File size: 4,000 Bytes
706c326 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 1000,
"global_step": 7615,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00039416633819471815,
"grad_norm": 6.560182094573975,
"learning_rate": 0.0,
"loss": 3.906,
"step": 1
},
{
"epoch": 0.3941663381947182,
"grad_norm": 4.686622619628906,
"learning_rate": 1.3118844386080105e-05,
"loss": 3.3873,
"step": 1000
},
{
"epoch": 0.3941663381947182,
"eval_cosine_accuracy": 0.9577242732048035,
"eval_loss": 1.444562554359436,
"eval_runtime": 24.0999,
"eval_samples_per_second": 394.567,
"eval_steps_per_second": 1.577,
"step": 1000
},
{
"epoch": 0.7883326763894364,
"grad_norm": 4.804063320159912,
"learning_rate": 1.9305058763413388e-05,
"loss": 2.6104,
"step": 2000
},
{
"epoch": 0.7883326763894364,
"eval_cosine_accuracy": 0.9649805426597595,
"eval_loss": 1.3182923793792725,
"eval_runtime": 24.3741,
"eval_samples_per_second": 390.127,
"eval_steps_per_second": 1.559,
"step": 2000
},
{
"epoch": 1.182355257975581,
"grad_norm": 4.845874786376953,
"learning_rate": 1.7845098182349078e-05,
"loss": 1.9638,
"step": 3000
},
{
"epoch": 1.182355257975581,
"eval_cosine_accuracy": 0.9649805426597595,
"eval_loss": 1.2991231679916382,
"eval_runtime": 24.0097,
"eval_samples_per_second": 396.049,
"eval_steps_per_second": 1.583,
"step": 3000
},
{
"epoch": 1.576211106734935,
"grad_norm": 4.727691173553467,
"learning_rate": 1.6386597561865833e-05,
"loss": 1.9904,
"step": 4000
},
{
"epoch": 1.576211106734935,
"eval_cosine_accuracy": 0.9685561060905457,
"eval_loss": 1.2640169858932495,
"eval_runtime": 23.8211,
"eval_samples_per_second": 399.185,
"eval_steps_per_second": 1.595,
"step": 4000
},
{
"epoch": 1.9700669554942891,
"grad_norm": 4.540011405944824,
"learning_rate": 1.4926636980801519e-05,
"loss": 1.8765,
"step": 5000
},
{
"epoch": 1.9700669554942891,
"eval_cosine_accuracy": 0.9704490303993225,
"eval_loss": 1.2718477249145508,
"eval_runtime": 23.8069,
"eval_samples_per_second": 399.422,
"eval_steps_per_second": 1.596,
"step": 5000
},
{
"epoch": 2.3639228042536433,
"grad_norm": 9.497809410095215,
"learning_rate": 1.3466676399737208e-05,
"loss": 1.7538,
"step": 6000
},
{
"epoch": 2.3639228042536433,
"eval_cosine_accuracy": 0.9702387452125549,
"eval_loss": 1.2771531343460083,
"eval_runtime": 25.1947,
"eval_samples_per_second": 377.421,
"eval_steps_per_second": 1.508,
"step": 6000
},
{
"epoch": 2.7577786530129975,
"grad_norm": 4.704818248748779,
"learning_rate": 1.2006715818672896e-05,
"loss": 1.6971,
"step": 7000
},
{
"epoch": 2.7577786530129975,
"eval_cosine_accuracy": 0.9713954925537109,
"eval_loss": 1.2673554420471191,
"eval_runtime": 23.8332,
"eval_samples_per_second": 398.981,
"eval_steps_per_second": 1.594,
"step": 7000
}
],
"logging_steps": 1000,
"max_steps": 15222,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"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": 0.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|