{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.8936170212765955, "eval_steps": 500, "global_step": 51, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.5673758865248227, "grad_norm": 2.9113449286995063, "learning_rate": 5e-06, "loss": 1.2194, "step": 10 }, { "epoch": 0.9645390070921985, "eval_loss": 1.0973232984542847, "eval_runtime": 54.5749, "eval_samples_per_second": 8.685, "eval_steps_per_second": 0.275, "step": 17 }, { "epoch": 1.1347517730496455, "grad_norm": 1.6732661613158009, "learning_rate": 5e-06, "loss": 1.0999, "step": 20 }, { "epoch": 1.702127659574468, "grad_norm": 1.0008753592465156, "learning_rate": 5e-06, "loss": 1.0343, "step": 30 }, { "epoch": 1.9858156028368794, "eval_loss": 1.0406028032302856, "eval_runtime": 54.3551, "eval_samples_per_second": 8.72, "eval_steps_per_second": 0.276, "step": 35 }, { "epoch": 2.269503546099291, "grad_norm": 1.5563219558040582, "learning_rate": 5e-06, "loss": 0.9923, "step": 40 }, { "epoch": 2.8368794326241136, "grad_norm": 1.5053587479166881, "learning_rate": 5e-06, "loss": 0.9575, "step": 50 }, { "epoch": 2.8936170212765955, "eval_loss": 1.0247434377670288, "eval_runtime": 54.2143, "eval_samples_per_second": 8.743, "eval_steps_per_second": 0.277, "step": 51 }, { "epoch": 2.8936170212765955, "step": 51, "total_flos": 85322209689600.0, "train_loss": 1.0582934162195992, "train_runtime": 8386.7811, "train_samples_per_second": 3.219, "train_steps_per_second": 0.006 } ], "logging_steps": 10, "max_steps": 51, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 85322209689600.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }