| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 17160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 4.8543123543123546e-05, | |
| "loss": 1.1321, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.708624708624709e-05, | |
| "loss": 1.1111, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 4.562937062937063e-05, | |
| "loss": 1.0592, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.4172494172494175e-05, | |
| "loss": 1.0563, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.271561771561772e-05, | |
| "loss": 1.0382, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.125874125874126e-05, | |
| "loss": 1.0295, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 3.9801864801864804e-05, | |
| "loss": 1.0196, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.834498834498835e-05, | |
| "loss": 1.0207, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.688811188811189e-05, | |
| "loss": 1.0309, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.5431235431235434e-05, | |
| "loss": 1.0039, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.397435897435898e-05, | |
| "loss": 1.0012, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 3.251748251748252e-05, | |
| "loss": 0.9437, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.106060606060606e-05, | |
| "loss": 0.871, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 2.9603729603729606e-05, | |
| "loss": 0.8709, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 2.8146853146853146e-05, | |
| "loss": 0.8775, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.6689976689976692e-05, | |
| "loss": 0.8558, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 2.5233100233100232e-05, | |
| "loss": 0.8449, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.377622377622378e-05, | |
| "loss": 0.8832, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.231934731934732e-05, | |
| "loss": 0.8747, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.0862470862470865e-05, | |
| "loss": 0.8595, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.84, | |
| "learning_rate": 1.9405594405594408e-05, | |
| "loss": 0.8546, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.794871794871795e-05, | |
| "loss": 0.8857, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 1.649184149184149e-05, | |
| "loss": 0.8425, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "learning_rate": 1.5034965034965034e-05, | |
| "loss": 0.806, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.357808857808858e-05, | |
| "loss": 0.8023, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.27, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 0.7991, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 1.0664335664335665e-05, | |
| "loss": 0.8154, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 9.207459207459208e-06, | |
| "loss": 0.8205, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 7.750582750582751e-06, | |
| "loss": 0.82, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.2937062937062944e-06, | |
| "loss": 0.8207, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "learning_rate": 4.836829836829837e-06, | |
| "loss": 0.8266, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "learning_rate": 3.3799533799533803e-06, | |
| "loss": 0.8146, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 1.9230769230769234e-06, | |
| "loss": 0.81, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 4.662004662004662e-07, | |
| "loss": 0.7898, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 17160, | |
| "total_flos": 5.399805267070157e+17, | |
| "train_loss": 0.9076518683444648, | |
| "train_runtime": 7155.0947, | |
| "train_samples_per_second": 19.186, | |
| "train_steps_per_second": 2.398 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 17160, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 5.399805267070157e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |