| { | |
| "best_metric": 2.670438766479492, | |
| "best_model_checkpoint": "output/bob-dylan/checkpoint-321", | |
| "epoch": 1.0, | |
| "global_step": 321, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00013711788223044424, | |
| "loss": 3.6967, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001368717255202631, | |
| "loss": 3.7692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00013646211919423798, | |
| "loss": 3.4916, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00013589004389254062, | |
| "loss": 3.6186, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00013515686922297834, | |
| "loss": 3.5756, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00013426435048201062, | |
| "loss": 3.236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001332146244523866, | |
| "loss": 3.3956, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00013201020428746477, | |
| "loss": 3.3277, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001306539734944624, | |
| "loss": 3.2617, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012914917903103908, | |
| "loss": 3.554, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00012749942353174222, | |
| "loss": 3.2625, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012570865668292503, | |
| "loss": 3.2986, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.0001237811657667863, | |
| "loss": 3.264, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00012172156539717071, | |
| "loss": 3.0437, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011953478647170303, | |
| "loss": 3.0527, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.000117226064366706, | |
| "loss": 3.3623, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0001148009264031647, | |
| "loss": 3.0801, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0001122651786137447, | |
| "loss": 3.0471, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010962489184254581, | |
| "loss": 3.051, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010688638721086951, | |
| "loss": 3.2191, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0001040562209837965, | |
| "loss": 2.9343, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00010114116887380613, | |
| "loss": 2.9893, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 9.814820981901533e-05, | |
| "loss": 3.1068, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.508450927487455e-05, | |
| "loss": 3.1636, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.195740205932179e-05, | |
| "loss": 3.1864, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 8.877437479246497e-05, | |
| "loss": 2.9116, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.554304797283438e-05, | |
| "loss": 3.1795, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 8.227115773311617e-05, | |
| "loss": 2.9074, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.896653731904552e-05, | |
| "loss": 3.1763, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.56370983358012e-05, | |
| "loss": 3.0588, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.229081180679942e-05, | |
| "loss": 2.9373, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.893568909023427e-05, | |
| "loss": 3.092, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 6.557976269905237e-05, | |
| "loss": 3.0733, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 6.223106707028106e-05, | |
| "loss": 2.9187, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 5.889761932974993e-05, | |
| "loss": 2.9659, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.5587400098257335e-05, | |
| "loss": 3.1799, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.230833438513365e-05, | |
| "loss": 2.9959, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.9068272614944106e-05, | |
| "loss": 2.8529, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.58749718327555e-05, | |
| "loss": 3.0337, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.2736077132963006e-05, | |
| "loss": 3.0827, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9659103356138536e-05, | |
| "loss": 2.8453, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.6651417097720435e-05, | |
| "loss": 2.9619, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.372021907161731e-05, | |
| "loss": 3.0061, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 3.0872526870949537e-05, | |
| "loss": 2.8687, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.8115158167201102e-05, | |
| "loss": 2.9913, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.5454714388004492e-05, | |
| "loss": 2.9778, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.289756491263597e-05, | |
| "loss": 3.0748, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 2.0449831823058788e-05, | |
| "loss": 2.7658, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8117375247021725e-05, | |
| "loss": 2.9792, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5905779328303487e-05, | |
| "loss": 2.7718, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3820338857691364e-05, | |
| "loss": 2.9954, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1866046596701035e-05, | |
| "loss": 2.9246, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 1.0047581324385938e-05, | |
| "loss": 2.9875, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.36929663585326e-06, | |
| "loss": 2.673, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.835210519304257e-06, | |
| "loss": 2.8515, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.448995736552248e-06, | |
| "loss": 2.9416, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.213971030048682e-06, | |
| "loss": 2.8573, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.133093177468323e-06, | |
| "loss": 2.6045, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.208949912875789e-06, | |
| "loss": 3.0414, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.4437537314208725e-06, | |
| "loss": 2.7666, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.39336592394954e-07, | |
| "loss": 2.7331, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.971455333297437e-07, | |
| "loss": 2.847, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.1823920563887646e-07, | |
| "loss": 2.7128, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.2853400962779e-09, | |
| "loss": 2.6074, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.670438766479492, | |
| "eval_runtime": 18.6137, | |
| "eval_samples_per_second": 22.833, | |
| "eval_steps_per_second": 2.901, | |
| "step": 321 | |
| } | |
| ], | |
| "max_steps": 321, | |
| "num_train_epochs": 1, | |
| "total_flos": 334715092992000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |