| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 3495, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08583690987124463, | |
| "grad_norm": 0.14276766777038574, | |
| "learning_rate": 0.0001998960663781063, | |
| "loss": 0.8221, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17167381974248927, | |
| "grad_norm": 0.16238582134246826, | |
| "learning_rate": 0.00019906589321760313, | |
| "loss": 0.6354, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2575107296137339, | |
| "grad_norm": 0.17749547958374023, | |
| "learning_rate": 0.00019741244594178857, | |
| "loss": 0.583, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.34334763948497854, | |
| "grad_norm": 0.2390095442533493, | |
| "learning_rate": 0.00019494946530743566, | |
| "loss": 0.5441, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4291845493562232, | |
| "grad_norm": 0.17979831993579865, | |
| "learning_rate": 0.00019169741959214142, | |
| "loss": 0.522, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5150214592274678, | |
| "grad_norm": 0.140522301197052, | |
| "learning_rate": 0.0001876833344953899, | |
| "loss": 0.5098, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6008583690987125, | |
| "grad_norm": 0.21116133034229279, | |
| "learning_rate": 0.0001829405685450202, | |
| "loss": 0.4874, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6866952789699571, | |
| "grad_norm": 0.1852499544620514, | |
| "learning_rate": 0.00017750853587555535, | |
| "loss": 0.4818, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7725321888412017, | |
| "grad_norm": 0.4188537001609802, | |
| "learning_rate": 0.00017143237868220553, | |
| "loss": 0.4731, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8583690987124464, | |
| "grad_norm": 0.21729667484760284, | |
| "learning_rate": 0.00016476259207257407, | |
| "loss": 0.4542, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.944206008583691, | |
| "grad_norm": 0.146463543176651, | |
| "learning_rate": 0.0001575546044336872, | |
| "loss": 0.4446, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0300429184549356, | |
| "grad_norm": 0.30392587184906006, | |
| "learning_rate": 0.00014986831680165167, | |
| "loss": 0.4309, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.1158798283261802, | |
| "grad_norm": 0.15569771826267242, | |
| "learning_rate": 0.00014176760506194906, | |
| "loss": 0.4182, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.201716738197425, | |
| "grad_norm": 0.17742669582366943, | |
| "learning_rate": 0.00013331978911726523, | |
| "loss": 0.4091, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.2875536480686696, | |
| "grad_norm": 0.18690788745880127, | |
| "learning_rate": 0.00012459507343426653, | |
| "loss": 0.4032, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.3733905579399142, | |
| "grad_norm": 0.20853546261787415, | |
| "learning_rate": 0.00011566596361858548, | |
| "loss": 0.4029, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.4592274678111588, | |
| "grad_norm": 0.15021710097789764, | |
| "learning_rate": 0.0001066066638664925, | |
| "loss": 0.3972, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.5450643776824036, | |
| "grad_norm": 0.22972844541072845, | |
| "learning_rate": 9.749246030065306e-05, | |
| "loss": 0.3919, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.6309012875536482, | |
| "grad_norm": 0.21528910100460052, | |
| "learning_rate": 8.839909531467737e-05, | |
| "loss": 0.3876, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.7167381974248928, | |
| "grad_norm": 0.2293170988559723, | |
| "learning_rate": 7.940213812589018e-05, | |
| "loss": 0.3857, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.8025751072961373, | |
| "grad_norm": 0.18554259836673737, | |
| "learning_rate": 7.057635676725945e-05, | |
| "loss": 0.3849, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.888412017167382, | |
| "grad_norm": 0.15123458206653595, | |
| "learning_rate": 6.199509673746246e-05, | |
| "loss": 0.3801, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.9742489270386265, | |
| "grad_norm": 0.25308290123939514, | |
| "learning_rate": 5.372967147273683e-05, | |
| "loss": 0.3768, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.060085836909871, | |
| "grad_norm": 0.15006066858768463, | |
| "learning_rate": 4.584876970591957e-05, | |
| "loss": 0.3743, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.1459227467811157, | |
| "grad_norm": 0.155056893825531, | |
| "learning_rate": 3.841788463774003e-05, | |
| "loss": 0.3623, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.2317596566523603, | |
| "grad_norm": 0.19726864993572235, | |
| "learning_rate": 3.149876966416321e-05, | |
| "loss": 0.3649, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.317596566523605, | |
| "grad_norm": 0.18135452270507812, | |
| "learning_rate": 2.514892518288988e-05, | |
| "loss": 0.3614, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.40343347639485, | |
| "grad_norm": 0.19063273072242737, | |
| "learning_rate": 1.9421120743841902e-05, | |
| "loss": 0.3658, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.4892703862660945, | |
| "grad_norm": 0.1328456848859787, | |
| "learning_rate": 1.436295651473667e-05, | |
| "loss": 0.3608, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.575107296137339, | |
| "grad_norm": 0.13175827264785767, | |
| "learning_rate": 1.0016467706135135e-05, | |
| "loss": 0.3641, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.6609442060085837, | |
| "grad_norm": 0.13532917201519012, | |
| "learning_rate": 6.417775243336544e-06, | |
| "loss": 0.3623, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 2.7467811158798283, | |
| "grad_norm": 0.14848333597183228, | |
| "learning_rate": 3.5967855881650302e-06, | |
| "loss": 0.3584, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 2.832618025751073, | |
| "grad_norm": 0.1793571412563324, | |
| "learning_rate": 1.576942205240317e-06, | |
| "loss": 0.3656, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 2.9184549356223175, | |
| "grad_norm": 0.19799640774726868, | |
| "learning_rate": 3.750307381389484e-07, | |
| "loss": 0.3575, | |
| "step": 3400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 3495, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2889443120552346e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |