| { | |
| "best_metric": 3.57045841217041, | |
| "best_model_checkpoint": "output/50-cent/checkpoint-258", | |
| "epoch": 1.0, | |
| "global_step": 258, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00013707289568217504, | |
| "loss": 4.0779, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.000136692053734753, | |
| "loss": 4.1148, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00013605888543050137, | |
| "loss": 4.0688, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.000135175737079198, | |
| "loss": 3.9408, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001340458813329925, | |
| "loss": 3.722, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001326735050590528, | |
| "loss": 3.9874, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001310636938244372, | |
| "loss": 3.8949, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00012922241305068514, | |
| "loss": 3.9061, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00012715648590796197, | |
| "loss": 3.8976, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012487356803067445, | |
| "loss": 3.672, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00012238211914825242, | |
| "loss": 3.6326, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.00011969137173622343, | |
| "loss": 3.7851, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.00011681129680374918, | |
| "loss": 3.7425, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011375256694440331, | |
| "loss": 3.7256, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00011052651678711246, | |
| "loss": 3.6549, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00010714510099381572, | |
| "loss": 3.7504, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00010362084995948948, | |
| "loss": 3.7761, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 9.99668233786982e-05, | |
| "loss": 3.6905, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 9.619656185073828e-05, | |
| "loss": 3.6569, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 9.232403670270978e-05, | |
| "loss": 3.6521, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.83635982164553e-05, | |
| "loss": 3.7574, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 8.432992245121922e-05, | |
| "loss": 3.6063, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 8.023795685908513e-05, | |
| "loss": 3.6537, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 7.61028648947222e-05, | |
| "loss": 3.6364, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 7.193996982469813e-05, | |
| "loss": 3.7473, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 6.776469794458297e-05, | |
| "loss": 3.6127, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 6.359252141426174e-05, | |
| "loss": 3.6751, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.943890092328931e-05, | |
| "loss": 3.6126, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.531922839875045e-05, | |
| "loss": 3.6423, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.1248769967930697e-05, | |
| "loss": 3.4521, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4.724260938715906e-05, | |
| "loss": 3.6127, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.331559214645638e-05, | |
| "loss": 3.7675, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 3.9482270457119095e-05, | |
| "loss": 3.6344, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 3.575684932609548e-05, | |
| "loss": 3.5602, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.215313391698519e-05, | |
| "loss": 3.6583, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 2.8684478392724447e-05, | |
| "loss": 3.6643, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 2.5363736429528382e-05, | |
| "loss": 3.4823, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 2.2203213585470068e-05, | |
| "loss": 3.4787, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.9214621700201495e-05, | |
| "loss": 3.4209, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.6409035494796526e-05, | |
| "loss": 3.3871, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 1.3796851532541997e-05, | |
| "loss": 3.3947, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1387749692754382e-05, | |
| "loss": 3.4866, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 3.5918, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 7.213716044354821e-06, | |
| "loss": 3.4983, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 5.464251807155671e-06, | |
| "loss": 3.7741, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 3.948747517607189e-06, | |
| "loss": 3.7211, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.6728191272803667e-06, | |
| "loss": 3.429, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 1.6411947996634035e-06, | |
| "loss": 3.5074, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 8.57697389170679e-07, | |
| "loss": 3.7424, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.252302749240256e-07, | |
| "loss": 3.5668, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.576660180157781e-08, | |
| "loss": 3.5697, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.57045841217041, | |
| "eval_runtime": 16.4667, | |
| "eval_samples_per_second": 22.47, | |
| "eval_steps_per_second": 2.854, | |
| "step": 258 | |
| } | |
| ], | |
| "max_steps": 258, | |
| "num_train_epochs": 1, | |
| "total_flos": 268869500928000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |