File size: 2,945 Bytes
6f567b9 1da666b 6f567b9 1da666b 6f567b9 b5870e5 6f567b9 b5870e5 6f567b9 860d975 b5870e5 860d975 585b52c b5870e5 585b52c 1da666b 6f567b9 1da666b 6f567b9 1da666b 6f567b9 |
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": 0.022988505747126436,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0022988505747126436,
"grad_norm": NaN,
"learning_rate": 2e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.0022988505747126436,
"eval_loss": NaN,
"eval_runtime": 55.532,
"eval_samples_per_second": 3.313,
"eval_steps_per_second": 1.657,
"step": 1
},
{
"epoch": 0.004597701149425287,
"grad_norm": NaN,
"learning_rate": 4e-05,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.006896551724137931,
"grad_norm": NaN,
"learning_rate": 6e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.006896551724137931,
"eval_loss": NaN,
"eval_runtime": 54.6552,
"eval_samples_per_second": 3.367,
"eval_steps_per_second": 1.683,
"step": 3
},
{
"epoch": 0.009195402298850575,
"grad_norm": NaN,
"learning_rate": 8e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 0.011494252873563218,
"grad_norm": NaN,
"learning_rate": 0.0001,
"loss": 0.0,
"step": 5
},
{
"epoch": 0.013793103448275862,
"grad_norm": NaN,
"learning_rate": 0.00012,
"loss": 0.0,
"step": 6
},
{
"epoch": 0.013793103448275862,
"eval_loss": NaN,
"eval_runtime": 54.5301,
"eval_samples_per_second": 3.374,
"eval_steps_per_second": 1.687,
"step": 6
},
{
"epoch": 0.016091954022988506,
"grad_norm": NaN,
"learning_rate": 0.00014,
"loss": 0.0,
"step": 7
},
{
"epoch": 0.01839080459770115,
"grad_norm": NaN,
"learning_rate": 0.00016,
"loss": 0.0,
"step": 8
},
{
"epoch": 0.020689655172413793,
"grad_norm": NaN,
"learning_rate": 0.00018,
"loss": 0.0,
"step": 9
},
{
"epoch": 0.020689655172413793,
"eval_loss": NaN,
"eval_runtime": 41.0679,
"eval_samples_per_second": 4.48,
"eval_steps_per_second": 2.24,
"step": 9
},
{
"epoch": 0.022988505747126436,
"grad_norm": NaN,
"learning_rate": 0.0002,
"loss": 0.0,
"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": 720954300825600.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|