{ "best_metric": 0.25369930267333984, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.06571921465538487, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0013143842931076974, "grad_norm": 371.1976318359375, "learning_rate": 5e-05, "loss": 10.6086, "step": 1 }, { "epoch": 0.0013143842931076974, "eval_loss": 10.13594913482666, "eval_runtime": 185.9656, "eval_samples_per_second": 27.564, "eval_steps_per_second": 3.447, "step": 1 }, { "epoch": 0.002628768586215395, "grad_norm": 331.77642822265625, "learning_rate": 0.0001, "loss": 10.1013, "step": 2 }, { "epoch": 0.003943152879323092, "grad_norm": 331.4448547363281, "learning_rate": 9.989294616193017e-05, "loss": 8.8893, "step": 3 }, { "epoch": 0.00525753717243079, "grad_norm": 265.9762268066406, "learning_rate": 9.957224306869053e-05, "loss": 4.6534, "step": 4 }, { "epoch": 0.006571921465538487, "grad_norm": 139.2206268310547, "learning_rate": 9.903926402016153e-05, "loss": 2.1205, "step": 5 }, { "epoch": 0.007886305758646184, "grad_norm": 118.2385482788086, "learning_rate": 9.829629131445342e-05, "loss": 1.0414, "step": 6 }, { "epoch": 0.009200690051753882, "grad_norm": 57.86403274536133, "learning_rate": 9.73465064747553e-05, "loss": 0.5641, "step": 7 }, { "epoch": 0.01051507434486158, "grad_norm": 37.358642578125, "learning_rate": 9.619397662556435e-05, "loss": 0.4053, "step": 8 }, { "epoch": 0.011829458637969276, "grad_norm": 16.414470672607422, "learning_rate": 9.484363707663442e-05, "loss": 0.3024, "step": 9 }, { "epoch": 0.013143842931076974, "grad_norm": 18.011436462402344, "learning_rate": 9.330127018922194e-05, "loss": 0.3606, "step": 10 }, { "epoch": 0.014458227224184671, "grad_norm": 16.299697875976562, "learning_rate": 9.157348061512727e-05, "loss": 0.3473, "step": 11 }, { "epoch": 0.015772611517292368, "grad_norm": 16.118730545043945, "learning_rate": 8.966766701456177e-05, "loss": 0.2959, "step": 12 }, { "epoch": 0.017086995810400067, "grad_norm": 13.439918518066406, "learning_rate": 8.759199037394887e-05, "loss": 0.2004, "step": 13 }, { "epoch": 0.018401380103507763, "grad_norm": 31.28091812133789, "learning_rate": 8.535533905932738e-05, "loss": 0.3077, "step": 14 }, { "epoch": 0.01971576439661546, "grad_norm": 32.543453216552734, "learning_rate": 8.296729075500344e-05, "loss": 0.3477, "step": 15 }, { "epoch": 0.02103014868972316, "grad_norm": 21.624889373779297, "learning_rate": 8.043807145043604e-05, "loss": 0.2785, "step": 16 }, { "epoch": 0.022344532982830855, "grad_norm": 15.556564331054688, "learning_rate": 7.777851165098012e-05, "loss": 0.2918, "step": 17 }, { "epoch": 0.02365891727593855, "grad_norm": 14.975417137145996, "learning_rate": 7.500000000000001e-05, "loss": 0.3198, "step": 18 }, { "epoch": 0.02497330156904625, "grad_norm": 13.913922309875488, "learning_rate": 7.211443451095007e-05, "loss": 0.2962, "step": 19 }, { "epoch": 0.026287685862153947, "grad_norm": 10.696459770202637, "learning_rate": 6.91341716182545e-05, "loss": 0.2768, "step": 20 }, { "epoch": 0.027602070155261643, "grad_norm": 26.95675277709961, "learning_rate": 6.607197326515808e-05, "loss": 0.3611, "step": 21 }, { "epoch": 0.028916454448369343, "grad_norm": 24.482088088989258, "learning_rate": 6.294095225512603e-05, "loss": 0.3461, "step": 22 }, { "epoch": 0.03023083874147704, "grad_norm": 13.456645011901855, "learning_rate": 5.9754516100806423e-05, "loss": 0.3032, "step": 23 }, { "epoch": 0.031545223034584735, "grad_norm": 13.197711944580078, "learning_rate": 5.6526309611002594e-05, "loss": 0.313, "step": 24 }, { "epoch": 0.032859607327692435, "grad_norm": 29.036270141601562, "learning_rate": 5.327015646150716e-05, "loss": 0.3102, "step": 25 }, { "epoch": 0.032859607327692435, "eval_loss": 0.2917022407054901, "eval_runtime": 186.7135, "eval_samples_per_second": 27.454, "eval_steps_per_second": 3.433, "step": 25 }, { "epoch": 0.034173991620800134, "grad_norm": 39.145835876464844, "learning_rate": 5e-05, "loss": 0.2671, "step": 26 }, { "epoch": 0.03548837591390783, "grad_norm": 13.07092571258545, "learning_rate": 4.6729843538492847e-05, "loss": 0.2708, "step": 27 }, { "epoch": 0.03680276020701553, "grad_norm": 13.324690818786621, "learning_rate": 4.347369038899744e-05, "loss": 0.2022, "step": 28 }, { "epoch": 0.038117144500123226, "grad_norm": 7.191089153289795, "learning_rate": 4.0245483899193595e-05, "loss": 0.1898, "step": 29 }, { "epoch": 0.03943152879323092, "grad_norm": 19.806900024414062, "learning_rate": 3.705904774487396e-05, "loss": 0.2829, "step": 30 }, { "epoch": 0.04074591308633862, "grad_norm": 36.52785873413086, "learning_rate": 3.392802673484193e-05, "loss": 0.4437, "step": 31 }, { "epoch": 0.04206029737944632, "grad_norm": 32.967159271240234, "learning_rate": 3.086582838174551e-05, "loss": 0.4069, "step": 32 }, { "epoch": 0.04337468167255401, "grad_norm": 28.414072036743164, "learning_rate": 2.7885565489049946e-05, "loss": 0.3775, "step": 33 }, { "epoch": 0.04468906596566171, "grad_norm": 23.762981414794922, "learning_rate": 2.500000000000001e-05, "loss": 0.3371, "step": 34 }, { "epoch": 0.04600345025876941, "grad_norm": 20.14028549194336, "learning_rate": 2.2221488349019903e-05, "loss": 0.3427, "step": 35 }, { "epoch": 0.0473178345518771, "grad_norm": 13.396416664123535, "learning_rate": 1.9561928549563968e-05, "loss": 0.3186, "step": 36 }, { "epoch": 0.0486322188449848, "grad_norm": 17.807111740112305, "learning_rate": 1.703270924499656e-05, "loss": 0.2514, "step": 37 }, { "epoch": 0.0499466031380925, "grad_norm": 26.70073890686035, "learning_rate": 1.4644660940672627e-05, "loss": 0.2482, "step": 38 }, { "epoch": 0.051260987431200195, "grad_norm": 27.880258560180664, "learning_rate": 1.2408009626051137e-05, "loss": 0.268, "step": 39 }, { "epoch": 0.052575371724307894, "grad_norm": 24.239660263061523, "learning_rate": 1.0332332985438248e-05, "loss": 0.2833, "step": 40 }, { "epoch": 0.053889756017415594, "grad_norm": 29.972881317138672, "learning_rate": 8.426519384872733e-06, "loss": 0.2505, "step": 41 }, { "epoch": 0.055204140310523286, "grad_norm": 20.25796127319336, "learning_rate": 6.698729810778065e-06, "loss": 0.2796, "step": 42 }, { "epoch": 0.056518524603630986, "grad_norm": 12.335623741149902, "learning_rate": 5.156362923365588e-06, "loss": 0.2809, "step": 43 }, { "epoch": 0.057832908896738686, "grad_norm": 16.632577896118164, "learning_rate": 3.8060233744356633e-06, "loss": 0.2659, "step": 44 }, { "epoch": 0.05914729318984638, "grad_norm": 12.694944381713867, "learning_rate": 2.653493525244721e-06, "loss": 0.2621, "step": 45 }, { "epoch": 0.06046167748295408, "grad_norm": 7.574565887451172, "learning_rate": 1.70370868554659e-06, "loss": 0.296, "step": 46 }, { "epoch": 0.06177606177606178, "grad_norm": 7.663303375244141, "learning_rate": 9.607359798384785e-07, "loss": 0.3015, "step": 47 }, { "epoch": 0.06309044606916947, "grad_norm": 7.7631049156188965, "learning_rate": 4.277569313094809e-07, "loss": 0.3052, "step": 48 }, { "epoch": 0.06440483036227718, "grad_norm": 8.332027435302734, "learning_rate": 1.0705383806982606e-07, "loss": 0.2844, "step": 49 }, { "epoch": 0.06571921465538487, "grad_norm": 6.904819965362549, "learning_rate": 0.0, "loss": 0.2775, "step": 50 }, { "epoch": 0.06571921465538487, "eval_loss": 0.25369930267333984, "eval_runtime": 186.8409, "eval_samples_per_second": 27.435, "eval_steps_per_second": 3.431, "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": 9.184639386124288e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }