| { | |
| "best_metric": 2.5420846939086914, | |
| "best_model_checkpoint": "output/lil-peep/checkpoint-273", | |
| "epoch": 3.0, | |
| "global_step": 273, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001362025229153997, | |
| "loss": 3.5516, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001332390992573511, | |
| "loss": 3.4721, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012839590824424674, | |
| "loss": 3.2627, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0001218137945423232, | |
| "loss": 3.1034, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011368417236691292, | |
| "loss": 3.1171, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00010424345897243074, | |
| "loss": 3.1489, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.376619941057568e-05, | |
| "loss": 2.8674, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.255708249541069e-05, | |
| "loss": 2.8656, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.09420801587574e-05, | |
| "loss": 2.9883, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.9258967871997494e-05, | |
| "loss": 2.8085, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.7847501809558206e-05, | |
| "loss": 3.0115, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.703953841164296e-05, | |
| "loss": 2.8815, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.7149383678852917e-05, | |
| "loss": 2.8724, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8464652850520685e-05, | |
| "loss": 2.6859, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.1237906276126852e-05, | |
| "loss": 2.8093, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.679304716725937e-06, | |
| "loss": 2.9932, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.9504976673012163e-06, | |
| "loss": 2.8374, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.5992243352900665e-07, | |
| "loss": 2.9176, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.7529633045196533, | |
| "eval_runtime": 5.2607, | |
| "eval_samples_per_second": 22.05, | |
| "eval_steps_per_second": 2.851, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 6.530415424531654e-07, | |
| "loss": 2.6804, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.2847281185250116e-06, | |
| "loss": 2.8371, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 7.857716640189785e-06, | |
| "loss": 2.912, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.21, | |
| "learning_rate": 1.4236088642155179e-05, | |
| "loss": 2.9544, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 2.223026601166984e-05, | |
| "loss": 2.6108, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.1602645633354905e-05, | |
| "loss": 2.743, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 4.207466143421867e-05, | |
| "loss": 2.7849, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.333506393059682e-05, | |
| "loss": 2.7864, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 6.504917119214327e-05, | |
| "loss": 2.7238, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.686881626551516e-05, | |
| "loss": 2.7156, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.844269540020853e-05, | |
| "loss": 2.739, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.942680950634723e-05, | |
| "loss": 2.8584, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00010949468850318882, | |
| "loss": 2.7199, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00011834709467003562, | |
| "loss": 2.4955, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012572091659634235, | |
| "loss": 2.878, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 0.00013139698938484013, | |
| "loss": 2.8072, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00013520660867542716, | |
| "loss": 2.8227, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 0.00013703654487986559, | |
| "loss": 2.5274, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.6319327354431152, | |
| "eval_runtime": 5.9403, | |
| "eval_samples_per_second": 20.706, | |
| "eval_steps_per_second": 2.693, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 0.0001368324085940902, | |
| "loss": 2.7572, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 0.000134600267161271, | |
| "loss": 2.5108, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 0.00013040646433810595, | |
| "loss": 2.5831, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "learning_rate": 0.00012437564842422732, | |
| "loss": 2.5252, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00011668706746270184, | |
| "loss": 2.5344, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 0.00010756924162575734, | |
| "loss": 2.4713, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 9.72931711332038e-05, | |
| "loss": 2.791, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 2.42, | |
| "learning_rate": 8.616428157794779e-05, | |
| "loss": 2.4278, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.47, | |
| "learning_rate": 7.451334605981051e-05, | |
| "loss": 2.5167, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 6.268665394018953e-05, | |
| "loss": 2.3747, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 5.103571842205231e-05, | |
| "loss": 2.4532, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "learning_rate": 3.990682886679629e-05, | |
| "loss": 2.4794, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 2.9630758374242683e-05, | |
| "loss": 2.4218, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2.051293253729814e-05, | |
| "loss": 2.4528, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 1.2824351575772677e-05, | |
| "loss": 2.6209, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 6.793535661894062e-06, | |
| "loss": 2.4639, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 2.599732838729015e-06, | |
| "loss": 2.4412, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 3.6759140590977833e-07, | |
| "loss": 2.487, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.5420846939086914, | |
| "eval_runtime": 5.9485, | |
| "eval_samples_per_second": 20.677, | |
| "eval_steps_per_second": 2.69, | |
| "step": 273 | |
| } | |
| ], | |
| "max_steps": 273, | |
| "num_train_epochs": 3, | |
| "total_flos": 282587332608000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |