| { | |
| "best_global_step": 808, | |
| "best_metric": 0.9108910891089109, | |
| "best_model_checkpoint": "./results_distilbert_custom/checkpoint-808", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 1010, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9900990099009901, | |
| "grad_norm": 2.6412200927734375, | |
| "learning_rate": 4.51980198019802e-05, | |
| "loss": 1.0179, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_intent_accuracy": 0.900990099009901, | |
| "eval_loss": 0.6627025008201599, | |
| "eval_runtime": 0.0532, | |
| "eval_samples_per_second": 3796.158, | |
| "eval_slot_f1": 0.8583372039015328, | |
| "eval_slot_precision": 0.8583372039015328, | |
| "eval_slot_recall": 0.8583372039015328, | |
| "eval_steps_per_second": 75.171, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.9801980198019802, | |
| "grad_norm": 1.697471022605896, | |
| "learning_rate": 4.0247524752475254e-05, | |
| "loss": 0.5933, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_intent_accuracy": 0.8910891089108911, | |
| "eval_loss": 0.5899206399917603, | |
| "eval_runtime": 0.0516, | |
| "eval_samples_per_second": 3912.995, | |
| "eval_slot_f1": 0.8471899674872271, | |
| "eval_slot_precision": 0.8471899674872271, | |
| "eval_slot_recall": 0.8471899674872271, | |
| "eval_steps_per_second": 77.485, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 2.9702970297029703, | |
| "grad_norm": 3.684925079345703, | |
| "learning_rate": 3.52970297029703e-05, | |
| "loss": 0.5248, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_intent_accuracy": 0.900990099009901, | |
| "eval_loss": 0.5877912640571594, | |
| "eval_runtime": 0.0512, | |
| "eval_samples_per_second": 3945.962, | |
| "eval_slot_f1": 0.864375290292615, | |
| "eval_slot_precision": 0.864375290292615, | |
| "eval_slot_recall": 0.864375290292615, | |
| "eval_steps_per_second": 78.138, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 3.9603960396039604, | |
| "grad_norm": 7.954131126403809, | |
| "learning_rate": 3.0346534653465347e-05, | |
| "loss": 0.489, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_intent_accuracy": 0.905940594059406, | |
| "eval_loss": 0.6087009906768799, | |
| "eval_runtime": 0.0514, | |
| "eval_samples_per_second": 3928.963, | |
| "eval_slot_f1": 0.864375290292615, | |
| "eval_slot_precision": 0.864375290292615, | |
| "eval_slot_recall": 0.864375290292615, | |
| "eval_steps_per_second": 77.801, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 4.9504950495049505, | |
| "grad_norm": 5.173593044281006, | |
| "learning_rate": 2.53960396039604e-05, | |
| "loss": 0.468, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_intent_accuracy": 0.8762376237623762, | |
| "eval_loss": 0.6051058173179626, | |
| "eval_runtime": 0.052, | |
| "eval_samples_per_second": 3887.446, | |
| "eval_slot_f1": 0.8732001857872735, | |
| "eval_slot_precision": 0.8732001857872735, | |
| "eval_slot_recall": 0.8732001857872735, | |
| "eval_steps_per_second": 76.979, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 5.9405940594059405, | |
| "grad_norm": 2.602719306945801, | |
| "learning_rate": 2.0445544554455444e-05, | |
| "loss": 0.4491, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_intent_accuracy": 0.905940594059406, | |
| "eval_loss": 0.6407473683357239, | |
| "eval_runtime": 0.0554, | |
| "eval_samples_per_second": 3647.88, | |
| "eval_slot_f1": 0.87598699489085, | |
| "eval_slot_precision": 0.87598699489085, | |
| "eval_slot_recall": 0.87598699489085, | |
| "eval_steps_per_second": 72.235, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 6.930693069306931, | |
| "grad_norm": 2.991025924682617, | |
| "learning_rate": 1.5495049504950496e-05, | |
| "loss": 0.4204, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_intent_accuracy": 0.8910891089108911, | |
| "eval_loss": 0.6234941482543945, | |
| "eval_runtime": 0.0568, | |
| "eval_samples_per_second": 3558.795, | |
| "eval_slot_f1": 0.8773803994426381, | |
| "eval_slot_precision": 0.8773803994426381, | |
| "eval_slot_recall": 0.8773803994426381, | |
| "eval_steps_per_second": 70.471, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 7.920792079207921, | |
| "grad_norm": 2.211575746536255, | |
| "learning_rate": 1.0544554455445545e-05, | |
| "loss": 0.4028, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_intent_accuracy": 0.9108910891089109, | |
| "eval_loss": 0.65041583776474, | |
| "eval_runtime": 0.0519, | |
| "eval_samples_per_second": 3893.86, | |
| "eval_slot_f1": 0.878309335810497, | |
| "eval_slot_precision": 0.878309335810497, | |
| "eval_slot_recall": 0.878309335810497, | |
| "eval_steps_per_second": 77.106, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 8.910891089108912, | |
| "grad_norm": 1.5847089290618896, | |
| "learning_rate": 5.594059405940594e-06, | |
| "loss": 0.3929, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_intent_accuracy": 0.900990099009901, | |
| "eval_loss": 0.6379386782646179, | |
| "eval_runtime": 0.051, | |
| "eval_samples_per_second": 3959.979, | |
| "eval_slot_f1": 0.8769159312587088, | |
| "eval_slot_precision": 0.8769159312587088, | |
| "eval_slot_recall": 0.8769159312587088, | |
| "eval_steps_per_second": 78.415, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 9.900990099009901, | |
| "grad_norm": 5.904131889343262, | |
| "learning_rate": 6.435643564356436e-07, | |
| "loss": 0.3679, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_intent_accuracy": 0.9108910891089109, | |
| "eval_loss": 0.6317320466041565, | |
| "eval_runtime": 0.0518, | |
| "eval_samples_per_second": 3899.99, | |
| "eval_slot_f1": 0.8797027403622851, | |
| "eval_slot_precision": 0.8797027403622851, | |
| "eval_slot_recall": 0.8797027403622851, | |
| "eval_steps_per_second": 77.228, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 1010, | |
| "total_flos": 526646237245440.0, | |
| "train_loss": 0.5116730279261523, | |
| "train_runtime": 22.7338, | |
| "train_samples_per_second": 709.076, | |
| "train_steps_per_second": 44.427 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1010, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 526646237245440.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |