| { | |
| "best_metric": 2.1315526962280273, | |
| "best_model_checkpoint": "output/ed-sheeran/checkpoint-370", | |
| "epoch": 2.0, | |
| "global_step": 370, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001369528677140173, | |
| "loss": 3.3545, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001362132514498528, | |
| "loss": 3.1766, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00013498648015963804, | |
| "loss": 3.1549, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00013328139275863037, | |
| "loss": 3.3386, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001311102744406261, | |
| "loss": 2.866, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012848876816285752, | |
| "loss": 3.055, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012543576193812758, | |
| "loss": 3.0083, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00012197325274624495, | |
| "loss": 3.0672, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00011812618804528037, | |
| "loss": 2.8137, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011392228602455959, | |
| "loss": 2.8218, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00010939183589447406, | |
| "loss": 2.878, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.0001045674796520261, | |
| "loss": 2.7698, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.948397689449238e-05, | |
| "loss": 2.6731, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 9.417795437572918e-05, | |
| "loss": 2.809, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.868764210957135e-05, | |
| "loss": 3.0541, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.305259792170682e-05, | |
| "loss": 2.9041, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 7.731342243463588e-05, | |
| "loss": 2.5536, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.151146653925577e-05, | |
| "loss": 2.6507, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 6.568853346074425e-05, | |
| "loss": 2.5611, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.9886577565364115e-05, | |
| "loss": 3.0623, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.4147402078293195e-05, | |
| "loss": 2.8889, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.851235789042865e-05, | |
| "loss": 2.5995, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.3022045624270836e-05, | |
| "loss": 2.6762, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.77160231055076e-05, | |
| "loss": 2.5995, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.263252034797391e-05, | |
| "loss": 2.867, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.780816410552594e-05, | |
| "loss": 2.8132, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 2.3277713975440426e-05, | |
| "loss": 2.5726, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.9073811954719624e-05, | |
| "loss": 2.3264, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.5226747253755063e-05, | |
| "loss": 2.6873, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1764238061872434e-05, | |
| "loss": 2.6771, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 8.711231837142493e-06, | |
| "loss": 2.7493, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 6.089725559373884e-06, | |
| "loss": 2.6171, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.9186072413696235e-06, | |
| "loss": 2.3292, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 2.2135198403619775e-06, | |
| "loss": 2.8869, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.867485501471999e-07, | |
| "loss": 2.572, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.471322859826806e-07, | |
| "loss": 2.7326, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.5258, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.3434901237487793, | |
| "eval_runtime": 11.1383, | |
| "eval_samples_per_second": 21.547, | |
| "eval_steps_per_second": 2.693, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 2.471322859826806e-07, | |
| "loss": 2.821, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.867485501471922e-07, | |
| "loss": 2.4731, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 2.2135198403619775e-06, | |
| "loss": 2.2909, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.9186072413696235e-06, | |
| "loss": 2.4008, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 6.0897255593738765e-06, | |
| "loss": 2.7587, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 8.711231837142484e-06, | |
| "loss": 2.4763, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.1764238061872427e-05, | |
| "loss": 2.6535, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.5226747253755048e-05, | |
| "loss": 2.4901, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 1.907381195471961e-05, | |
| "loss": 2.5176, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.327771397544039e-05, | |
| "loss": 2.214, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.7808164105525947e-05, | |
| "loss": 2.4581, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.263252034797388e-05, | |
| "loss": 2.4393, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.35, | |
| "learning_rate": 3.771602310550759e-05, | |
| "loss": 2.3357, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 4.302204562427082e-05, | |
| "loss": 2.1878, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 4.851235789042865e-05, | |
| "loss": 2.5465, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 5.4147402078293195e-05, | |
| "loss": 2.3914, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 5.988657756536409e-05, | |
| "loss": 2.4728, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 6.56885334607442e-05, | |
| "loss": 2.4695, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 7.151146653925577e-05, | |
| "loss": 2.4773, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 7.731342243463588e-05, | |
| "loss": 2.4631, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 8.305259792170678e-05, | |
| "loss": 2.5178, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 8.868764210957132e-05, | |
| "loss": 2.5653, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.62, | |
| "learning_rate": 9.417795437572915e-05, | |
| "loss": 2.5981, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 9.948397689449238e-05, | |
| "loss": 2.5919, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.68, | |
| "learning_rate": 0.0001045674796520261, | |
| "loss": 2.4098, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 0.00010939183589447404, | |
| "loss": 2.2096, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 0.00011392228602455961, | |
| "loss": 2.5258, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 0.00011812618804528036, | |
| "loss": 2.3155, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 0.00012197325274624495, | |
| "loss": 2.2606, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.81, | |
| "learning_rate": 0.00012543576193812755, | |
| "loss": 2.2948, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 0.00012848876816285752, | |
| "loss": 2.5757, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.0001311102744406261, | |
| "loss": 2.1925, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 0.00013328139275863037, | |
| "loss": 2.1671, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 0.00013498648015963801, | |
| "loss": 2.729, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 0.0001362132514498528, | |
| "loss": 2.2679, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 0.0001369528677140173, | |
| "loss": 2.0086, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0001372, | |
| "loss": 2.2398, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.1315526962280273, | |
| "eval_runtime": 11.157, | |
| "eval_samples_per_second": 21.511, | |
| "eval_steps_per_second": 2.689, | |
| "step": 370 | |
| } | |
| ], | |
| "max_steps": 370, | |
| "num_train_epochs": 2, | |
| "total_flos": 386450915328000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |