File size: 2,778 Bytes
d9a8fbd 8cac699 714013b 8cac699 d9a8fbd 714013b d9a8fbd 714013b 51b74f1 8cac699 d9a8fbd 714013b d9a8fbd 714013b d9a8fbd 714013b d9a8fbd 8cac699 d9a8fbd |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.020950846091861403,
"eval_steps": 10,
"global_step": 39,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0005372011818426001,
"eval_loss": 0.18501441180706024,
"eval_runtime": 79.5189,
"eval_samples_per_second": 9.859,
"eval_steps_per_second": 4.93,
"step": 1
},
{
"epoch": 0.0026860059092130005,
"grad_norm": 0.7118232250213623,
"learning_rate": 5e-05,
"loss": 0.6911,
"step": 5
},
{
"epoch": 0.005372011818426001,
"grad_norm": 0.3719102740287781,
"learning_rate": 0.0001,
"loss": 0.6331,
"step": 10
},
{
"epoch": 0.005372011818426001,
"eval_loss": 0.1662459820508957,
"eval_runtime": 79.9488,
"eval_samples_per_second": 9.806,
"eval_steps_per_second": 4.903,
"step": 10
},
{
"epoch": 0.008058017727639,
"grad_norm": 0.5022017955780029,
"learning_rate": 9.619397662556435e-05,
"loss": 0.6189,
"step": 15
},
{
"epoch": 0.010744023636852002,
"grad_norm": 0.42121511697769165,
"learning_rate": 8.535533905932738e-05,
"loss": 0.4692,
"step": 20
},
{
"epoch": 0.010744023636852002,
"eval_loss": 0.12234125286340714,
"eval_runtime": 80.4411,
"eval_samples_per_second": 9.746,
"eval_steps_per_second": 4.873,
"step": 20
},
{
"epoch": 0.013430029546065002,
"grad_norm": 0.5769535303115845,
"learning_rate": 6.91341716182545e-05,
"loss": 0.493,
"step": 25
},
{
"epoch": 0.016116035455278,
"grad_norm": 0.3808046877384186,
"learning_rate": 5e-05,
"loss": 0.4076,
"step": 30
},
{
"epoch": 0.016116035455278,
"eval_loss": 0.10152747482061386,
"eval_runtime": 80.2919,
"eval_samples_per_second": 9.764,
"eval_steps_per_second": 4.882,
"step": 30
},
{
"epoch": 0.018802041364491002,
"grad_norm": 0.31879931688308716,
"learning_rate": 3.086582838174551e-05,
"loss": 0.3137,
"step": 35
}
],
"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": false
},
"attributes": {}
}
},
"total_flos": 6861701498535936.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|