23.95,
|
| 15 |
+
"eval_steps_per_second": 1.501,
|
| 16 |
+
"eval_wer": 1.0,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.43,
|
| 21 |
+
"eval_loss": 3.1129117012023926,
|
| 22 |
+
"eval_runtime": 202.5006,
|
| 23 |
+
"eval_samples_per_second": 24.193,
|
| 24 |
+
"eval_steps_per_second": 1.516,
|
| 25 |
+
"eval_wer": 1.0,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.65,
|
| 30 |
+
"eval_loss": 3.050328254699707,
|
| 31 |
+
"eval_runtime": 212.2496,
|
| 32 |
+
"eval_samples_per_second": 23.081,
|
| 33 |
+
"eval_steps_per_second": 1.446,
|
| 34 |
+
"eval_wer": 1.0,
|
| 35 |
+
"step": 300
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.87,
|
| 39 |
+
"eval_loss": 3.027885913848877,
|
| 40 |
+
"eval_runtime": 207.467,
|
| 41 |
+
"eval_samples_per_second": 23.613,
|
| 42 |
+
"eval_steps_per_second": 1.48,
|
| 43 |
+
"eval_wer": 1.0,
|
| 44 |
+
"step": 400
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.09,
|
| 48 |
+
"learning_rate": 0.00029759999999999997,
|
| 49 |
+
"loss": 6.2756,
|
| 50 |
+
"step": 500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.09,
|
| 54 |
+
"eval_loss": 2.996450662612915,
|
| 55 |
+
"eval_runtime": 204.103,
|
| 56 |
+
"eval_samples_per_second": 24.003,
|
| 57 |
+
"eval_steps_per_second": 1.504,
|
| 58 |
+
"eval_wer": 1.0,
|
| 59 |
+
"step": 500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.3,
|
| 63 |
+
"eval_loss": 2.3617873191833496,
|
| 64 |
+
"eval_runtime": 203.0453,
|
| 65 |
+
"eval_samples_per_second": 24.128,
|
| 66 |
+
"eval_steps_per_second": 1.512,
|
| 67 |
+
"eval_wer": 0.999270151916527,
|
| 68 |
+
"step": 600
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.52,
|
| 72 |
+
"eval_loss": 1.2715116739273071,
|
| 73 |
+
"eval_runtime": 201.791,
|
| 74 |
+
"eval_samples_per_second": 24.278,
|
| 75 |
+
"eval_steps_per_second": 1.521,
|
| 76 |
+
"eval_wer": 0.8758177001675947,
|
| 77 |
+
"step": 700
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.74,
|
| 81 |
+
"eval_loss": 0.9970846772193909,
|
| 82 |
+
"eval_runtime": 204.0755,
|
| 83 |
+
"eval_samples_per_second": 24.006,
|
| 84 |
+
"eval_steps_per_second": 1.504,
|
| 85 |
+
"eval_wer": 0.7156295615505217,
|
| 86 |
+
"step": 800
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.96,
|
| 90 |
+
"eval_loss": 0.8927041292190552,
|
| 91 |
+
"eval_runtime": 204.7029,
|
| 92 |
+
"eval_samples_per_second": 23.932,
|
| 93 |
+
"eval_steps_per_second": 1.5,
|
| 94 |
+
"eval_wer": 0.6382116018813861,
|
| 95 |
+
"step": 900
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.17,
|
| 99 |
+
"learning_rate": 0.00027675,
|
| 100 |
+
"loss": 1.712,
|
| 101 |
+
"step": 1000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 2.17,
|
| 105 |
+
"eval_loss": 0.8251833319664001,
|
| 106 |
+
"eval_runtime": 201.65,
|
| 107 |
+
"eval_samples_per_second": 24.295,
|
| 108 |
+
"eval_steps_per_second": 1.522,
|
| 109 |
+
"eval_wer": 0.5926366437800724,
|
| 110 |
+
"step": 1000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.39,
|
| 114 |
+
"eval_loss": 0.7793710827827454,
|
| 115 |
+
"eval_runtime": 203.5019,
|
| 116 |
+
"eval_samples_per_second": 24.073,
|
| 117 |
+
"eval_steps_per_second": 1.509,
|
| 118 |
+
"eval_wer": 0.5433854138508948,
|
| 119 |
+
"step": 1100
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.61,
|
| 123 |
+
"eval_loss": 0.7556658983230591,
|
| 124 |
+
"eval_runtime": 204.1458,
|
| 125 |
+
"eval_samples_per_second": 23.998,
|
| 126 |
+
"eval_steps_per_second": 1.504,
|
| 127 |
+
"eval_wer": 0.509244742390658,
|
| 128 |
+
"step": 1200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.83,
|
| 132 |
+
"eval_loss": 0.7346892952919006,
|
| 133 |
+
"eval_runtime": 201.906,
|
| 134 |
+
"eval_samples_per_second": 24.264,
|
| 135 |
+
"eval_steps_per_second": 1.521,
|
| 136 |
+
"eval_wer": 0.5203005892847489,
|
| 137 |
+
"step": 1300
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.04,
|
| 141 |
+
"eval_loss": 0.7189395427703857,
|
| 142 |
+
"eval_runtime": 202.2047,
|
| 143 |
+
"eval_samples_per_second": 24.228,
|
| 144 |
+
"eval_steps_per_second": 1.518,
|
| 145 |
+
"eval_wer": 0.49286370762826404,
|
| 146 |
+
"step": 1400
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.26,
|
| 150 |
+
"learning_rate": 0.00025331249999999996,
|
| 151 |
+
"loss": 0.9305,
|
| 152 |
+
"step": 1500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.26,
|
| 156 |
+
"eval_loss": 0.6819509267807007,
|
| 157 |
+
"eval_runtime": 201.6073,
|
| 158 |
+
"eval_samples_per_second": 24.3,
|
| 159 |
+
"eval_steps_per_second": 1.523,
|
| 160 |
+
"eval_wer": 0.45947991566199925,
|
| 161 |
+
"step": 1500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 3.48,
|
| 165 |
+
"eval_loss": 0.679171085357666,
|
| 166 |
+
"eval_runtime": 201.2709,
|
| 167 |
+
"eval_samples_per_second": 24.34,
|
| 168 |
+
"eval_steps_per_second": 1.525,
|
| 169 |
+
"eval_wer": 0.4504243931448343,
|
| 170 |
+
"step": 1600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.69,
|
| 174 |
+
"eval_loss": 0.6596325635910034,
|
| 175 |
+
"eval_runtime": 201.0715,
|
| 176 |
+
"eval_samples_per_second": 24.364,
|
| 177 |
+
"eval_steps_per_second": 1.527,
|
| 178 |
+
"eval_wer": 0.44423420014056336,
|
| 179 |
+
"step": 1700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.91,
|
| 183 |
+
"eval_loss": 0.6755712628364563,
|
| 184 |
+
"eval_runtime": 202.0726,
|
| 185 |
+
"eval_samples_per_second": 24.244,
|
| 186 |
+
"eval_steps_per_second": 1.519,
|
| 187 |
+
"eval_wer": 0.4431529437206033,
|
| 188 |
+
"step": 1800
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.13,
|
| 192 |
+
"eval_loss": 0.6663188338279724,
|
| 193 |
+
"eval_runtime": 200.5093,
|
| 194 |
+
"eval_samples_per_second": 24.433,
|
| 195 |
+
"eval_steps_per_second": 1.531,
|
| 196 |
+
"eval_wer": 0.43920635778774936,
|
| 197 |
+
"step": 1900
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 4.35,
|
| 201 |
+
"learning_rate": 0.00022987499999999996,
|
| 202 |
+
"loss": 0.737,
|
| 203 |
+
"step": 2000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 4.35,
|
| 207 |
+
"eval_loss": 0.6478506326675415,
|
| 208 |
+
"eval_runtime": 202.9556,
|
| 209 |
+
"eval_samples_per_second": 24.138,
|
| 210 |
+
"eval_steps_per_second": 1.513,
|
| 211 |
+
"eval_wer": 0.43720603341082337,
|
| 212 |
+
"step": 2000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.56,
|
| 216 |
+
"eval_loss": 0.6353247761726379,
|
| 217 |
+
"eval_runtime": 202.5451,
|
| 218 |
+
"eval_samples_per_second": 24.187,
|
| 219 |
+
"eval_steps_per_second": 1.516,
|
| 220 |
+
"eval_wer": 0.4203384332594475,
|
| 221 |
+
"step": 2100
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.78,
|
| 225 |
+
"eval_loss": 0.6251159906387329,
|
| 226 |
+
"eval_runtime": 204.4658,
|
| 227 |
+
"eval_samples_per_second": 23.96,
|
| 228 |
+
"eval_steps_per_second": 1.501,
|
| 229 |
+
"eval_wer": 0.4087960209763746,
|
| 230 |
+
"step": 2200
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.0,
|
| 234 |
+
"eval_loss": 0.6208750605583191,
|
| 235 |
+
"eval_runtime": 204.1125,
|
| 236 |
+
"eval_samples_per_second": 24.001,
|
| 237 |
+
"eval_steps_per_second": 1.504,
|
| 238 |
+
"eval_wer": 0.4176893550305455,
|
| 239 |
+
"step": 2300
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 5.22,
|
| 243 |
+
"eval_loss": 0.6639252305030823,
|
| 244 |
+
"eval_runtime": 235.6403,
|
| 245 |
+
"eval_samples_per_second": 20.79,
|
| 246 |
+
"eval_steps_per_second": 1.303,
|
| 247 |
+
"eval_wer": 0.40941774341785153,
|
| 248 |
+
"step": 2400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 5.43,
|
| 252 |
+
"learning_rate": 0.00020643749999999997,
|
| 253 |
+
"loss": 0.6247,
|
| 254 |
+
"step": 2500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.43,
|
| 258 |
+
"eval_loss": 0.6407893300056458,
|
| 259 |
+
"eval_runtime": 278.1573,
|
| 260 |
+
"eval_samples_per_second": 17.612,
|
| 261 |
+
"eval_steps_per_second": 1.104,
|
| 262 |
+
"eval_wer": 0.39701032599881064,
|
| 263 |
+
"step": 2500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 5.65,
|
| 267 |
+
"eval_loss": 0.6373021006584167,
|
| 268 |
+
"eval_runtime": 207.7541,
|
| 269 |
+
"eval_samples_per_second": 23.581,
|
| 270 |
+
"eval_steps_per_second": 1.478,
|
| 271 |
+
"eval_wer": 0.39322592852895066,
|
| 272 |
+
"step": 2600
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 5.87,
|
| 276 |
+
"eval_loss": 0.6411147713661194,
|
| 277 |
+
"eval_runtime": 228.4908,
|
| 278 |
+
"eval_samples_per_second": 21.441,
|
| 279 |
+
"eval_steps_per_second": 1.344,
|
| 280 |
+
"eval_wer": 0.39276639455046763,
|
| 281 |
+
"step": 2700
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.09,
|
| 285 |
+
"eval_loss": 0.6378452181816101,
|
| 286 |
+
"eval_runtime": 202.0494,
|
| 287 |
+
"eval_samples_per_second": 24.247,
|
| 288 |
+
"eval_steps_per_second": 1.519,
|
| 289 |
+
"eval_wer": 0.38971184516408064,
|
| 290 |
+
"step": 2800
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.3,
|
| 294 |
+
"eval_loss": 0.6396178007125854,
|
| 295 |
+
"eval_runtime": 201.6642,
|
| 296 |
+
"eval_samples_per_second": 24.293,
|
| 297 |
+
"eval_steps_per_second": 1.522,
|
| 298 |
+
"eval_wer": 0.39287452019246366,
|
| 299 |
+
"step": 2900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 6.52,
|
| 303 |
+
"learning_rate": 0.00018299999999999998,
|
| 304 |
+
"loss": 0.5443,
|
| 305 |
+
"step": 3000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 6.52,
|
| 309 |
+
"eval_loss": 0.6544364094734192,
|
| 310 |
+
"eval_runtime": 201.2122,
|
| 311 |
+
"eval_samples_per_second": 24.347,
|
| 312 |
+
"eval_steps_per_second": 1.526,
|
| 313 |
+
"eval_wer": 0.38641401308320267,
|
| 314 |
+
"step": 3000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 6.74,
|
| 318 |
+
"eval_loss": 0.6217912435531616,
|
| 319 |
+
"eval_runtime": 202.6291,
