{ "batch_size": 1, "best_eval_metric_checkpoint_number": 1, "best_eval_metric_epoch": 0, "best_eval_metric_steps": 10804, "best_eval_metric_value": 1.2898268699645996, "best_eval_test_metrics": { "combined": { "loss": 1.2531609535217285 }, "title": { "bleu": 0.0180843286216259, "char_error_rate": 9.017064094543457, "loss": 1.2531609535217285, "next_token_perplexity": 17219.509765625, "perplexity": 31900.73046875, "rouge1_fmeasure": 0.11042051762342453, "rouge1_precision": 0.060600001364946365, "rouge1_recall": 0.6982588171958923, "rouge2_fmeasure": 0.05184469372034073, "rouge2_precision": 0.028261005878448486, "rouge2_recall": 0.3632716238498688, "rougeL_fmeasure": 0.09752275049686432, "rougeL_precision": 0.053463079035282135, "rougeL_recall": 0.6240717768669128, "rougeLsum_fmeasure": 0.10595671832561493, "rougeLsum_precision": 0.05813445523381233, "rougeLsum_recall": 0.6721860766410828, "sequence_accuracy": 0.0, "token_accuracy": 3.437707346165553e-05, "word_error_rate": 11.557415008544922 } }, "best_eval_train_metrics": { "combined": { "loss": 1.1997183561325073 }, "title": { "bleu": 0.018341578543186188, "char_error_rate": 9.083020210266113, "loss": 1.1997183561325073, "next_token_perplexity": 17061.228515625, "perplexity": 31874.365234375, "rouge1_fmeasure": 0.11363156139850616, "rouge1_precision": 0.062363866716623306, "rouge1_recall": 0.7099939584732056, "rouge2_fmeasure": 0.05589400604367256, "rouge2_precision": 0.030487291514873505, "rouge2_recall": 0.380205899477005, "rougeL_fmeasure": 0.10056732594966888, "rougeL_precision": 0.055148735642433167, "rougeL_recall": 0.6347331404685974, "rougeLsum_fmeasure": 0.10977762192487717, "rougeLsum_precision": 0.060230888426303864, "rougeLsum_recall": 0.6885234117507935, "sequence_accuracy": 0.0, "token_accuracy": 3.639719579950906e-05, "word_error_rate": 11.418218612670898 } }, "best_eval_validation_metrics": { "combined": { "loss": 1.2898268699645996 }, "title": { "bleu": 0.015481029637157917, "char_error_rate": 9.0972900390625, "loss": 1.2898268699645996, "next_token_perplexity": 17339.482421875, "perplexity": 31906.75390625, "rouge1_fmeasure": 0.10748682916164398, "rouge1_precision": 0.058967169374227524, "rouge1_recall": 0.6764949560165405, "rouge2_fmeasure": 0.050337474793195724, "rouge2_precision": 0.02745284140110016, "rouge2_recall": 0.3486025929450989, "rougeL_fmeasure": 0.09531988948583603, "rougeL_precision": 0.05225425586104393, "rougeL_recall": 0.6058534979820251, "rougeLsum_fmeasure": 0.103290855884552, "rougeLsum_precision": 0.056647758930921555, "rougeLsum_recall": 0.6526778936386108, "sequence_accuracy": 0.0, "token_accuracy": 0.0, "word_error_rate": 11.665448188781738 } }, "best_increase_batch_size_eval_metric": Infinity, "checkpoint_number": 1, "epoch": 1, "last_improvement_steps": 0, "last_increase_batch_size": 0, "last_increase_batch_size_eval_metric_improvement": 0, "last_increase_batch_size_steps": 0, "last_learning_rate_reduction": 0, "last_learning_rate_reduction_steps": 0, "learning_rate": 0.0004, "num_increases_batch_size": 0, "num_reductions_learning_rate": 0, "steps": 10804, "test_metrics": { "combined": { "loss": [ [ 0, 10804, 1.2531609535217285 ] ] }, "title": { "bleu": [ [ 0, 10804, 0.0180843286216259 ] ], "char_error_rate": [ [ 0, 10804, 9.017064094543457 ] ], "loss": [ [ 0, 10804, 1.2531609535217285 ] ], "next_token_perplexity": [ [ 0, 10804, 17219.509765625 ] ], "perplexity": [ [ 0, 10804, 31900.73046875 ] ], "rouge1_fmeasure": [ [ 0, 10804, 0.11042051762342453 ] ], "rouge1_precision": [ [ 0, 10804, 0.060600001364946365 ] ], "rouge1_recall": [ [ 0, 10804, 0.6982588171958923 ] ], "rouge2_fmeasure": [ [ 0, 10804, 0.05184469372034073 ] ], "rouge2_precision": [ [ 0, 10804, 0.028261005878448486 ] ], "rouge2_recall": [ [ 0, 10804, 0.3632716238498688 ] ], "rougeL_fmeasure": [ [ 0, 10804, 0.09752275049686432 ] ], "rougeL_precision": [ [ 0, 10804, 0.053463079035282135 ] ], "rougeL_recall": [ [ 0, 10804, 0.6240717768669128 ] ], "rougeLsum_fmeasure": [ [ 0, 10804, 0.10595671832561493 ] ], "rougeLsum_precision": [ [ 0, 10804, 0.05813445523381233 ] ], "rougeLsum_recall": [ [ 0, 10804, 0.6721860766410828 ] ], "sequence_accuracy": [ [ 0, 10804, 0.0 ] ], "token_accuracy": [ [ 0, 10804, 3.437707346165553e-05 ] ], "word_error_rate": [ [ 0, 10804, 11.557415008544922 ] ] } }, "train_metrics": { "combined": { "loss": [ [ 0, 10804, 1.1997183561325073 ] ] }, "title": { "bleu": [ [ 0, 10804, 0.018341578543186188 ] ], "char_error_rate": [ [ 0, 10804, 9.083020210266113 ] ], "loss": [ [ 0, 10804, 1.1997183561325073 ] ], "next_token_perplexity": [ [ 0, 10804, 17061.228515625 ] ], "perplexity": [ [ 0, 10804, 31874.365234375 ] ], "rouge1_fmeasure": [ [ 0, 10804, 0.11363156139850616 ] ], "rouge1_precision": [ [ 0, 10804, 0.062363866716623306 ] ], "rouge1_recall": [ [ 0, 10804, 0.7099939584732056 ] ], "rouge2_fmeasure": [ [ 0, 10804, 0.05589400604367256 ] ], "rouge2_precision": [ [ 0, 10804, 0.030487291514873505 ] ], "rouge2_recall": [ [ 0, 10804, 0.380205899477005 ] ], "rougeL_fmeasure": [ [ 0, 10804, 0.10056732594966888 ] ], "rougeL_precision": [ [ 0, 10804, 0.055148735642433167 ] ], "rougeL_recall": [ [ 0, 10804, 0.6347331404685974 ] ], "rougeLsum_fmeasure": [ [ 0, 10804, 0.10977762192487717 ] ], "rougeLsum_precision": [ [ 0, 10804, 0.060230888426303864 ] ], "rougeLsum_recall": [ [ 0, 10804, 0.6885234117507935 ] ], "sequence_accuracy": [ [ 0, 10804, 0.0 ] ], "token_accuracy": [ [ 0, 10804, 3.639719579950906e-05 ] ], "word_error_rate": [ [ 0, 10804, 11.418218612670898 ] ] } }, "tune_checkpoint_num": 0, "validation_metrics": { "combined": { "loss": [ [ 0, 10804, 1.2898268699645996 ] ] }, "title": { "bleu": [ [ 0, 10804, 0.015481029637157917 ] ], "char_error_rate": [ [ 0, 10804, 9.0972900390625 ] ], "loss": [ [ 0, 10804, 1.2898268699645996 ] ], "next_token_perplexity": [ [ 0, 10804, 17339.482421875 ] ], "perplexity": [ [ 0, 10804, 31906.75390625 ] ], "rouge1_fmeasure": [ [ 0, 10804, 0.10748682916164398 ] ], "rouge1_precision": [ [ 0, 10804, 0.058967169374227524 ] ], "rouge1_recall": [ [ 0, 10804, 0.6764949560165405 ] ], "rouge2_fmeasure": [ [ 0, 10804, 0.050337474793195724 ] ], "rouge2_precision": [ [ 0, 10804, 0.02745284140110016 ] ], "rouge2_recall": [ [ 0, 10804, 0.3486025929450989 ] ], "rougeL_fmeasure": [ [ 0, 10804, 0.09531988948583603 ] ], "rougeL_precision": [ [ 0, 10804, 0.05225425586104393 ] ], "rougeL_recall": [ [ 0, 10804, 0.6058534979820251 ] ], "rougeLsum_fmeasure": [ [ 0, 10804, 0.103290855884552 ] ], "rougeLsum_precision": [ [ 0, 10804, 0.056647758930921555 ] ], "rougeLsum_recall": [ [ 0, 10804, 0.6526778936386108 ] ], "sequence_accuracy": [ [ 0, 10804, 0.0 ] ], "token_accuracy": [ [ 0, 10804, 0.0 ] ], "word_error_rate": [ [ 0, 10804, 11.665448188781738 ] ] } } }