| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.79150915963943, | |
| "global_step": 4800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 6.122448979591835e-06, | |
| "loss": 1.1171, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029680384374347184, | |
| "loss": 1.0109, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000290536870691456, | |
| "loss": 0.9896, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002842698976394401, | |
| "loss": 0.9585, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002780029245874242, | |
| "loss": 0.9377, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.00027173595153540835, | |
| "loss": 0.9123, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002654689784833925, | |
| "loss": 0.9131, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00025920200543137664, | |
| "loss": 0.9059, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 0.0002529350323793608, | |
| "loss": 0.9045, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.00024666805932734487, | |
| "loss": 0.8838, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.000240401086275329, | |
| "loss": 0.8889, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00023413411322331312, | |
| "loss": 0.8715, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 0.00022786714017129724, | |
| "loss": 0.8569, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.00022160016711928138, | |
| "loss": 0.8623, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0002153331940672655, | |
| "loss": 0.8612, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 0.0002090662210152496, | |
| "loss": 0.8409, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.00020279924796323375, | |
| "loss": 0.846, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 0.00019653227491121786, | |
| "loss": 0.8467, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.00019026530185920198, | |
| "loss": 0.7872, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0001839983288071861, | |
| "loss": 0.7711, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 0.00017773135575517023, | |
| "loss": 0.7451, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.00017146438270315435, | |
| "loss": 0.754, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 0.0001651974096511385, | |
| "loss": 0.7648, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.00015893043659912263, | |
| "loss": 0.7585, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 0.00015266346354710674, | |
| "loss": 0.7654, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.45, | |
| "learning_rate": 0.00014639649049509086, | |
| "loss": 0.7578, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 0.000140129517443075, | |
| "loss": 0.7324, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 0.00013386254439105911, | |
| "loss": 0.7439, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 0.00012759557133904323, | |
| "loss": 0.7515, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.69, | |
| "learning_rate": 0.00012132859828702736, | |
| "loss": 0.7484, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "learning_rate": 0.00011506162523501148, | |
| "loss": 0.7466, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 0.0001087946521829956, | |
| "loss": 0.7242, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 0.00010252767913097973, | |
| "loss": 0.7357, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 9.626070607896384e-05, | |
| "loss": 0.7283, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.98, | |
| "learning_rate": 8.999373302694798e-05, | |
| "loss": 0.7375, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 8.372675997493211e-05, | |
| "loss": 0.6901, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 7.745978692291623e-05, | |
| "loss": 0.6553, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "learning_rate": 7.119281387090035e-05, | |
| "loss": 0.6572, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 6.492584081888447e-05, | |
| "loss": 0.6609, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 5.8658867766868595e-05, | |
| "loss": 0.6704, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 5.239189471485272e-05, | |
| "loss": 0.6513, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.6124921662836844e-05, | |
| "loss": 0.6589, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "learning_rate": 3.985794861082097e-05, | |
| "loss": 0.6755, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.359097555880509e-05, | |
| "loss": 0.6519, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 2.7324002506789218e-05, | |
| "loss": 0.6512, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.1057029454773346e-05, | |
| "loss": 0.6537, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 1.4790056402757467e-05, | |
| "loss": 0.6436, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 8.523083350741591e-06, | |
| "loss": 0.6488, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.2561102987257156e-06, | |
| "loss": 0.6393, | |
| "step": 4800 | |
| } | |
| ], | |
| "max_steps": 4836, | |
| "num_train_epochs": 3, | |
| "total_flos": 8.901906445628056e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |