[ { "checkpoint": "chck_1M", "words_trained": 1000000, "global_step": 123, "val_loss": 8.828307991027833, "val_perplexity": 6824.729537261262 }, { "checkpoint": "chck_2M", "words_trained": 2000000, "global_step": 245, "val_loss": 7.891160659790039, "val_perplexity": 2673.545196972284 }, { "checkpoint": "chck_3M", "words_trained": 3000000, "global_step": 367, "val_loss": 7.473162097930908, "val_perplexity": 1760.1637050347072 }, { "checkpoint": "chck_4M", "words_trained": 4000000, "global_step": 489, "val_loss": 7.247150421142578, "val_perplexity": 1404.098053949613 }, { "checkpoint": "chck_5M", "words_trained": 5000000, "global_step": 611, "val_loss": 7.1073360347747805, "val_perplexity": 1220.8907994543215 }, { "checkpoint": "chck_6M", "words_trained": 6000000, "global_step": 733, "val_loss": 6.992768697738647, "val_perplexity": 1088.7316760256444 }, { "checkpoint": "chck_7M", "words_trained": 7000000, "global_step": 855, "val_loss": 6.954772806167602, "val_perplexity": 1048.1403798694926 }, { "checkpoint": "chck_8M", "words_trained": 8000000, "global_step": 977, "val_loss": 6.980320081710816, "val_perplexity": 1075.2624837754731 }, { "checkpoint": "chck_9M", "words_trained": 9000000, "global_step": 1099, "val_loss": 6.91542799949646, "val_perplexity": 1007.7022312619913 }, { "checkpoint": "chck_10M", "words_trained": 10000000, "global_step": 1221, "val_loss": 6.75490553855896, "val_perplexity": 858.2586737081385 }, { "checkpoint": "chck_20M", "words_trained": 20000000, "global_step": 2442, "val_loss": 6.233925104141235, "val_perplexity": 509.7523931221479 }, { "checkpoint": "chck_30M", "words_trained": 30000000, "global_step": 3663, "val_loss": 5.89044976234436, "val_perplexity": 361.56786741937503 }, { "checkpoint": "chck_40M", "words_trained": 40000000, "global_step": 4883, "val_loss": 5.774474506378174, "val_perplexity": 321.9751943439883 }, { "checkpoint": "chck_50M", "words_trained": 50000000, "global_step": 6104, "val_loss": 5.673352279663086, "val_perplexity": 291.0084427575258 }, { "checkpoint": "chck_60M", "words_trained": 60000000, "global_step": 7325, "val_loss": 5.440233287811279, "val_perplexity": 230.49594908443646 }, { "checkpoint": "chck_70M", "words_trained": 70000000, "global_step": 8545, "val_loss": 5.381023740768432, "val_perplexity": 217.24456373934882 }, { "checkpoint": "chck_80M", "words_trained": 80000000, "global_step": 9766, "val_loss": 5.3431094455718995, "val_perplexity": 209.1620782767871 }, { "checkpoint": "chck_90M", "words_trained": 90000000, "global_step": 10987, "val_loss": 5.234307689666748, "val_perplexity": 187.5991845223238 }, { "checkpoint": "chck_100M", "words_trained": 100000000, "global_step": 12208, "val_loss": 5.198590564727783, "val_perplexity": 181.01693034837896 }, { "checkpoint": "main", "words_trained": 126812160, "global_step": 15480, "val_loss": 5.1443859958648686, "val_perplexity": 171.4661714047026 } ]