| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6699636307656782, | |
| "eval_steps": 500, | |
| "global_step": 272, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 3.5714285714285716e-07, | |
| "loss": 1.4263, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.7857142857142859e-06, | |
| "loss": 1.4275, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 3.5714285714285718e-06, | |
| "loss": 1.4298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 1.424, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 7.1428571428571436e-06, | |
| "loss": 1.4395, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 1.4306, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 9.998342337571566e-06, | |
| "loss": 1.4306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.97970625586178e-06, | |
| "loss": 1.4257, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 9.940439480455386e-06, | |
| "loss": 1.4302, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 9.880704691794608e-06, | |
| "loss": 1.4312, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 9.80074936835801e-06, | |
| "loss": 1.4136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 9.70090476136855e-06, | |
| "loss": 1.4217, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 9.581584522435025e-06, | |
| "loss": 1.4138, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 9.443282989812494e-06, | |
| "loss": 1.4091, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 9.286573140381663e-06, | |
| "loss": 1.4004, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 9.112104215832047e-06, | |
| "loss": 1.3973, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 8.920599032883553e-06, | |
| "loss": 1.3976, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 8.712850988690094e-06, | |
| "loss": 1.3982, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 8.489720773831717e-06, | |
| "loss": 1.3978, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 8.25213280651317e-06, | |
| "loss": 1.3858, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 8.001071402741843e-06, | |
| "loss": 1.379, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 7.737576698351878e-06, | |
| "loss": 1.386, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 7.462740339769323e-06, | |
| "loss": 1.4033, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 7.177700961371239e-06, | |
| "loss": 1.3782, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 6.883639468175926e-06, | |
| "loss": 1.3731, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 6.58177414340781e-06, | |
| "loss": 1.3741, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 6.273355601206143e-06, | |
| "loss": 1.3714, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 5.959661605388229e-06, | |
| "loss": 1.3783, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 5.641991775732756e-06, | |
| "loss": 1.3813, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 5.321662203714909e-06, | |
| "loss": 1.3619, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 5e-06, | |
| "loss": 1.3739, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.678337796285093e-06, | |
| "loss": 1.364, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.358008224267245e-06, | |
| "loss": 1.3588, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 4.040338394611772e-06, | |
| "loss": 1.3539, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 3.726644398793857e-06, | |
| "loss": 1.3588, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 3.4182258565921933e-06, | |
| "loss": 1.3632, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 3.116360531824074e-06, | |
| "loss": 1.3584, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 2.822299038628762e-06, | |
| "loss": 1.3546, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 2.537259660230679e-06, | |
| "loss": 1.3628, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 2.2624233016481224e-06, | |
| "loss": 1.3627, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 1.9989285972581595e-06, | |
| "loss": 1.3644, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.7478671934868302e-06, | |
| "loss": 1.356, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.5102792261682813e-06, | |
| "loss": 1.3556, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.2871490113099066e-06, | |
| "loss": 1.3545, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.0794009671164484e-06, | |
| "loss": 1.3502, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 8.878957841679542e-07, | |
| "loss": 1.3656, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 7.13426859618338e-07, | |
| "loss": 1.356, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 5.567170101875074e-07, | |
| "loss": 1.3602, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 4.184154775649768e-07, | |
| "loss": 1.3582, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 2.990952386314505e-07, | |
| "loss": 1.3545, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.992506316419912e-07, | |
| "loss": 1.3565, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 1.192953082053927e-07, | |
| "loss": 1.3637, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 5.9560519544614725e-08, | |
| "loss": 1.3604, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 2.0293744138219495e-08, | |
| "loss": 1.347, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 1.657662428434792e-09, | |
| "loss": 1.3556, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_loss": 1.3605483770370483, | |
| "eval_runtime": 2578.3151, | |
| "eval_samples_per_second": 8.963, | |
| "eval_steps_per_second": 1.12, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "step": 272, | |
| "total_flos": 2.233306234264486e+18, | |
| "train_loss": 1.3824449540937649, | |
| "train_runtime": 69463.2349, | |
| "train_samples_per_second": 2.005, | |
| "train_steps_per_second": 0.004 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 272, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2.233306234264486e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |