| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 19.0145875, | |
| "global_step": 8000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "eval_loss": 2.681640625, | |
| "eval_runtime": 8.3811, | |
| "eval_samples_per_second": 109.293, | |
| "eval_steps_per_second": 13.721, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "eval_loss": 2.513671875, | |
| "eval_runtime": 8.2785, | |
| "eval_samples_per_second": 110.649, | |
| "eval_steps_per_second": 13.891, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 5e-05, | |
| "loss": 6.5037, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_loss": 2.380859375, | |
| "eval_runtime": 8.3078, | |
| "eval_samples_per_second": 110.258, | |
| "eval_steps_per_second": 13.842, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "eval_loss": 2.34375, | |
| "eval_runtime": 8.3276, | |
| "eval_samples_per_second": 109.996, | |
| "eval_steps_per_second": 13.81, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 5e-05, | |
| "loss": 4.8504, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "eval_loss": 2.275390625, | |
| "eval_runtime": 8.3087, | |
| "eval_samples_per_second": 110.247, | |
| "eval_steps_per_second": 13.841, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_loss": 2.333984375, | |
| "eval_runtime": 8.287, | |
| "eval_samples_per_second": 110.535, | |
| "eval_steps_per_second": 13.877, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "eval_loss": 2.20703125, | |
| "eval_runtime": 8.3018, | |
| "eval_samples_per_second": 110.337, | |
| "eval_steps_per_second": 13.852, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 5e-05, | |
| "loss": 4.3741, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "eval_loss": 2.248046875, | |
| "eval_runtime": 8.2881, | |
| "eval_samples_per_second": 110.521, | |
| "eval_steps_per_second": 13.875, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_loss": 2.205078125, | |
| "eval_runtime": 8.2889, | |
| "eval_samples_per_second": 110.51, | |
| "eval_steps_per_second": 13.874, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 5e-05, | |
| "loss": 5.6907, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "eval_loss": 2.25, | |
| "eval_runtime": 8.2748, | |
| "eval_samples_per_second": 110.698, | |
| "eval_steps_per_second": 13.898, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_loss": 2.1640625, | |
| "eval_runtime": 8.2832, | |
| "eval_samples_per_second": 110.586, | |
| "eval_steps_per_second": 13.884, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "eval_loss": 2.146484375, | |
| "eval_runtime": 8.2965, | |
| "eval_samples_per_second": 110.408, | |
| "eval_steps_per_second": 13.861, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 5e-05, | |
| "loss": 4.6906, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_loss": 2.13671875, | |
| "eval_runtime": 8.2725, | |
| "eval_samples_per_second": 110.729, | |
| "eval_steps_per_second": 13.902, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 6.03, | |
| "eval_loss": 2.140625, | |
| "eval_runtime": 8.2842, | |
| "eval_samples_per_second": 110.572, | |
| "eval_steps_per_second": 13.882, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4001, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_loss": 2.146484375, | |
| "eval_runtime": 8.2802, | |
| "eval_samples_per_second": 110.625, | |
| "eval_steps_per_second": 13.888, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "eval_loss": 2.126953125, | |
| "eval_runtime": 8.3968, | |
| "eval_samples_per_second": 109.089, | |
| "eval_steps_per_second": 13.696, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "eval_loss": 2.181640625, | |
| "eval_runtime": 8.3172, | |
| "eval_samples_per_second": 110.133, | |
| "eval_steps_per_second": 13.827, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 8.02, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6049, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "eval_loss": 2.12890625, | |
| "eval_runtime": 8.2765, | |
| "eval_samples_per_second": 110.675, | |
| "eval_steps_per_second": 13.895, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_loss": 2.169921875, | |
| "eval_runtime": 8.296, | |
| "eval_samples_per_second": 110.414, | |
| "eval_steps_per_second": 13.862, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 5e-05, | |
| "loss": 3.5502, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "eval_loss": 2.162109375, | |
| "eval_runtime": 8.2755, | |
| "eval_samples_per_second": 110.688, | |
| "eval_steps_per_second": 13.896, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "eval_loss": 2.201171875, | |
| "eval_runtime": 8.2728, | |
| "eval_samples_per_second": 110.724, | |
| "eval_steps_per_second": 13.901, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 10.03, | |
| "eval_loss": 2.212890625, | |
| "eval_runtime": 8.2776, | |
| "eval_samples_per_second": 110.66, | |
| "eval_steps_per_second": 13.893, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 10.04, | |
| "learning_rate": 5e-05, | |
| "loss": 4.1514, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "eval_loss": 2.279296875, | |
| "eval_runtime": 8.2705, | |
| "eval_samples_per_second": 110.754, | |
| "eval_steps_per_second": 13.905, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 11.03, | |
| "eval_loss": 2.212890625, | |
| "eval_runtime": 8.303, | |
| "eval_samples_per_second": 110.321, | |
| "eval_steps_per_second": 13.85, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2494, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 2.263671875, | |
| "eval_runtime": 8.2843, | |
| "eval_samples_per_second": 110.57, | |
| "eval_steps_per_second": 13.882, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 12.02, | |
| "eval_loss": 2.267578125, | |
| "eval_runtime": 8.2766, | |
| "eval_samples_per_second": 110.674, | |
| "eval_steps_per_second": 13.895, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 2.31640625, | |
| "eval_runtime": 8.3166, | |
| "eval_samples_per_second": 110.142, | |
| "eval_steps_per_second": 13.828, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7284, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 13.02, | |
| "eval_loss": 2.314453125, | |
| "eval_runtime": 8.2867, | |
| "eval_samples_per_second": 110.539, | |
| "eval_steps_per_second": 13.878, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 2.3203125, | |
| "eval_runtime": 8.2686, | |
| "eval_samples_per_second": 110.781, | |
| "eval_steps_per_second": 13.908, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5881, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 14.02, | |
| "eval_loss": 2.375, | |
| "eval_runtime": 8.2905, | |
| "eval_samples_per_second": 110.488, | |
| "eval_steps_per_second": 13.871, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 14.04, | |
| "eval_loss": 2.337890625, | |
| "eval_runtime": 8.2824, | |
| "eval_samples_per_second": 110.596, | |
| "eval_steps_per_second": 13.885, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 15.02, | |
| "eval_loss": 2.3828125, | |
| "eval_runtime": 8.302, | |
| "eval_samples_per_second": 110.335, | |
| "eval_steps_per_second": 13.852, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 15.03, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8623, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "eval_loss": 2.390625, | |
| "eval_runtime": 8.2657, | |
| "eval_samples_per_second": 110.819, | |
| "eval_steps_per_second": 13.913, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 16.02, | |
| "eval_loss": 2.466796875, | |
| "eval_runtime": 8.2805, | |
| "eval_samples_per_second": 110.622, | |
| "eval_steps_per_second": 13.888, | |
| "step": 6800 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9491, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 16.04, | |
| "eval_loss": 2.49609375, | |
| "eval_runtime": 8.2778, | |
| "eval_samples_per_second": 110.658, | |
| "eval_steps_per_second": 13.893, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 17.02, | |
| "eval_loss": 2.498046875, | |
| "eval_runtime": 8.2955, | |
| "eval_samples_per_second": 110.422, | |
| "eval_steps_per_second": 13.863, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 17.04, | |
| "eval_loss": 2.654296875, | |
| "eval_runtime": 8.2783, | |
| "eval_samples_per_second": 110.651, | |
| "eval_steps_per_second": 13.892, | |
| "step": 7400 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3629, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 18.02, | |
| "eval_loss": 2.595703125, | |
| "eval_runtime": 8.301, | |
| "eval_samples_per_second": 110.348, | |
| "eval_steps_per_second": 13.854, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 18.04, | |
| "eval_loss": 2.64453125, | |
| "eval_runtime": 8.2827, | |
| "eval_samples_per_second": 110.592, | |
| "eval_steps_per_second": 13.884, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "learning_rate": 5e-05, | |
| "loss": 1.977, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "eval_loss": 2.701171875, | |
| "eval_runtime": 8.2814, | |
| "eval_samples_per_second": 110.609, | |
| "eval_steps_per_second": 13.886, | |
| "step": 8000 | |
| } | |
| ], | |
| "max_steps": 10000, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 47707692466176.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |