| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 669, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 0.0002998660541859271, | |
| "loss": 1.1033, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002994033387324446, | |
| "loss": 0.9066, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0002986112199359036, | |
| "loss": 0.846, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00029749144425379216, | |
| "loss": 0.8246, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000296205525182313, | |
| "loss": 0.8011, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00029447059587783353, | |
| "loss": 0.7911, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002924171389041629, | |
| "loss": 0.7719, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0002903004140503956, | |
| "loss": 0.7793, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002876548000410533, | |
| "loss": 0.7633, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00028470568577725704, | |
| "loss": 0.7623, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0002814595734436687, | |
| "loss": 0.7519, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002779236200440321, | |
| "loss": 0.7471, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0002741056216214651, | |
| "loss": 0.7505, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.00027001399606980383, | |
| "loss": 0.7342, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.0002656577645738938, | |
| "loss": 0.7443, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.0002610465317197509, | |
| "loss": 0.7247, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002561904643184426, | |
| "loss": 0.7319, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00025110026899038105, | |
| "loss": 0.7297, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0002457871685594478, | |
| "loss": 0.7373, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0002402628773089967, | |
| "loss": 0.7267, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00023453957515429192, | |
| "loss": 0.7341, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002286298807883231, | |
| "loss": 0.7195, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.00022254682386020736, | |
| "loss": 0.7221, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.00021630381624751795, | |
| "loss": 0.7214, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.00020991462248587929, | |
| "loss": 0.7192, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00020339332942102297, | |
| "loss": 0.7139, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.0001967543151502182, | |
| "loss": 0.7164, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00019001221732155218, | |
| "loss": 0.7219, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0001831819008609551, | |
| "loss": 0.7237, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00017627842519812485, | |
| "loss": 0.7236, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00016931701106361107, | |
| "loss": 0.7038, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00016231300693026433, | |
| "loss": 0.7073, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00015528185517304027, | |
| "loss": 0.711, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.00014823905802176872, | |
| "loss": 0.7029, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.0001412001433819556, | |
| "loss": 0.7199, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.00013418063059897524, | |
| "loss": 0.7229, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00012719599624113573, | |
| "loss": 0.7189, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00012026163997705916, | |
| "loss": 0.7147, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00011339285062260957, | |
| "loss": 0.6928, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.00010660477243222808, | |
| "loss": 0.7002, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 9.991237170899614e-05, | |
| "loss": 0.7198, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 9.33304038070446e-05, | |
| "loss": 0.701, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 8.68733805990611e-05, | |
| "loss": 0.6928, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 8.055553848062404e-05, | |
| "loss": 0.696, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.439080698190579e-05, | |
| "loss": 0.7038, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 6.839277805595081e-05, | |
| "loss": 0.6949, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 6.257467611124105e-05, | |
| "loss": 0.7054, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 5.6949328854621045e-05, | |
| "loss": 0.7013, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 5.152913900886729e-05, | |
| "loss": 0.6976, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 4.632605696725987e-05, | |
| "loss": 0.6978, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 4.13515544454462e-05, | |
| "loss": 0.6964, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 3.66165991886898e-05, | |
| "loss": 0.7135, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 3.2131630790269134e-05, | |
| "loss": 0.7026, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 2.790653767434181e-05, | |
| "loss": 0.6986, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 2.3950635294022347e-05, | |
| "loss": 0.6809, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 2.027264559274224e-05, | |
| "loss": 0.6954, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.6880677774175354e-05, | |
| "loss": 0.7028, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.3782210423127449e-05, | |
| "loss": 0.6802, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.0984075016809528e-05, | |
| "loss": 0.6969, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 8.492440862848787e-06, | |
| "loss": 0.6995, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 6.312801497246206e-06, | |
| "loss": 0.6908, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 4.44996257227021e-06, | |
| "loss": 0.6933, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 2.908031260991195e-06, | |
| "loss": 0.6993, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6904072018175786e-06, | |
| "loss": 0.6977, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.997750029989647e-07, | |
| "loss": 0.6936, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 2.380983236223377e-07, | |
| "loss": 0.6879, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 669, | |
| "total_flos": 5.563883205708218e+18, | |
| "train_loss": 0.7295773652993331, | |
| "train_runtime": 13470.6062, | |
| "train_samples_per_second": 6.356, | |
| "train_steps_per_second": 0.05 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 669, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 5.563883205708218e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |