| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9997314859567156, | |
| "eval_steps": 500, | |
| "global_step": 2327, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0214811234627571, | |
| "grad_norm": 31.968038601385185, | |
| "learning_rate": 1.1933174224343676e-06, | |
| "loss": 7.2731, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0429622469255142, | |
| "grad_norm": 5.528123518866496, | |
| "learning_rate": 2.386634844868735e-06, | |
| "loss": 4.5176, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0644433703882713, | |
| "grad_norm": 4.013416984799431, | |
| "learning_rate": 3.579952267303103e-06, | |
| "loss": 3.944, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0859244938510284, | |
| "grad_norm": 4.1892340035922215, | |
| "learning_rate": 4.77326968973747e-06, | |
| "loss": 3.8281, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1074056173137855, | |
| "grad_norm": 4.356313571336095, | |
| "learning_rate": 5.966587112171838e-06, | |
| "loss": 3.7427, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1288867407765426, | |
| "grad_norm": 5.346040312976452, | |
| "learning_rate": 7.159904534606206e-06, | |
| "loss": 3.6489, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1503678642392997, | |
| "grad_norm": 4.776939807791867, | |
| "learning_rate": 8.353221957040574e-06, | |
| "loss": 3.5823, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1718489877020568, | |
| "grad_norm": 10.247146453472746, | |
| "learning_rate": 9.54653937947494e-06, | |
| "loss": 3.5253, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1933301111648139, | |
| "grad_norm": 6.332195173962142, | |
| "learning_rate": 9.999870719949443e-06, | |
| "loss": 3.4787, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.214811234627571, | |
| "grad_norm": 6.145898491034506, | |
| "learning_rate": 9.999117393223764e-06, | |
| "loss": 3.4273, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23629235809032811, | |
| "grad_norm": 10.904777995897074, | |
| "learning_rate": 9.99769155693599e-06, | |
| "loss": 3.3669, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2577734815530852, | |
| "grad_norm": 6.61764216296632, | |
| "learning_rate": 9.995593402897697e-06, | |
| "loss": 3.3476, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2792546050158423, | |
| "grad_norm": 6.2657567340957865, | |
| "learning_rate": 9.992823213364433e-06, | |
| "loss": 3.3088, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3007357284785994, | |
| "grad_norm": 6.995191940894484, | |
| "learning_rate": 9.989381360997774e-06, | |
| "loss": 3.2714, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3222168519413565, | |
| "grad_norm": 6.203290180438067, | |
| "learning_rate": 9.985268308815177e-06, | |
| "loss": 3.2397, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3436979754041136, | |
| "grad_norm": 7.490753987379018, | |
| "learning_rate": 9.980484610127696e-06, | |
| "loss": 3.2138, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3651790988668707, | |
| "grad_norm": 8.648997976996425, | |
| "learning_rate": 9.975030908465552e-06, | |
| "loss": 3.1921, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.3866602223296278, | |
| "grad_norm": 6.113805971386634, | |
| "learning_rate": 9.968907937491556e-06, | |
| "loss": 3.1802, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4081413457923849, | |
| "grad_norm": 5.804493355360227, | |
| "learning_rate": 9.962116520902414e-06, | |
| "loss": 3.1549, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.429622469255142, | |
| "grad_norm": 5.672462264835336, | |
| "learning_rate": 9.954657572317915e-06, | |
| "loss": 3.1404, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4511035927178991, | |
| "grad_norm": 6.0559387120141785, | |
| "learning_rate": 9.946532095158037e-06, | |
| "loss": 3.1279, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.47258471618065623, | |
| "grad_norm": 6.210237139675206, | |
| "learning_rate": 9.937741182507946e-06, | |
| "loss": 3.098, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.49406583964341333, | |
| "grad_norm": 7.431184266924992, | |
| "learning_rate": 9.928286016970965e-06, | |
| "loss": 3.107, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5155469631061704, | |
| "grad_norm": 6.625965920694867, | |
| "learning_rate": 9.918167870509469e-06, | |
| "loss": 3.0814, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5370280865689275, | |
| "grad_norm": 7.118592442886439, | |
| "learning_rate": 9.907388104273776e-06, | |
| "loss": 3.0478, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5585092100316846, | |
| "grad_norm": 6.091819271475767, | |
| "learning_rate": 9.895948168419045e-06, | |
| "loss": 3.0431, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5799903334944417, | |
| "grad_norm": 6.206825982763474, | |
| "learning_rate": 9.883849601910185e-06, | |
| "loss": 3.0611, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6014714569571988, | |
| "grad_norm": 6.978024482259336, | |
| "learning_rate": 9.871094032314833e-06, | |
| "loss": 3.0588, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.6229525804199559, | |
| "grad_norm": 6.373929621089481, | |
| "learning_rate": 9.857683175584394e-06, | |
| "loss": 3.0439, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.644433703882713, | |
| "grad_norm": 6.9083655211278225, | |
| "learning_rate": 9.843618835823208e-06, | |
| "loss": 3.0259, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6659148273454701, | |
| "grad_norm": 6.899677057241488, | |
| "learning_rate": 9.82890290504585e-06, | |
| "loss": 3.0046, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6873959508082272, | |
| "grad_norm": 6.0934482084027906, | |
| "learning_rate": 9.813537362922608e-06, | |
| "loss": 2.9895, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7088770742709843, | |
| "grad_norm": 6.928618562605459, | |
| "learning_rate": 9.797524276513162e-06, | |
| "loss": 3.0121, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7303581977337414, | |
| "grad_norm": 6.950669980345654, | |
| "learning_rate": 9.780865799988516e-06, | |
| "loss": 2.9924, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7518393211964985, | |
| "grad_norm": 7.231466841681743, | |
| "learning_rate": 9.763564174341203e-06, | |
| "loss": 2.98, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.7733204446592556, | |
| "grad_norm": 6.379449871420294, | |
| "learning_rate": 9.745621727083817e-06, | |
| "loss": 2.9774, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7948015681220127, | |
| "grad_norm": 7.2185660169531065, | |
| "learning_rate": 9.727040871935898e-06, | |
| "loss": 2.9838, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.8162826915847698, | |
| "grad_norm": 6.189276666554435, | |
| "learning_rate": 9.707824108499233e-06, | |
| "loss": 2.9345, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.837763815047527, | |
| "grad_norm": 6.1735836440437115, | |
| "learning_rate": 9.68797402192159e-06, | |
| "loss": 2.9305, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.859244938510284, | |
| "grad_norm": 6.814578159329923, | |
| "learning_rate": 9.667493282548945e-06, | |
| "loss": 2.945, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8807260619730412, | |
| "grad_norm": 7.0951355912718626, | |
| "learning_rate": 9.646384645566263e-06, | |
| "loss": 2.9128, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.9022071854357983, | |
| "grad_norm": 6.871591433945105, | |
| "learning_rate": 9.624650950626846e-06, | |
| "loss": 2.9113, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.9236883088985554, | |
| "grad_norm": 6.778622650056036, | |
| "learning_rate": 9.602295121470328e-06, | |
| "loss": 2.9063, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.9451694323613125, | |
| "grad_norm": 7.472433386997439, | |
| "learning_rate": 9.57932016552936e-06, | |
| "loss": 2.9005, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.9666505558240696, | |
| "grad_norm": 6.3018605300569215, | |
| "learning_rate": 9.555729173525035e-06, | |
| "loss": 2.8921, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.9881316792868267, | |
| "grad_norm": 6.616217022995068, | |
| "learning_rate": 9.531525319051097e-06, | |
| "loss": 2.9017, | |
| "step": 2300 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 13962, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 1.0, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |