File size: 3,004 Bytes
4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 1fd16ed 4a9c4c0 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 6.289308176100629,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_accuracy": 0.5803225806451613,
"eval_loss": 0.19005867838859558,
"eval_runtime": 5.674,
"eval_samples_per_second": 546.354,
"eval_steps_per_second": 11.456,
"step": 318
},
{
"epoch": 1.5723270440251573,
"grad_norm": 0.5149380564689636,
"learning_rate": 1.685534591194969e-05,
"loss": 0.3072,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.817741935483871,
"eval_loss": 0.0924694836139679,
"eval_runtime": 6.0294,
"eval_samples_per_second": 514.15,
"eval_steps_per_second": 10.781,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.8770967741935484,
"eval_loss": 0.06209348514676094,
"eval_runtime": 5.7978,
"eval_samples_per_second": 534.685,
"eval_steps_per_second": 11.211,
"step": 954
},
{
"epoch": 3.1446540880503147,
"grad_norm": 0.4281909167766571,
"learning_rate": 1.371069182389937e-05,
"loss": 0.1072,
"step": 1000
},
{
"epoch": 4.0,
"eval_accuracy": 0.9009677419354839,
"eval_loss": 0.048012129962444305,
"eval_runtime": 5.7482,
"eval_samples_per_second": 539.302,
"eval_steps_per_second": 11.308,
"step": 1272
},
{
"epoch": 4.716981132075472,
"grad_norm": 0.2933551073074341,
"learning_rate": 1.0566037735849058e-05,
"loss": 0.0684,
"step": 1500
},
{
"epoch": 5.0,
"eval_accuracy": 0.9093548387096774,
"eval_loss": 0.03922256454825401,
"eval_runtime": 5.9235,
"eval_samples_per_second": 523.338,
"eval_steps_per_second": 10.973,
"step": 1590
},
{
"epoch": 6.0,
"eval_accuracy": 0.912258064516129,
"eval_loss": 0.03422800451517105,
"eval_runtime": 5.7032,
"eval_samples_per_second": 543.553,
"eval_steps_per_second": 11.397,
"step": 1908
},
{
"epoch": 6.289308176100629,
"grad_norm": 0.25101438164711,
"learning_rate": 7.421383647798742e-06,
"loss": 0.0534,
"step": 2000
}
],
"logging_steps": 500,
"max_steps": 3180,
"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": 520991326672152.0,
"train_batch_size": 48,
"trial_name": null,
"trial_params": {
"alpha": 0.7637668053146042,
"num_train_epochs": 10,
"temperature": 18
}
}
|