{ "best_metric": 1.1890357732772827, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.06780810306831667, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0013561620613663332, "grad_norm": 2.852473735809326, "learning_rate": 5e-05, "loss": 1.8006, "step": 1 }, { "epoch": 0.0013561620613663332, "eval_loss": 1.861175537109375, "eval_runtime": 82.7696, "eval_samples_per_second": 60.022, "eval_steps_per_second": 7.503, "step": 1 }, { "epoch": 0.0027123241227326664, "grad_norm": 2.986945390701294, "learning_rate": 0.0001, "loss": 1.8261, "step": 2 }, { "epoch": 0.0040684861840989996, "grad_norm": 1.968458652496338, "learning_rate": 9.989294616193017e-05, "loss": 1.6889, "step": 3 }, { "epoch": 0.005424648245465333, "grad_norm": 2.078989028930664, "learning_rate": 9.957224306869053e-05, "loss": 1.5043, "step": 4 }, { "epoch": 0.006780810306831667, "grad_norm": 1.3944963216781616, "learning_rate": 9.903926402016153e-05, "loss": 1.4348, "step": 5 }, { "epoch": 0.008136972368197999, "grad_norm": 1.0220277309417725, "learning_rate": 9.829629131445342e-05, "loss": 1.3875, "step": 6 }, { "epoch": 0.009493134429564332, "grad_norm": 0.6817047595977783, "learning_rate": 9.73465064747553e-05, "loss": 1.2852, "step": 7 }, { "epoch": 0.010849296490930666, "grad_norm": 0.674114465713501, "learning_rate": 9.619397662556435e-05, "loss": 1.2928, "step": 8 }, { "epoch": 0.012205458552296999, "grad_norm": 0.6182920336723328, "learning_rate": 9.484363707663442e-05, "loss": 1.2517, "step": 9 }, { "epoch": 0.013561620613663334, "grad_norm": 0.5390492677688599, "learning_rate": 9.330127018922194e-05, "loss": 1.2533, "step": 10 }, { "epoch": 0.014917782675029667, "grad_norm": 0.4900094270706177, "learning_rate": 9.157348061512727e-05, "loss": 1.2403, "step": 11 }, { "epoch": 0.016273944736395998, "grad_norm": 0.510083019733429, "learning_rate": 8.966766701456177e-05, "loss": 1.2955, "step": 12 }, { "epoch": 0.01763010679776233, "grad_norm": 0.486646831035614, "learning_rate": 8.759199037394887e-05, "loss": 1.3456, "step": 13 }, { "epoch": 0.018986268859128665, "grad_norm": 0.440630704164505, "learning_rate": 8.535533905932738e-05, "loss": 1.2407, "step": 14 }, { "epoch": 0.020342430920494998, "grad_norm": 0.42777761816978455, "learning_rate": 8.296729075500344e-05, "loss": 1.261, "step": 15 }, { "epoch": 0.02169859298186133, "grad_norm": 0.4407661259174347, "learning_rate": 8.043807145043604e-05, "loss": 1.2406, "step": 16 }, { "epoch": 0.023054755043227664, "grad_norm": 0.44828706979751587, "learning_rate": 7.777851165098012e-05, "loss": 1.2327, "step": 17 }, { "epoch": 0.024410917104593997, "grad_norm": 0.4163109064102173, "learning_rate": 7.500000000000001e-05, "loss": 1.2363, "step": 18 }, { "epoch": 0.02576707916596033, "grad_norm": 0.4135110676288605, "learning_rate": 7.211443451095007e-05, "loss": 1.2585, "step": 19 }, { "epoch": 0.027123241227326667, "grad_norm": 0.4255843162536621, "learning_rate": 6.91341716182545e-05, "loss": 1.2716, "step": 20 }, { "epoch": 0.028479403288693, "grad_norm": 0.3930562734603882, "learning_rate": 6.607197326515808e-05, "loss": 1.2165, "step": 21 }, { "epoch": 0.029835565350059334, "grad_norm": 0.3968987762928009, "learning_rate": 6.294095225512603e-05, "loss": 1.2606, "step": 22 }, { "epoch": 0.031191727411425667, "grad_norm": 0.40137743949890137, "learning_rate": 5.9754516100806423e-05, "loss": 1.2374, "step": 23 }, { "epoch": 0.032547889472791997, "grad_norm": 0.3884185254573822, "learning_rate": 5.6526309611002594e-05, "loss": 1.2152, "step": 24 }, { "epoch": 0.03390405153415833, "grad_norm": 0.43205586075782776, "learning_rate": 5.327015646150716e-05, "loss": 1.2734, "step": 25 }, { "epoch": 0.03390405153415833, "eval_loss": 1.208978295326233, "eval_runtime": 82.6548, "eval_samples_per_second": 60.105, "eval_steps_per_second": 7.513, "step": 25 }, { "epoch": 0.03526021359552466, "grad_norm": 0.389554500579834, "learning_rate": 5e-05, "loss": 1.2252, "step": 26 }, { "epoch": 0.036616375656891, "grad_norm": 0.384280264377594, "learning_rate": 4.6729843538492847e-05, "loss": 1.2031, "step": 27 }, { "epoch": 0.03797253771825733, "grad_norm": 0.38361260294914246, "learning_rate": 4.347369038899744e-05, "loss": 1.2121, "step": 28 }, { "epoch": 0.039328699779623666, "grad_norm": 0.36062079668045044, "learning_rate": 4.0245483899193595e-05, "loss": 1.231, "step": 29 }, { "epoch": 0.040684861840989996, "grad_norm": 0.38161206245422363, "learning_rate": 3.705904774487396e-05, "loss": 1.1932, "step": 30 }, { "epoch": 0.04204102390235633, "grad_norm": 0.3707989454269409, "learning_rate": 3.392802673484193e-05, "loss": 1.2412, "step": 31 }, { "epoch": 0.04339718596372266, "grad_norm": 0.3845455050468445, "learning_rate": 3.086582838174551e-05, "loss": 1.1926, "step": 32 }, { "epoch": 0.044753348025089, "grad_norm": 0.37922942638397217, "learning_rate": 2.7885565489049946e-05, "loss": 1.2045, "step": 33 }, { "epoch": 0.04610951008645533, "grad_norm": 0.3843218684196472, "learning_rate": 2.500000000000001e-05, "loss": 1.2378, "step": 34 }, { "epoch": 0.047465672147821665, "grad_norm": 0.4299803376197815, "learning_rate": 2.2221488349019903e-05, "loss": 1.1565, "step": 35 }, { "epoch": 0.048821834209187995, "grad_norm": 0.3997567296028137, "learning_rate": 1.9561928549563968e-05, "loss": 1.1827, "step": 36 }, { "epoch": 0.05017799627055433, "grad_norm": 0.41545793414115906, "learning_rate": 1.703270924499656e-05, "loss": 1.2315, "step": 37 }, { "epoch": 0.05153415833192066, "grad_norm": 0.4381093382835388, "learning_rate": 1.4644660940672627e-05, "loss": 1.2169, "step": 38 }, { "epoch": 0.052890320393287, "grad_norm": 0.40602096915245056, "learning_rate": 1.2408009626051137e-05, "loss": 1.2269, "step": 39 }, { "epoch": 0.054246482454653334, "grad_norm": 0.40004175901412964, "learning_rate": 1.0332332985438248e-05, "loss": 1.2234, "step": 40 }, { "epoch": 0.055602644516019664, "grad_norm": 0.3891931176185608, "learning_rate": 8.426519384872733e-06, "loss": 1.2178, "step": 41 }, { "epoch": 0.056958806577386, "grad_norm": 0.3980973958969116, "learning_rate": 6.698729810778065e-06, "loss": 1.1764, "step": 42 }, { "epoch": 0.05831496863875233, "grad_norm": 0.35641881823539734, "learning_rate": 5.156362923365588e-06, "loss": 1.1581, "step": 43 }, { "epoch": 0.05967113070011867, "grad_norm": 0.38389772176742554, "learning_rate": 3.8060233744356633e-06, "loss": 1.1908, "step": 44 }, { "epoch": 0.061027292761485, "grad_norm": 0.37814661860466003, "learning_rate": 2.653493525244721e-06, "loss": 1.178, "step": 45 }, { "epoch": 0.062383454822851334, "grad_norm": 0.37529122829437256, "learning_rate": 1.70370868554659e-06, "loss": 1.2016, "step": 46 }, { "epoch": 0.06373961688421767, "grad_norm": 0.37107303738594055, "learning_rate": 9.607359798384785e-07, "loss": 1.1675, "step": 47 }, { "epoch": 0.06509577894558399, "grad_norm": 0.374933123588562, "learning_rate": 4.277569313094809e-07, "loss": 1.1817, "step": 48 }, { "epoch": 0.06645194100695033, "grad_norm": 0.4079557955265045, "learning_rate": 1.0705383806982606e-07, "loss": 1.1845, "step": 49 }, { "epoch": 0.06780810306831667, "grad_norm": 0.4347075819969177, "learning_rate": 0.0, "loss": 1.2665, "step": 50 }, { "epoch": 0.06780810306831667, "eval_loss": 1.1890357732772827, "eval_runtime": 82.6203, "eval_samples_per_second": 60.13, "eval_steps_per_second": 7.516, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.62480894509056e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }