| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.351123595505618, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.988295880149813e-05, | |
| "loss": 1.7828, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.976591760299626e-05, | |
| "loss": 1.7581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.964887640449438e-05, | |
| "loss": 1.7499, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.953183520599251e-05, | |
| "loss": 1.7351, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.941479400749064e-05, | |
| "loss": 1.6748, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.929775280898877e-05, | |
| "loss": 1.6994, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.918071161048689e-05, | |
| "loss": 1.6761, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.906367041198502e-05, | |
| "loss": 1.6459, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.8946629213483144e-05, | |
| "loss": 1.6372, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.882958801498127e-05, | |
| "loss": 1.6715, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.87125468164794e-05, | |
| "loss": 1.6141, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.859550561797753e-05, | |
| "loss": 1.6354, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8478464419475654e-05, | |
| "loss": 1.6343, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.836142322097378e-05, | |
| "loss": 1.6072, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.824438202247191e-05, | |
| "loss": 1.6131, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.812734082397004e-05, | |
| "loss": 1.6301, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.801029962546817e-05, | |
| "loss": 1.597, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.789325842696629e-05, | |
| "loss": 1.5489, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.777621722846442e-05, | |
| "loss": 1.5998, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.765917602996255e-05, | |
| "loss": 1.6023, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.754213483146068e-05, | |
| "loss": 1.6847, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.742509363295881e-05, | |
| "loss": 1.5816, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.730805243445693e-05, | |
| "loss": 1.673, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.719101123595506e-05, | |
| "loss": 1.6192, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.707397003745318e-05, | |
| "loss": 1.6183, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.695692883895131e-05, | |
| "loss": 1.6262, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.683988764044944e-05, | |
| "loss": 1.5945, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6722846441947563e-05, | |
| "loss": 1.659, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.660580524344569e-05, | |
| "loss": 1.6135, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.648876404494382e-05, | |
| "loss": 1.6102, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.637172284644195e-05, | |
| "loss": 1.6202, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.625468164794008e-05, | |
| "loss": 1.6499, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.61376404494382e-05, | |
| "loss": 1.656, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.602059925093633e-05, | |
| "loss": 1.629, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.590355805243446e-05, | |
| "loss": 1.6194, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.578651685393259e-05, | |
| "loss": 1.6308, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.566947565543072e-05, | |
| "loss": 1.6013, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.555243445692884e-05, | |
| "loss": 1.6103, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.543539325842697e-05, | |
| "loss": 1.6281, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.531835205992509e-05, | |
| "loss": 1.5684, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.520131086142322e-05, | |
| "loss": 1.6165, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.508426966292135e-05, | |
| "loss": 1.6187, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.496722846441947e-05, | |
| "loss": 1.6211, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.48501872659176e-05, | |
| "loss": 1.6104, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.473314606741573e-05, | |
| "loss": 1.6058, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.461610486891386e-05, | |
| "loss": 1.5639, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.449906367041199e-05, | |
| "loss": 1.5879, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.438202247191011e-05, | |
| "loss": 1.5911, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.426498127340824e-05, | |
| "loss": 1.6679, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.414794007490637e-05, | |
| "loss": 1.578, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4272, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 3.1601241096192e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |