| { | |
| "best_metric": 0.40127208828926086, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-2125", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.703668861712135e-06, | |
| "loss": 0.6976, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 9.40733772342427e-06, | |
| "loss": 0.5756, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.4111006585136408e-05, | |
| "loss": 0.5905, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 1.881467544684854e-05, | |
| "loss": 0.5445, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 2.3518344308560677e-05, | |
| "loss": 0.5061, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 2.8222013170272817e-05, | |
| "loss": 0.4163, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 3.292568203198495e-05, | |
| "loss": 0.4063, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 3.762935089369708e-05, | |
| "loss": 0.4095, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.233301975540922e-05, | |
| "loss": 0.4238, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.7036688617121355e-05, | |
| "loss": 0.431, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 4.9806525831416025e-05, | |
| "loss": 0.437, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.9283622673080946e-05, | |
| "loss": 0.4363, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.8760719514745873e-05, | |
| "loss": 0.4071, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 4.8237816356410795e-05, | |
| "loss": 0.4217, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 4.7714913198075716e-05, | |
| "loss": 0.4258, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.7192010039740643e-05, | |
| "loss": 0.3626, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.6669106881405564e-05, | |
| "loss": 0.402, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 4.614620372307049e-05, | |
| "loss": 0.4052, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 4.562330056473541e-05, | |
| "loss": 0.4162, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 4.5100397406400334e-05, | |
| "loss": 0.4147, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 4.457749424806526e-05, | |
| "loss": 0.4177, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.81825, | |
| "eval_auc": 0.8725866639820129, | |
| "eval_f1": 0.6585251291686237, | |
| "eval_loss": 0.40127208828926086, | |
| "eval_precision": 0.6154521510096576, | |
| "eval_recall": 0.7080808080808081, | |
| "eval_runtime": 648.355, | |
| "eval_samples_per_second": 6.169, | |
| "eval_steps_per_second": 0.386, | |
| "step": 2125 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 10625, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 1118221985280000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |