File size: 4,641 Bytes
661ca1b 7c7a578 661ca1b 7c7a578 661ca1b a5bd058 c7f7551 34730da 7c7a578 661ca1b 7c7a578 661ca1b |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
{
"best_metric": 0.04502652958035469,
"best_model_checkpoint": "doc-topic-model_eval-04_train-02/checkpoint-5000",
"epoch": 2.465483234714004,
"eval_steps": 1000,
"global_step": 5000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2465483234714004,
"grad_norm": 0.3822348415851593,
"learning_rate": 1.9950690335305722e-05,
"loss": 0.1664,
"step": 500
},
{
"epoch": 0.4930966469428008,
"grad_norm": 0.40402480959892273,
"learning_rate": 1.9901380670611442e-05,
"loss": 0.0944,
"step": 1000
},
{
"epoch": 0.4930966469428008,
"eval_accuracy": 0.981496987239155,
"eval_f1": 0.0,
"eval_loss": 0.08949843794107437,
"eval_precision": 0.0,
"eval_recall": 0.0,
"eval_runtime": 12.0575,
"eval_samples_per_second": 672.857,
"eval_steps_per_second": 2.654,
"step": 1000
},
{
"epoch": 0.7396449704142012,
"grad_norm": 0.385586678981781,
"learning_rate": 1.9852071005917162e-05,
"loss": 0.0863,
"step": 1500
},
{
"epoch": 0.9861932938856016,
"grad_norm": 0.3922920525074005,
"learning_rate": 1.980276134122288e-05,
"loss": 0.0769,
"step": 2000
},
{
"epoch": 0.9861932938856016,
"eval_accuracy": 0.981509738166785,
"eval_f1": 0.0013773050730736859,
"eval_loss": 0.0685219094157219,
"eval_precision": 1.0,
"eval_recall": 0.0006891271056661562,
"eval_runtime": 14.5319,
"eval_samples_per_second": 558.288,
"eval_steps_per_second": 2.202,
"step": 2000
},
{
"epoch": 1.232741617357002,
"grad_norm": 0.40515828132629395,
"learning_rate": 1.9753451676528602e-05,
"loss": 0.0677,
"step": 2500
},
{
"epoch": 1.4792899408284024,
"grad_norm": 0.3946343958377838,
"learning_rate": 1.9704142011834322e-05,
"loss": 0.0607,
"step": 3000
},
{
"epoch": 1.4792899408284024,
"eval_accuracy": 0.9822932118311607,
"eval_f1": 0.10664760543245175,
"eval_loss": 0.05599680170416832,
"eval_precision": 0.8021505376344086,
"eval_recall": 0.057120980091883614,
"eval_runtime": 14.3217,
"eval_samples_per_second": 566.482,
"eval_steps_per_second": 2.234,
"step": 3000
},
{
"epoch": 1.725838264299803,
"grad_norm": 0.35836198925971985,
"learning_rate": 1.965483234714004e-05,
"loss": 0.0564,
"step": 3500
},
{
"epoch": 1.972386587771203,
"grad_norm": 0.385370135307312,
"learning_rate": 1.9605522682445763e-05,
"loss": 0.0535,
"step": 4000
},
{
"epoch": 1.972386587771203,
"eval_accuracy": 0.9845742111071913,
"eval_f1": 0.3747559434937407,
"eval_loss": 0.050051942467689514,
"eval_precision": 0.7494258153422141,
"eval_recall": 0.2498468606431853,
"eval_runtime": 14.4421,
"eval_samples_per_second": 561.762,
"eval_steps_per_second": 2.216,
"step": 4000
},
{
"epoch": 2.2189349112426036,
"grad_norm": 0.3222791850566864,
"learning_rate": 1.9556213017751483e-05,
"loss": 0.0476,
"step": 4500
},
{
"epoch": 2.465483234714004,
"grad_norm": 0.3560543656349182,
"learning_rate": 1.95069033530572e-05,
"loss": 0.0466,
"step": 5000
},
{
"epoch": 2.465483234714004,
"eval_accuracy": 0.9858323026333499,
"eval_f1": 0.48990002040399916,
"eval_loss": 0.04502652958035469,
"eval_precision": 0.73380195599022,
"eval_recall": 0.367687595712098,
"eval_runtime": 14.4276,
"eval_samples_per_second": 562.324,
"eval_steps_per_second": 2.218,
"step": 5000
}
],
"logging_steps": 500,
"max_steps": 202800,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 1000,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 112902580652976.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|