File size: 2,995 Bytes
78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 cc63d16 78cb0d3 |
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": 0.5838709677419355,
"eval_loss": 0.19346614181995392,
"eval_runtime": 5.1609,
"eval_samples_per_second": 600.675,
"eval_steps_per_second": 12.595,
"step": 318
},
{
"epoch": 1.5723270440251573,
"grad_norm": 0.5179193019866943,
"learning_rate": 1.685534591194969e-05,
"loss": 0.3125,
"step": 500
},
{
"epoch": 2.0,
"eval_accuracy": 0.82,
"eval_loss": 0.09356740862131119,
"eval_runtime": 5.2878,
"eval_samples_per_second": 586.255,
"eval_steps_per_second": 12.292,
"step": 636
},
{
"epoch": 3.0,
"eval_accuracy": 0.8790322580645161,
"eval_loss": 0.06245172396302223,
"eval_runtime": 5.0672,
"eval_samples_per_second": 611.776,
"eval_steps_per_second": 12.828,
"step": 954
},
{
"epoch": 3.1446540880503147,
"grad_norm": 0.4341842532157898,
"learning_rate": 1.371069182389937e-05,
"loss": 0.1085,
"step": 1000
},
{
"epoch": 4.0,
"eval_accuracy": 0.9006451612903226,
"eval_loss": 0.048103515058755875,
"eval_runtime": 5.1362,
"eval_samples_per_second": 603.564,
"eval_steps_per_second": 12.655,
"step": 1272
},
{
"epoch": 4.716981132075472,
"grad_norm": 0.29487845301628113,
"learning_rate": 1.0566037735849058e-05,
"loss": 0.069,
"step": 1500
},
{
"epoch": 5.0,
"eval_accuracy": 0.9093548387096774,
"eval_loss": 0.03922608867287636,
"eval_runtime": 5.2603,
"eval_samples_per_second": 589.32,
"eval_steps_per_second": 12.357,
"step": 1590
},
{
"epoch": 6.0,
"eval_accuracy": 0.912258064516129,
"eval_loss": 0.03417789563536644,
"eval_runtime": 5.0804,
"eval_samples_per_second": 610.188,
"eval_steps_per_second": 12.794,
"step": 1908
},
{
"epoch": 6.289308176100629,
"grad_norm": 0.2546312212944031,
"learning_rate": 7.421383647798742e-06,
"loss": 0.0537,
"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": 0.5365842802514643,
"num_train_epochs": 10,
"temperature": 14
}
}
|