File size: 3,170 Bytes
b0396aa b093718 b0396aa b093718 b0396aa b8ff451 ed74fc4 b093718 b0396aa b093718 b0396aa b093718 b0396aa |
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": 0.030534351145038167,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0030534351145038168,
"grad_norm": 7.624812602996826,
"learning_rate": 2e-05,
"loss": 3.721,
"step": 1
},
{
"epoch": 0.0030534351145038168,
"eval_loss": 2.613229513168335,
"eval_runtime": 18.2389,
"eval_samples_per_second": 7.566,
"eval_steps_per_second": 3.783,
"step": 1
},
{
"epoch": 0.0061068702290076335,
"grad_norm": 2.746663808822632,
"learning_rate": 4e-05,
"loss": 2.0161,
"step": 2
},
{
"epoch": 0.00916030534351145,
"grad_norm": 1.5935509204864502,
"learning_rate": 6e-05,
"loss": 2.4389,
"step": 3
},
{
"epoch": 0.00916030534351145,
"eval_loss": 2.592705726623535,
"eval_runtime": 18.95,
"eval_samples_per_second": 7.282,
"eval_steps_per_second": 3.641,
"step": 3
},
{
"epoch": 0.012213740458015267,
"grad_norm": 1.3037679195404053,
"learning_rate": 8e-05,
"loss": 2.2116,
"step": 4
},
{
"epoch": 0.015267175572519083,
"grad_norm": 1.0085657835006714,
"learning_rate": 0.0001,
"loss": 1.9184,
"step": 5
},
{
"epoch": 0.0183206106870229,
"grad_norm": 4.906698226928711,
"learning_rate": 0.00012,
"loss": 2.8942,
"step": 6
},
{
"epoch": 0.0183206106870229,
"eval_loss": 2.3518502712249756,
"eval_runtime": 19.535,
"eval_samples_per_second": 7.064,
"eval_steps_per_second": 3.532,
"step": 6
},
{
"epoch": 0.021374045801526718,
"grad_norm": 6.759243965148926,
"learning_rate": 0.00014,
"loss": 2.655,
"step": 7
},
{
"epoch": 0.024427480916030534,
"grad_norm": 0.7865249514579773,
"learning_rate": 0.00016,
"loss": 2.0324,
"step": 8
},
{
"epoch": 0.02748091603053435,
"grad_norm": 1.0031616687774658,
"learning_rate": 0.00018,
"loss": 1.7614,
"step": 9
},
{
"epoch": 0.02748091603053435,
"eval_loss": 2.113194227218628,
"eval_runtime": 19.745,
"eval_samples_per_second": 6.989,
"eval_steps_per_second": 3.495,
"step": 9
},
{
"epoch": 0.030534351145038167,
"grad_norm": 1.1229645013809204,
"learning_rate": 0.0002,
"loss": 1.9255,
"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": 2052393617326080.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|