{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.003947264545669851, "eval_steps": 13, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 7.894529091339702e-05, "eval_loss": 0.7521783113479614, "eval_runtime": 64.617, "eval_samples_per_second": 41.274, "eval_steps_per_second": 20.645, "step": 1 }, { "epoch": 0.0007894529091339702, "grad_norm": 11.056082725524902, "learning_rate": 0.00019396926207859084, "loss": 4.0906, "step": 10 }, { "epoch": 0.001026288781874161, "eval_loss": 0.5578336119651794, "eval_runtime": 63.0798, "eval_samples_per_second": 42.28, "eval_steps_per_second": 21.148, "step": 13 }, { "epoch": 0.0015789058182679404, "grad_norm": 4.497377872467041, "learning_rate": 0.00015000000000000001, "loss": 2.5267, "step": 20 }, { "epoch": 0.002052577563748322, "eval_loss": 0.3773026764392853, "eval_runtime": 63.2797, "eval_samples_per_second": 42.146, "eval_steps_per_second": 21.081, "step": 26 }, { "epoch": 0.0023683587274019105, "grad_norm": 10.23695182800293, "learning_rate": 8.263518223330697e-05, "loss": 1.566, "step": 30 }, { "epoch": 0.0030788663456224837, "eval_loss": 0.35432279109954834, "eval_runtime": 63.1588, "eval_samples_per_second": 42.227, "eval_steps_per_second": 21.121, "step": 39 }, { "epoch": 0.003157811636535881, "grad_norm": 4.301798343658447, "learning_rate": 2.339555568810221e-05, "loss": 1.2228, "step": 40 }, { "epoch": 0.003947264545669851, "grad_norm": 5.790259838104248, "learning_rate": 0.0, "loss": 1.3358, "step": 50 } ], "logging_steps": 10, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2553702254641152.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }