| { | |
| "best_metric": 0.8150910139083862, | |
| "best_model_checkpoint": "autotrein-BERT-iiLEX-dgs-0001/checkpoint-112", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 112, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.044642857142857144, | |
| "grad_norm": 33.14796829223633, | |
| "learning_rate": 7.3529411764705884e-06, | |
| "loss": 5.2291, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 39.71625900268555, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 3.251, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13392857142857142, | |
| "grad_norm": 9.014291763305664, | |
| "learning_rate": 2.2058823529411766e-05, | |
| "loss": 1.3772, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 13.757031440734863, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 1.001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22321428571428573, | |
| "grad_norm": 4.103291988372803, | |
| "learning_rate": 3.6764705882352945e-05, | |
| "loss": 0.881, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 11.08597469329834, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 0.9336, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 5.988820552825928, | |
| "learning_rate": 4.983443708609272e-05, | |
| "loss": 0.799, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 7.977931499481201, | |
| "learning_rate": 4.900662251655629e-05, | |
| "loss": 0.9223, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4017857142857143, | |
| "grad_norm": 12.102520942687988, | |
| "learning_rate": 4.8178807947019873e-05, | |
| "loss": 0.7429, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44642857142857145, | |
| "grad_norm": 7.033493518829346, | |
| "learning_rate": 4.735099337748345e-05, | |
| "loss": 0.8271, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49107142857142855, | |
| "grad_norm": 5.403349876403809, | |
| "learning_rate": 4.652317880794702e-05, | |
| "loss": 0.6135, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 7.016264915466309, | |
| "learning_rate": 4.56953642384106e-05, | |
| "loss": 0.8159, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5803571428571429, | |
| "grad_norm": 7.3167500495910645, | |
| "learning_rate": 4.4867549668874174e-05, | |
| "loss": 0.7253, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 6.7996015548706055, | |
| "learning_rate": 4.403973509933775e-05, | |
| "loss": 0.797, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6696428571428571, | |
| "grad_norm": 13.33212947845459, | |
| "learning_rate": 4.321192052980133e-05, | |
| "loss": 0.7843, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 6.970618724822998, | |
| "learning_rate": 4.23841059602649e-05, | |
| "loss": 0.6673, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7589285714285714, | |
| "grad_norm": 6.666952133178711, | |
| "learning_rate": 4.155629139072848e-05, | |
| "loss": 0.8371, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8035714285714286, | |
| "grad_norm": 3.545180559158325, | |
| "learning_rate": 4.0728476821192055e-05, | |
| "loss": 0.7972, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8482142857142857, | |
| "grad_norm": 5.373492240905762, | |
| "learning_rate": 3.990066225165563e-05, | |
| "loss": 0.7545, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 15.798254013061523, | |
| "learning_rate": 3.907284768211921e-05, | |
| "loss": 0.6231, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 2.651522397994995, | |
| "learning_rate": 3.824503311258278e-05, | |
| "loss": 0.6489, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9821428571428571, | |
| "grad_norm": 7.664308071136475, | |
| "learning_rate": 3.741721854304636e-05, | |
| "loss": 0.9191, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7008928571428571, | |
| "eval_f1_macro": 0.5174652578289578, | |
| "eval_f1_micro": 0.7008928571428571, | |
| "eval_f1_weighted": 0.6724501356321512, | |
| "eval_loss": 0.8150910139083862, | |
| "eval_precision_macro": 0.5358578040466585, | |
| "eval_precision_micro": 0.7008928571428571, | |
| "eval_precision_weighted": 0.6896257780424769, | |
| "eval_recall_macro": 0.5462726914951846, | |
| "eval_recall_micro": 0.7008928571428571, | |
| "eval_recall_weighted": 0.7008928571428571, | |
| "eval_runtime": 176.4709, | |
| "eval_samples_per_second": 1.269, | |
| "eval_steps_per_second": 0.079, | |
| "step": 112 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 336, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "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": 235753855647744.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |