| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9735449735449735, | |
| "eval_steps": 500, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.21164021164021163, | |
| "grad_norm": 0.01096427347511053, | |
| "learning_rate": 5.4347826086956525e-06, | |
| "loss": 0.3143, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.42328042328042326, | |
| "grad_norm": 0.013951408676803112, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 0.3576, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 0.01673784852027893, | |
| "learning_rate": 1.630434782608696e-05, | |
| "loss": 0.3639, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8465608465608465, | |
| "grad_norm": 0.019934486597776413, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 0.3458, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0846560846560847, | |
| "grad_norm": 0.02395496889948845, | |
| "learning_rate": 2.7173913043478262e-05, | |
| "loss": 0.4603, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.2962962962962963, | |
| "grad_norm": 0.017271244898438454, | |
| "learning_rate": 3.260869565217392e-05, | |
| "loss": 0.3034, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.507936507936508, | |
| "grad_norm": 0.023819392547011375, | |
| "learning_rate": 3.804347826086957e-05, | |
| "loss": 0.3317, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.7195767195767195, | |
| "grad_norm": 0.021737879142165184, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.3382, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.9312169312169312, | |
| "grad_norm": 0.023687848821282387, | |
| "learning_rate": 4.891304347826087e-05, | |
| "loss": 0.3288, | |
| "step": 45 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 460, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 23, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7870126965103e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |