| { | |
| "best_metric": 0.030037986114621162, | |
| "best_model_checkpoint": "EN-DE_1/checkpoint-4000", | |
| "epoch": 18.264840182648403, | |
| "global_step": 4000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.943150684931507e-06, | |
| "loss": 0.0458, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_loss": 0.0317346565425396, | |
| "eval_mse": 0.0317346565425396, | |
| "eval_pearson_correlation": 0.46990232914177965, | |
| "eval_rmse": 0.1781422346830368, | |
| "eval_runtime": 2.578, | |
| "eval_samples_per_second": 387.905, | |
| "eval_spearman_corr": 0.4789856726431624, | |
| "eval_steps_per_second": 12.413, | |
| "learning_rate": 4.943150684931507e-06, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "learning_rate": 4.8860730593607305e-06, | |
| "loss": 0.0363, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.57, | |
| "eval_loss": 0.031161895021796227, | |
| "eval_mse": 0.031161896884441376, | |
| "eval_pearson_correlation": 0.4681432735823584, | |
| "eval_rmse": 0.17652732133865356, | |
| "eval_runtime": 2.5825, | |
| "eval_samples_per_second": 387.218, | |
| "eval_spearman_corr": 0.5022684527295919, | |
| "eval_steps_per_second": 12.391, | |
| "learning_rate": 4.8860730593607305e-06, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "learning_rate": 4.829109589041096e-06, | |
| "loss": 0.03, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.85, | |
| "eval_loss": 0.03813818097114563, | |
| "eval_mse": 0.03813818469643593, | |
| "eval_pearson_correlation": 0.47614034267336836, | |
| "eval_rmse": 0.1952899992465973, | |
| "eval_runtime": 2.586, | |
| "eval_samples_per_second": 386.701, | |
| "eval_spearman_corr": 0.5117927401539177, | |
| "eval_steps_per_second": 12.374, | |
| "learning_rate": 4.829109589041096e-06, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "learning_rate": 4.77203196347032e-06, | |
| "loss": 0.0235, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "eval_loss": 0.03011469729244709, | |
| "eval_mse": 0.03011469729244709, | |
| "eval_pearson_correlation": 0.5004122369046293, | |
| "eval_rmse": 0.17353586852550507, | |
| "eval_runtime": 2.5817, | |
| "eval_samples_per_second": 387.347, | |
| "eval_spearman_corr": 0.5088055517612488, | |
| "eval_steps_per_second": 12.395, | |
| "learning_rate": 4.77203196347032e-06, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 4.7149543378995435e-06, | |
| "loss": 0.0196, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "eval_loss": 0.040484823286533356, | |
| "eval_mse": 0.040484823286533356, | |
| "eval_pearson_correlation": 0.4791417607023304, | |
| "eval_rmse": 0.20120841264724731, | |
| "eval_runtime": 2.5689, | |
| "eval_samples_per_second": 389.264, | |
| "eval_spearman_corr": 0.49223680640020745, | |
| "eval_steps_per_second": 12.456, | |
| "learning_rate": 4.7149543378995435e-06, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "learning_rate": 4.6578767123287675e-06, | |
| "loss": 0.0169, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 13.7, | |
| "eval_loss": 0.03211166337132454, | |
| "eval_mse": 0.03211166337132454, | |
| "eval_pearson_correlation": 0.509159843974805, | |
| "eval_rmse": 0.1791972815990448, | |
| "eval_runtime": 2.5988, | |
| "eval_samples_per_second": 384.8, | |
| "eval_spearman_corr": 0.4970874031697612, | |
| "eval_steps_per_second": 12.314, | |
| "learning_rate": 4.6578767123287675e-06, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "learning_rate": 4.600799086757991e-06, | |
| "loss": 0.0144, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 15.98, | |
| "eval_loss": 0.03915296494960785, | |
| "eval_mse": 0.03915296494960785, | |
| "eval_pearson_correlation": 0.49790449972703843, | |
| "eval_rmse": 0.19787108898162842, | |
| "eval_runtime": 2.5896, | |
| "eval_samples_per_second": 386.156, | |
| "eval_spearman_corr": 0.4949469011494366, | |
| "eval_steps_per_second": 12.357, | |
| "learning_rate": 4.600799086757991e-06, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "learning_rate": 4.543721461187215e-06, | |
| "loss": 0.0124, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 18.26, | |
| "eval_loss": 0.030037986114621162, | |
| "eval_mse": 0.030037986114621162, | |
| "eval_pearson_correlation": 0.5246180486388605, | |
| "eval_rmse": 0.17331470549106598, | |
| "eval_runtime": 2.5739, | |
| "eval_samples_per_second": 388.513, | |
| "eval_spearman_corr": 0.5060582469818566, | |
| "eval_steps_per_second": 12.432, | |
| "learning_rate": 4.543721461187215e-06, | |
| "step": 4000 | |
| } | |
| ], | |
| "max_steps": 43800, | |
| "num_train_epochs": 200, | |
| "total_flos": 3.49079923232496e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |