| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003723580036025637, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.447160072051273e-05, | |
| "grad_norm": 0.3564011752605438, | |
| "learning_rate": 1e-05, | |
| "loss": 1.3649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.447160072051273e-05, | |
| "eval_loss": 1.5576103925704956, | |
| "eval_runtime": 4722.8576, | |
| "eval_samples_per_second": 4.789, | |
| "eval_steps_per_second": 2.394, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014894320144102547, | |
| "grad_norm": 0.43472617864608765, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4554, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00014894320144102547, | |
| "eval_loss": 1.55040442943573, | |
| "eval_runtime": 6356.0985, | |
| "eval_samples_per_second": 3.558, | |
| "eval_steps_per_second": 1.779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00022341480216153822, | |
| "grad_norm": 0.3920201361179352, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3379, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029788640288205094, | |
| "grad_norm": 0.3567448854446411, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2315, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00029788640288205094, | |
| "eval_loss": 1.5421010255813599, | |
| "eval_runtime": 7196.0111, | |
| "eval_samples_per_second": 3.143, | |
| "eval_steps_per_second": 1.571, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003723580036025637, | |
| "grad_norm": 0.5058178901672363, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4981, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5964844700270592.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |