| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00899786300753571, | |
| "eval_steps": 5, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001799572601507142, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001799572601507142, | |
| "eval_loss": NaN, | |
| "eval_runtime": 106.9541, | |
| "eval_samples_per_second": 8.751, | |
| "eval_steps_per_second": 4.376, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003599145203014284, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005398717804521426, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007198290406028568, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00899786300753571, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00899786300753571, | |
| "eval_loss": NaN, | |
| "eval_runtime": 20.3472, | |
| "eval_samples_per_second": 46.001, | |
| "eval_steps_per_second": 23.001, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 250853688606720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |