| { | |
| "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": 11.80153053831896, | |
| "learning_rate": 1.1933174224343676e-06, | |
| "loss": 5.7433, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0429622469255142, | |
| "grad_norm": 3.9560565670689787, | |
| "learning_rate": 2.386634844868735e-06, | |
| "loss": 4.6773, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0644433703882713, | |
| "grad_norm": 3.1697190737531535, | |
| "learning_rate": 3.579952267303103e-06, | |
| "loss": 4.1765, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0859244938510284, | |
| "grad_norm": 3.0629881164511814, | |
| "learning_rate": 4.77326968973747e-06, | |
| "loss": 3.9862, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1074056173137855, | |
| "grad_norm": 3.782319031089094, | |
| "learning_rate": 5.966587112171838e-06, | |
| "loss": 3.8765, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1288867407765426, | |
| "grad_norm": 4.981876775635735, | |
| "learning_rate": 7.159904534606206e-06, | |
| "loss": 3.7555, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1503678642392997, | |
| "grad_norm": 5.086535704279024, | |
| "learning_rate": 8.353221957040574e-06, | |
| "loss": 3.6723, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1718489877020568, | |
| "grad_norm": 5.687053039301101, | |
| "learning_rate": 9.54653937947494e-06, | |
| "loss": 3.6078, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1933301111648139, | |
| "grad_norm": 5.528308193865339, | |
| "learning_rate": 9.999870719949443e-06, | |
| "loss": 3.5469, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.214811234627571, | |
| "grad_norm": 5.706889809403439, | |
| "learning_rate": 9.999117393223764e-06, | |
| "loss": 3.4902, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23629235809032811, | |
| "grad_norm": 8.153143367841682, | |
| "learning_rate": 9.99769155693599e-06, | |
| "loss": 3.4188, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2577734815530852, | |
| "grad_norm": 5.845809899861177, | |
| "learning_rate": 9.995593402897697e-06, | |
| "loss": 3.3961, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.2792546050158423, | |
| "grad_norm": 6.193786755519171, | |
| "learning_rate": 9.992823213364433e-06, | |
| "loss": 3.3581, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.3007357284785994, | |
| "grad_norm": 6.287910360630115, | |
| "learning_rate": 9.989381360997774e-06, | |
| "loss": 3.3181, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3222168519413565, | |
| "grad_norm": 6.7245258610858025, | |
| "learning_rate": 9.985268308815177e-06, | |
| "loss": 3.2873, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3436979754041136, | |
| "grad_norm": 6.2374846893994125, | |
| "learning_rate": 9.980484610127696e-06, | |
| "loss": 3.2627, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.3651790988668707, | |
| "grad_norm": 6.157634090577404, | |
| "learning_rate": 9.975030908465552e-06, | |
| "loss": 3.2385, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.3866602223296278, | |
| "grad_norm": 6.055313983623131, | |
| "learning_rate": 9.968907937491556e-06, | |
| "loss": 3.2332, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4081413457923849, | |
| "grad_norm": 5.643811929136974, | |
| "learning_rate": 9.962116520902414e-06, | |
| "loss": 3.2023, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.429622469255142, | |
| "grad_norm": 5.926620348550728, | |
| "learning_rate": 9.954657572317915e-06, | |
| "loss": 3.1881, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4511035927178991, | |
| "grad_norm": 6.701182779844167, | |
| "learning_rate": 9.946532095158037e-06, | |
| "loss": 3.1679, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.47258471618065623, | |
| "grad_norm": 6.36759463453718, | |
| "learning_rate": 9.937741182507946e-06, | |
| "loss": 3.1442, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.49406583964341333, | |
| "grad_norm": 7.096154490236862, | |
| "learning_rate": 9.928286016970965e-06, | |
| "loss": 3.155, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.5155469631061704, | |
| "grad_norm": 6.088872047795586, | |
| "learning_rate": 9.918167870509469e-06, | |
| "loss": 3.1275, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5370280865689275, | |
| "grad_norm": 6.761966156468945, | |
| "learning_rate": 9.907388104273776e-06, | |
| "loss": 3.095, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.5585092100316846, | |
| "grad_norm": 6.21960112723293, | |
| "learning_rate": 9.895948168419045e-06, | |
| "loss": 3.0861, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.5799903334944417, | |
| "grad_norm": 6.396312085808871, | |
| "learning_rate": 9.883849601910185e-06, | |
| "loss": 3.1002, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6014714569571988, | |
| "grad_norm": 6.84214950380231, | |
| "learning_rate": 9.871094032314833e-06, | |
| "loss": 3.1037, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.6229525804199559, | |
| "grad_norm": 6.454543297291967, | |
| "learning_rate": 9.857683175584394e-06, | |
| "loss": 3.0833, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.644433703882713, | |
| "grad_norm": 6.794657141475511, | |
| "learning_rate": 9.843618835823208e-06, | |
| "loss": 3.0685, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6659148273454701, | |
| "grad_norm": 6.573147319811302, | |
| "learning_rate": 9.82890290504585e-06, | |
| "loss": 3.047, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.6873959508082272, | |
| "grad_norm": 6.666311208864922, | |
| "learning_rate": 9.813537362922608e-06, | |
| "loss": 3.0326, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7088770742709843, | |
| "grad_norm": 6.490840785958152, | |
| "learning_rate": 9.797524276513162e-06, | |
| "loss": 3.0562, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7303581977337414, | |
| "grad_norm": 7.096203367165056, | |
| "learning_rate": 9.780865799988516e-06, | |
| "loss": 3.031, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.7518393211964985, | |
| "grad_norm": 6.752554004118515, | |
| "learning_rate": 9.763564174341203e-06, | |
| "loss": 3.0211, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.7733204446592556, | |
| "grad_norm": 6.267973471607311, | |
| "learning_rate": 9.745621727083817e-06, | |
| "loss": 3.017, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.7948015681220127, | |
| "grad_norm": 6.4153741524585435, | |
| "learning_rate": 9.727040871935898e-06, | |
| "loss": 3.0248, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.8162826915847698, | |
| "grad_norm": 6.44854230007588, | |
| "learning_rate": 9.707824108499233e-06, | |
| "loss": 2.974, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.837763815047527, | |
| "grad_norm": 6.434347899473903, | |
| "learning_rate": 9.68797402192159e-06, | |
| "loss": 2.9643, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.859244938510284, | |
| "grad_norm": 6.623547979694668, | |
| "learning_rate": 9.667493282548945e-06, | |
| "loss": 2.9832, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8807260619730412, | |
| "grad_norm": 7.423714925680245, | |
| "learning_rate": 9.646384645566263e-06, | |
| "loss": 2.9494, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.9022071854357983, | |
| "grad_norm": 6.539828516530332, | |
| "learning_rate": 9.624650950626846e-06, | |
| "loss": 2.9489, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.9236883088985554, | |
| "grad_norm": 6.884977149689985, | |
| "learning_rate": 9.602295121470328e-06, | |
| "loss": 2.9446, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.9451694323613125, | |
| "grad_norm": 7.167446447983352, | |
| "learning_rate": 9.57932016552936e-06, | |
| "loss": 2.9367, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.9666505558240696, | |
| "grad_norm": 6.06922872483934, | |
| "learning_rate": 9.555729173525035e-06, | |
| "loss": 2.9252, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.9881316792868267, | |
| "grad_norm": 6.386687065769196, | |
| "learning_rate": 9.531525319051097e-06, | |
| "loss": 2.9342, | |
| "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 | |
| } | |