| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00022596742302984652, | |
| "eval_steps": 3, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.532247434328218e-05, | |
| "grad_norm": 0.07794299721717834, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3751, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.532247434328218e-05, | |
| "eval_loss": 10.367362022399902, | |
| "eval_runtime": 14.1833, | |
| "eval_samples_per_second": 394.125, | |
| "eval_steps_per_second": 197.063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015064494868656435, | |
| "grad_norm": 0.07240435481071472, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3733, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022596742302984652, | |
| "grad_norm": 0.08178043365478516, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3623, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00022596742302984652, | |
| "eval_loss": 10.367290496826172, | |
| "eval_runtime": 13.9963, | |
| "eval_samples_per_second": 399.392, | |
| "eval_steps_per_second": 199.696, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 38792724480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |