| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2705993776214315, | |
| "eval_steps": 500, | |
| "global_step": 2000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.8518972396850586, | |
| "learning_rate": 4.933026654038696e-05, | |
| "loss": 0.5532, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.7409780621528625, | |
| "learning_rate": 4.865376809633338e-05, | |
| "loss": 0.5033, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.7067281007766724, | |
| "learning_rate": 4.79772696522798e-05, | |
| "loss": 0.4602, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.7321436405181885, | |
| "learning_rate": 4.7300771208226225e-05, | |
| "loss": 0.4523, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.6380289793014526, | |
| "learning_rate": 4.6624272764172644e-05, | |
| "loss": 0.4606, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.5421116352081299, | |
| "learning_rate": 4.594777432011906e-05, | |
| "loss": 0.4262, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.5193295478820801, | |
| "learning_rate": 4.527127587606549e-05, | |
| "loss": 0.4105, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.5962494611740112, | |
| "learning_rate": 4.459477743201191e-05, | |
| "loss": 0.4174, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.6797559261322021, | |
| "learning_rate": 4.391827898795833e-05, | |
| "loss": 0.4346, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.5834950804710388, | |
| "learning_rate": 4.324178054390475e-05, | |
| "loss": 0.4233, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.5665029287338257, | |
| "learning_rate": 4.256528209985117e-05, | |
| "loss": 0.4119, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.5659196972846985, | |
| "learning_rate": 4.188878365579759e-05, | |
| "loss": 0.4242, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.5055731534957886, | |
| "learning_rate": 4.121228521174402e-05, | |
| "loss": 0.4075, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.5024439692497253, | |
| "learning_rate": 4.053578676769044e-05, | |
| "loss": 0.3856, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.5468323826789856, | |
| "learning_rate": 3.9859288323636856e-05, | |
| "loss": 0.3942, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.579856812953949, | |
| "learning_rate": 3.918278987958328e-05, | |
| "loss": 0.3914, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.6119765043258667, | |
| "learning_rate": 3.85062914355297e-05, | |
| "loss": 0.4195, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.4361695647239685, | |
| "learning_rate": 3.782979299147612e-05, | |
| "loss": 0.3926, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.4878581464290619, | |
| "learning_rate": 3.715329454742254e-05, | |
| "loss": 0.3738, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.6861026883125305, | |
| "learning_rate": 3.6476796103368965e-05, | |
| "loss": 0.4021, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 7391, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 5.62657090338816e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |