{ "best_metric": 1.2041057348251343, "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-900", "epoch": 1.9607843137254903, "eval_steps": 100, "global_step": 1000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.2, "learning_rate": 1.807843137254902e-05, "loss": 3.2307, "step": 100 }, { "epoch": 0.2, "eval_loss": 1.8958784341812134, "eval_runtime": 17.3462, "eval_samples_per_second": 690.006, "eval_steps_per_second": 10.838, "step": 100 }, { "epoch": 0.39, "learning_rate": 1.6117647058823533e-05, "loss": 1.9581, "step": 200 }, { "epoch": 0.39, "eval_loss": 1.485579490661621, "eval_runtime": 17.3451, "eval_samples_per_second": 690.051, "eval_steps_per_second": 10.839, "step": 200 }, { "epoch": 0.59, "learning_rate": 1.415686274509804e-05, "loss": 1.6358, "step": 300 }, { "epoch": 0.59, "eval_loss": 1.3947598934173584, "eval_runtime": 17.3855, "eval_samples_per_second": 688.449, "eval_steps_per_second": 10.814, "step": 300 }, { "epoch": 0.78, "learning_rate": 1.2196078431372552e-05, "loss": 1.4964, "step": 400 }, { "epoch": 0.78, "eval_loss": 1.293440818786621, "eval_runtime": 17.3267, "eval_samples_per_second": 690.782, "eval_steps_per_second": 10.85, "step": 400 }, { "epoch": 0.98, "learning_rate": 1.023529411764706e-05, "loss": 1.4169, "step": 500 }, { "epoch": 0.98, "eval_loss": 1.2604990005493164, "eval_runtime": 17.3401, "eval_samples_per_second": 690.251, "eval_steps_per_second": 10.842, "step": 500 }, { "epoch": 1.18, "learning_rate": 8.274509803921569e-06, "loss": 1.327, "step": 600 }, { "epoch": 1.18, "eval_loss": 1.2218035459518433, "eval_runtime": 17.3253, "eval_samples_per_second": 690.84, "eval_steps_per_second": 10.851, "step": 600 }, { "epoch": 1.37, "learning_rate": 6.313725490196079e-06, "loss": 1.2763, "step": 700 }, { "epoch": 1.37, "eval_loss": 1.2539091110229492, "eval_runtime": 17.3618, "eval_samples_per_second": 689.388, "eval_steps_per_second": 10.828, "step": 700 }, { "epoch": 1.57, "learning_rate": 4.352941176470588e-06, "loss": 1.2755, "step": 800 }, { "epoch": 1.57, "eval_loss": 1.2090030908584595, "eval_runtime": 17.401, "eval_samples_per_second": 687.833, "eval_steps_per_second": 10.804, "step": 800 }, { "epoch": 1.76, "learning_rate": 2.392156862745098e-06, "loss": 1.251, "step": 900 }, { "epoch": 1.76, "eval_loss": 1.2041057348251343, "eval_runtime": 17.3449, "eval_samples_per_second": 690.06, "eval_steps_per_second": 10.839, "step": 900 }, { "epoch": 1.96, "learning_rate": 4.3137254901960787e-07, "loss": 1.229, "step": 1000 }, { "epoch": 1.96, "eval_loss": 1.215934157371521, "eval_runtime": 17.3882, "eval_samples_per_second": 688.342, "eval_steps_per_second": 10.812, "step": 1000 }, { "epoch": 1.96, "step": 1000, "total_flos": 6.687707580928205e+16, "train_loss": 0.0, "train_runtime": 0.4781, "train_samples_per_second": 272946.308, "train_steps_per_second": 533.331 }, { "epoch": 1.96, "eval_loss": 1.204106092453003, "eval_runtime": 17.0762, "eval_samples_per_second": 700.916, "eval_steps_per_second": 5.505, "step": 1000 } ], "logging_steps": 100, "max_steps": 255, "num_train_epochs": 1, "save_steps": 100, "total_flos": 6.687707580928205e+16, "trial_name": null, "trial_params": null }