| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "/scratch/czm5kz/finetuned_pythia70M_nondeduped_cp_1430008_1_0.0002_sequential/checkpoint-20", | |
| "epoch": 0.9975062344139651, | |
| "eval_steps": 20, | |
| "global_step": 5600, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1146, | |
| "eval_samples_per_second": 696.823, | |
| "eval_steps_per_second": 87.126, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2377, | |
| "eval_samples_per_second": 691.539, | |
| "eval_steps_per_second": 86.465, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0293, | |
| "eval_samples_per_second": 700.529, | |
| "eval_steps_per_second": 87.589, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1982, | |
| "eval_samples_per_second": 693.223, | |
| "eval_steps_per_second": 86.676, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0082, | |
| "eval_samples_per_second": 701.454, | |
| "eval_steps_per_second": 87.705, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1988, | |
| "eval_samples_per_second": 693.2, | |
| "eval_steps_per_second": 86.673, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1782, | |
| "eval_samples_per_second": 694.08, | |
| "eval_steps_per_second": 86.783, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.992, | |
| "eval_samples_per_second": 702.163, | |
| "eval_steps_per_second": 87.794, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1988, | |
| "eval_samples_per_second": 693.201, | |
| "eval_steps_per_second": 86.673, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0093, | |
| "eval_samples_per_second": 701.407, | |
| "eval_steps_per_second": 87.699, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1792, | |
| "eval_samples_per_second": 694.038, | |
| "eval_steps_per_second": 86.778, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0036, | |
| "eval_samples_per_second": 701.654, | |
| "eval_steps_per_second": 87.73, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1856, | |
| "eval_samples_per_second": 693.763, | |
| "eval_steps_per_second": 86.744, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.203, | |
| "eval_samples_per_second": 693.019, | |
| "eval_steps_per_second": 86.651, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9989, | |
| "eval_samples_per_second": 701.86, | |
| "eval_steps_per_second": 87.756, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1855, | |
| "eval_samples_per_second": 693.771, | |
| "eval_steps_per_second": 86.745, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0192, | |
| "eval_samples_per_second": 700.973, | |
| "eval_steps_per_second": 87.645, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1801, | |
| "eval_samples_per_second": 694.0, | |
| "eval_steps_per_second": 86.773, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0121, | |
| "eval_samples_per_second": 701.281, | |
| "eval_steps_per_second": 87.684, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1904, | |
| "eval_samples_per_second": 693.561, | |
| "eval_steps_per_second": 86.718, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1998, | |
| "eval_samples_per_second": 693.156, | |
| "eval_steps_per_second": 86.668, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0087, | |
| "eval_samples_per_second": 701.43, | |
| "eval_steps_per_second": 87.702, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.199, | |
| "eval_samples_per_second": 693.193, | |
| "eval_steps_per_second": 86.672, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9611, | |
| "eval_samples_per_second": 703.522, | |
| "eval_steps_per_second": 87.964, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1944, | |
| "eval_samples_per_second": 693.387, | |
| "eval_steps_per_second": 86.697, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0222, | |
| "eval_samples_per_second": 700.838, | |
| "eval_steps_per_second": 87.628, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1622, | |
| "eval_samples_per_second": 694.77, | |
| "eval_steps_per_second": 86.869, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1899, | |
| "eval_samples_per_second": 693.581, | |
| "eval_steps_per_second": 86.721, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0008, | |
| "eval_samples_per_second": 701.775, | |
| "eval_steps_per_second": 87.745, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1819, | |
| "eval_samples_per_second": 693.923, | |
| "eval_steps_per_second": 86.764, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9831, | |
| "eval_samples_per_second": 702.554, | |
| "eval_steps_per_second": 87.843, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1804, | |
| "eval_samples_per_second": 693.989, | |
| "eval_steps_per_second": 86.772, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0085, | |
| "eval_samples_per_second": 701.438, | |
| "eval_steps_per_second": 87.703, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1876, | |
| "eval_samples_per_second": 693.679, | |
| "eval_steps_per_second": 86.733, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1685, | |
| "eval_samples_per_second": 694.499, | |
| "eval_steps_per_second": 86.836, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0219, | |
| "eval_samples_per_second": 700.852, | |
| "eval_steps_per_second": 87.63, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1706, | |
| "eval_samples_per_second": 694.409, | |
| "eval_steps_per_second": 86.824, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0001, | |
| "eval_samples_per_second": 701.808, | |
| "eval_steps_per_second": 87.749, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1874, | |
| "eval_samples_per_second": 693.687, | |
| "eval_steps_per_second": 86.734, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0324, | |
| "eval_samples_per_second": 700.394, | |
| "eval_steps_per_second": 87.573, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2018, | |
| "eval_samples_per_second": 693.07, | |
| "eval_steps_per_second": 86.657, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 2.7079, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1881, | |
| "eval_samples_per_second": 693.659, | |
| "eval_steps_per_second": 86.731, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0096, | |
| "eval_samples_per_second": 701.392, | |
| "eval_steps_per_second": 87.697, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2063, | |
| "eval_samples_per_second": 692.877, | |
| "eval_steps_per_second": 86.633, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9917, | |
| "eval_samples_per_second": 702.178, | |
| "eval_steps_per_second": 87.796, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2069, | |
| "eval_samples_per_second": 692.853, | |
| "eval_steps_per_second": 86.63, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0224, | |
| "eval_samples_per_second": 700.833, | |
| "eval_steps_per_second": 87.627, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2025, | |
| "eval_samples_per_second": 693.043, | |
| "eval_steps_per_second": 86.653, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2371, | |
| "eval_samples_per_second": 691.563, | |
| "eval_steps_per_second": 86.468, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0227, | |
| "eval_samples_per_second": 700.819, | |
| "eval_steps_per_second": 87.626, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1836, | |
| "eval_samples_per_second": 693.852, | |
| "eval_steps_per_second": 86.755, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0089, | |
| "eval_samples_per_second": 701.424, | |
| "eval_steps_per_second": 87.701, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2159, | |
| "eval_samples_per_second": 692.468, | |
| "eval_steps_per_second": 86.582, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0071, | |
| "eval_samples_per_second": 701.499, | |
| "eval_steps_per_second": 87.711, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1828, | |
| "eval_samples_per_second": 693.885, | |
| "eval_steps_per_second": 86.759, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2019, | |
| "eval_samples_per_second": 693.066, | |
| "eval_steps_per_second": 86.656, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0117, | |
| "eval_samples_per_second": 701.301, | |
| "eval_steps_per_second": 87.686, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2337, | |
| "eval_samples_per_second": 691.71, | |
| "eval_steps_per_second": 86.487, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9876, | |
| "eval_samples_per_second": 702.357, | |
| "eval_steps_per_second": 87.818, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.193, | |
| "eval_samples_per_second": 693.449, | |
| "eval_steps_per_second": 86.704, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0244, | |
| "eval_samples_per_second": 700.743, | |
| "eval_steps_per_second": 87.616, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2076, | |
| "eval_samples_per_second": 692.821, | |
| "eval_steps_per_second": 86.626, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0179, | |
| "eval_samples_per_second": 701.027, | |
| "eval_steps_per_second": 87.652, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0135, | |
| "eval_samples_per_second": 701.223, | |
| "eval_steps_per_second": 87.676, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1956, | |
| "eval_samples_per_second": 693.337, | |
| "eval_steps_per_second": 86.69, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0336, | |
| "eval_samples_per_second": 700.342, | |
| "eval_steps_per_second": 87.566, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2227, | |
| "eval_samples_per_second": 692.18, | |
| "eval_steps_per_second": 86.546, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0535, | |
| "eval_samples_per_second": 699.473, | |
| "eval_steps_per_second": 87.457, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1935, | |
| "eval_samples_per_second": 693.425, | |
| "eval_steps_per_second": 86.701, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0209, | |
| "eval_samples_per_second": 700.898, | |
| "eval_steps_per_second": 87.636, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0299, | |
| "eval_samples_per_second": 700.505, | |
| "eval_steps_per_second": 87.587, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0606, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.202, | |
| "eval_samples_per_second": 693.065, | |
| "eval_steps_per_second": 86.656, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9122, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0103, | |
| "eval_samples_per_second": 701.36, | |
| "eval_steps_per_second": 87.693, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0306, | |
| "eval_samples_per_second": 700.471, | |
| "eval_steps_per_second": 87.582, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2098, | |
| "eval_samples_per_second": 692.728, | |
| "eval_steps_per_second": 86.614, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0138, | |
| "eval_samples_per_second": 701.208, | |
| "eval_steps_per_second": 87.674, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2276, | |
| "eval_samples_per_second": 691.968, | |
| "eval_steps_per_second": 86.519, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0281, | |
| "eval_samples_per_second": 700.584, | |
| "eval_steps_per_second": 87.596, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.232, | |
| "eval_samples_per_second": 691.782, | |
| "eval_steps_per_second": 86.496, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.034, | |
| "eval_samples_per_second": 700.326, | |
| "eval_steps_per_second": 87.564, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0337, | |
| "eval_samples_per_second": 700.336, | |
| "eval_steps_per_second": 87.565, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2259, | |
| "eval_samples_per_second": 692.043, | |
| "eval_steps_per_second": 86.529, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0115, | |
| "eval_samples_per_second": 701.31, | |
| "eval_steps_per_second": 87.687, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1906, | |
| "eval_samples_per_second": 693.551, | |
| "eval_steps_per_second": 86.717, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0064, | |
| "eval_samples_per_second": 701.532, | |
| "eval_steps_per_second": 87.715, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2263, | |
| "eval_samples_per_second": 692.025, | |
| "eval_steps_per_second": 86.526, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.022, | |
| "eval_samples_per_second": 700.85, | |
| "eval_steps_per_second": 87.63, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0469, | |
| "eval_samples_per_second": 699.762, | |
| "eval_steps_per_second": 87.494, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2208, | |
| "eval_samples_per_second": 692.26, | |
| "eval_steps_per_second": 86.556, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0447, | |
| "eval_samples_per_second": 699.857, | |
| "eval_steps_per_second": 87.505, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2161, | |
| "eval_samples_per_second": 692.462, | |
| "eval_steps_per_second": 86.581, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0155, | |
| "eval_samples_per_second": 701.133, | |
| "eval_steps_per_second": 87.665, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1884, | |
| "eval_samples_per_second": 693.644, | |
| "eval_steps_per_second": 86.729, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.025, | |
| "eval_samples_per_second": 700.718, | |
| "eval_steps_per_second": 87.613, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2084, | |
| "eval_samples_per_second": 692.79, | |
| "eval_steps_per_second": 86.622, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2095, | |
| "eval_samples_per_second": 692.744, | |
| "eval_steps_per_second": 86.616, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0186, | |
| "eval_samples_per_second": 700.997, | |
| "eval_steps_per_second": 87.648, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1962, | |
| "eval_samples_per_second": 693.312, | |
| "eval_steps_per_second": 86.687, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0472, | |
| "eval_samples_per_second": 699.747, | |
| "eval_steps_per_second": 87.492, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2021, | |
| "eval_samples_per_second": 693.06, | |
| "eval_steps_per_second": 86.656, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0067, | |
| "eval_samples_per_second": 701.518, | |
| "eval_steps_per_second": 87.713, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1988, | |
| "eval_samples_per_second": 693.198, | |
| "eval_steps_per_second": 86.673, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1992, | |
| "eval_samples_per_second": 693.183, | |
| "eval_steps_per_second": 86.671, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0247, | |
| "eval_samples_per_second": 700.73, | |
| "eval_steps_per_second": 87.615, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.188, | |
| "eval_samples_per_second": 693.663, | |
| "eval_steps_per_second": 86.731, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0324, | |
| "eval_samples_per_second": 700.393, | |
| "eval_steps_per_second": 87.573, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2289, | |
| "eval_samples_per_second": 691.914, | |
| "eval_steps_per_second": 86.512, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0005, | |
| "eval_samples_per_second": 701.79, | |
| "eval_steps_per_second": 87.747, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2072, | |
| "eval_samples_per_second": 692.842, | |
| "eval_steps_per_second": 86.628, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2049, | |
| "eval_samples_per_second": 692.941, | |
| "eval_steps_per_second": 86.641, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0208, | |
| "eval_samples_per_second": 700.902, | |
| "eval_steps_per_second": 87.636, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2122, | |
| "eval_samples_per_second": 692.626, | |
| "eval_steps_per_second": 86.601, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0178, | |
| "eval_samples_per_second": 701.034, | |
| "eval_steps_per_second": 87.653, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2241, | |
| "eval_samples_per_second": 692.117, | |
| "eval_steps_per_second": 86.538, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9947, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0265, | |
| "eval_samples_per_second": 700.653, | |
| "eval_steps_per_second": 87.605, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2331, | |
| "eval_samples_per_second": 691.736, | |
| "eval_steps_per_second": 86.49, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2, | |
| "eval_samples_per_second": 693.148, | |
| "eval_steps_per_second": 86.667, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.044, | |
| "eval_samples_per_second": 699.889, | |
| "eval_steps_per_second": 87.509, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2276, | |
| "eval_samples_per_second": 691.968, | |
| "eval_steps_per_second": 86.519, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0377, | |
| "eval_samples_per_second": 700.161, | |
| "eval_steps_per_second": 87.543, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2405 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2397, | |
| "eval_samples_per_second": 691.455, | |
| "eval_steps_per_second": 86.455, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2435 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0588, | |
| "eval_samples_per_second": 699.244, | |
| "eval_steps_per_second": 87.429, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2263, | |
| "eval_samples_per_second": 692.024, | |
| "eval_steps_per_second": 86.526, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.215, | |
| "eval_samples_per_second": 692.506, | |
| "eval_steps_per_second": 86.586, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0384, | |
| "eval_samples_per_second": 700.132, | |
| "eval_steps_per_second": 87.54, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2515 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2142, | |
| "eval_samples_per_second": 692.54, | |
| "eval_steps_per_second": 86.591, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0257, | |
| "eval_samples_per_second": 700.687, | |
| "eval_steps_per_second": 87.609, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2545 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2346, | |
| "eval_samples_per_second": 691.672, | |
| "eval_steps_per_second": 86.482, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0287, | |
| "eval_samples_per_second": 700.555, | |
| "eval_steps_per_second": 87.593, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2119, | |
| "eval_samples_per_second": 692.641, | |
| "eval_steps_per_second": 86.603, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2605 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2615 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2398, | |
| "eval_samples_per_second": 691.449, | |
| "eval_steps_per_second": 86.454, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0618, | |
| "eval_samples_per_second": 699.113, | |
| "eval_steps_per_second": 87.412, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2534, | |
| "eval_samples_per_second": 690.873, | |
| "eval_steps_per_second": 86.382, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2665 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0344, | |
| "eval_samples_per_second": 700.309, | |
| "eval_steps_per_second": 87.562, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2211, | |
| "eval_samples_per_second": 692.246, | |
| "eval_steps_per_second": 86.554, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0518, | |
| "eval_samples_per_second": 699.549, | |
| "eval_steps_per_second": 87.467, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2735 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2309, | |
| "eval_samples_per_second": 691.83, | |
| "eval_steps_per_second": 86.502, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2755 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2124, | |
| "eval_samples_per_second": 692.618, | |
| "eval_steps_per_second": 86.6, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0539, | |
| "eval_samples_per_second": 699.456, | |
| "eval_steps_per_second": 87.455, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2785 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2795 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2032, | |
| "eval_samples_per_second": 693.012, | |
| "eval_steps_per_second": 86.65, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0294, | |
| "eval_samples_per_second": 700.524, | |
| "eval_steps_per_second": 87.589, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2244, | |
| "eval_samples_per_second": 692.105, | |
| "eval_steps_per_second": 86.536, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2845 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2855 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0285, | |
| "eval_samples_per_second": 700.563, | |
| "eval_steps_per_second": 87.594, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2292, | |
| "eval_samples_per_second": 691.901, | |
| "eval_steps_per_second": 86.511, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2885 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2277, | |
| "eval_samples_per_second": 691.967, | |
| "eval_steps_per_second": 86.519, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2915 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0565, | |
| "eval_samples_per_second": 699.342, | |
| "eval_steps_per_second": 87.441, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2935 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2374, | |
| "eval_samples_per_second": 691.552, | |
| "eval_steps_per_second": 86.467, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2945 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9983, | |
| "eval_samples_per_second": 701.889, | |
| "eval_steps_per_second": 87.76, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2965 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2161, | |
| "eval_samples_per_second": 692.461, | |
| "eval_steps_per_second": 86.581, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 2995 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0362, | |
| "eval_samples_per_second": 700.226, | |
| "eval_steps_per_second": 87.552, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3005 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1901, | |
| "eval_samples_per_second": 693.572, | |
| "eval_steps_per_second": 86.72, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3035 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2307, | |
| "eval_samples_per_second": 691.838, | |
| "eval_steps_per_second": 86.503, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3055 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0487, | |
| "eval_samples_per_second": 699.684, | |
| "eval_steps_per_second": 87.484, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3065 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.224, | |
| "eval_samples_per_second": 692.121, | |
| "eval_steps_per_second": 86.538, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3085 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3095 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0323, | |
| "eval_samples_per_second": 700.397, | |
| "eval_steps_per_second": 87.573, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2229, | |
| "eval_samples_per_second": 692.171, | |
| "eval_steps_per_second": 86.545, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3135 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0233, | |
| "eval_samples_per_second": 700.792, | |
| "eval_steps_per_second": 87.622, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3155 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2068, | |
| "eval_samples_per_second": 692.859, | |
| "eval_steps_per_second": 86.631, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3165 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2238, | |
| "eval_samples_per_second": 692.13, | |
| "eval_steps_per_second": 86.539, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3195 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0258, | |
| "eval_samples_per_second": 700.681, | |
| "eval_steps_per_second": 87.609, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3205 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3215 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2216, | |
| "eval_samples_per_second": 692.224, | |
| "eval_steps_per_second": 86.551, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3235 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0142, | |
| "eval_samples_per_second": 701.189, | |
| "eval_steps_per_second": 87.672, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2272, | |
| "eval_samples_per_second": 691.986, | |
| "eval_steps_per_second": 86.521, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3265 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0324, | |
| "eval_samples_per_second": 700.396, | |
| "eval_steps_per_second": 87.573, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3285 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3295 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2259, | |
| "eval_samples_per_second": 692.041, | |
| "eval_steps_per_second": 86.528, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3305 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0161, | |
| "eval_samples_per_second": 701.105, | |
| "eval_steps_per_second": 87.662, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3335 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0254, | |
| "eval_samples_per_second": 700.698, | |
| "eval_steps_per_second": 87.611, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3345 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3355 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2087, | |
| "eval_samples_per_second": 692.777, | |
| "eval_steps_per_second": 86.62, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3365 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0227, | |
| "eval_samples_per_second": 700.819, | |
| "eval_steps_per_second": 87.626, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3385 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3395 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.243, | |
| "eval_samples_per_second": 691.313, | |
| "eval_steps_per_second": 86.437, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3405 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3415 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.039, | |
| "eval_samples_per_second": 700.106, | |
| "eval_steps_per_second": 87.537, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3435 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2351, | |
| "eval_samples_per_second": 691.649, | |
| "eval_steps_per_second": 86.479, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3445 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3455 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2344, | |
| "eval_samples_per_second": 691.678, | |
| "eval_steps_per_second": 86.483, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3465 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0437, | |
| "eval_samples_per_second": 699.902, | |
| "eval_steps_per_second": 87.511, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3485 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3495 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2445, | |
| "eval_samples_per_second": 691.251, | |
| "eval_steps_per_second": 86.43, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3505 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3515 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2224, | |
| "eval_samples_per_second": 692.19, | |
| "eval_steps_per_second": 86.547, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3535 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0451, | |
| "eval_samples_per_second": 699.839, | |
| "eval_steps_per_second": 87.503, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3545 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3555 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2249, | |
| "eval_samples_per_second": 692.086, | |
| "eval_steps_per_second": 86.534, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3565 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0399, | |
| "eval_samples_per_second": 700.067, | |
| "eval_steps_per_second": 87.532, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3585 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3595 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.213, | |
| "eval_samples_per_second": 692.592, | |
| "eval_steps_per_second": 86.597, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3605 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3615 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.024, | |
| "eval_samples_per_second": 700.763, | |
| "eval_steps_per_second": 87.619, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3635 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1716, | |
| "eval_samples_per_second": 694.364, | |
| "eval_steps_per_second": 86.819, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3645 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3655 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2026, | |
| "eval_samples_per_second": 693.037, | |
| "eval_steps_per_second": 86.653, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3665 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0215, | |
| "eval_samples_per_second": 700.871, | |
| "eval_steps_per_second": 87.632, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3685 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3695 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2265, | |
| "eval_samples_per_second": 692.018, | |
| "eval_steps_per_second": 86.525, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3705 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3715 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0397, | |
| "eval_samples_per_second": 700.075, | |
| "eval_steps_per_second": 87.533, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3735 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2032, | |
| "eval_samples_per_second": 693.013, | |
| "eval_steps_per_second": 86.65, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3745 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3755 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0241, | |
| "eval_samples_per_second": 700.757, | |
| "eval_steps_per_second": 87.618, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3765 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2732, | |
| "eval_samples_per_second": 690.029, | |
| "eval_steps_per_second": 86.277, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3785 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3795 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2369, | |
| "eval_samples_per_second": 691.574, | |
| "eval_steps_per_second": 86.47, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3805 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3815 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0547, | |
| "eval_samples_per_second": 699.421, | |
| "eval_steps_per_second": 87.451, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3835 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2346, | |
| "eval_samples_per_second": 691.669, | |
| "eval_steps_per_second": 86.482, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3845 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3855 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0457, | |
| "eval_samples_per_second": 699.813, | |
| "eval_steps_per_second": 87.5, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3865 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.219, | |
| "eval_samples_per_second": 692.334, | |
| "eval_steps_per_second": 86.565, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3885 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3895 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0291, | |
| "eval_samples_per_second": 700.537, | |
| "eval_steps_per_second": 87.591, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3905 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3915 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0499, | |
| "eval_samples_per_second": 699.629, | |
| "eval_steps_per_second": 87.477, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3935 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2243, | |
| "eval_samples_per_second": 692.11, | |
| "eval_steps_per_second": 86.537, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3945 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3955 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0464, | |
| "eval_samples_per_second": 699.783, | |
| "eval_steps_per_second": 87.496, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3965 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2257, | |
| "eval_samples_per_second": 692.05, | |
| "eval_steps_per_second": 86.529, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3985 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3995 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0446, | |
| "eval_samples_per_second": 699.861, | |
| "eval_steps_per_second": 87.506, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4005 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4015 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.237, | |
| "eval_samples_per_second": 691.567, | |
| "eval_steps_per_second": 86.469, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4035 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.06, | |
| "eval_samples_per_second": 699.191, | |
| "eval_steps_per_second": 87.422, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4045 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4055 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2165, | |
| "eval_samples_per_second": 692.444, | |
| "eval_steps_per_second": 86.579, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4065 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2461, | |
| "eval_samples_per_second": 691.182, | |
| "eval_steps_per_second": 86.421, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4085 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0545, | |
| "eval_samples_per_second": 699.43, | |
| "eval_steps_per_second": 87.452, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4105 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4115 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2396, | |
| "eval_samples_per_second": 691.458, | |
| "eval_steps_per_second": 86.455, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4135 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0719, | |
| "eval_samples_per_second": 698.673, | |
| "eval_steps_per_second": 87.358, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4145 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4155 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2286, | |
| "eval_samples_per_second": 691.928, | |
| "eval_steps_per_second": 86.514, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4165 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0422, | |
| "eval_samples_per_second": 699.968, | |
| "eval_steps_per_second": 87.519, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4185 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4195 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2302, | |
| "eval_samples_per_second": 691.859, | |
| "eval_steps_per_second": 86.505, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4205 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4215 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2332, | |
| "eval_samples_per_second": 691.729, | |
| "eval_steps_per_second": 86.489, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4235 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0487, | |
| "eval_samples_per_second": 699.685, | |
| "eval_steps_per_second": 87.484, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4245 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4255 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2278, | |
| "eval_samples_per_second": 691.959, | |
| "eval_steps_per_second": 86.518, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4265 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0539, | |
| "eval_samples_per_second": 699.457, | |
| "eval_steps_per_second": 87.456, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4285 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4295 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2238, | |
| "eval_samples_per_second": 692.131, | |
| "eval_steps_per_second": 86.539, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4305 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4315 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2288, | |
| "eval_samples_per_second": 691.917, | |
| "eval_steps_per_second": 86.513, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4335 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0182, | |
| "eval_samples_per_second": 701.016, | |
| "eval_steps_per_second": 87.65, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4345 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4355 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2045, | |
| "eval_samples_per_second": 692.954, | |
| "eval_steps_per_second": 86.642, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4365 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0271, | |
| "eval_samples_per_second": 700.624, | |
| "eval_steps_per_second": 87.601, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4385 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4395 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.23, | |
| "eval_samples_per_second": 691.867, | |
| "eval_steps_per_second": 86.506, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4405 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4415 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0458, | |
| "eval_samples_per_second": 699.809, | |
| "eval_steps_per_second": 87.5, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4435 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2118, | |
| "eval_samples_per_second": 692.643, | |
| "eval_steps_per_second": 86.604, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4445 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4455 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2235, | |
| "eval_samples_per_second": 692.144, | |
| "eval_steps_per_second": 86.541, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4465 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0349, | |
| "eval_samples_per_second": 700.284, | |
| "eval_steps_per_second": 87.559, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4485 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4495 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2202, | |
| "eval_samples_per_second": 692.283, | |
| "eval_steps_per_second": 86.559, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4505 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4515 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0564, | |
| "eval_samples_per_second": 699.346, | |
| "eval_steps_per_second": 87.442, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4535 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2223, | |
| "eval_samples_per_second": 692.194, | |
| "eval_steps_per_second": 86.547, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4545 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4555 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.047, | |
| "eval_samples_per_second": 699.756, | |
| "eval_steps_per_second": 87.493, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4565 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.222, | |
| "eval_samples_per_second": 692.209, | |
| "eval_steps_per_second": 86.549, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4595 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2166, | |
| "eval_samples_per_second": 692.441, | |
| "eval_steps_per_second": 86.578, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4605 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4615 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0315, | |
| "eval_samples_per_second": 700.432, | |
| "eval_steps_per_second": 87.577, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4635 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.1928, | |
| "eval_samples_per_second": 693.456, | |
| "eval_steps_per_second": 86.705, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4645 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4655 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.051, | |
| "eval_samples_per_second": 699.584, | |
| "eval_steps_per_second": 87.471, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4665 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2287, | |
| "eval_samples_per_second": 691.924, | |
| "eval_steps_per_second": 86.514, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4685 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4695 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0295, | |
| "eval_samples_per_second": 700.522, | |
| "eval_steps_per_second": 87.589, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4705 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 4.5394, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4715 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2048, | |
| "eval_samples_per_second": 692.942, | |
| "eval_steps_per_second": 86.641, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4735 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2222, | |
| "eval_samples_per_second": 692.2, | |
| "eval_steps_per_second": 86.548, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4745 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4755 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0418, | |
| "eval_samples_per_second": 699.985, | |
| "eval_steps_per_second": 87.521, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4765 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2095, | |
| "eval_samples_per_second": 692.74, | |
| "eval_steps_per_second": 86.616, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4785 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4795 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0422, | |
| "eval_samples_per_second": 699.967, | |
| "eval_steps_per_second": 87.519, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4805 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4815 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.208, | |
| "eval_samples_per_second": 692.804, | |
| "eval_steps_per_second": 86.624, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4835 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0149, | |
| "eval_samples_per_second": 701.158, | |
| "eval_steps_per_second": 87.668, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4845 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4855 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2398, | |
| "eval_samples_per_second": 691.449, | |
| "eval_steps_per_second": 86.454, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4865 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2201, | |
| "eval_samples_per_second": 692.287, | |
| "eval_steps_per_second": 86.559, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4885 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4895 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0619, | |
| "eval_samples_per_second": 699.108, | |
| "eval_steps_per_second": 87.412, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4905 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4915 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2578, | |
| "eval_samples_per_second": 690.684, | |
| "eval_steps_per_second": 86.359, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4935 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0639, | |
| "eval_samples_per_second": 699.022, | |
| "eval_steps_per_second": 87.401, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4945 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4955 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2248, | |
| "eval_samples_per_second": 692.088, | |
| "eval_steps_per_second": 86.534, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4965 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0412, | |
| "eval_samples_per_second": 700.009, | |
| "eval_steps_per_second": 87.525, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4985 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 4995 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2237, | |
| "eval_samples_per_second": 692.135, | |
| "eval_steps_per_second": 86.54, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5005 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5015 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2149, | |
| "eval_samples_per_second": 692.51, | |
| "eval_steps_per_second": 86.587, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5035 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0549, | |
| "eval_samples_per_second": 699.413, | |
| "eval_steps_per_second": 87.45, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5045 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5055 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2118, | |
| "eval_samples_per_second": 692.643, | |
| "eval_steps_per_second": 86.604, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5065 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2351, | |
| "eval_samples_per_second": 691.649, | |
| "eval_steps_per_second": 86.479, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5085 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5095 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0484, | |
| "eval_samples_per_second": 699.695, | |
| "eval_steps_per_second": 87.485, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5105 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5115 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2149, | |
| "eval_samples_per_second": 692.509, | |
| "eval_steps_per_second": 86.587, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5135 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0666, | |
| "eval_samples_per_second": 698.905, | |
| "eval_steps_per_second": 87.386, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5145 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5155 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2188, | |
| "eval_samples_per_second": 692.345, | |
| "eval_steps_per_second": 86.566, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5165 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0397, | |
| "eval_samples_per_second": 700.076, | |
| "eval_steps_per_second": 87.533, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5185 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5195 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2146, | |
| "eval_samples_per_second": 692.522, | |
| "eval_steps_per_second": 86.588, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5205 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5215 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2211, | |
| "eval_samples_per_second": 692.245, | |
| "eval_steps_per_second": 86.554, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5235 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0255, | |
| "eval_samples_per_second": 700.697, | |
| "eval_steps_per_second": 87.611, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5245 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5255 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2139, | |
| "eval_samples_per_second": 692.555, | |
| "eval_steps_per_second": 86.593, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5265 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0283, | |
| "eval_samples_per_second": 700.572, | |
| "eval_steps_per_second": 87.595, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5285 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5295 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.213, | |
| "eval_samples_per_second": 692.591, | |
| "eval_steps_per_second": 86.597, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5305 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5315 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0339, | |
| "eval_samples_per_second": 700.33, | |
| "eval_steps_per_second": 87.565, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5335 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2354, | |
| "eval_samples_per_second": 691.638, | |
| "eval_steps_per_second": 86.478, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5345 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5355 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2232, | |
| "eval_samples_per_second": 692.158, | |
| "eval_steps_per_second": 86.543, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5365 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0655, | |
| "eval_samples_per_second": 698.951, | |
| "eval_steps_per_second": 87.392, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5385 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5395 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2374, | |
| "eval_samples_per_second": 691.554, | |
| "eval_steps_per_second": 86.467, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5405 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5415 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0445, | |
| "eval_samples_per_second": 699.864, | |
| "eval_steps_per_second": 87.506, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5435 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2238, | |
| "eval_samples_per_second": 692.132, | |
| "eval_steps_per_second": 86.54, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5445 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5455 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0567, | |
| "eval_samples_per_second": 699.333, | |
| "eval_steps_per_second": 87.44, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5465 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 6.6023, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2554, | |
| "eval_samples_per_second": 690.785, | |
| "eval_steps_per_second": 86.371, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5485 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5495 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2286, | |
| "eval_samples_per_second": 691.928, | |
| "eval_steps_per_second": 86.514, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5505 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5515 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0415, | |
| "eval_samples_per_second": 699.999, | |
| "eval_steps_per_second": 87.523, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5535 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.2151, | |
| "eval_samples_per_second": 692.505, | |
| "eval_steps_per_second": 86.586, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5545 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5555 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0155, | |
| "eval_samples_per_second": 701.132, | |
| "eval_steps_per_second": 87.665, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5565 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.227, | |
| "eval_samples_per_second": 691.997, | |
| "eval_steps_per_second": 86.523, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5585 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5595 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0337, | |
| "eval_samples_per_second": 700.338, | |
| "eval_steps_per_second": 87.566, | |
| "step": 5600 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 5614, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "total_flos": 1585617322377216.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |