| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.24937655860349128, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012468827930174564, | |
| "grad_norm": 0.0348743200302124, | |
| "learning_rate": 4.9995205016168205e-05, | |
| "loss": 0.4047, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02493765586034913, | |
| "grad_norm": 0.052354972809553146, | |
| "learning_rate": 4.998082190402241e-05, | |
| "loss": 0.3855, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03740648379052369, | |
| "grad_norm": 0.02390989102423191, | |
| "learning_rate": 4.995685618090584e-05, | |
| "loss": 0.3818, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04987531172069826, | |
| "grad_norm": 0.01846301183104515, | |
| "learning_rate": 4.9923317040038885e-05, | |
| "loss": 0.3884, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06234413965087282, | |
| "grad_norm": 0.018641460686922073, | |
| "learning_rate": 4.988021734699259e-05, | |
| "loss": 0.3713, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07481296758104738, | |
| "grad_norm": 0.016644474118947983, | |
| "learning_rate": 4.982757363475346e-05, | |
| "loss": 0.3492, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08728179551122195, | |
| "grad_norm": 0.01785973273217678, | |
| "learning_rate": 4.9765406097381426e-05, | |
| "loss": 0.3596, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09975062344139651, | |
| "grad_norm": 0.01776760071516037, | |
| "learning_rate": 4.96937385822634e-05, | |
| "loss": 0.3792, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11221945137157108, | |
| "grad_norm": 0.019663693383336067, | |
| "learning_rate": 4.96125985809655e-05, | |
| "loss": 0.3393, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12468827930174564, | |
| "grad_norm": 0.036602046340703964, | |
| "learning_rate": 4.952201721868727e-05, | |
| "loss": 0.3433, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1371571072319202, | |
| "grad_norm": 0.020088447257876396, | |
| "learning_rate": 4.94220292423221e-05, | |
| "loss": 0.3563, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.14962593516209477, | |
| "grad_norm": 0.023927291855216026, | |
| "learning_rate": 4.9312673007128405e-05, | |
| "loss": 0.3543, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.16209476309226933, | |
| "grad_norm": 0.023712489753961563, | |
| "learning_rate": 4.919399046201656e-05, | |
| "loss": 0.3442, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1745635910224439, | |
| "grad_norm": 0.02708962745964527, | |
| "learning_rate": 4.906602713345735e-05, | |
| "loss": 0.344, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18703241895261846, | |
| "grad_norm": 0.026062602177262306, | |
| "learning_rate": 4.8928832108018106e-05, | |
| "loss": 0.3426, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19950124688279303, | |
| "grad_norm": 0.025727244094014168, | |
| "learning_rate": 4.878245801353313e-05, | |
| "loss": 0.3677, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2119700748129676, | |
| "grad_norm": 0.03201605752110481, | |
| "learning_rate": 4.862696099891573e-05, | |
| "loss": 0.333, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.22443890274314215, | |
| "grad_norm": 0.03317998722195625, | |
| "learning_rate": 4.846240071261959e-05, | |
| "loss": 0.3596, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.23690773067331672, | |
| "grad_norm": 0.02743816375732422, | |
| "learning_rate": 4.828884027975768e-05, | |
| "loss": 0.3156, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.24937655860349128, | |
| "grad_norm": 0.030033418908715248, | |
| "learning_rate": 4.810634627788756e-05, | |
| "loss": 0.3355, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 802, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.842735695541043e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |