| { | |
| "best_metric": 0.6880093812942505, | |
| "best_model_checkpoint": "/content/drive/MyDrive/NLP/HW_2/LORA_AUG_GREATER/checkpoint-2250", | |
| "epoch": 1.027749229188078, | |
| "eval_steps": 250, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08564576909900651, | |
| "grad_norm": 13.67185115814209, | |
| "learning_rate": 4.9143542309009935e-05, | |
| "loss": 0.968, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08564576909900651, | |
| "eval_accuracy": 0.6621503496503497, | |
| "eval_f1": 0.6578961107049218, | |
| "eval_loss": 0.7989072799682617, | |
| "eval_precision": 0.6884699634047233, | |
| "eval_recall": 0.6621503496503497, | |
| "eval_runtime": 154.1603, | |
| "eval_samples_per_second": 14.842, | |
| "eval_steps_per_second": 0.467, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17129153819801302, | |
| "grad_norm": 6.074775218963623, | |
| "learning_rate": 4.8287084618019874e-05, | |
| "loss": 0.6005, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17129153819801302, | |
| "eval_accuracy": 0.7145979020979021, | |
| "eval_f1": 0.7094250928713455, | |
| "eval_loss": 0.7962299585342407, | |
| "eval_precision": 0.7248927170802172, | |
| "eval_recall": 0.7145979020979021, | |
| "eval_runtime": 156.9154, | |
| "eval_samples_per_second": 14.581, | |
| "eval_steps_per_second": 0.459, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2569373072970195, | |
| "grad_norm": 4.536829471588135, | |
| "learning_rate": 4.7430626927029806e-05, | |
| "loss": 0.5234, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.2569373072970195, | |
| "eval_accuracy": 0.7447552447552448, | |
| "eval_f1": 0.7415547688528572, | |
| "eval_loss": 0.7522953152656555, | |
| "eval_precision": 0.7440074461201359, | |
| "eval_recall": 0.7447552447552448, | |
| "eval_runtime": 156.5246, | |
| "eval_samples_per_second": 14.618, | |
| "eval_steps_per_second": 0.46, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.34258307639602603, | |
| "grad_norm": 6.346406936645508, | |
| "learning_rate": 4.6574169236039745e-05, | |
| "loss": 0.4843, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.34258307639602603, | |
| "eval_accuracy": 0.7097902097902098, | |
| "eval_f1": 0.6943907906472824, | |
| "eval_loss": 0.9078171849250793, | |
| "eval_precision": 0.7203113605498284, | |
| "eval_recall": 0.7097902097902098, | |
| "eval_runtime": 156.7861, | |
| "eval_samples_per_second": 14.593, | |
| "eval_steps_per_second": 0.459, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.42822884549503254, | |
| "grad_norm": 4.173954486846924, | |
| "learning_rate": 4.571771154504968e-05, | |
| "loss": 0.4593, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.42822884549503254, | |
| "eval_accuracy": 0.729458041958042, | |
| "eval_f1": 0.7221199642365762, | |
| "eval_loss": 0.8215415477752686, | |
| "eval_precision": 0.739759876127429, | |
| "eval_recall": 0.729458041958042, | |
| "eval_runtime": 156.9233, | |
| "eval_samples_per_second": 14.58, | |
| "eval_steps_per_second": 0.459, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.513874614594039, | |
| "grad_norm": 5.52806282043457, | |
| "learning_rate": 4.486125385405961e-05, | |
| "loss": 0.4274, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.513874614594039, | |
| "eval_accuracy": 0.736013986013986, | |
| "eval_f1": 0.7246914620886431, | |
| "eval_loss": 0.8586153388023376, | |
| "eval_precision": 0.7426058097276803, | |
| "eval_recall": 0.736013986013986, | |
| "eval_runtime": 154.5125, | |
| "eval_samples_per_second": 14.808, | |
| "eval_steps_per_second": 0.466, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.5995203836930456, | |
| "grad_norm": 4.5602898597717285, | |
| "learning_rate": 4.400479616306955e-05, | |
| "loss": 0.4272, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.5995203836930456, | |
| "eval_accuracy": 0.7596153846153846, | |
| "eval_f1": 0.75381427721012, | |
| "eval_loss": 0.7090545296669006, | |
| "eval_precision": 0.7584790142699676, | |
| "eval_recall": 0.7596153846153846, | |
| "eval_runtime": 154.0482, | |
| "eval_samples_per_second": 14.852, | |
| "eval_steps_per_second": 0.467, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.6851661527920521, | |
| "grad_norm": 4.625553607940674, | |
| "learning_rate": 4.314833847207948e-05, | |
| "loss": 0.3975, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.6851661527920521, | |
| "eval_accuracy": 0.7543706293706294, | |
| "eval_f1": 0.745514070883235, | |
| "eval_loss": 0.7486010193824768, | |
| "eval_precision": 0.7586667809302097, | |
| "eval_recall": 0.7543706293706294, | |
| "eval_runtime": 154.7216, | |
| "eval_samples_per_second": 14.788, | |
| "eval_steps_per_second": 0.465, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.7708119218910586, | |
| "grad_norm": 4.490630626678467, | |
| "learning_rate": 4.229188078108942e-05, | |
| "loss": 0.3916, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.7708119218910586, | |
| "eval_accuracy": 0.7539335664335665, | |
| "eval_f1": 0.7428581792552783, | |
| "eval_loss": 0.6880093812942505, | |
| "eval_precision": 0.7522960627196311, | |
| "eval_recall": 0.7539335664335665, | |
| "eval_runtime": 154.2223, | |
| "eval_samples_per_second": 14.836, | |
| "eval_steps_per_second": 0.467, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.8564576909900651, | |
| "grad_norm": 2.426281452178955, | |
| "learning_rate": 4.143542309009935e-05, | |
| "loss": 0.3835, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.8564576909900651, | |
| "eval_accuracy": 0.7556818181818182, | |
| "eval_f1": 0.7470266895815383, | |
| "eval_loss": 0.7790956497192383, | |
| "eval_precision": 0.7554129003944599, | |
| "eval_recall": 0.7556818181818182, | |
| "eval_runtime": 158.6172, | |
| "eval_samples_per_second": 14.425, | |
| "eval_steps_per_second": 0.454, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9421034600890716, | |
| "grad_norm": 2.668764591217041, | |
| "learning_rate": 4.0578965399109283e-05, | |
| "loss": 0.3744, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.9421034600890716, | |
| "eval_accuracy": 0.7552447552447552, | |
| "eval_f1": 0.7477654252537256, | |
| "eval_loss": 0.7511053085327148, | |
| "eval_precision": 0.7591641056843698, | |
| "eval_recall": 0.7552447552447552, | |
| "eval_runtime": 158.6161, | |
| "eval_samples_per_second": 14.425, | |
| "eval_steps_per_second": 0.454, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.027749229188078, | |
| "grad_norm": 4.129087448120117, | |
| "learning_rate": 3.972250770811922e-05, | |
| "loss": 0.3902, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.027749229188078, | |
| "eval_accuracy": 0.7683566433566433, | |
| "eval_f1": 0.7647199540664621, | |
| "eval_loss": 0.6985490918159485, | |
| "eval_precision": 0.7701853452045943, | |
| "eval_recall": 0.7683566433566433, | |
| "eval_runtime": 150.2872, | |
| "eval_samples_per_second": 15.224, | |
| "eval_steps_per_second": 0.479, | |
| "step": 3000 | |
| } | |
| ], | |
| "logging_steps": 250, | |
| "max_steps": 14595, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.7057888093675e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |