File size: 3,833 Bytes
629ab29 e0a45b9 629ab29 e0a45b9 629ab29 b766607 3336f0d db287fb ac79f38 e0a45b9 629ab29 e0a45b9 629ab29 e0a45b9 629ab29 |
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 |
{
"best_metric": 0.6382145069577949,
"best_model_checkpoint": "training_dir/checkpoint-750",
"epoch": 6.0,
"eval_steps": 500,
"global_step": 750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 3.6677370071411133,
"learning_rate": 2.5e-05,
"loss": 0.9403,
"step": 125
},
{
"epoch": 1.0,
"eval_accuracy": 0.47246503496503495,
"eval_f1": 0.37635514577655893,
"eval_loss": 1.0853666067123413,
"eval_precision": 0.4261448543164962,
"eval_recall": 0.47246503496503495,
"eval_runtime": 29.0544,
"eval_samples_per_second": 78.749,
"eval_steps_per_second": 9.844,
"step": 125
},
{
"epoch": 2.0,
"grad_norm": 4.521803855895996,
"learning_rate": 5e-05,
"loss": 0.5748,
"step": 250
},
{
"epoch": 2.0,
"eval_accuracy": 0.6407342657342657,
"eval_f1": 0.6361710372570955,
"eval_loss": 0.8366930484771729,
"eval_precision": 0.6428210794762689,
"eval_recall": 0.6407342657342657,
"eval_runtime": 29.8222,
"eval_samples_per_second": 76.721,
"eval_steps_per_second": 9.59,
"step": 250
},
{
"epoch": 3.0,
"grad_norm": 7.845700263977051,
"learning_rate": 7.500000000000001e-05,
"loss": 0.3732,
"step": 375
},
{
"epoch": 3.0,
"eval_accuracy": 0.603583916083916,
"eval_f1": 0.565369682305176,
"eval_loss": 1.3425886631011963,
"eval_precision": 0.6364003210803549,
"eval_recall": 0.603583916083916,
"eval_runtime": 29.9297,
"eval_samples_per_second": 76.446,
"eval_steps_per_second": 9.556,
"step": 375
},
{
"epoch": 4.0,
"grad_norm": 27.72207260131836,
"learning_rate": 0.0001,
"loss": 0.2795,
"step": 500
},
{
"epoch": 4.0,
"eval_accuracy": 0.611451048951049,
"eval_f1": 0.5839059582567918,
"eval_loss": 1.4940129518508911,
"eval_precision": 0.6264845385709801,
"eval_recall": 0.611451048951049,
"eval_runtime": 29.8938,
"eval_samples_per_second": 76.538,
"eval_steps_per_second": 9.567,
"step": 500
},
{
"epoch": 5.0,
"grad_norm": 7.975765705108643,
"learning_rate": 5e-05,
"loss": 0.2239,
"step": 625
},
{
"epoch": 5.0,
"eval_accuracy": 0.6324300699300699,
"eval_f1": 0.6186338450685905,
"eval_loss": 1.4131898880004883,
"eval_precision": 0.657121853967928,
"eval_recall": 0.6324300699300699,
"eval_runtime": 29.8857,
"eval_samples_per_second": 76.558,
"eval_steps_per_second": 9.57,
"step": 625
},
{
"epoch": 6.0,
"grad_norm": 0.12321516871452332,
"learning_rate": 0.0,
"loss": 0.0917,
"step": 750
},
{
"epoch": 6.0,
"eval_accuracy": 0.6494755244755245,
"eval_f1": 0.6382145069577949,
"eval_loss": 1.7655272483825684,
"eval_precision": 0.6518973060481164,
"eval_recall": 0.6494755244755245,
"eval_runtime": 30.1035,
"eval_samples_per_second": 76.005,
"eval_steps_per_second": 9.501,
"step": 750
}
],
"logging_steps": 500,
"max_steps": 750,
"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": true
},
"attributes": {}
}
},
"total_flos": 1223275449456000.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|