|
| 320 |
+
"eval_samples_per_second": 24.177,
|
| 321 |
+
"eval_steps_per_second": 1.515,
|
| 322 |
+
"eval_wer": 0.37857490403849275,
|
| 323 |
+
"step": 3100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 6.96,
|
| 327 |
+
"eval_loss": 0.6200193166732788,
|
| 328 |
+
"eval_runtime": 202.7362,
|
| 329 |
+
"eval_samples_per_second": 24.164,
|
| 330 |
+
"eval_steps_per_second": 1.514,
|
| 331 |
+
"eval_wer": 0.37843974698599775,
|
| 332 |
+
"step": 3200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 7.17,
|
| 336 |
+
"eval_loss": 0.6156935691833496,
|
| 337 |
+
"eval_runtime": 203.722,
|
| 338 |
+
"eval_samples_per_second": 24.047,
|
| 339 |
+
"eval_steps_per_second": 1.507,
|
| 340 |
+
"eval_wer": 0.3790614694274747,
|
| 341 |
+
"step": 3300
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 7.39,
|
| 345 |
+
"eval_loss": 0.6316530704498291,
|
| 346 |
+
"eval_runtime": 202.1843,
|
| 347 |
+
"eval_samples_per_second": 24.23,
|
| 348 |
+
"eval_steps_per_second": 1.518,
|
| 349 |
+
"eval_wer": 0.37979131751094775,
|
| 350 |
+
"step": 3400
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 7.61,
|
| 354 |
+
"learning_rate": 0.00015956249999999998,
|
| 355 |
+
"loss": 0.4845,
|
| 356 |
+
"step": 3500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 7.61,
|
| 360 |
+
"eval_loss": 0.6540383100509644,
|
| 361 |
+
"eval_runtime": 203.1885,
|
| 362 |
+
"eval_samples_per_second": 24.111,
|
| 363 |
+
"eval_steps_per_second": 1.511,
|
| 364 |
+
"eval_wer": 0.37711520787154673,
|
| 365 |
+
"step": 3500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 7.83,
|
| 369 |
+
"eval_loss": 0.6435653567314148,
|
| 370 |
+
"eval_runtime": 201.9898,
|
| 371 |
+
"eval_samples_per_second": 24.254,
|
| 372 |
+
"eval_steps_per_second": 1.52,
|
| 373 |
+
"eval_wer": 0.3669784289344218,
|
| 374 |
+
"step": 3600
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.04,
|
| 378 |
+
"eval_loss": 0.63348388671875,
|
| 379 |
+
"eval_runtime": 201.5967,
|
| 380 |
+
"eval_samples_per_second": 24.301,
|
| 381 |
+
"eval_steps_per_second": 1.523,
|
| 382 |
+
"eval_wer": 0.3694653187003298,
|
| 383 |
+
"step": 3700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 8.26,
|
| 387 |
+
"eval_loss": 0.657917320728302,
|
| 388 |
+
"eval_runtime": 208.9718,
|
| 389 |
+
"eval_samples_per_second": 23.443,
|
| 390 |
+
"eval_steps_per_second": 1.469,
|
| 391 |
+
"eval_wer": 0.36100448721414286,
|
| 392 |
+
"step": 3800
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.48,
|
| 396 |
+
"eval_loss": 0.6169739961624146,
|
| 397 |
+
"eval_runtime": 203.6316,
|
| 398 |
+
"eval_samples_per_second": 24.058,
|
| 399 |
+
"eval_steps_per_second": 1.508,
|
| 400 |
+
"eval_wer": 0.3613288641401308,
|
| 401 |
+
"step": 3900
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 8.69,
|
| 405 |
+
"learning_rate": 0.000136125,
|
| 406 |
+
"loss": 0.4279,
|
| 407 |
+
"step": 4000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 8.69,
|
| 411 |
+
"eval_loss": 0.6523476243019104,
|
| 412 |
+
"eval_runtime": 201.8094,
|
| 413 |
+
"eval_samples_per_second": 24.275,
|
| 414 |
+
"eval_steps_per_second": 1.521,
|
| 415 |
+
"eval_wer": 0.36165324106611885,
|
| 416 |
+
"step": 4000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 8.91,
|
| 420 |
+
"eval_loss": 0.634904146194458,
|
| 421 |
+
"eval_runtime": 202.5275,
|
| 422 |
+
"eval_samples_per_second": 24.189,
|
| 423 |
+
"eval_steps_per_second": 1.516,
|
| 424 |
+
"eval_wer": 0.35773368654376386,
|
| 425 |
+
"step": 4100
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 9.13,
|
| 429 |
+
"eval_loss": 0.6343770027160645,
|
| 430 |
+
"eval_runtime": 200.9349,
|
| 431 |
+
"eval_samples_per_second": 24.381,
|
| 432 |
+
"eval_steps_per_second": 1.528,
|
| 433 |
+
"eval_wer": 0.3673298372709088,
|
| 434 |
+
"step": 4200
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 9.35,
|
| 438 |
+
"eval_loss": 0.6215314269065857,
|
| 439 |
+
"eval_runtime": 200.3697,
|
| 440 |
+
"eval_samples_per_second": 24.45,
|
| 441 |
+
"eval_steps_per_second": 1.532,
|
| 442 |
+
"eval_wer": 0.3641130994215278,
|
| 443 |
+
"step": 4300
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 9.56,
|
| 447 |
+
"eval_loss": 0.6512671709060669,
|
| 448 |
+
"eval_runtime": 201.0806,
|
| 449 |
+
"eval_samples_per_second": 24.363,
|
| 450 |
+
"eval_steps_per_second": 1.527,
|
| 451 |
+
"eval_wer": 0.36081526734064984,
|
| 452 |
+
"step": 4400
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 9.78,
|
| 456 |
+
"learning_rate": 0.00011268749999999998,
|
| 457 |
+
"loss": 0.3825,
|
| 458 |
+
"step": 4500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 9.78,
|
| 462 |
+
"eval_loss": 0.638552725315094,
|
| 463 |
+
"eval_runtime": 201.1524,
|
| 464 |
+
"eval_samples_per_second": 24.355,
|
| 465 |
+
"eval_steps_per_second": 1.526,
|
| 466 |
+
"eval_wer": 0.36051792182516085,
|
| 467 |
+
"step": 4500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 10.0,
|
| 471 |
+
"eval_loss": 0.6724193692207336,
|
| 472 |
+
"eval_runtime": 201.6562,
|
| 473 |
+
"eval_samples_per_second": 24.294,
|
| 474 |
+
"eval_steps_per_second": 1.522,
|
| 475 |
+
"eval_wer": 0.3549494512623669,
|
| 476 |
+
"step": 4600
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 10.22,
|
| 480 |
+
"eval_loss": 0.6775844693183899,
|
| 481 |
+
"eval_runtime": 201.0063,
|
| 482 |
+
"eval_samples_per_second": 24.372,
|
| 483 |
+
"eval_steps_per_second": 1.527,
|
| 484 |
+
"eval_wer": 0.36016651348867385,
|
| 485 |
+
"step": 4700
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 10.43,
|
| 489 |
+
"eval_loss": 0.673897385597229,
|
| 490 |
+
"eval_runtime": 200.6197,
|
| 491 |
+
"eval_samples_per_second": 24.419,
|
| 492 |
+
"eval_steps_per_second": 1.53,
|
| 493 |
+
"eval_wer": 0.3543817916418879,
|
| 494 |
+
"step": 4800
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 10.65,
|
| 498 |
+
"eval_loss": 0.6688181161880493,
|
| 499 |
+
"eval_runtime": 202.0195,
|
| 500 |
+
"eval_samples_per_second": 24.25,
|
| 501 |
+
"eval_steps_per_second": 1.52,
|
| 502 |
+
"eval_wer": 0.3557333621668379,
|
| 503 |
+
"step": 4900
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 10.87,
|
| 507 |
+
"learning_rate": 8.924999999999999e-05,
|
| 508 |
+
"loss": 0.3477,
|
| 509 |
+
"step": 5000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 10.87,
|
| 513 |
+
"eval_loss": 0.6674283146858215,
|
| 514 |
+
"eval_runtime": 204.4147,
|
| 515 |
+
"eval_samples_per_second": 23.966,
|
| 516 |
+
"eval_steps_per_second": 1.502,
|
| 517 |
+
"eval_wer": 0.3564361788398119,
|
| 518 |
+
"step": 5000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 11.09,
|
| 522 |
+
"eval_loss": 0.6786395907402039,
|
| 523 |
+
"eval_runtime": 201.526,
|
| 524 |
+
"eval_samples_per_second": 24.31,
|
| 525 |
+
"eval_steps_per_second": 1.523,
|
| 526 |
+
"eval_wer": 0.3475969076066389,
|
| 527 |
+
"step": 5100
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 11.3,
|
| 531 |
+
"eval_loss": 0.6817718148231506,
|
| 532 |
+
"eval_runtime": 201.6908,
|
| 533 |
+
"eval_samples_per_second": 24.29,
|
| 534 |
+
"eval_steps_per_second": 1.522,
|
| 535 |
+
"eval_wer": 0.34778612748013193,
|
| 536 |
+
"step": 5200
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 11.52,
|
| 540 |
+
"eval_loss": 0.6873587965965271,
|
| 541 |
+
"eval_runtime": 199.7159,
|
| 542 |
+
"eval_samples_per_second": 24.53,
|
| 543 |
+
"eval_steps_per_second": 1.537,
|
| 544 |
+
"eval_wer": 0.3469751851651619,
|
| 545 |
+
"step": 5300
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 11.74,
|
| 549 |
+
"eval_loss": 0.6992678642272949,
|
| 550 |
+
"eval_runtime": 201.0468,
|
| 551 |
+
"eval_samples_per_second": 24.367,
|
| 552 |
+
"eval_steps_per_second": 1.527,
|
| 553 |
+
"eval_wer": 0.3424068767908309,
|
| 554 |
+
"step": 5400
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 11.96,
|
| 558 |
+
"learning_rate": 6.58125e-05,
|
| 559 |
+
"loss": 0.3101,
|
| 560 |
+
"step": 5500
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 11.96,
|
| 564 |
+
"eval_loss": 0.6949637532234192,
|
| 565 |
+
"eval_runtime": 201.2671,
|
| 566 |
+
"eval_samples_per_second": 24.341,
|
| 567 |
+
"eval_steps_per_second": 1.525,
|
| 568 |
+
"eval_wer": 0.34040655241390494,
|
| 569 |
+
"step": 5500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 12.17,
|
| 573 |
+
"eval_loss": 0.6872305274009705,
|
| 574 |
+
"eval_runtime": 205.5246,
|
| 575 |
+
"eval_samples_per_second": 23.837,
|
| 576 |
+
"eval_steps_per_second": 1.494,
|
| 577 |
+
"eval_wer": 0.34062280369789694,
|
| 578 |
+
"step": 5600
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 12.39,
|
| 582 |
+
"eval_loss": 0.6846413016319275,
|
| 583 |
+
"eval_runtime": 201.5806,
|
| 584 |
+
"eval_samples_per_second": 24.303,
|
| 585 |
+
"eval_steps_per_second": 1.523,
|
| 586 |
+
"eval_wer": 0.34237984538033195,
|
| 587 |
+
"step": 5700
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 12.61,
|
| 591 |
+
"eval_loss": 0.7050597667694092,
|
| 592 |
+
"eval_runtime": 201.3274,
|
| 593 |
+
"eval_samples_per_second": 24.333,
|
| 594 |
+
"eval_steps_per_second": 1.525,
|
| 595 |
+
"eval_wer": 0.34046061523490295,
|
| 596 |
+
"step": 5800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 12.83,
|
| 600 |
+
"eval_loss": 0.7051235437393188,
|
| 601 |
+
"eval_runtime": 201.5539,
|
| 602 |
+
"eval_samples_per_second": 24.306,
|
| 603 |
+
"eval_steps_per_second": 1.523,
|
| 604 |
+
"eval_wer": 0.337811537006001,
|
| 605 |
+
"step": 5900
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 13.04,
|
| 609 |
+
"learning_rate": 4.237499999999999e-05,
|
| 610 |
+
"loss": 0.2859,
|
| 611 |
+
"step": 6000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 13.04,
|
| 615 |
+
"eval_loss": 0.6955370306968689,
|
| 616 |
+
"eval_runtime": 201.221,
|
| 617 |
