{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.046756282875511396, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.009351256575102279, "grad_norm": 32.29426574707031, "learning_rate": 1e-05, "loss": 17.6072, "step": 1 }, { "epoch": 0.009351256575102279, "eval_loss": 16.884273529052734, "eval_runtime": 82.3294, "eval_samples_per_second": 2.198, "eval_steps_per_second": 1.105, "step": 1 }, { "epoch": 0.018702513150204558, "grad_norm": 32.29195785522461, "learning_rate": 2e-05, "loss": 16.8811, "step": 2 }, { "epoch": 0.018702513150204558, "eval_loss": 16.41873550415039, "eval_runtime": 9.4646, "eval_samples_per_second": 19.124, "eval_steps_per_second": 9.615, "step": 2 }, { "epoch": 0.028053769725306838, "grad_norm": 34.5294303894043, "learning_rate": 3e-05, "loss": 18.2464, "step": 3 }, { "epoch": 0.037405026300409115, "grad_norm": 33.32879638671875, "learning_rate": 4e-05, "loss": 16.4067, "step": 4 }, { "epoch": 0.037405026300409115, "eval_loss": 14.808712005615234, "eval_runtime": 9.4616, "eval_samples_per_second": 19.13, "eval_steps_per_second": 9.618, "step": 4 }, { "epoch": 0.046756282875511396, "grad_norm": 35.54813003540039, "learning_rate": 5e-05, "loss": 14.7126, "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": 3822182832537600.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }