| { | |
| "best_metric": 0.7640588283538818, | |
| "best_model_checkpoint": "./model_20230703_attempt1/checkpoint-400", | |
| "epoch": 4.481792717086835, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 2.5488, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.3131, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 2.1798, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 1.6567, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.000147, | |
| "loss": 1.2086, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.00017699999999999997, | |
| "loss": 0.8952, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 0.00020699999999999996, | |
| "loss": 1.0646, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 0.000237, | |
| "loss": 0.7725, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.000267, | |
| "loss": 0.8192, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.00029699999999999996, | |
| "loss": 0.7403, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 0.00029764397905759156, | |
| "loss": 0.6473, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0002950261780104712, | |
| "loss": 0.7524, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 0.00029240837696335075, | |
| "loss": 0.6775, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00028979057591623034, | |
| "loss": 0.5884, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.00028717277486910994, | |
| "loss": 0.7117, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 0.00028455497382198953, | |
| "loss": 0.5925, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 0.00028193717277486907, | |
| "loss": 0.6675, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 0.00027931937172774867, | |
| "loss": 0.6126, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "learning_rate": 0.00027670157068062826, | |
| "loss": 0.557, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 0.00027408376963350786, | |
| "loss": 0.5362, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_loss": 0.8287817239761353, | |
| "eval_runtime": 34.4542, | |
| "eval_samples_per_second": 11.61, | |
| "eval_steps_per_second": 1.451, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 0.0002714659685863874, | |
| "loss": 0.4951, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 0.000268848167539267, | |
| "loss": 0.4904, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 0.0002662303664921466, | |
| "loss": 0.4544, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 0.0002636125654450262, | |
| "loss": 0.5705, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 0.0002609947643979057, | |
| "loss": 0.5654, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 0.0002583769633507853, | |
| "loss": 0.445, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 0.0002557591623036649, | |
| "loss": 0.3859, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 0.0002531413612565445, | |
| "loss": 0.5015, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.25, | |
| "learning_rate": 0.00025052356020942404, | |
| "loss": 0.4177, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 0.00024790575916230364, | |
| "loss": 0.4322, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.47, | |
| "learning_rate": 0.00024528795811518323, | |
| "loss": 0.3028, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.59, | |
| "learning_rate": 0.00024267015706806283, | |
| "loss": 0.3839, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.7, | |
| "learning_rate": 0.0002400523560209424, | |
| "loss": 0.3121, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 0.00023743455497382196, | |
| "loss": 0.5043, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 0.00023481675392670153, | |
| "loss": 0.3569, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 0.00023219895287958115, | |
| "loss": 0.2791, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.15, | |
| "learning_rate": 0.00022958115183246072, | |
| "loss": 0.2648, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.26, | |
| "learning_rate": 0.00022696335078534028, | |
| "loss": 0.2998, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.37, | |
| "learning_rate": 0.00022434554973821985, | |
| "loss": 0.3416, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 0.00022172774869109947, | |
| "loss": 0.3044, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "eval_loss": 0.7640588283538818, | |
| "eval_runtime": 34.4837, | |
| "eval_samples_per_second": 11.6, | |
| "eval_steps_per_second": 1.45, | |
| "step": 400 | |
| } | |
| ], | |
| "max_steps": 1246, | |
| "num_train_epochs": 14, | |
| "total_flos": 1.32826870923264e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |