File size: 3,205 Bytes
0f16cb8 61fe3ec 0f16cb8 61fe3ec 0f16cb8 2441b72 7cd4dd5 61fe3ec 0f16cb8 61fe3ec 0f16cb8 61fe3ec 0f16cb8 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0017139429257005741,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0001713942925700574,
"grad_norm": 0.6686254739761353,
"learning_rate": 2e-05,
"loss": 5.2217,
"step": 1
},
{
"epoch": 0.0001713942925700574,
"eval_loss": 1.2500425577163696,
"eval_runtime": 159.7511,
"eval_samples_per_second": 15.38,
"eval_steps_per_second": 7.693,
"step": 1
},
{
"epoch": 0.0003427885851401148,
"grad_norm": 0.4754451811313629,
"learning_rate": 4e-05,
"loss": 5.07,
"step": 2
},
{
"epoch": 0.0005141828777101723,
"grad_norm": 0.6181484460830688,
"learning_rate": 6e-05,
"loss": 4.7613,
"step": 3
},
{
"epoch": 0.0005141828777101723,
"eval_loss": 1.2496237754821777,
"eval_runtime": 159.9853,
"eval_samples_per_second": 15.358,
"eval_steps_per_second": 7.682,
"step": 3
},
{
"epoch": 0.0006855771702802296,
"grad_norm": 0.5108266472816467,
"learning_rate": 8e-05,
"loss": 4.2006,
"step": 4
},
{
"epoch": 0.0008569714628502871,
"grad_norm": 0.9380823373794556,
"learning_rate": 0.0001,
"loss": 4.482,
"step": 5
},
{
"epoch": 0.0010283657554203446,
"grad_norm": 0.6530066728591919,
"learning_rate": 0.00012,
"loss": 4.6658,
"step": 6
},
{
"epoch": 0.0010283657554203446,
"eval_loss": 1.2455629110336304,
"eval_runtime": 160.3867,
"eval_samples_per_second": 15.319,
"eval_steps_per_second": 7.663,
"step": 6
},
{
"epoch": 0.0011997600479904018,
"grad_norm": 0.6245144009590149,
"learning_rate": 0.00014,
"loss": 4.9164,
"step": 7
},
{
"epoch": 0.0013711543405604593,
"grad_norm": 0.6565183997154236,
"learning_rate": 0.00016,
"loss": 4.8597,
"step": 8
},
{
"epoch": 0.0015425486331305167,
"grad_norm": 0.7676700353622437,
"learning_rate": 0.00018,
"loss": 4.2699,
"step": 9
},
{
"epoch": 0.0015425486331305167,
"eval_loss": 1.2163201570510864,
"eval_runtime": 160.2337,
"eval_samples_per_second": 15.334,
"eval_steps_per_second": 7.67,
"step": 9
},
{
"epoch": 0.0017139429257005741,
"grad_norm": 1.026441216468811,
"learning_rate": 0.0002,
"loss": 5.0367,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 4246709207040000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|