{ "best_metric": 0.13778184354305267, "best_model_checkpoint": "bert-intent-classifier/checkpoint-1071", "epoch": 4.0, "eval_steps": 500, "global_step": 2142, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.9990662931839402, "grad_norm": 5.298245906829834, "learning_rate": 1.600747663551402e-05, "loss": 0.3131, "step": 535 }, { "epoch": 0.9990662931839402, "eval_accuracy": 0.9557281024383599, "eval_loss": 0.16336975991725922, "eval_runtime": 25.6475, "eval_samples_per_second": 286.227, "eval_steps_per_second": 17.897, "step": 535 }, { "epoch": 2.0, "grad_norm": 5.548210620880127, "learning_rate": 1.2e-05, "loss": 0.1143, "step": 1071 }, { "epoch": 2.0, "eval_accuracy": 0.9619942787086228, "eval_loss": 0.13778184354305267, "eval_runtime": 25.2843, "eval_samples_per_second": 290.339, "eval_steps_per_second": 18.154, "step": 1071 }, { "epoch": 2.9990662931839402, "grad_norm": 3.810972213745117, "learning_rate": 8.000000000000001e-06, "loss": 0.0754, "step": 1606 }, { "epoch": 2.9990662931839402, "eval_accuracy": 0.9653998092902875, "eval_loss": 0.13948151469230652, "eval_runtime": 25.178, "eval_samples_per_second": 291.564, "eval_steps_per_second": 18.23, "step": 1606 }, { "epoch": 4.0, "grad_norm": 0.10682384669780731, "learning_rate": 3.992523364485982e-06, "loss": 0.0571, "step": 2142 }, { "epoch": 4.0, "eval_accuracy": 0.9644462607274213, "eval_loss": 0.13912545144557953, "eval_runtime": 25.6125, "eval_samples_per_second": 286.618, "eval_steps_per_second": 17.921, "step": 2142 } ], "logging_steps": 500, "max_steps": 2675, "num_input_tokens_seen": 0, "num_train_epochs": 5, "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": 9072755267279040.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }