| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "/scratch/czm5kz/finetuned_pythia70M_nondeduped_cp_1430008_1_0.0001_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": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8948, | |
| "eval_samples_per_second": 706.459, | |
| "eval_steps_per_second": 88.331, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0773, | |
| "eval_samples_per_second": 698.44, | |
| "eval_steps_per_second": 87.328, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.871, | |
| "eval_samples_per_second": 707.518, | |
| "eval_steps_per_second": 88.463, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0516, | |
| "eval_samples_per_second": 699.558, | |
| "eval_steps_per_second": 87.468, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8432, | |
| "eval_samples_per_second": 708.76, | |
| "eval_steps_per_second": 88.619, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0563, | |
| "eval_samples_per_second": 699.35, | |
| "eval_steps_per_second": 87.442, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0438, | |
| "eval_samples_per_second": 699.895, | |
| "eval_steps_per_second": 87.51, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8537, | |
| "eval_samples_per_second": 708.288, | |
| "eval_steps_per_second": 88.56, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0411, | |
| "eval_samples_per_second": 700.014, | |
| "eval_steps_per_second": 87.525, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8706, | |
| "eval_samples_per_second": 707.535, | |
| "eval_steps_per_second": 88.465, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0255, | |
| "eval_samples_per_second": 700.694, | |
| "eval_steps_per_second": 87.61, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8504, | |
| "eval_samples_per_second": 708.438, | |
| "eval_steps_per_second": 88.578, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0386, | |
| "eval_samples_per_second": 700.125, | |
| "eval_steps_per_second": 87.539, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8472, | |
| "eval_samples_per_second": 708.578, | |
| "eval_steps_per_second": 88.596, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0075, | |
| "eval_samples_per_second": 701.482, | |
| "eval_steps_per_second": 87.709, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0304, | |
| "eval_samples_per_second": 700.484, | |
| "eval_steps_per_second": 87.584, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8369, | |
| "eval_samples_per_second": 709.04, | |
| "eval_steps_per_second": 88.654, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9944, | |
| "eval_samples_per_second": 702.056, | |
| "eval_steps_per_second": 87.78, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8288, | |
| "eval_samples_per_second": 709.402, | |
| "eval_steps_per_second": 88.699, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0205, | |
| "eval_samples_per_second": 700.916, | |
| "eval_steps_per_second": 87.638, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8572, | |
| "eval_samples_per_second": 708.134, | |
| "eval_steps_per_second": 88.54, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0289, | |
| "eval_samples_per_second": 700.548, | |
| "eval_steps_per_second": 87.592, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0113, | |
| "eval_samples_per_second": 701.319, | |
| "eval_steps_per_second": 87.688, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8323, | |
| "eval_samples_per_second": 709.246, | |
| "eval_steps_per_second": 88.679, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0554, | |
| "eval_samples_per_second": 699.391, | |
| "eval_steps_per_second": 87.447, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8485, | |
| "eval_samples_per_second": 708.522, | |
| "eval_steps_per_second": 88.589, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0662, | |
| "eval_samples_per_second": 698.919, | |
| "eval_steps_per_second": 87.388, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8687, | |
| "eval_samples_per_second": 707.618, | |
| "eval_steps_per_second": 88.476, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0433, | |
| "eval_samples_per_second": 699.919, | |
| "eval_steps_per_second": 87.513, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8586, | |
| "eval_samples_per_second": 708.072, | |
| "eval_steps_per_second": 88.533, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8759, | |
| "eval_samples_per_second": 707.296, | |
| "eval_steps_per_second": 88.436, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0595, | |
| "eval_samples_per_second": 699.213, | |
| "eval_steps_per_second": 87.425, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1917, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8638, | |
| "eval_samples_per_second": 707.84, | |
| "eval_steps_per_second": 88.504, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0511, | |
| "eval_samples_per_second": 699.578, | |
| "eval_steps_per_second": 87.471, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8555, | |
| "eval_samples_per_second": 708.208, | |
| "eval_steps_per_second": 88.55, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9996, | |
| "eval_samples_per_second": 701.831, | |
| "eval_steps_per_second": 87.752, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8126, | |
| "eval_samples_per_second": 710.128, | |
| "eval_steps_per_second": 88.79, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": NaN, | |
| "eval_runtime": 16.0183, | |
| "eval_samples_per_second": 701.011, | |
| "eval_steps_per_second": 87.65, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9885, | |
| "eval_samples_per_second": 702.317, | |
| "eval_steps_per_second": 87.813, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8301, | |
| "eval_samples_per_second": 709.347, | |
| "eval_steps_per_second": 88.692, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9921, | |
| "eval_samples_per_second": 702.16, | |
| "eval_steps_per_second": 87.793, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7952, | |
| "eval_samples_per_second": 710.914, | |
| "eval_steps_per_second": 88.888, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9778, | |
| "eval_samples_per_second": 702.786, | |
| "eval_steps_per_second": 87.872, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7758, | |
| "eval_samples_per_second": 711.785, | |
| "eval_steps_per_second": 88.997, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9261, | |
| "eval_samples_per_second": 705.068, | |
| "eval_steps_per_second": 88.157, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.755, | |
| "eval_samples_per_second": 712.727, | |
| "eval_steps_per_second": 89.115, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9384, | |
| "eval_samples_per_second": 704.526, | |
| "eval_steps_per_second": 88.089, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9462, | |
| "eval_samples_per_second": 704.178, | |
| "eval_steps_per_second": 88.046, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7491, | |
| "eval_samples_per_second": 712.992, | |
| "eval_steps_per_second": 89.148, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9538, | |
| "eval_samples_per_second": 703.844, | |
| "eval_steps_per_second": 88.004, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1898, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7443, | |
| "eval_samples_per_second": 713.21, | |
| "eval_steps_per_second": 89.175, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9443, | |
| "eval_samples_per_second": 704.266, | |
| "eval_steps_per_second": 88.057, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7424, | |
| "eval_samples_per_second": 713.296, | |
| "eval_steps_per_second": 89.186, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9509, | |
| "eval_samples_per_second": 703.972, | |
| "eval_steps_per_second": 88.02, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1085 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1095 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.943, | |
| "eval_samples_per_second": 704.32, | |
| "eval_steps_per_second": 88.064, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1105 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1115 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7698, | |
| "eval_samples_per_second": 712.058, | |
| "eval_steps_per_second": 89.031, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1135 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9199, | |
| "eval_samples_per_second": 705.346, | |
| "eval_steps_per_second": 88.192, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1145 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1155 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7367, | |
| "eval_samples_per_second": 713.557, | |
| "eval_steps_per_second": 89.218, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1165 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9137, | |
| "eval_samples_per_second": 705.62, | |
| "eval_steps_per_second": 88.226, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1185 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1195 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7216, | |
| "eval_samples_per_second": 714.242, | |
| "eval_steps_per_second": 89.304, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1205 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1215 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9017, | |
| "eval_samples_per_second": 706.149, | |
| "eval_steps_per_second": 88.292, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1235 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7285, | |
| "eval_samples_per_second": 713.925, | |
| "eval_steps_per_second": 89.265, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1245 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1255 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.87, | |
| "eval_samples_per_second": 707.564, | |
| "eval_steps_per_second": 88.469, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1265 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8805, | |
| "eval_samples_per_second": 707.092, | |
| "eval_steps_per_second": 88.41, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1285 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1295 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7036, | |
| "eval_samples_per_second": 715.058, | |
| "eval_steps_per_second": 89.406, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1305 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1315 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.886, | |
| "eval_samples_per_second": 706.849, | |
| "eval_steps_per_second": 88.38, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1335 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6885, | |
| "eval_samples_per_second": 715.746, | |
| "eval_steps_per_second": 89.492, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1345 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1355 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8594, | |
| "eval_samples_per_second": 708.034, | |
| "eval_steps_per_second": 88.528, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6957, | |
| "eval_samples_per_second": 715.418, | |
| "eval_steps_per_second": 89.451, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1385 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1395 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8791, | |
| "eval_samples_per_second": 707.154, | |
| "eval_steps_per_second": 88.418, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1405 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1415 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6831, | |
| "eval_samples_per_second": 715.994, | |
| "eval_steps_per_second": 89.523, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1435 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8786, | |
| "eval_samples_per_second": 707.177, | |
| "eval_steps_per_second": 88.421, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1445 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1455 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8934, | |
| "eval_samples_per_second": 706.521, | |
| "eval_steps_per_second": 88.339, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1465 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.713, | |
| "eval_samples_per_second": 714.633, | |
| "eval_steps_per_second": 89.353, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1485 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1495 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8915, | |
| "eval_samples_per_second": 706.603, | |
| "eval_steps_per_second": 88.349, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1505 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1515 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6977, | |
| "eval_samples_per_second": 715.329, | |
| "eval_steps_per_second": 89.44, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1535 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8745, | |
| "eval_samples_per_second": 707.36, | |
| "eval_steps_per_second": 88.444, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1545 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1555 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7165, | |
| "eval_samples_per_second": 714.474, | |
| "eval_steps_per_second": 89.333, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1565 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8769, | |
| "eval_samples_per_second": 707.255, | |
| "eval_steps_per_second": 88.431, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1585 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1595 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6837, | |
| "eval_samples_per_second": 715.966, | |
| "eval_steps_per_second": 89.52, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1605 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1615 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8588, | |
| "eval_samples_per_second": 708.06, | |
| "eval_steps_per_second": 88.531, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1635 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6417, | |
| "eval_samples_per_second": 717.887, | |
| "eval_steps_per_second": 89.76, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1645 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1655 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6714, | |
| "eval_samples_per_second": 716.53, | |
| "eval_steps_per_second": 89.59, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1665 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8411, | |
| "eval_samples_per_second": 708.85, | |
| "eval_steps_per_second": 88.63, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1685 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1695 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6626, | |
| "eval_samples_per_second": 716.931, | |
| "eval_steps_per_second": 89.64, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1705 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1715 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8371, | |
| "eval_samples_per_second": 709.031, | |
| "eval_steps_per_second": 88.653, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1735 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6868, | |
| "eval_samples_per_second": 715.827, | |
| "eval_steps_per_second": 89.502, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1745 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1755 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8592, | |
| "eval_samples_per_second": 708.042, | |
| "eval_steps_per_second": 88.529, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1765 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.678, | |
| "eval_samples_per_second": 716.228, | |
| "eval_steps_per_second": 89.552, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1785 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1795 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8719, | |
| "eval_samples_per_second": 707.475, | |
| "eval_steps_per_second": 88.458, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1805 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1815 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6641, | |
| "eval_samples_per_second": 716.862, | |
| "eval_steps_per_second": 89.632, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1835 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8041, | |
| "eval_samples_per_second": 710.513, | |
| "eval_steps_per_second": 88.838, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1845 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1855 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8721, | |
| "eval_samples_per_second": 707.47, | |
| "eval_steps_per_second": 88.457, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1865 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6938, | |
| "eval_samples_per_second": 715.504, | |
| "eval_steps_per_second": 89.462, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1885 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1895 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8722, | |
| "eval_samples_per_second": 707.463, | |
| "eval_steps_per_second": 88.456, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1905 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1915 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6748, | |
| "eval_samples_per_second": 716.371, | |
| "eval_steps_per_second": 89.57, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1935 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.879, | |
| "eval_samples_per_second": 707.159, | |
| "eval_steps_per_second": 88.419, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1945 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1955 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7268, | |
| "eval_samples_per_second": 714.006, | |
| "eval_steps_per_second": 89.275, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1965 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9165, | |
| "eval_samples_per_second": 705.492, | |
| "eval_steps_per_second": 88.21, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1985 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 1995 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.696, | |
| "eval_samples_per_second": 715.404, | |
| "eval_steps_per_second": 89.449, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2005 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2015 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8867, | |
| "eval_samples_per_second": 706.819, | |
| "eval_steps_per_second": 88.376, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2035 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9066, | |
| "eval_samples_per_second": 705.935, | |
| "eval_steps_per_second": 88.265, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2045 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2055 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6924, | |
| "eval_samples_per_second": 715.57, | |
| "eval_steps_per_second": 89.47, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2065 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9015, | |
| "eval_samples_per_second": 706.162, | |
| "eval_steps_per_second": 88.294, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2085 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2095 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7098, | |
| "eval_samples_per_second": 714.778, | |
| "eval_steps_per_second": 89.371, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2105 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2115 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8632, | |
| "eval_samples_per_second": 707.863, | |
| "eval_steps_per_second": 88.506, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2135 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.705, | |
| "eval_samples_per_second": 714.995, | |
| "eval_steps_per_second": 89.398, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2145 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2155 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8874, | |
| "eval_samples_per_second": 706.785, | |
| "eval_steps_per_second": 88.372, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2165 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6771, | |
| "eval_samples_per_second": 716.267, | |
| "eval_steps_per_second": 89.557, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2185 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2195 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8698, | |
| "eval_samples_per_second": 707.572, | |
| "eval_steps_per_second": 88.47, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2205 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2215 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.879, | |
| "eval_samples_per_second": 707.161, | |
| "eval_steps_per_second": 88.419, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2235 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6856, | |
| "eval_samples_per_second": 715.878, | |
| "eval_steps_per_second": 89.509, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2245 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2255 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8683, | |
| "eval_samples_per_second": 707.639, | |
| "eval_steps_per_second": 88.479, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2265 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6867, | |
| "eval_samples_per_second": 715.831, | |
| "eval_steps_per_second": 89.503, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2285 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2295 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8511, | |
| "eval_samples_per_second": 708.404, | |
| "eval_steps_per_second": 88.574, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2305 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2315 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6951, | |
| "eval_samples_per_second": 715.446, | |
| "eval_steps_per_second": 89.455, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2335 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8559, | |
| "eval_samples_per_second": 708.191, | |
| "eval_steps_per_second": 88.548, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2345 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2355 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6855, | |
| "eval_samples_per_second": 715.884, | |
| "eval_steps_per_second": 89.509, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2365 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8547, | |
| "eval_samples_per_second": 708.246, | |
| "eval_steps_per_second": 88.554, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2385 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2395 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7556, | |
| "eval_samples_per_second": 712.7, | |
| "eval_steps_per_second": 89.111, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2405 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2415 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6988, | |
| "eval_samples_per_second": 715.279, | |
| "eval_steps_per_second": 89.434, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2435 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8568, | |
| "eval_samples_per_second": 708.149, | |
| "eval_steps_per_second": 88.542, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2445 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2455 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6752, | |
| "eval_samples_per_second": 716.355, | |
| "eval_steps_per_second": 89.568, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2465 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8836, | |
| "eval_samples_per_second": 706.955, | |
| "eval_steps_per_second": 88.393, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2485 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2495 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7085, | |
| "eval_samples_per_second": 714.836, | |
| "eval_steps_per_second": 89.378, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2505 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2515 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8686, | |
| "eval_samples_per_second": 707.623, | |
| "eval_steps_per_second": 88.476, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2535 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6849, | |
| "eval_samples_per_second": 715.912, | |
| "eval_steps_per_second": 89.513, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2545 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2555 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9002, | |
| "eval_samples_per_second": 706.218, | |
| "eval_steps_per_second": 88.301, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2565 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7079, | |
| "eval_samples_per_second": 714.861, | |
| "eval_steps_per_second": 89.381, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2585 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2595 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7419, | |
| "eval_samples_per_second": 713.319, | |
| "eval_steps_per_second": 89.189, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2605 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2615 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.861, | |
| "eval_samples_per_second": 707.963, | |
| "eval_steps_per_second": 88.519, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6752, | |
| "eval_samples_per_second": 716.355, | |
| "eval_steps_per_second": 89.568, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2645 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2655 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8773, | |
| "eval_samples_per_second": 707.237, | |
| "eval_steps_per_second": 88.428, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2665 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6817, | |
| "eval_samples_per_second": 716.056, | |
| "eval_steps_per_second": 89.531, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2685 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2695 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8711, | |
| "eval_samples_per_second": 707.514, | |
| "eval_steps_per_second": 88.463, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2705 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2715 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6883, | |
| "eval_samples_per_second": 715.757, | |
| "eval_steps_per_second": 89.493, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2735 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8874, | |
| "eval_samples_per_second": 706.785, | |
| "eval_steps_per_second": 88.372, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2745 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2755 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7057, | |
| "eval_samples_per_second": 714.964, | |
| "eval_steps_per_second": 89.394, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2765 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.893, | |
| "eval_samples_per_second": 706.538, | |
| "eval_steps_per_second": 88.341, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2785 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2795 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8887, | |
| "eval_samples_per_second": 706.727, | |
| "eval_steps_per_second": 88.365, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2805 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2815 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7063, | |
| "eval_samples_per_second": 714.936, | |
| "eval_steps_per_second": 89.391, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2835 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8851, | |
| "eval_samples_per_second": 706.887, | |
| "eval_steps_per_second": 88.384, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2845 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2855 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6847, | |
| "eval_samples_per_second": 715.919, | |
| "eval_steps_per_second": 89.514, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2865 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2875 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.886, | |
| "eval_samples_per_second": 706.847, | |
| "eval_steps_per_second": 88.38, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2885 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2895 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7008, | |
| "eval_samples_per_second": 715.184, | |
| "eval_steps_per_second": 89.422, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2905 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2915 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9108, | |
| "eval_samples_per_second": 705.746, | |
| "eval_steps_per_second": 88.242, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2925 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2935 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7225, | |
| "eval_samples_per_second": 714.199, | |
| "eval_steps_per_second": 89.299, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2945 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2955 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9111, | |
| "eval_samples_per_second": 705.732, | |
| "eval_steps_per_second": 88.24, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2965 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2975 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9132, | |
| "eval_samples_per_second": 705.64, | |
| "eval_steps_per_second": 88.229, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2985 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2995 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7213, | |
| "eval_samples_per_second": 714.252, | |
| "eval_steps_per_second": 89.305, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3005 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3015 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8913, | |
| "eval_samples_per_second": 706.611, | |
| "eval_steps_per_second": 88.35, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3025 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3035 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7138, | |
| "eval_samples_per_second": 714.595, | |
| "eval_steps_per_second": 89.348, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3045 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3055 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8922, | |
| "eval_samples_per_second": 706.574, | |
| "eval_steps_per_second": 88.345, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3065 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3075 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6886, | |
| "eval_samples_per_second": 715.74, | |
| "eval_steps_per_second": 89.491, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3085 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3095 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8929, | |
| "eval_samples_per_second": 706.542, | |
| "eval_steps_per_second": 88.341, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3105 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3115 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.711, | |
| "eval_samples_per_second": 714.72, | |
| "eval_steps_per_second": 89.364, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3125 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3135 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8906, | |
| "eval_samples_per_second": 706.643, | |
| "eval_steps_per_second": 88.354, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3145 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3155 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8781, | |
| "eval_samples_per_second": 707.201, | |
| "eval_steps_per_second": 88.424, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3165 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3175 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7055, | |
| "eval_samples_per_second": 714.972, | |
| "eval_steps_per_second": 89.395, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3185 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3195 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9074, | |
| "eval_samples_per_second": 705.896, | |
| "eval_steps_per_second": 88.261, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3205 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3215 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6997, | |
| "eval_samples_per_second": 715.237, | |
| "eval_steps_per_second": 89.429, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3225 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3235 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8919, | |
| "eval_samples_per_second": 706.586, | |
| "eval_steps_per_second": 88.347, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3245 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3255 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7046, | |
| "eval_samples_per_second": 715.013, | |
| "eval_steps_per_second": 89.401, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3265 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3275 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9052, | |
| "eval_samples_per_second": 705.995, | |
| "eval_steps_per_second": 88.273, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3285 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3295 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7063, | |
| "eval_samples_per_second": 714.934, | |
| "eval_steps_per_second": 89.391, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3305 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3315 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9043, | |
| "eval_samples_per_second": 706.037, | |
| "eval_steps_per_second": 88.278, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3335 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7016, | |
| "eval_samples_per_second": 715.148, | |
| "eval_steps_per_second": 89.417, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3345 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3355 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8932, | |
| "eval_samples_per_second": 706.527, | |
| "eval_steps_per_second": 88.34, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3365 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3375 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9063, | |
| "eval_samples_per_second": 705.945, | |
| "eval_steps_per_second": 88.267, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3385 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2168, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3395 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7081, | |
| "eval_samples_per_second": 714.853, | |
| "eval_steps_per_second": 89.38, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3405 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3415 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9178, | |
| "eval_samples_per_second": 705.437, | |
| "eval_steps_per_second": 88.203, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3425 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3435 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7364, | |
| "eval_samples_per_second": 713.57, | |
| "eval_steps_per_second": 89.22, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3445 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3455 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8945, | |
| "eval_samples_per_second": 706.471, | |
| "eval_steps_per_second": 88.332, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3465 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3475 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7262, | |
| "eval_samples_per_second": 714.029, | |
| "eval_steps_per_second": 89.277, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3485 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3495 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9073, | |
| "eval_samples_per_second": 705.901, | |
| "eval_steps_per_second": 88.261, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3505 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3515 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7094, | |
| "eval_samples_per_second": 714.794, | |
| "eval_steps_per_second": 89.373, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3525 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3535 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9005, | |
| "eval_samples_per_second": 706.204, | |
| "eval_steps_per_second": 88.299, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3545 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3555 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7145, | |
| "eval_samples_per_second": 714.561, | |
| "eval_steps_per_second": 89.344, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3565 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3575 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8773, | |
| "eval_samples_per_second": 707.234, | |
| "eval_steps_per_second": 88.428, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3585 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3595 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7233, | |
| "eval_samples_per_second": 714.162, | |
| "eval_steps_per_second": 89.294, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3605 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3615 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6906, | |
| "eval_samples_per_second": 715.649, | |
| "eval_steps_per_second": 89.48, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3625 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3635 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8897, | |
| "eval_samples_per_second": 706.686, | |
| "eval_steps_per_second": 88.359, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3645 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3655 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7193, | |
| "eval_samples_per_second": 714.344, | |
| "eval_steps_per_second": 89.317, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3665 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3675 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8928, | |
| "eval_samples_per_second": 706.546, | |
| "eval_steps_per_second": 88.342, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3685 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3695 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6995, | |
| "eval_samples_per_second": 715.244, | |
| "eval_steps_per_second": 89.429, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3705 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3715 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8739, | |
| "eval_samples_per_second": 707.388, | |
| "eval_steps_per_second": 88.447, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3725 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3735 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7018, | |
| "eval_samples_per_second": 715.141, | |
| "eval_steps_per_second": 89.417, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3745 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3755 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8704, | |
| "eval_samples_per_second": 707.545, | |
| "eval_steps_per_second": 88.467, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3765 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3775 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6876, | |
| "eval_samples_per_second": 715.786, | |
| "eval_steps_per_second": 89.497, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3785 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3795 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9025, | |
| "eval_samples_per_second": 706.117, | |
| "eval_steps_per_second": 88.288, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3805 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3815 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6921, | |
| "eval_samples_per_second": 715.584, | |
| "eval_steps_per_second": 89.472, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3825 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3835 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.84, | |
| "eval_samples_per_second": 708.902, | |
| "eval_steps_per_second": 88.636, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3845 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3855 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9108, | |
| "eval_samples_per_second": 705.749, | |
| "eval_steps_per_second": 88.242, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3865 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3875 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7141, | |
| "eval_samples_per_second": 714.583, | |
| "eval_steps_per_second": 89.347, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3885 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3895 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8962, | |
| "eval_samples_per_second": 706.397, | |
| "eval_steps_per_second": 88.323, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3905 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3915 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7251, | |
| "eval_samples_per_second": 714.08, | |
| "eval_steps_per_second": 89.284, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3925 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3935 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9257, | |
| "eval_samples_per_second": 705.087, | |
| "eval_steps_per_second": 88.159, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3945 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3955 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7363, | |
| "eval_samples_per_second": 713.571, | |
| "eval_steps_per_second": 89.22, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3965 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3975 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9102, | |
| "eval_samples_per_second": 705.774, | |
| "eval_steps_per_second": 88.245, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3985 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 3995 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7315, | |
| "eval_samples_per_second": 713.79, | |
| "eval_steps_per_second": 89.248, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4005 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4015 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9232, | |
| "eval_samples_per_second": 705.196, | |
| "eval_steps_per_second": 88.173, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4025 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4035 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7267, | |
| "eval_samples_per_second": 714.009, | |
| "eval_steps_per_second": 89.275, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4045 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4055 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9143, | |
| "eval_samples_per_second": 705.59, | |
| "eval_steps_per_second": 88.222, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4065 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4075 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.912, | |
| "eval_samples_per_second": 705.692, | |
| "eval_steps_per_second": 88.235, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4085 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7099, | |
| "eval_samples_per_second": 714.771, | |
| "eval_steps_per_second": 89.37, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4105 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4115 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8939, | |
| "eval_samples_per_second": 706.497, | |
| "eval_steps_per_second": 88.336, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4125 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4135 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7099, | |
| "eval_samples_per_second": 714.773, | |
| "eval_steps_per_second": 89.371, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4145 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4155 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8976, | |
| "eval_samples_per_second": 706.332, | |
| "eval_steps_per_second": 88.315, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4165 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4175 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7214, | |
| "eval_samples_per_second": 714.25, | |
| "eval_steps_per_second": 89.305, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4185 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4195 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8908, | |
| "eval_samples_per_second": 706.637, | |
| "eval_steps_per_second": 88.353, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4205 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4215 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7125, | |
| "eval_samples_per_second": 714.655, | |
| "eval_steps_per_second": 89.356, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4225 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4235 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9201, | |
| "eval_samples_per_second": 705.333, | |
| "eval_steps_per_second": 88.19, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4245 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4255 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7117, | |
| "eval_samples_per_second": 714.69, | |
| "eval_steps_per_second": 89.36, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4265 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9492, | |
| "eval_samples_per_second": 704.048, | |
| "eval_steps_per_second": 88.03, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4285 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4295 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7234, | |
| "eval_samples_per_second": 714.156, | |
| "eval_steps_per_second": 89.293, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4305 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4315 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7337, | |
| "eval_samples_per_second": 713.69, | |
| "eval_steps_per_second": 89.235, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4325 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4335 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9172, | |
| "eval_samples_per_second": 705.462, | |
| "eval_steps_per_second": 88.206, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4345 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4355 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7292, | |
| "eval_samples_per_second": 713.893, | |
| "eval_steps_per_second": 89.26, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4365 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4375 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9237, | |
| "eval_samples_per_second": 705.177, | |
| "eval_steps_per_second": 88.171, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4385 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4395 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7352, | |
| "eval_samples_per_second": 713.622, | |
| "eval_steps_per_second": 89.227, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4405 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4415 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.919, | |
| "eval_samples_per_second": 705.385, | |
| "eval_steps_per_second": 88.197, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4425 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4435 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7246, | |
| "eval_samples_per_second": 714.102, | |
| "eval_steps_per_second": 89.287, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4445 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4455 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9071, | |
| "eval_samples_per_second": 705.909, | |
| "eval_steps_per_second": 88.262, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4465 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4475 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7139, | |
| "eval_samples_per_second": 714.59, | |
| "eval_steps_per_second": 89.348, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4485 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4495 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6999, | |
| "eval_samples_per_second": 715.228, | |
| "eval_steps_per_second": 89.427, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4505 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4515 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9069, | |
| "eval_samples_per_second": 705.922, | |
| "eval_steps_per_second": 88.264, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4525 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4535 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7098, | |
| "eval_samples_per_second": 714.779, | |
| "eval_steps_per_second": 89.371, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4545 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4555 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.917, | |
| "eval_samples_per_second": 705.474, | |
| "eval_steps_per_second": 88.208, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4565 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4575 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7225, | |
| "eval_samples_per_second": 714.198, | |
| "eval_steps_per_second": 89.299, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4585 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4595 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8884, | |
| "eval_samples_per_second": 706.743, | |
| "eval_steps_per_second": 88.366, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4605 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4615 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7303, | |
| "eval_samples_per_second": 713.844, | |
| "eval_steps_per_second": 89.254, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4625 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4635 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9083, | |
| "eval_samples_per_second": 705.859, | |
| "eval_steps_per_second": 88.256, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4645 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4655 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7041, | |
| "eval_samples_per_second": 715.034, | |
| "eval_steps_per_second": 89.403, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4665 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4675 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7857, | |
| "eval_samples_per_second": 711.34, | |
| "eval_steps_per_second": 88.941, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4685 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4695 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9077, | |
| "eval_samples_per_second": 705.883, | |
| "eval_steps_per_second": 88.259, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4705 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4715 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6901, | |
| "eval_samples_per_second": 715.673, | |
| "eval_steps_per_second": 89.483, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4725 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4735 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8769, | |
| "eval_samples_per_second": 707.254, | |
| "eval_steps_per_second": 88.43, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4745 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4755 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7061, | |
| "eval_samples_per_second": 714.947, | |
| "eval_steps_per_second": 89.392, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4765 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4775 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9232, | |
| "eval_samples_per_second": 705.195, | |
| "eval_steps_per_second": 88.173, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4785 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4795 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7073, | |
| "eval_samples_per_second": 714.889, | |
| "eval_steps_per_second": 89.385, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4805 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4810 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4815 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9364, | |
| "eval_samples_per_second": 704.615, | |
| "eval_steps_per_second": 88.1, | |
| "step": 4820 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4825 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4830 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4835 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7249, | |
| "eval_samples_per_second": 714.091, | |
| "eval_steps_per_second": 89.285, | |
| "step": 4840 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4845 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4855 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9282, | |
| "eval_samples_per_second": 704.974, | |
| "eval_steps_per_second": 88.145, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4865 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4870 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4875 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9044, | |
| "eval_samples_per_second": 706.029, | |
| "eval_steps_per_second": 88.277, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4885 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4890 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4895 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7192, | |
| "eval_samples_per_second": 714.351, | |
| "eval_steps_per_second": 89.318, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4905 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4910 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4915 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9272, | |
| "eval_samples_per_second": 705.022, | |
| "eval_steps_per_second": 88.151, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4925 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4930 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4935 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7305, | |
| "eval_samples_per_second": 713.837, | |
| "eval_steps_per_second": 89.253, | |
| "step": 4940 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4945 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4955 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.908, | |
| "eval_samples_per_second": 705.87, | |
| "eval_steps_per_second": 88.257, | |
| "step": 4960 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4965 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4970 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4975 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7244, | |
| "eval_samples_per_second": 714.111, | |
| "eval_steps_per_second": 89.288, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4985 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4990 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 4995 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9047, | |
| "eval_samples_per_second": 706.019, | |
| "eval_steps_per_second": 88.276, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5005 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5010 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5015 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7105, | |
| "eval_samples_per_second": 714.744, | |
| "eval_steps_per_second": 89.367, | |
| "step": 5020 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5025 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5030 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5035 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8981, | |
| "eval_samples_per_second": 706.309, | |
| "eval_steps_per_second": 88.312, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5045 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5055 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9217, | |
| "eval_samples_per_second": 705.264, | |
| "eval_steps_per_second": 88.182, | |
| "step": 5060 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5065 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5070 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5075 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.6829, | |
| "eval_samples_per_second": 716.002, | |
| "eval_steps_per_second": 89.524, | |
| "step": 5080 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5085 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5090 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5095 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9071, | |
| "eval_samples_per_second": 705.909, | |
| "eval_steps_per_second": 88.262, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5105 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5110 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5115 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7211, | |
| "eval_samples_per_second": 714.264, | |
| "eval_steps_per_second": 89.307, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5125 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5130 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5135 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8927, | |
| "eval_samples_per_second": 706.553, | |
| "eval_steps_per_second": 88.343, | |
| "step": 5140 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5145 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5155 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7165, | |
| "eval_samples_per_second": 714.472, | |
| "eval_steps_per_second": 89.333, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5165 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5170 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5175 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.904, | |
| "eval_samples_per_second": 706.051, | |
| "eval_steps_per_second": 88.28, | |
| "step": 5180 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5185 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5190 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5195 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7137, | |
| "eval_samples_per_second": 714.598, | |
| "eval_steps_per_second": 89.349, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5205 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5210 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5215 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9059, | |
| "eval_samples_per_second": 705.963, | |
| "eval_steps_per_second": 88.269, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5230 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5235 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 7.4831, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.917, | |
| "eval_samples_per_second": 705.474, | |
| "eval_steps_per_second": 88.208, | |
| "step": 5240 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5245 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5255 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7074, | |
| "eval_samples_per_second": 714.886, | |
| "eval_steps_per_second": 89.385, | |
| "step": 5260 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5265 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5270 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5275 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9083, | |
| "eval_samples_per_second": 705.859, | |
| "eval_steps_per_second": 88.256, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5285 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5290 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5295 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7278, | |
| "eval_samples_per_second": 713.959, | |
| "eval_steps_per_second": 89.269, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5305 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5310 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5315 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9046, | |
| "eval_samples_per_second": 706.02, | |
| "eval_steps_per_second": 88.276, | |
| "step": 5320 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5325 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5330 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5335 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7439, | |
| "eval_samples_per_second": 713.229, | |
| "eval_steps_per_second": 89.177, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5345 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5355 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8989, | |
| "eval_samples_per_second": 706.274, | |
| "eval_steps_per_second": 88.308, | |
| "step": 5360 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5365 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5370 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5375 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7299, | |
| "eval_samples_per_second": 713.861, | |
| "eval_steps_per_second": 89.256, | |
| "step": 5380 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5385 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5390 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5395 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9164, | |
| "eval_samples_per_second": 705.497, | |
| "eval_steps_per_second": 88.211, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5405 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5410 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5415 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9009, | |
| "eval_samples_per_second": 706.187, | |
| "eval_steps_per_second": 88.297, | |
| "step": 5420 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5425 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5430 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5435 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.708, | |
| "eval_samples_per_second": 714.86, | |
| "eval_steps_per_second": 89.381, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5445 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5455 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8909, | |
| "eval_samples_per_second": 706.63, | |
| "eval_steps_per_second": 88.352, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5465 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5470 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5475 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7301, | |
| "eval_samples_per_second": 713.854, | |
| "eval_steps_per_second": 89.256, | |
| "step": 5480 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5485 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5490 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5495 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8742, | |
| "eval_samples_per_second": 707.376, | |
| "eval_steps_per_second": 88.446, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5505 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5510 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5515 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7415, | |
| "eval_samples_per_second": 713.337, | |
| "eval_steps_per_second": 89.191, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5525 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5530 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5535 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8979, | |
| "eval_samples_per_second": 706.321, | |
| "eval_steps_per_second": 88.314, | |
| "step": 5540 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5545 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5555 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.7083, | |
| "eval_samples_per_second": 714.847, | |
| "eval_steps_per_second": 89.38, | |
| "step": 5560 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5565 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5570 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5575 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.8717, | |
| "eval_samples_per_second": 707.484, | |
| "eval_steps_per_second": 88.459, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5585 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5590 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5595 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": NaN, | |
| "eval_runtime": 15.9323, | |
| "eval_samples_per_second": 704.795, | |
| "eval_steps_per_second": 88.123, | |
| "step": 5600 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 5614, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "total_flos": 1586150840991744.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |