File size: 3,711 Bytes
82615f0 e730a4f 551973a e730a4f 82615f0 551973a 82615f0 551973a c615dc9 0be4ca3 e730a4f 82615f0 551973a 82615f0 551973a 82615f0 e730a4f 82615f0 e730a4f 82615f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06587615283267458,
"eval_steps": 10,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0013175230566534915,
"eval_loss": 2.429551601409912,
"eval_runtime": 34.1229,
"eval_samples_per_second": 9.378,
"eval_steps_per_second": 4.689,
"step": 1
},
{
"epoch": 0.006587615283267457,
"grad_norm": 1.0831778049468994,
"learning_rate": 5e-05,
"loss": 2.1113,
"step": 5
},
{
"epoch": 0.013175230566534914,
"grad_norm": 0.8124720454216003,
"learning_rate": 0.0001,
"loss": 1.9417,
"step": 10
},
{
"epoch": 0.013175230566534914,
"eval_loss": 1.9890544414520264,
"eval_runtime": 34.7293,
"eval_samples_per_second": 9.214,
"eval_steps_per_second": 4.607,
"step": 10
},
{
"epoch": 0.019762845849802372,
"grad_norm": 0.7260387539863586,
"learning_rate": 9.619397662556435e-05,
"loss": 1.5863,
"step": 15
},
{
"epoch": 0.026350461133069828,
"grad_norm": 0.6288080811500549,
"learning_rate": 8.535533905932738e-05,
"loss": 1.4501,
"step": 20
},
{
"epoch": 0.026350461133069828,
"eval_loss": 1.3593571186065674,
"eval_runtime": 34.6864,
"eval_samples_per_second": 9.226,
"eval_steps_per_second": 4.613,
"step": 20
},
{
"epoch": 0.03293807641633729,
"grad_norm": 0.6772316694259644,
"learning_rate": 6.91341716182545e-05,
"loss": 1.2137,
"step": 25
},
{
"epoch": 0.039525691699604744,
"grad_norm": 0.6072627902030945,
"learning_rate": 5e-05,
"loss": 1.1616,
"step": 30
},
{
"epoch": 0.039525691699604744,
"eval_loss": 1.1616449356079102,
"eval_runtime": 34.7532,
"eval_samples_per_second": 9.208,
"eval_steps_per_second": 4.604,
"step": 30
},
{
"epoch": 0.0461133069828722,
"grad_norm": 0.6614992618560791,
"learning_rate": 3.086582838174551e-05,
"loss": 1.0897,
"step": 35
},
{
"epoch": 0.052700922266139656,
"grad_norm": 0.5868863463401794,
"learning_rate": 1.4644660940672627e-05,
"loss": 1.0003,
"step": 40
},
{
"epoch": 0.052700922266139656,
"eval_loss": 1.061147928237915,
"eval_runtime": 34.8273,
"eval_samples_per_second": 9.188,
"eval_steps_per_second": 4.594,
"step": 40
},
{
"epoch": 0.05928853754940711,
"grad_norm": 0.5653367638587952,
"learning_rate": 3.8060233744356633e-06,
"loss": 1.0647,
"step": 45
},
{
"epoch": 0.06587615283267458,
"grad_norm": 0.5659787654876709,
"learning_rate": 0.0,
"loss": 1.1004,
"step": 50
},
{
"epoch": 0.06587615283267458,
"eval_loss": 1.0537097454071045,
"eval_runtime": 34.7012,
"eval_samples_per_second": 9.222,
"eval_steps_per_second": 4.611,
"step": 50
}
],
"logging_steps": 5,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.64316422602752e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|