+
"eval_samples_per_second": 24.346,
|
| 618 |
+
"eval_steps_per_second": 1.526,
|
| 619 |
+
"eval_wer": 0.34032545818240795,
|
| 620 |
+
"step": 6000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 13.26,
|
| 624 |
+
"eval_loss": 0.7115095257759094,
|
| 625 |
+
"eval_runtime": 201.4349,
|
| 626 |
+
"eval_samples_per_second": 24.321,
|
| 627 |
+
"eval_steps_per_second": 1.524,
|
| 628 |
+
"eval_wer": 0.33902795047845596,
|
| 629 |
+
"step": 6100
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 13.48,
|
| 633 |
+
"eval_loss": 0.7074177861213684,
|
| 634 |
+
"eval_runtime": 200.2975,
|
| 635 |
+
"eval_samples_per_second": 24.459,
|
| 636 |
+
"eval_steps_per_second": 1.533,
|
| 637 |
+
"eval_wer": 0.338433259447478,
|
| 638 |
+
"step": 6200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 13.69,
|
| 642 |
+
"eval_loss": 0.7001507878303528,
|
| 643 |
+
"eval_runtime": 201.4343,
|
| 644 |
+
"eval_samples_per_second": 24.321,
|
| 645 |
+
"eval_steps_per_second": 1.524,
|
| 646 |
+
"eval_wer": 0.33756825431151,
|
| 647 |
+
"step": 6300
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 13.91,
|
| 651 |
+
"eval_loss": 0.7170686721801758,
|
| 652 |
+
"eval_runtime": 203.7443,
|
| 653 |
+
"eval_samples_per_second": 24.045,
|
| 654 |
+
"eval_steps_per_second": 1.507,
|
| 655 |
+
"eval_wer": 0.336027463913067,
|
| 656 |
+
"step": 6400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 14.13,
|
| 660 |
+
"learning_rate": 1.89375e-05,
|
| 661 |
+
"loss": 0.2714,
|
| 662 |
+
"step": 6500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 14.13,
|
| 666 |
+
"eval_loss": 0.7192927002906799,
|
| 667 |
+
"eval_runtime": 200.9828,
|
| 668 |
+
"eval_samples_per_second": 24.375,
|
| 669 |
+
"eval_steps_per_second": 1.527,
|
| 670 |
+
"eval_wer": 0.33405417094663997,
|
| 671 |
+
"step": 6500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 14.35,
|
| 675 |
+
"eval_loss": 0.7131814360618591,
|
| 676 |
+
"eval_runtime": 199.8266,
|
| 677 |
+
"eval_samples_per_second": 24.516,
|
| 678 |
+
"eval_steps_per_second": 1.536,
|
| 679 |
+
"eval_wer": 0.334729956209115,
|
| 680 |
+
"step": 6600
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 14.56,
|
| 684 |
+
"eval_loss": 0.7184281349182129,
|
| 685 |
+
"eval_runtime": 202.0064,
|
| 686 |
+
"eval_samples_per_second": 24.252,
|
| 687 |
+
"eval_steps_per_second": 1.52,
|
| 688 |
+
"eval_wer": 0.335297615829594,
|
| 689 |
+
"step": 6700
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 14.78,
|
| 693 |
+
"eval_loss": 0.7170840501785278,
|
| 694 |
+
"eval_runtime": 201.3006,
|
| 695 |
+
"eval_samples_per_second": 24.337,
|
| 696 |
+
"eval_steps_per_second": 1.525,
|
| 697 |
+
"eval_wer": 0.333054008758177,
|
| 698 |
+
"step": 6800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 14.78,
|
| 702 |
+
"step": 6800,
|
| 703 |
+
"total_flos": 2.9460768962998075e+19,
|
| 704 |
+
"train_loss": 0.0,
|
| 705 |
+
"train_runtime": 70.228,
|
| 706 |
+
"train_samples_per_second": 4194.91,
|
| 707 |
+
"train_steps_per_second": 65.501
|
| 708 |
+
}
|
| 709 |
+
],
|
| 710 |
+
"max_steps": 4600,
|
| 711 |
+
"num_train_epochs": 20,
|
| 712 |
+
"total_flos": 2.9460768962998075e+19,
|
| 713 |
+
"trial_name": null,
|
| 714 |
+
"trial_params": null
|
| 715 |
+
}
|