File size: 2,941 Bytes
6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 9a6a790 6c21a39 |
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 |
{
"best_metric": 0.7901376146788991,
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-2108",
"epoch": 5.0,
"eval_steps": 500,
"global_step": 2635,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 5.95961856842041,
"learning_rate": 9.55389368279823e-06,
"loss": 1.5369,
"step": 527
},
{
"epoch": 1.0,
"eval_accuracy": 0.7339449541284404,
"eval_loss": 1.2773902416229248,
"eval_runtime": 2.5957,
"eval_samples_per_second": 335.939,
"eval_steps_per_second": 2.697,
"step": 527
},
{
"epoch": 2.0,
"grad_norm": 15.252978324890137,
"learning_rate": 8.492349940265094e-06,
"loss": 1.2159,
"step": 1054
},
{
"epoch": 2.0,
"eval_accuracy": 0.7786697247706422,
"eval_loss": 1.022659182548523,
"eval_runtime": 2.5741,
"eval_samples_per_second": 338.753,
"eval_steps_per_second": 2.719,
"step": 1054
},
{
"epoch": 3.0,
"grad_norm": 18.01114845275879,
"learning_rate": 7.430806197731956e-06,
"loss": 1.0132,
"step": 1581
},
{
"epoch": 3.0,
"eval_accuracy": 0.7844036697247706,
"eval_loss": 0.9622328281402588,
"eval_runtime": 2.5865,
"eval_samples_per_second": 337.137,
"eval_steps_per_second": 2.706,
"step": 1581
},
{
"epoch": 4.0,
"grad_norm": 15.912079811096191,
"learning_rate": 6.371276769700781e-06,
"loss": 0.9206,
"step": 2108
},
{
"epoch": 4.0,
"eval_accuracy": 0.7901376146788991,
"eval_loss": 0.9278557896614075,
"eval_runtime": 2.5808,
"eval_samples_per_second": 337.878,
"eval_steps_per_second": 2.712,
"step": 2108
},
{
"epoch": 5.0,
"grad_norm": 10.149016380310059,
"learning_rate": 5.3097330271676446e-06,
"loss": 0.8564,
"step": 2635
},
{
"epoch": 5.0,
"eval_accuracy": 0.7901376146788991,
"eval_loss": 0.9079629182815552,
"eval_runtime": 2.5658,
"eval_samples_per_second": 339.852,
"eval_steps_per_second": 2.728,
"step": 2635
}
],
"logging_steps": 500,
"max_steps": 5270,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"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": 40447180739880.0,
"train_batch_size": 128,
"trial_name": null,
"trial_params": {
"alpha": 0.27608826195592573,
"learning_rate": 1.0615437425331367e-05,
"num_train_epochs": 10,
"temperature": 2
}
}
|