| { | |
| "best_metric": 1.5718337297439575, | |
| "best_model_checkpoint": "autotrein-BERT-iiLEX-dgs-0004/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": 2.0444529056549072, | |
| "learning_rate": 7.3529411764705884e-06, | |
| "loss": 0.266, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08928571428571429, | |
| "grad_norm": 17.472654342651367, | |
| "learning_rate": 1.4705882352941177e-05, | |
| "loss": 0.1248, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13392857142857142, | |
| "grad_norm": 6.122802257537842, | |
| "learning_rate": 2.2058823529411766e-05, | |
| "loss": 0.1436, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 12.507484436035156, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 0.1236, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22321428571428573, | |
| "grad_norm": 1.480406403541565, | |
| "learning_rate": 3.6764705882352945e-05, | |
| "loss": 0.0626, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26785714285714285, | |
| "grad_norm": 0.38904812932014465, | |
| "learning_rate": 4.411764705882353e-05, | |
| "loss": 0.0915, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3125, | |
| "grad_norm": 0.2865840792655945, | |
| "learning_rate": 4.983443708609272e-05, | |
| "loss": 0.0897, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 25.76744842529297, | |
| "learning_rate": 4.900662251655629e-05, | |
| "loss": 0.0871, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4017857142857143, | |
| "grad_norm": 0.760350227355957, | |
| "learning_rate": 4.8178807947019873e-05, | |
| "loss": 0.0056, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.44642857142857145, | |
| "grad_norm": 11.40116024017334, | |
| "learning_rate": 4.735099337748345e-05, | |
| "loss": 0.0448, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.49107142857142855, | |
| "grad_norm": 0.7093308568000793, | |
| "learning_rate": 4.652317880794702e-05, | |
| "loss": 0.005, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 13.429608345031738, | |
| "learning_rate": 4.56953642384106e-05, | |
| "loss": 0.1927, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5803571428571429, | |
| "grad_norm": 18.583410263061523, | |
| "learning_rate": 4.4867549668874174e-05, | |
| "loss": 0.3076, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 0.15568283200263977, | |
| "learning_rate": 4.403973509933775e-05, | |
| "loss": 0.227, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6696428571428571, | |
| "grad_norm": 21.115196228027344, | |
| "learning_rate": 4.321192052980133e-05, | |
| "loss": 0.1072, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.23123915493488312, | |
| "learning_rate": 4.23841059602649e-05, | |
| "loss": 0.2157, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7589285714285714, | |
| "grad_norm": 1.810465931892395, | |
| "learning_rate": 4.155629139072848e-05, | |
| "loss": 0.0198, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8035714285714286, | |
| "grad_norm": 7.193124771118164, | |
| "learning_rate": 4.0728476821192055e-05, | |
| "loss": 0.2872, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8482142857142857, | |
| "grad_norm": 0.040846243500709534, | |
| "learning_rate": 3.990066225165563e-05, | |
| "loss": 0.1349, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 1.4968816041946411, | |
| "learning_rate": 3.907284768211921e-05, | |
| "loss": 0.0838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9375, | |
| "grad_norm": 0.02432333491742611, | |
| "learning_rate": 3.824503311258278e-05, | |
| "loss": 0.0513, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9821428571428571, | |
| "grad_norm": 11.377039909362793, | |
| "learning_rate": 3.741721854304636e-05, | |
| "loss": 0.6275, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6607142857142857, | |
| "eval_f1_macro": 0.5764297665936106, | |
| "eval_f1_micro": 0.6607142857142857, | |
| "eval_f1_weighted": 0.6685474450942381, | |
| "eval_loss": 1.5718337297439575, | |
| "eval_precision_macro": 0.5781369792997699, | |
| "eval_precision_micro": 0.6607142857142857, | |
| "eval_precision_weighted": 0.6808154556545336, | |
| "eval_recall_macro": 0.5778714544420972, | |
| "eval_recall_micro": 0.6607142857142857, | |
| "eval_recall_weighted": 0.6607142857142857, | |
| "eval_runtime": 266.3448, | |
| "eval_samples_per_second": 0.841, | |
| "eval_steps_per_second": 0.053, | |
| "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 | |
| } | |