| { | |
| "best_metric": 0.6127167630057804, | |
| "best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/rte/checkpoint-312", | |
| "epoch": 4.0, | |
| "eval_steps": 500, | |
| "global_step": 1248, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5179855823516846, | |
| "eval_f1": 0.6127167630057804, | |
| "eval_loss": 0.6988222599029541, | |
| "eval_mcc": 0.09869207097117276, | |
| "eval_runtime": 0.2603, | |
| "eval_samples_per_second": 534.027, | |
| "eval_steps_per_second": 69.155, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.6025641025641026, | |
| "grad_norm": 2.8960421085357666, | |
| "learning_rate": 2.7596153846153846e-05, | |
| "loss": 0.6829, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5899280309677124, | |
| "eval_f1": 0.4864864864864865, | |
| "eval_loss": 0.6877012848854065, | |
| "eval_mcc": 0.1635282583804096, | |
| "eval_runtime": 0.2394, | |
| "eval_samples_per_second": 580.645, | |
| "eval_steps_per_second": 75.191, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.46043166518211365, | |
| "eval_f1": 0.5714285714285714, | |
| "eval_loss": 1.203949213027954, | |
| "eval_mcc": -0.03987122665174367, | |
| "eval_runtime": 0.2479, | |
| "eval_samples_per_second": 560.646, | |
| "eval_steps_per_second": 72.602, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 3.2051282051282053, | |
| "grad_norm": 10.899106979370117, | |
| "learning_rate": 2.5192307692307694e-05, | |
| "loss": 0.4839, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.49640288949012756, | |
| "eval_f1": 0.5454545454545454, | |
| "eval_loss": 1.811629295349121, | |
| "eval_mcc": 0.016953317256112287, | |
| "eval_runtime": 0.2418, | |
| "eval_samples_per_second": 574.756, | |
| "eval_steps_per_second": 74.429, | |
| "step": 1248 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "step": 1248, | |
| "total_flos": 587617475420160.0, | |
| "train_loss": 0.5243261960836557, | |
| "train_runtime": 82.8963, | |
| "train_samples_per_second": 600.751, | |
| "train_steps_per_second": 75.275 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.001 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 587617475420160.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |