File size: 3,240 Bytes
3f09330 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 12.0,
"eval_steps": 500,
"global_step": 15,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 1.7059780359268188,
"eval_runtime": 3.184,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 1
},
{
"epoch": 2.0,
"eval_loss": 1.552927017211914,
"eval_runtime": 3.1846,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 2
},
{
"epoch": 3.0,
"eval_loss": 1.338813304901123,
"eval_runtime": 3.1854,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 4
},
{
"epoch": 4.0,
"eval_loss": 1.2230206727981567,
"eval_runtime": 3.1854,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 5
},
{
"epoch": 5.0,
"eval_loss": 1.1060389280319214,
"eval_runtime": 3.185,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 6
},
{
"epoch": 6.0,
"eval_loss": 0.9127510190010071,
"eval_runtime": 3.1854,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 8
},
{
"epoch": 7.0,
"eval_loss": 0.8066120147705078,
"eval_runtime": 3.1857,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 9
},
{
"epoch": 8.0,
"grad_norm": 0.31343773007392883,
"learning_rate": 0.0002,
"loss": 0.3573,
"step": 10
},
{
"epoch": 8.0,
"eval_loss": 0.713127076625824,
"eval_runtime": 3.1868,
"eval_samples_per_second": 0.941,
"eval_steps_per_second": 0.941,
"step": 10
},
{
"epoch": 9.0,
"eval_loss": 0.6134043335914612,
"eval_runtime": 3.1858,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 11
},
{
"epoch": 10.0,
"eval_loss": 0.5432830452919006,
"eval_runtime": 3.1857,
"eval_samples_per_second": 0.942,
"eval_steps_per_second": 0.942,
"step": 12
},
{
"epoch": 11.0,
"eval_loss": 0.5256462693214417,
"eval_runtime": 3.1867,
"eval_samples_per_second": 0.941,
"eval_steps_per_second": 0.941,
"step": 14
},
{
"epoch": 12.0,
"eval_loss": 0.4858134686946869,
"eval_runtime": 3.1872,
"eval_samples_per_second": 0.941,
"eval_steps_per_second": 0.941,
"step": 15
}
],
"logging_steps": 10,
"max_steps": 60,
"num_input_tokens_seen": 0,
"num_train_epochs": 60,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3694308335026176.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|