| { |
| "best_metric": 0.9135991932046025, |
| "best_model_checkpoint": "../models/eusts/checkpoint-2180", |
| "epoch": 10.0, |
| "global_step": 2180, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 2.8726207906295755e-05, |
| "loss": 1.4053, |
| "step": 218 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.8498445305588846, |
| "eval_loss": 0.5913795232772827, |
| "eval_pearson": 0.8576485507627736, |
| "eval_runtime": 10.4654, |
| "eval_samples_per_second": 83.227, |
| "eval_spearmanr": 0.8420405103549957, |
| "eval_steps_per_second": 10.415, |
| "step": 218 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 2.553440702781845e-05, |
| "loss": 0.3881, |
| "step": 436 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.887035736675172, |
| "eval_loss": 0.447421669960022, |
| "eval_pearson": 0.8917341241804541, |
| "eval_runtime": 10.5067, |
| "eval_samples_per_second": 82.899, |
| "eval_spearmanr": 0.8823373491698899, |
| "eval_steps_per_second": 10.374, |
| "step": 436 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 2.2342606149341143e-05, |
| "loss": 0.2083, |
| "step": 654 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.8970108216951012, |
| "eval_loss": 0.4096603989601135, |
| "eval_pearson": 0.9016467997316473, |
| "eval_runtime": 10.4817, |
| "eval_samples_per_second": 83.097, |
| "eval_spearmanr": 0.8923748436585551, |
| "eval_steps_per_second": 10.399, |
| "step": 654 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 1.9150805270863837e-05, |
| "loss": 0.1393, |
| "step": 872 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.9009673665742599, |
| "eval_loss": 0.3968064486980438, |
| "eval_pearson": 0.9046095606853766, |
| "eval_runtime": 10.448, |
| "eval_samples_per_second": 83.366, |
| "eval_spearmanr": 0.8973251724631434, |
| "eval_steps_per_second": 10.433, |
| "step": 872 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 1.595900439238653e-05, |
| "loss": 0.1023, |
| "step": 1090 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.906389648678596, |
| "eval_loss": 0.38093939423561096, |
| "eval_pearson": 0.9095917410726173, |
| "eval_runtime": 10.7338, |
| "eval_samples_per_second": 81.146, |
| "eval_spearmanr": 0.9031875562845746, |
| "eval_steps_per_second": 10.155, |
| "step": 1090 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 1.2767203513909225e-05, |
| "loss": 0.0841, |
| "step": 1308 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.9098955778506463, |
| "eval_loss": 0.37849491834640503, |
| "eval_pearson": 0.9139073667065271, |
| "eval_runtime": 10.6077, |
| "eval_samples_per_second": 82.11, |
| "eval_spearmanr": 0.9058837889947655, |
| "eval_steps_per_second": 10.276, |
| "step": 1308 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 9.575402635431918e-06, |
| "loss": 0.0664, |
| "step": 1526 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_combined_score": 0.9111955743924036, |
| "eval_loss": 0.35929641127586365, |
| "eval_pearson": 0.9148956072886006, |
| "eval_runtime": 10.7134, |
| "eval_samples_per_second": 81.3, |
| "eval_spearmanr": 0.9074955414962067, |
| "eval_steps_per_second": 10.174, |
| "step": 1526 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 6.383601756954612e-06, |
| "loss": 0.057, |
| "step": 1744 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_combined_score": 0.9122781067251765, |
| "eval_loss": 0.3573194146156311, |
| "eval_pearson": 0.9160432969800479, |
| "eval_runtime": 10.694, |
| "eval_samples_per_second": 81.448, |
| "eval_spearmanr": 0.9085129164703051, |
| "eval_steps_per_second": 10.193, |
| "step": 1744 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 3.191800878477306e-06, |
| "loss": 0.0485, |
| "step": 1962 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_combined_score": 0.9128873266818468, |
| "eval_loss": 0.3531445860862732, |
| "eval_pearson": 0.9165594039106797, |
| "eval_runtime": 10.7576, |
| "eval_samples_per_second": 80.966, |
| "eval_spearmanr": 0.9092152494530139, |
| "eval_steps_per_second": 10.132, |
| "step": 1962 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 0.0, |
| "loss": 0.0449, |
| "step": 2180 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_combined_score": 0.9135991932046025, |
| "eval_loss": 0.3487534821033478, |
| "eval_pearson": 0.917271052630473, |
| "eval_runtime": 10.8295, |
| "eval_samples_per_second": 80.428, |
| "eval_spearmanr": 0.9099273337787319, |
| "eval_steps_per_second": 10.065, |
| "step": 2180 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 2180, |
| "total_flos": 1.834393807540224e+16, |
| "train_loss": 0.2544048738042149, |
| "train_runtime": 2592.0512, |
| "train_samples_per_second": 26.898, |
| "train_steps_per_second": 0.841 |
| } |
| ], |
| "max_steps": 2180, |
| "num_train_epochs": 10, |
| "total_flos": 1.834393807540224e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
