| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0344827586206895, | |
| "eval_steps": 25, | |
| "global_step": 11, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.81771838126524e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "eval_loss": NaN, | |
| "eval_runtime": 3.4522, | |
| "eval_samples_per_second": 14.484, | |
| "eval_steps_per_second": 3.766, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.285640897740315e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.446873302753784e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.369367558508489e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.140416772229784e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.859583227770218e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.9310344827586206, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.630632441491512e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.206896551724138, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5531266972462177e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.4827586206896552, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7143591022596845e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.7586206896551726, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1822816187347623e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0344827586206895, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 11, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1570143893966029e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |