{ "best_metric": 11.816559791564941, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.1866977829638273, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0037339556592765463, "grad_norm": 2.9516172409057617, "learning_rate": 5e-05, "loss": 11.9501, "step": 1 }, { "epoch": 0.0037339556592765463, "eval_loss": 11.950103759765625, "eval_runtime": 7.7476, "eval_samples_per_second": 232.974, "eval_steps_per_second": 29.17, "step": 1 }, { "epoch": 0.007467911318553093, "grad_norm": 2.9323055744171143, "learning_rate": 0.0001, "loss": 11.9501, "step": 2 }, { "epoch": 0.011201866977829638, "grad_norm": 2.8429534435272217, "learning_rate": 9.989294616193017e-05, "loss": 11.9472, "step": 3 }, { "epoch": 0.014935822637106185, "grad_norm": 2.777496099472046, "learning_rate": 9.957224306869053e-05, "loss": 11.9418, "step": 4 }, { "epoch": 0.01866977829638273, "grad_norm": 2.6327879428863525, "learning_rate": 9.903926402016153e-05, "loss": 11.9365, "step": 5 }, { "epoch": 0.022403733955659276, "grad_norm": 2.4832563400268555, "learning_rate": 9.829629131445342e-05, "loss": 11.9315, "step": 6 }, { "epoch": 0.026137689614935823, "grad_norm": 2.4022910594940186, "learning_rate": 9.73465064747553e-05, "loss": 11.9269, "step": 7 }, { "epoch": 0.02987164527421237, "grad_norm": 2.381385087966919, "learning_rate": 9.619397662556435e-05, "loss": 11.9219, "step": 8 }, { "epoch": 0.03360560093348892, "grad_norm": 2.3741588592529297, "learning_rate": 9.484363707663442e-05, "loss": 11.917, "step": 9 }, { "epoch": 0.03733955659276546, "grad_norm": 2.390129327774048, "learning_rate": 9.330127018922194e-05, "loss": 11.9122, "step": 10 }, { "epoch": 0.041073512252042005, "grad_norm": 2.3822999000549316, "learning_rate": 9.157348061512727e-05, "loss": 11.9087, "step": 11 }, { "epoch": 0.04480746791131855, "grad_norm": 2.4623894691467285, "learning_rate": 8.966766701456177e-05, "loss": 11.9041, "step": 12 }, { "epoch": 0.0485414235705951, "grad_norm": 2.5058255195617676, "learning_rate": 8.759199037394887e-05, "loss": 11.9001, "step": 13 }, { "epoch": 0.052275379229871646, "grad_norm": 2.583550214767456, "learning_rate": 8.535533905932738e-05, "loss": 11.8957, "step": 14 }, { "epoch": 0.056009334889148193, "grad_norm": 2.6756393909454346, "learning_rate": 8.296729075500344e-05, "loss": 11.8907, "step": 15 }, { "epoch": 0.05974329054842474, "grad_norm": 2.6872572898864746, "learning_rate": 8.043807145043604e-05, "loss": 11.8871, "step": 16 }, { "epoch": 0.06347724620770129, "grad_norm": 2.787407159805298, "learning_rate": 7.777851165098012e-05, "loss": 11.8825, "step": 17 }, { "epoch": 0.06721120186697783, "grad_norm": 2.8923518657684326, "learning_rate": 7.500000000000001e-05, "loss": 11.8771, "step": 18 }, { "epoch": 0.07094515752625438, "grad_norm": 2.9403088092803955, "learning_rate": 7.211443451095007e-05, "loss": 11.873, "step": 19 }, { "epoch": 0.07467911318553092, "grad_norm": 3.014322280883789, "learning_rate": 6.91341716182545e-05, "loss": 11.868, "step": 20 }, { "epoch": 0.07841306884480746, "grad_norm": 3.006171941757202, "learning_rate": 6.607197326515808e-05, "loss": 11.864, "step": 21 }, { "epoch": 0.08214702450408401, "grad_norm": 3.0072121620178223, "learning_rate": 6.294095225512603e-05, "loss": 11.8607, "step": 22 }, { "epoch": 0.08588098016336056, "grad_norm": 2.9735445976257324, "learning_rate": 5.9754516100806423e-05, "loss": 11.8577, "step": 23 }, { "epoch": 0.0896149358226371, "grad_norm": 2.999457359313965, "learning_rate": 5.6526309611002594e-05, "loss": 11.8527, "step": 24 }, { "epoch": 0.09334889148191365, "grad_norm": 2.999213695526123, "learning_rate": 5.327015646150716e-05, "loss": 11.8493, "step": 25 }, { "epoch": 0.09334889148191365, "eval_loss": 11.845855712890625, "eval_runtime": 7.7884, "eval_samples_per_second": 231.756, "eval_steps_per_second": 29.018, "step": 25 }, { "epoch": 0.0970828471411902, "grad_norm": 2.9534995555877686, "learning_rate": 5e-05, "loss": 11.8459, "step": 26 }, { "epoch": 0.10081680280046675, "grad_norm": 2.955491781234741, "learning_rate": 4.6729843538492847e-05, "loss": 11.8433, "step": 27 }, { "epoch": 0.10455075845974329, "grad_norm": 2.891913890838623, "learning_rate": 4.347369038899744e-05, "loss": 11.841, "step": 28 }, { "epoch": 0.10828471411901984, "grad_norm": 2.914942502975464, "learning_rate": 4.0245483899193595e-05, "loss": 11.8363, "step": 29 }, { "epoch": 0.11201866977829639, "grad_norm": 2.8910973072052, "learning_rate": 3.705904774487396e-05, "loss": 11.8331, "step": 30 }, { "epoch": 0.11575262543757293, "grad_norm": 2.835066318511963, "learning_rate": 3.392802673484193e-05, "loss": 11.8321, "step": 31 }, { "epoch": 0.11948658109684948, "grad_norm": 2.7818522453308105, "learning_rate": 3.086582838174551e-05, "loss": 11.8309, "step": 32 }, { "epoch": 0.12322053675612601, "grad_norm": 2.7701222896575928, "learning_rate": 2.7885565489049946e-05, "loss": 11.8288, "step": 33 }, { "epoch": 0.12695449241540258, "grad_norm": 2.7583718299865723, "learning_rate": 2.500000000000001e-05, "loss": 11.8265, "step": 34 }, { "epoch": 0.1306884480746791, "grad_norm": 2.7240748405456543, "learning_rate": 2.2221488349019903e-05, "loss": 11.8255, "step": 35 }, { "epoch": 0.13442240373395567, "grad_norm": 2.7345070838928223, "learning_rate": 1.9561928549563968e-05, "loss": 11.8233, "step": 36 }, { "epoch": 0.1381563593932322, "grad_norm": 2.70548152923584, "learning_rate": 1.703270924499656e-05, "loss": 11.823, "step": 37 }, { "epoch": 0.14189031505250876, "grad_norm": 2.6903340816497803, "learning_rate": 1.4644660940672627e-05, "loss": 11.8199, "step": 38 }, { "epoch": 0.1456242707117853, "grad_norm": 2.6467480659484863, "learning_rate": 1.2408009626051137e-05, "loss": 11.821, "step": 39 }, { "epoch": 0.14935822637106183, "grad_norm": 2.666109085083008, "learning_rate": 1.0332332985438248e-05, "loss": 11.8185, "step": 40 }, { "epoch": 0.1530921820303384, "grad_norm": 2.642460584640503, "learning_rate": 8.426519384872733e-06, "loss": 11.8179, "step": 41 }, { "epoch": 0.15682613768961493, "grad_norm": 2.6411454677581787, "learning_rate": 6.698729810778065e-06, "loss": 11.818, "step": 42 }, { "epoch": 0.16056009334889149, "grad_norm": 2.620548725128174, "learning_rate": 5.156362923365588e-06, "loss": 11.8159, "step": 43 }, { "epoch": 0.16429404900816802, "grad_norm": 2.590919017791748, "learning_rate": 3.8060233744356633e-06, "loss": 11.8172, "step": 44 }, { "epoch": 0.16802800466744458, "grad_norm": 2.6139168739318848, "learning_rate": 2.653493525244721e-06, "loss": 11.8185, "step": 45 }, { "epoch": 0.1717619603267211, "grad_norm": 2.604081153869629, "learning_rate": 1.70370868554659e-06, "loss": 11.8167, "step": 46 }, { "epoch": 0.17549591598599767, "grad_norm": 2.6263182163238525, "learning_rate": 9.607359798384785e-07, "loss": 11.8167, "step": 47 }, { "epoch": 0.1792298716452742, "grad_norm": 2.586052656173706, "learning_rate": 4.277569313094809e-07, "loss": 11.819, "step": 48 }, { "epoch": 0.18296382730455077, "grad_norm": 2.631632089614868, "learning_rate": 1.0705383806982606e-07, "loss": 11.8153, "step": 49 }, { "epoch": 0.1866977829638273, "grad_norm": 2.6062960624694824, "learning_rate": 0.0, "loss": 11.8145, "step": 50 }, { "epoch": 0.1866977829638273, "eval_loss": 11.816559791564941, "eval_runtime": 7.6632, "eval_samples_per_second": 235.54, "eval_steps_per_second": 29.491, "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": 1042494259200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }