Commit
•
2c33eb6
1
Parent(s):
0e7ce8d
Upload trainer_state.json
Browse files- trainer_state.json +814 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,814 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.757429718875502,
|
| 3 |
+
"best_model_checkpoint": "./results_small_seed2CasedUnstripped/checkpoint-19000",
|
| 4 |
+
"epoch": 0.7741199478487614,
|
| 5 |
+
"global_step": 19000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 1.0183299389002038e-05,
|
| 13 |
+
"loss": 1.0885,
|
| 14 |
+
"step": 250
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 2.0366598778004075e-05,
|
| 19 |
+
"loss": 0.9616,
|
| 20 |
+
"step": 500
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"eval_accuracy": 0.6345381526104418,
|
| 25 |
+
"eval_loss": 0.8497252464294434,
|
| 26 |
+
"eval_runtime": 4.8371,
|
| 27 |
+
"eval_samples_per_second": 514.77,
|
| 28 |
+
"eval_steps_per_second": 16.125,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.03,
|
| 33 |
+
"learning_rate": 3.0549898167006117e-05,
|
| 34 |
+
"loss": 0.8224,
|
| 35 |
+
"step": 750
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.04,
|
| 39 |
+
"learning_rate": 4.073319755600815e-05,
|
| 40 |
+
"loss": 0.7802,
|
| 41 |
+
"step": 1000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.04,
|
| 45 |
+
"eval_accuracy": 0.6522088353413654,
|
| 46 |
+
"eval_loss": 0.8134140968322754,
|
| 47 |
+
"eval_runtime": 4.8807,
|
| 48 |
+
"eval_samples_per_second": 510.173,
|
| 49 |
+
"eval_steps_per_second": 15.981,
|
| 50 |
+
"step": 1000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.05,
|
| 54 |
+
"learning_rate": 5.0916496945010185e-05,
|
| 55 |
+
"loss": 0.7951,
|
| 56 |
+
"step": 1250
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.06,
|
| 60 |
+
"learning_rate": 6.109979633401223e-05,
|
| 61 |
+
"loss": 0.7652,
|
| 62 |
+
"step": 1500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.06,
|
| 66 |
+
"eval_accuracy": 0.6859437751004016,
|
| 67 |
+
"eval_loss": 0.762012243270874,
|
| 68 |
+
"eval_runtime": 4.8074,
|
| 69 |
+
"eval_samples_per_second": 517.952,
|
| 70 |
+
"eval_steps_per_second": 16.225,
|
| 71 |
+
"step": 1500
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.07,
|
| 75 |
+
"learning_rate": 7.128309572301426e-05,
|
| 76 |
+
"loss": 0.758,
|
| 77 |
+
"step": 1750
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.08,
|
| 81 |
+
"learning_rate": 8.14663951120163e-05,
|
| 82 |
+
"loss": 0.7811,
|
| 83 |
+
"step": 2000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.08,
|
| 87 |
+
"eval_accuracy": 0.6746987951807228,
|
| 88 |
+
"eval_loss": 0.7685323357582092,
|
| 89 |
+
"eval_runtime": 4.7928,
|
| 90 |
+
"eval_samples_per_second": 519.528,
|
| 91 |
+
"eval_steps_per_second": 16.274,
|
| 92 |
+
"step": 2000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.09,
|
| 96 |
+
"learning_rate": 9.164969450101833e-05,
|
| 97 |
+
"loss": 0.7824,
|
| 98 |
+
"step": 2250
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.1,
|
| 102 |
+
"learning_rate": 9.979627869075105e-05,
|
| 103 |
+
"loss": 0.81,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.1,
|
| 108 |
+
"eval_accuracy": 0.6481927710843374,
|
| 109 |
+
"eval_loss": 0.7982615232467651,
|
| 110 |
+
"eval_runtime": 4.802,
|
| 111 |
+
"eval_samples_per_second": 518.539,
|
| 112 |
+
"eval_steps_per_second": 16.243,
|
| 113 |
+
"step": 2500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.11,
|
| 117 |
+
"learning_rate": 9.866449363936802e-05,
|
| 118 |
+
"loss": 0.791,
|
| 119 |
+
"step": 2750
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.12,
|
| 123 |
+
"learning_rate": 9.753270858798497e-05,
|
| 124 |
+
"loss": 0.793,
|
| 125 |
+
"step": 3000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.12,
|
| 129 |
+
"eval_accuracy": 0.6365461847389559,
|
| 130 |
+
"eval_loss": 0.8263759016990662,
|
| 131 |
+
"eval_runtime": 4.8663,
|
| 132 |
+
"eval_samples_per_second": 511.678,
|
| 133 |
+
"eval_steps_per_second": 16.028,
|
| 134 |
+
"step": 3000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.13,
|
| 138 |
+
"learning_rate": 9.640092353660193e-05,
|
| 139 |
+
"loss": 0.785,
|
| 140 |
+
"step": 3250
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.14,
|
| 144 |
+
"learning_rate": 9.526913848521888e-05,
|
| 145 |
+
"loss": 0.7876,
|
| 146 |
+
"step": 3500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.14,
|
| 150 |
+
"eval_accuracy": 0.6598393574297189,
|
| 151 |
+
"eval_loss": 0.7989997267723083,
|
| 152 |
+
"eval_runtime": 4.7903,
|
| 153 |
+
"eval_samples_per_second": 519.799,
|
| 154 |
+
"eval_steps_per_second": 16.283,
|
| 155 |
+
"step": 3500
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.15,
|
| 159 |
+
"learning_rate": 9.413735343383585e-05,
|
| 160 |
+
"loss": 0.7866,
|
| 161 |
+
"step": 3750
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.16,
|
| 165 |
+
"learning_rate": 9.30055683824528e-05,
|
| 166 |
+
"loss": 0.7799,
|
| 167 |
+
"step": 4000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.16,
|
| 171 |
+
"eval_accuracy": 0.6718875502008033,
|
| 172 |
+
"eval_loss": 0.7617995142936707,
|
| 173 |
+
"eval_runtime": 4.8098,
|
| 174 |
+
"eval_samples_per_second": 517.691,
|
| 175 |
+
"eval_steps_per_second": 16.217,
|
| 176 |
+
"step": 4000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.17,
|
| 180 |
+
"learning_rate": 9.187378333106976e-05,
|
| 181 |
+
"loss": 0.7699,
|
| 182 |
+
"step": 4250
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.18,
|
| 186 |
+
"learning_rate": 9.074199827968673e-05,
|
| 187 |
+
"loss": 0.7487,
|
| 188 |
+
"step": 4500
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.18,
|
| 192 |
+
"eval_accuracy": 0.6767068273092369,
|
| 193 |
+
"eval_loss": 0.7875193357467651,
|
| 194 |
+
"eval_runtime": 4.8759,
|
| 195 |
+
"eval_samples_per_second": 510.674,
|
| 196 |
+
"eval_steps_per_second": 15.997,
|
| 197 |
+
"step": 4500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.19,
|
| 201 |
+
"learning_rate": 8.961021322830368e-05,
|
| 202 |
+
"loss": 0.7532,
|
| 203 |
+
"step": 4750
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.2,
|
| 207 |
+
"learning_rate": 8.847842817692065e-05,
|
| 208 |
+
"loss": 0.7375,
|
| 209 |
+
"step": 5000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.2,
|
| 213 |
+
"eval_accuracy": 0.6726907630522089,
|
| 214 |
+
"eval_loss": 0.7819647789001465,
|
| 215 |
+
"eval_runtime": 4.7823,
|
| 216 |
+
"eval_samples_per_second": 520.672,
|
| 217 |
+
"eval_steps_per_second": 16.31,
|
| 218 |
+
"step": 5000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.21,
|
| 222 |
+
"learning_rate": 8.73466431255376e-05,
|
| 223 |
+
"loss": 0.7374,
|
| 224 |
+
"step": 5250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.22,
|
| 228 |
+
"learning_rate": 8.621485807415456e-05,
|
| 229 |
+
"loss": 0.7674,
|
| 230 |
+
"step": 5500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.22,
|
| 234 |
+
"eval_accuracy": 0.6751004016064257,
|
| 235 |
+
"eval_loss": 0.7469549179077148,
|
| 236 |
+
"eval_runtime": 4.7908,
|
| 237 |
+
"eval_samples_per_second": 519.751,
|
| 238 |
+
"eval_steps_per_second": 16.281,
|
| 239 |
+
"step": 5500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.23,
|
| 243 |
+
"learning_rate": 8.508307302277152e-05,
|
| 244 |
+
"loss": 0.7531,
|
| 245 |
+
"step": 5750
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.24,
|
| 249 |
+
"learning_rate": 8.395128797138848e-05,
|
| 250 |
+
"loss": 0.74,
|
| 251 |
+
"step": 6000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.24,
|
| 255 |
+
"eval_accuracy": 0.6763052208835342,
|
| 256 |
+
"eval_loss": 0.7755768895149231,
|
| 257 |
+
"eval_runtime": 4.7885,
|
| 258 |
+
"eval_samples_per_second": 519.996,
|
| 259 |
+
"eval_steps_per_second": 16.289,
|
| 260 |
+
"step": 6000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.25,
|
| 264 |
+
"learning_rate": 8.281950292000543e-05,
|
| 265 |
+
"loss": 0.7448,
|
| 266 |
+
"step": 6250
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.26,
|
| 270 |
+
"learning_rate": 8.16877178686224e-05,
|
| 271 |
+
"loss": 0.7444,
|
| 272 |
+
"step": 6500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.26,
|
| 276 |
+
"eval_accuracy": 0.6775100401606425,
|
| 277 |
+
"eval_loss": 0.7682979702949524,
|
| 278 |
+
"eval_runtime": 4.7945,
|
| 279 |
+
"eval_samples_per_second": 519.348,
|
| 280 |
+
"eval_steps_per_second": 16.269,
|
| 281 |
+
"step": 6500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.28,
|
| 285 |
+
"learning_rate": 8.055593281723935e-05,
|
| 286 |
+
"loss": 0.7326,
|
| 287 |
+
"step": 6750
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.29,
|
| 291 |
+
"learning_rate": 7.942414776585632e-05,
|
| 292 |
+
"loss": 0.7431,
|
| 293 |
+
"step": 7000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.29,
|
| 297 |
+
"eval_accuracy": 0.6783132530120481,
|
| 298 |
+
"eval_loss": 0.7539064288139343,
|
| 299 |
+
"eval_runtime": 4.7996,
|
| 300 |
+
"eval_samples_per_second": 518.797,
|
| 301 |
+
"eval_steps_per_second": 16.251,
|
| 302 |
+
"step": 7000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3,
|
| 306 |
+
"learning_rate": 7.829236271447327e-05,
|
| 307 |
+
"loss": 0.7284,
|
| 308 |
+
"step": 7250
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.31,
|
| 312 |
+
"learning_rate": 7.716057766309023e-05,
|
| 313 |
+
"loss": 0.7155,
|
| 314 |
+
"step": 7500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.31,
|
| 318 |
+
"eval_accuracy": 0.6827309236947792,
|
| 319 |
+
"eval_loss": 0.7247231602668762,
|
| 320 |
+
"eval_runtime": 4.7845,
|
| 321 |
+
"eval_samples_per_second": 520.426,
|
| 322 |
+
"eval_steps_per_second": 16.302,
|
| 323 |
+
"step": 7500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.32,
|
| 327 |
+
"learning_rate": 7.60287926117072e-05,
|
| 328 |
+
"loss": 0.7499,
|
| 329 |
+
"step": 7750
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.33,
|
| 333 |
+
"learning_rate": 7.489700756032415e-05,
|
| 334 |
+
"loss": 0.7087,
|
| 335 |
+
"step": 8000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.33,
|
| 339 |
+
"eval_accuracy": 0.7116465863453815,
|
| 340 |
+
"eval_loss": 0.7027077674865723,
|
| 341 |
+
"eval_runtime": 4.7959,
|
| 342 |
+
"eval_samples_per_second": 519.195,
|
| 343 |
+
"eval_steps_per_second": 16.264,
|
| 344 |
+
"step": 8000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.34,
|
| 348 |
+
"learning_rate": 7.37652225089411e-05,
|
| 349 |
+
"loss": 0.7144,
|
| 350 |
+
"step": 8250
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.35,
|
| 354 |
+
"learning_rate": 7.263343745755806e-05,
|
| 355 |
+
"loss": 0.719,
|
| 356 |
+
"step": 8500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.35,
|
| 360 |
+
"eval_accuracy": 0.7004016064257028,
|
| 361 |
+
"eval_loss": 0.73233962059021,
|
| 362 |
+
"eval_runtime": 4.8318,
|
| 363 |
+
"eval_samples_per_second": 515.339,
|
| 364 |
+
"eval_steps_per_second": 16.143,
|
| 365 |
+
"step": 8500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.36,
|
| 369 |
+
"learning_rate": 7.150165240617503e-05,
|
| 370 |
+
"loss": 0.7301,
|
| 371 |
+
"step": 8750
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.37,
|
| 375 |
+
"learning_rate": 7.036986735479198e-05,
|
| 376 |
+
"loss": 0.7225,
|
| 377 |
+
"step": 9000
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.37,
|
| 381 |
+
"eval_accuracy": 0.7156626506024096,
|
| 382 |
+
"eval_loss": 0.7080035209655762,
|
| 383 |
+
"eval_runtime": 4.8777,
|
| 384 |
+
"eval_samples_per_second": 510.486,
|
| 385 |
+
"eval_steps_per_second": 15.991,
|
| 386 |
+
"step": 9000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.38,
|
| 390 |
+
"learning_rate": 6.923808230340894e-05,
|
| 391 |
+
"loss": 0.7216,
|
| 392 |
+
"step": 9250
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.39,
|
| 396 |
+
"learning_rate": 6.810629725202589e-05,
|
| 397 |
+
"loss": 0.707,
|
| 398 |
+
"step": 9500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.39,
|
| 402 |
+
"eval_accuracy": 0.7004016064257028,
|
| 403 |
+
"eval_loss": 0.7323043942451477,
|
| 404 |
+
"eval_runtime": 4.9132,
|
| 405 |
+
"eval_samples_per_second": 506.797,
|
| 406 |
+
"eval_steps_per_second": 15.876,
|
| 407 |
+
"step": 9500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.4,
|
| 411 |
+
"learning_rate": 6.697451220064286e-05,
|
| 412 |
+
"loss": 0.7133,
|
| 413 |
+
"step": 9750
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.41,
|
| 417 |
+
"learning_rate": 6.584272714925982e-05,
|
| 418 |
+
"loss": 0.6908,
|
| 419 |
+
"step": 10000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.41,
|
| 423 |
+
"eval_accuracy": 0.706425702811245,
|
| 424 |
+
"eval_loss": 0.7354196310043335,
|
| 425 |
+
"eval_runtime": 4.8275,
|
| 426 |
+
"eval_samples_per_second": 515.794,
|
| 427 |
+
"eval_steps_per_second": 16.157,
|
| 428 |
+
"step": 10000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.42,
|
| 432 |
+
"learning_rate": 6.471094209787677e-05,
|
| 433 |
+
"loss": 0.7053,
|
| 434 |
+
"step": 10250
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.43,
|
| 438 |
+
"learning_rate": 6.357915704649372e-05,
|
| 439 |
+
"loss": 0.705,
|
| 440 |
+
"step": 10500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.43,
|
| 444 |
+
"eval_accuracy": 0.7261044176706827,
|
| 445 |
+
"eval_loss": 0.6736636161804199,
|
| 446 |
+
"eval_runtime": 4.8326,
|
| 447 |
+
"eval_samples_per_second": 515.256,
|
| 448 |
+
"eval_steps_per_second": 16.141,
|
| 449 |
+
"step": 10500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.44,
|
| 453 |
+
"learning_rate": 6.24473719951107e-05,
|
| 454 |
+
"loss": 0.7213,
|
| 455 |
+
"step": 10750
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.45,
|
| 459 |
+
"learning_rate": 6.131558694372765e-05,
|
| 460 |
+
"loss": 0.6961,
|
| 461 |
+
"step": 11000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.45,
|
| 465 |
+
"eval_accuracy": 0.7208835341365462,
|
| 466 |
+
"eval_loss": 0.6973076462745667,
|
| 467 |
+
"eval_runtime": 4.901,
|
| 468 |
+
"eval_samples_per_second": 508.056,
|
| 469 |
+
"eval_steps_per_second": 15.915,
|
| 470 |
+
"step": 11000
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.46,
|
| 474 |
+
"learning_rate": 6.01838018923446e-05,
|
| 475 |
+
"loss": 0.7029,
|
| 476 |
+
"step": 11250
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.47,
|
| 480 |
+
"learning_rate": 5.9052016840961564e-05,
|
| 481 |
+
"loss": 0.6842,
|
| 482 |
+
"step": 11500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.47,
|
| 486 |
+
"eval_accuracy": 0.6855421686746987,
|
| 487 |
+
"eval_loss": 0.7288179993629456,
|
| 488 |
+
"eval_runtime": 4.8248,
|
| 489 |
+
"eval_samples_per_second": 516.079,
|
| 490 |
+
"eval_steps_per_second": 16.166,
|
| 491 |
+
"step": 11500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.48,
|
| 495 |
+
"learning_rate": 5.7920231789578526e-05,
|
| 496 |
+
"loss": 0.6894,
|
| 497 |
+
"step": 11750
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.49,
|
| 501 |
+
"learning_rate": 5.678844673819549e-05,
|
| 502 |
+
"loss": 0.6879,
|
| 503 |
+
"step": 12000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.49,
|
| 507 |
+
"eval_accuracy": 0.7204819277108434,
|
| 508 |
+
"eval_loss": 0.6706427931785583,
|
| 509 |
+
"eval_runtime": 4.816,
|
| 510 |
+
"eval_samples_per_second": 517.027,
|
| 511 |
+
"eval_steps_per_second": 16.196,
|
| 512 |
+
"step": 12000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.5,
|
| 516 |
+
"learning_rate": 5.565666168681244e-05,
|
| 517 |
+
"loss": 0.6962,
|
| 518 |
+
"step": 12250
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.51,
|
| 522 |
+
"learning_rate": 5.4524876635429404e-05,
|
| 523 |
+
"loss": 0.6782,
|
| 524 |
+
"step": 12500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.51,
|
| 528 |
+
"eval_accuracy": 0.7172690763052209,
|
| 529 |
+
"eval_loss": 0.6858745813369751,
|
| 530 |
+
"eval_runtime": 4.8781,
|
| 531 |
+
"eval_samples_per_second": 510.448,
|
| 532 |
+
"eval_steps_per_second": 15.99,
|
| 533 |
+
"step": 12500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.52,
|
| 537 |
+
"learning_rate": 5.339309158404636e-05,
|
| 538 |
+
"loss": 0.6871,
|
| 539 |
+
"step": 12750
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.53,
|
| 543 |
+
"learning_rate": 5.226130653266332e-05,
|
| 544 |
+
"loss": 0.6606,
|
| 545 |
+
"step": 13000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.53,
|
| 549 |
+
"eval_accuracy": 0.7244979919678715,
|
| 550 |
+
"eval_loss": 0.6812068819999695,
|
| 551 |
+
"eval_runtime": 4.8174,
|
| 552 |
+
"eval_samples_per_second": 516.876,
|
| 553 |
+
"eval_steps_per_second": 16.191,
|
| 554 |
+
"step": 13000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.54,
|
| 558 |
+
"learning_rate": 5.1129521481280275e-05,
|
| 559 |
+
"loss": 0.6948,
|
| 560 |
+
"step": 13250
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.55,
|
| 564 |
+
"learning_rate": 4.9997736429897236e-05,
|
| 565 |
+
"loss": 0.6752,
|
| 566 |
+
"step": 13500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.55,
|
| 570 |
+
"eval_accuracy": 0.7321285140562249,
|
| 571 |
+
"eval_loss": 0.6839885115623474,
|
| 572 |
+
"eval_runtime": 4.8713,
|
| 573 |
+
"eval_samples_per_second": 511.155,
|
| 574 |
+
"eval_steps_per_second": 16.012,
|
| 575 |
+
"step": 13500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.56,
|
| 579 |
+
"learning_rate": 4.88659513785142e-05,
|
| 580 |
+
"loss": 0.6692,
|
| 581 |
+
"step": 13750
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.57,
|
| 585 |
+
"learning_rate": 4.773416632713115e-05,
|
| 586 |
+
"loss": 0.6502,
|
| 587 |
+
"step": 14000
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.57,
|
| 591 |
+
"eval_accuracy": 0.7240963855421687,
|
| 592 |
+
"eval_loss": 0.6590266823768616,
|
| 593 |
+
"eval_runtime": 4.9174,
|
| 594 |
+
"eval_samples_per_second": 506.361,
|
| 595 |
+
"eval_steps_per_second": 15.862,
|
| 596 |
+
"step": 14000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.58,
|
| 600 |
+
"learning_rate": 4.6602381275748114e-05,
|
| 601 |
+
"loss": 0.6626,
|
| 602 |
+
"step": 14250
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.59,
|
| 606 |
+
"learning_rate": 4.547059622436507e-05,
|
| 607 |
+
"loss": 0.6677,
|
| 608 |
+
"step": 14500
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.59,
|
| 612 |
+
"eval_accuracy": 0.7289156626506024,
|
| 613 |
+
"eval_loss": 0.6861540079116821,
|
| 614 |
+
"eval_runtime": 4.8286,
|
| 615 |
+
"eval_samples_per_second": 515.672,
|
| 616 |
+
"eval_steps_per_second": 16.154,
|
| 617 |
+
"step": 14500
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.6,
|
| 621 |
+
"learning_rate": 4.433881117298203e-05,
|
| 622 |
+
"loss": 0.6559,
|
| 623 |
+
"step": 14750
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.61,
|
| 627 |
+
"learning_rate": 4.3207026121598985e-05,
|
| 628 |
+
"loss": 0.6694,
|
| 629 |
+
"step": 15000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.61,
|
| 633 |
+
"eval_accuracy": 0.7261044176706827,
|
| 634 |
+
"eval_loss": 0.6638771891593933,
|
| 635 |
+
"eval_runtime": 4.8259,
|
| 636 |
+
"eval_samples_per_second": 515.971,
|
| 637 |
+
"eval_steps_per_second": 16.163,
|
| 638 |
+
"step": 15000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.62,
|
| 642 |
+
"learning_rate": 4.207524107021595e-05,
|
| 643 |
+
"loss": 0.6623,
|
| 644 |
+
"step": 15250
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.63,
|
| 648 |
+
"learning_rate": 4.09434560188329e-05,
|
| 649 |
+
"loss": 0.6653,
|
| 650 |
+
"step": 15500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.63,
|
| 654 |
+
"eval_accuracy": 0.7128514056224899,
|
| 655 |
+
"eval_loss": 0.6940041184425354,
|
| 656 |
+
"eval_runtime": 4.9313,
|
| 657 |
+
"eval_samples_per_second": 504.94,
|
| 658 |
+
"eval_steps_per_second": 15.817,
|
| 659 |
+
"step": 15500
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.64,
|
| 663 |
+
"learning_rate": 3.981167096744986e-05,
|
| 664 |
+
"loss": 0.6343,
|
| 665 |
+
"step": 15750
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.65,
|
| 669 |
+
"learning_rate": 3.8679885916066825e-05,
|
| 670 |
+
"loss": 0.6636,
|
| 671 |
+
"step": 16000
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.65,
|
| 675 |
+
"eval_accuracy": 0.7397590361445783,
|
| 676 |
+
"eval_loss": 0.6664681434631348,
|
| 677 |
+
"eval_runtime": 4.8293,
|
| 678 |
+
"eval_samples_per_second": 515.605,
|
| 679 |
+
"eval_steps_per_second": 16.151,
|
| 680 |
+
"step": 16000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.66,
|
| 684 |
+
"learning_rate": 3.754810086468378e-05,
|
| 685 |
+
"loss": 0.6591,
|
| 686 |
+
"step": 16250
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.67,
|
| 690 |
+
"learning_rate": 3.641631581330074e-05,
|
| 691 |
+
"loss": 0.6394,
|
| 692 |
+
"step": 16500
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.67,
|
| 696 |
+
"eval_accuracy": 0.7441767068273092,
|
| 697 |
+
"eval_loss": 0.6528923511505127,
|
| 698 |
+
"eval_runtime": 4.8454,
|
| 699 |
+
"eval_samples_per_second": 513.891,
|
| 700 |
+
"eval_steps_per_second": 16.098,
|
| 701 |
+
"step": 16500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.68,
|
| 705 |
+
"learning_rate": 3.52845307619177e-05,
|
| 706 |
+
"loss": 0.6483,
|
| 707 |
+
"step": 16750
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.69,
|
| 711 |
+
"learning_rate": 3.415274571053466e-05,
|
| 712 |
+
"loss": 0.6545,
|
| 713 |
+
"step": 17000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.69,
|
| 717 |
+
"eval_accuracy": 0.7365461847389558,
|
| 718 |
+
"eval_loss": 0.6435971260070801,
|
| 719 |
+
"eval_runtime": 4.8617,
|
| 720 |
+
"eval_samples_per_second": 512.163,
|
| 721 |
+
"eval_steps_per_second": 16.044,
|
| 722 |
+
"step": 17000
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.7,
|
| 726 |
+
"learning_rate": 3.302096065915162e-05,
|
| 727 |
+
"loss": 0.6298,
|
| 728 |
+
"step": 17250
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.71,
|
| 732 |
+
"learning_rate": 3.1889175607768574e-05,
|
| 733 |
+
"loss": 0.6377,
|
| 734 |
+
"step": 17500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.71,
|
| 738 |
+
"eval_accuracy": 0.738152610441767,
|
| 739 |
+
"eval_loss": 0.6470540165901184,
|
| 740 |
+
"eval_runtime": 4.8301,
|
| 741 |
+
"eval_samples_per_second": 515.517,
|
| 742 |
+
"eval_steps_per_second": 16.149,
|
| 743 |
+
"step": 17500
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.72,
|
| 747 |
+
"learning_rate": 3.0757390556385535e-05,
|
| 748 |
+
"loss": 0.6441,
|
| 749 |
+
"step": 17750
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.73,
|
| 753 |
+
"learning_rate": 2.962560550500249e-05,
|
| 754 |
+
"loss": 0.6305,
|
| 755 |
+
"step": 18000
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.73,
|
| 759 |
+
"eval_accuracy": 0.7248995983935743,
|
| 760 |
+
"eval_loss": 0.6817350387573242,
|
| 761 |
+
"eval_runtime": 4.833,
|
| 762 |
+
"eval_samples_per_second": 515.206,
|
| 763 |
+
"eval_steps_per_second": 16.139,
|
| 764 |
+
"step": 18000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.74,
|
| 768 |
+
"learning_rate": 2.849382045361945e-05,
|
| 769 |
+
"loss": 0.62,
|
| 770 |
+
"step": 18250
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.75,
|
| 774 |
+
"learning_rate": 2.7362035402236406e-05,
|
| 775 |
+
"loss": 0.6345,
|
| 776 |
+
"step": 18500
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.75,
|
| 780 |
+
"eval_accuracy": 0.7493975903614458,
|
| 781 |
+
"eval_loss": 0.6382141709327698,
|
| 782 |
+
"eval_runtime": 4.8844,
|
| 783 |
+
"eval_samples_per_second": 509.786,
|
| 784 |
+
"eval_steps_per_second": 15.969,
|
| 785 |
+
"step": 18500
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.76,
|
| 789 |
+
"learning_rate": 2.6230250350853368e-05,
|
| 790 |
+
"loss": 0.6236,
|
| 791 |
+
"step": 18750
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.77,
|
| 795 |
+
"learning_rate": 2.5098465299470326e-05,
|
| 796 |
+
"loss": 0.62,
|
| 797 |
+
"step": 19000
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.77,
|
| 801 |
+
"eval_accuracy": 0.757429718875502,
|
| 802 |
+
"eval_loss": 0.6400189399719238,
|
| 803 |
+
"eval_runtime": 4.8308,
|
| 804 |
+
"eval_samples_per_second": 515.438,
|
| 805 |
+
"eval_steps_per_second": 16.146,
|
| 806 |
+
"step": 19000
|
| 807 |
+
}
|
| 808 |
+
],
|
| 809 |
+
"max_steps": 24544,
|
| 810 |
+
"num_train_epochs": 1,
|
| 811 |
+
"total_flos": 1.1363112060596352e+16,
|
| 812 |
+
"trial_name": null,
|
| 813 |
+
"trial_params": null
|
| 814 |
+
}
|