{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.01701041888156496, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0034020837763129915, "grad_norm": 3.8531107902526855, "learning_rate": 1e-05, "loss": 3.6487, "step": 1 }, { "epoch": 0.0034020837763129915, "eval_loss": 4.047966957092285, "eval_runtime": 71.0701, "eval_samples_per_second": 6.965, "eval_steps_per_second": 3.49, "step": 1 }, { "epoch": 0.006804167552625983, "grad_norm": 4.155609130859375, "learning_rate": 2e-05, "loss": 4.0375, "step": 2 }, { "epoch": 0.006804167552625983, "eval_loss": 4.015207767486572, "eval_runtime": 16.0274, "eval_samples_per_second": 30.885, "eval_steps_per_second": 15.473, "step": 2 }, { "epoch": 0.010206251328938975, "grad_norm": 4.313231945037842, "learning_rate": 3e-05, "loss": 3.9577, "step": 3 }, { "epoch": 0.013608335105251966, "grad_norm": 4.151477813720703, "learning_rate": 4e-05, "loss": 4.0456, "step": 4 }, { "epoch": 0.013608335105251966, "eval_loss": 3.935382127761841, "eval_runtime": 16.0027, "eval_samples_per_second": 30.932, "eval_steps_per_second": 15.497, "step": 4 }, { "epoch": 0.01701041888156496, "grad_norm": 4.242020130157471, "learning_rate": 5e-05, "loss": 3.9886, "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": 978955586764800.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }