| { | |
| "best_metric": 1.1458996534347534, | |
| "best_model_checkpoint": "/content/drive/My Drive/Colab Notebooks/aai520-project/checkpoints/bert-finetuned-uncased/checkpoint-1500", | |
| "epoch": 3.9215686274509802, | |
| "eval_steps": 100, | |
| "global_step": 2000, | |
| "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": 2.16, | |
| "learning_rate": 9.23529411764706e-06, | |
| "loss": 1.1921, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "eval_loss": 1.1828099489212036, | |
| "eval_runtime": 17.2866, | |
| "eval_samples_per_second": 692.384, | |
| "eval_steps_per_second": 10.875, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "learning_rate": 8.254901960784314e-06, | |
| "loss": 1.1926, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.35, | |
| "eval_loss": 1.2119532823562622, | |
| "eval_runtime": 17.2797, | |
| "eval_samples_per_second": 692.663, | |
| "eval_steps_per_second": 10.88, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 7.284313725490196e-06, | |
| "loss": 1.1606, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_loss": 1.1737300157546997, | |
| "eval_runtime": 17.272, | |
| "eval_samples_per_second": 692.971, | |
| "eval_steps_per_second": 10.885, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 6.303921568627452e-06, | |
| "loss": 1.1486, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_loss": 1.1468586921691895, | |
| "eval_runtime": 17.2965, | |
| "eval_samples_per_second": 691.99, | |
| "eval_steps_per_second": 10.869, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "learning_rate": 5.3235294117647064e-06, | |
| "loss": 1.1195, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "eval_loss": 1.1458996534347534, | |
| "eval_runtime": 17.2925, | |
| "eval_samples_per_second": 692.148, | |
| "eval_steps_per_second": 10.872, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "learning_rate": 4.343137254901961e-06, | |
| "loss": 1.0883, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.14, | |
| "eval_loss": 1.1569820642471313, | |
| "eval_runtime": 17.2745, | |
| "eval_samples_per_second": 692.872, | |
| "eval_steps_per_second": 10.883, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "learning_rate": 3.3627450980392163e-06, | |
| "loss": 1.0526, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.33, | |
| "eval_loss": 1.177062749862671, | |
| "eval_runtime": 17.2742, | |
| "eval_samples_per_second": 692.885, | |
| "eval_steps_per_second": 10.883, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "learning_rate": 2.3823529411764705e-06, | |
| "loss": 1.0611, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "eval_loss": 1.174006462097168, | |
| "eval_runtime": 17.2639, | |
| "eval_samples_per_second": 693.295, | |
| "eval_steps_per_second": 10.89, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 1.4019607843137257e-06, | |
| "loss": 1.0521, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "eval_loss": 1.1595549583435059, | |
| "eval_runtime": 17.2716, | |
| "eval_samples_per_second": 692.987, | |
| "eval_steps_per_second": 10.885, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "learning_rate": 4.2156862745098044e-07, | |
| "loss": 1.0476, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 1.1538442373275757, | |
| "eval_runtime": 17.2708, | |
| "eval_samples_per_second": 693.021, | |
| "eval_steps_per_second": 10.885, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "step": 2000, | |
| "total_flos": 1.3373925770343014e+17, | |
| "train_loss": 0.0, | |
| "train_runtime": 0.6295, | |
| "train_samples_per_second": 829205.072, | |
| "train_steps_per_second": 1620.249 | |
| }, | |
| { | |
| "epoch": 3.92, | |
| "eval_loss": 1.1459009647369385, | |
| "eval_runtime": 17.0183, | |
| "eval_samples_per_second": 703.303, | |
| "eval_steps_per_second": 5.523, | |
| "step": 2000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1020, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "total_flos": 1.3373925770343014e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |