| { | |
| "best_metric": 0.8066666666666666, | |
| "best_model_checkpoint": "Bert_tinybert-distilled/run-42/checkpoint-516", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 516, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.7573084831237793, | |
| "learning_rate": 0.000305006369799479, | |
| "loss": 0.4693, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_AUC": 0.8182613333333333, | |
| "eval_BAC": 0.7513333333333333, | |
| "eval_MCC": 0.5152913712924717, | |
| "eval_PR_AUC": 0.7722575860284886, | |
| "eval_accuracy": 0.7513333333333333, | |
| "eval_loss": 0.42800581455230713, | |
| "eval_runtime": 6.2417, | |
| "eval_samples_per_second": 240.319, | |
| "eval_steps_per_second": 7.53, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.3580737113952637, | |
| "learning_rate": 0.0002541719748328992, | |
| "loss": 0.4408, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_AUC": 0.8542542222222222, | |
| "eval_BAC": 0.782, | |
| "eval_MCC": 0.5907158713484734, | |
| "eval_PR_AUC": 0.809219961633705, | |
| "eval_accuracy": 0.782, | |
| "eval_loss": 0.40324756503105164, | |
| "eval_runtime": 6.2606, | |
| "eval_samples_per_second": 239.595, | |
| "eval_steps_per_second": 7.507, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.3590539693832397, | |
| "learning_rate": 0.00020333757986631934, | |
| "loss": 0.4252, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_AUC": 0.8693333333333334, | |
| "eval_BAC": 0.8066666666666666, | |
| "eval_MCC": 0.6195523600437505, | |
| "eval_PR_AUC": 0.8436352184846998, | |
| "eval_accuracy": 0.8066666666666666, | |
| "eval_loss": 0.3929729461669922, | |
| "eval_runtime": 6.25, | |
| "eval_samples_per_second": 239.999, | |
| "eval_steps_per_second": 7.52, | |
| "step": 516 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1204, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1351133190000.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.7141253736150909, | |
| "learning_rate": 0.00035584076476605887, | |
| "num_train_epochs": 7, | |
| "temperature": 8 | |
| } | |
| } | |