{ "best_metric": 25.2705, "best_model_checkpoint": "./ArabartModel-1/checkpoint-1528", "epoch": 2.0, "eval_steps": 500, "global_step": 3056, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.32722513089005234, "grad_norm": 1.563672423362732, "learning_rate": 4.6727748691099475e-05, "loss": 0.0195, "step": 500 }, { "epoch": 0.6544502617801047, "grad_norm": 1.7397737503051758, "learning_rate": 4.3455497382198955e-05, "loss": 0.0244, "step": 1000 }, { "epoch": 0.981675392670157, "grad_norm": 3.006633758544922, "learning_rate": 4.018324607329843e-05, "loss": 0.0293, "step": 1500 }, { "epoch": 1.0, "eval_loss": 5.626201629638672, "eval_rouge1": 25.2705, "eval_rouge2": 9.9865, "eval_rougeL": 21.8678, "eval_runtime": 372.5145, "eval_samples_per_second": 5.892, "eval_steps_per_second": 0.591, "step": 1528 }, { "epoch": 1.3089005235602094, "grad_norm": 3.4732136726379395, "learning_rate": 4.3455497382198955e-05, "loss": 0.0456, "step": 2000 }, { "epoch": 1.6361256544502618, "grad_norm": 2.2575156688690186, "learning_rate": 4.181937172774869e-05, "loss": 0.0619, "step": 2500 }, { "epoch": 1.9633507853403143, "grad_norm": 6.030032157897949, "learning_rate": 4.018324607329843e-05, "loss": 0.0993, "step": 3000 }, { "epoch": 2.0, "eval_loss": 5.542174339294434, "eval_rouge1": 25.0744, "eval_rouge2": 9.8534, "eval_rougeL": 21.6992, "eval_runtime": 411.9676, "eval_samples_per_second": 5.328, "eval_steps_per_second": 0.534, "step": 3056 } ], "logging_steps": 500, "max_steps": 15280, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.4662889498529792e+16, "train_batch_size": 10, "trial_name": null, "trial_params": null }