| { | |
| "best_metric": 0.41906410455703735, | |
| "best_model_checkpoint": "autotrain-f7fct-dx9rn/checkpoint-100", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 3.968233823776245, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.7162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 5.004212856292725, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.702, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 5.395503520965576, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.7072, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 4.344860076904297, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.722, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 3.5571045875549316, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.6178, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 7.521437644958496, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6845, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 5.477353096008301, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 0.6131, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 11.997583389282227, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 0.7953, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 6.525259017944336, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.7484, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 7.6074748039245605, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.7293, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 6.682773590087891, | |
| "learning_rate": 4.5370370370370374e-05, | |
| "loss": 0.6188, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 4.664694786071777, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.5287, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 5.581724643707275, | |
| "learning_rate": 4.351851851851852e-05, | |
| "loss": 0.5358, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 14.359504699707031, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.4202, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 7.6025919914245605, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.5042, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 16.40511703491211, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.4972, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 7.792325973510742, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 0.8613, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 4.322792053222656, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.4195, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 3.8841655254364014, | |
| "learning_rate": 3.7962962962962964e-05, | |
| "loss": 0.3093, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 17.78056526184082, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.426, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.835, | |
| "eval_auc": 0.9059649122807018, | |
| "eval_f1": 0.8493150684931506, | |
| "eval_loss": 0.41906410455703735, | |
| "eval_precision": 0.8157894736842105, | |
| "eval_recall": 0.8857142857142857, | |
| "eval_runtime": 32.1015, | |
| "eval_samples_per_second": 6.23, | |
| "eval_steps_per_second": 0.405, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 300, | |
| "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": 52622211072000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |