| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3295978905735003, | |
| "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": 4.98901340364755e-05, | |
| "loss": 1.7796, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4.9780268072951005e-05, | |
| "loss": 1.7713, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 4.96704021094265e-05, | |
| "loss": 1.7176, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.9560536145902e-05, | |
| "loss": 1.6604, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.94506701823775e-05, | |
| "loss": 1.6656, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.9340804218853e-05, | |
| "loss": 1.6062, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.92309382553285e-05, | |
| "loss": 1.5675, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.9121072291804e-05, | |
| "loss": 1.5991, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 4.90112063282795e-05, | |
| "loss": 1.5755, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8901340364755e-05, | |
| "loss": 1.5343, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8791474401230506e-05, | |
| "loss": 1.5777, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 4.8681608437706e-05, | |
| "loss": 1.5148, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.85717424741815e-05, | |
| "loss": 1.514, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8461876510657e-05, | |
| "loss": 1.5594, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.83520105471325e-05, | |
| "loss": 1.5238, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.8242144583608e-05, | |
| "loss": 1.5445, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 4.81322786200835e-05, | |
| "loss": 1.4958, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 4.8022412656559004e-05, | |
| "loss": 1.531, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.79125466930345e-05, | |
| "loss": 1.4877, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.780268072951e-05, | |
| "loss": 1.5099, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.76928147659855e-05, | |
| "loss": 1.5628, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.7582948802461e-05, | |
| "loss": 1.5843, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 4.74730828389365e-05, | |
| "loss": 1.4917, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.7363216875412e-05, | |
| "loss": 1.5552, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 4.72533509118875e-05, | |
| "loss": 1.5284, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.7143484948363e-05, | |
| "loss": 1.5283, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.70336189848385e-05, | |
| "loss": 1.5425, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 4.6923753021313996e-05, | |
| "loss": 1.5408, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 4.68138870577895e-05, | |
| "loss": 1.5508, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6704021094265e-05, | |
| "loss": 1.5359, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6594155130740496e-05, | |
| "loss": 1.5042, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.6484289167216e-05, | |
| "loss": 1.5511, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.63744232036915e-05, | |
| "loss": 1.5468, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 4.6264557240167003e-05, | |
| "loss": 1.4891, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6154691276642495e-05, | |
| "loss": 1.5386, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.6044825313118e-05, | |
| "loss": 1.525, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 4.59349593495935e-05, | |
| "loss": 1.5367, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 4.5825093386068995e-05, | |
| "loss": 1.5011, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.57152274225445e-05, | |
| "loss": 1.5259, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.560536145902e-05, | |
| "loss": 1.4764, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.54954954954955e-05, | |
| "loss": 1.5166, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.5385629531971e-05, | |
| "loss": 1.5049, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.52757635684465e-05, | |
| "loss": 1.5383, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.5165897604921995e-05, | |
| "loss": 1.5166, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.505603164139749e-05, | |
| "loss": 1.5898, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.4946165677873e-05, | |
| "loss": 1.5512, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 4.4836299714348496e-05, | |
| "loss": 1.5215, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.4726433750824e-05, | |
| "loss": 1.5372, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 4.46165677872995e-05, | |
| "loss": 1.4994, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4506701823774996e-05, | |
| "loss": 1.5261, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 4551, | |
| "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 | |
| } | |