{ "best_metric": 0.913843035697937, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.0445335114673792, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0008906702293475841, "grad_norm": 2.870659351348877, "learning_rate": 5e-05, "loss": 4.8853, "step": 1 }, { "epoch": 0.0008906702293475841, "eval_loss": 5.536528587341309, "eval_runtime": 683.5493, "eval_samples_per_second": 22.132, "eval_steps_per_second": 1.384, "step": 1 }, { "epoch": 0.0017813404586951682, "grad_norm": 2.751068353652954, "learning_rate": 0.0001, "loss": 4.6889, "step": 2 }, { "epoch": 0.0026720106880427524, "grad_norm": 3.1351728439331055, "learning_rate": 9.989294616193017e-05, "loss": 5.0974, "step": 3 }, { "epoch": 0.0035626809173903364, "grad_norm": 3.4856443405151367, "learning_rate": 9.957224306869053e-05, "loss": 4.8272, "step": 4 }, { "epoch": 0.00445335114673792, "grad_norm": 3.695927143096924, "learning_rate": 9.903926402016153e-05, "loss": 4.1781, "step": 5 }, { "epoch": 0.005344021376085505, "grad_norm": 4.327292442321777, "learning_rate": 9.829629131445342e-05, "loss": 3.7587, "step": 6 }, { "epoch": 0.006234691605433089, "grad_norm": 4.269476413726807, "learning_rate": 9.73465064747553e-05, "loss": 3.1728, "step": 7 }, { "epoch": 0.007125361834780673, "grad_norm": 3.913806915283203, "learning_rate": 9.619397662556435e-05, "loss": 2.9581, "step": 8 }, { "epoch": 0.008016032064128256, "grad_norm": 3.744333505630493, "learning_rate": 9.484363707663442e-05, "loss": 2.4833, "step": 9 }, { "epoch": 0.00890670229347584, "grad_norm": 2.7655162811279297, "learning_rate": 9.330127018922194e-05, "loss": 2.2542, "step": 10 }, { "epoch": 0.009797372522823424, "grad_norm": 2.441098928451538, "learning_rate": 9.157348061512727e-05, "loss": 2.0602, "step": 11 }, { "epoch": 0.01068804275217101, "grad_norm": 2.0439741611480713, "learning_rate": 8.966766701456177e-05, "loss": 1.8792, "step": 12 }, { "epoch": 0.011578712981518594, "grad_norm": 2.3753600120544434, "learning_rate": 8.759199037394887e-05, "loss": 1.9429, "step": 13 }, { "epoch": 0.012469383210866177, "grad_norm": 2.663454532623291, "learning_rate": 8.535533905932738e-05, "loss": 1.7253, "step": 14 }, { "epoch": 0.013360053440213761, "grad_norm": 1.836509346961975, "learning_rate": 8.296729075500344e-05, "loss": 1.4754, "step": 15 }, { "epoch": 0.014250723669561345, "grad_norm": 1.9437190294265747, "learning_rate": 8.043807145043604e-05, "loss": 1.2775, "step": 16 }, { "epoch": 0.01514139389890893, "grad_norm": 1.7349357604980469, "learning_rate": 7.777851165098012e-05, "loss": 1.0976, "step": 17 }, { "epoch": 0.01603206412825651, "grad_norm": 1.7044882774353027, "learning_rate": 7.500000000000001e-05, "loss": 1.2912, "step": 18 }, { "epoch": 0.016922734357604097, "grad_norm": 1.5817137956619263, "learning_rate": 7.211443451095007e-05, "loss": 1.0439, "step": 19 }, { "epoch": 0.01781340458695168, "grad_norm": 1.3615355491638184, "learning_rate": 6.91341716182545e-05, "loss": 1.0764, "step": 20 }, { "epoch": 0.018704074816299265, "grad_norm": 1.6596283912658691, "learning_rate": 6.607197326515808e-05, "loss": 1.1359, "step": 21 }, { "epoch": 0.019594745045646848, "grad_norm": 1.5128414630889893, "learning_rate": 6.294095225512603e-05, "loss": 1.0777, "step": 22 }, { "epoch": 0.020485415274994433, "grad_norm": 1.5737196207046509, "learning_rate": 5.9754516100806423e-05, "loss": 1.1119, "step": 23 }, { "epoch": 0.02137608550434202, "grad_norm": 1.522108554840088, "learning_rate": 5.6526309611002594e-05, "loss": 1.0674, "step": 24 }, { "epoch": 0.0222667557336896, "grad_norm": 2.2869157791137695, "learning_rate": 5.327015646150716e-05, "loss": 1.1544, "step": 25 }, { "epoch": 0.0222667557336896, "eval_loss": 1.0574125051498413, "eval_runtime": 684.925, "eval_samples_per_second": 22.087, "eval_steps_per_second": 1.381, "step": 25 }, { "epoch": 0.023157425963037187, "grad_norm": 1.4434211254119873, "learning_rate": 5e-05, "loss": 1.1979, "step": 26 }, { "epoch": 0.02404809619238477, "grad_norm": 1.282379150390625, "learning_rate": 4.6729843538492847e-05, "loss": 1.1556, "step": 27 }, { "epoch": 0.024938766421732355, "grad_norm": 1.0546919107437134, "learning_rate": 4.347369038899744e-05, "loss": 0.9802, "step": 28 }, { "epoch": 0.025829436651079937, "grad_norm": 1.0919930934906006, "learning_rate": 4.0245483899193595e-05, "loss": 0.9473, "step": 29 }, { "epoch": 0.026720106880427523, "grad_norm": 1.013401985168457, "learning_rate": 3.705904774487396e-05, "loss": 0.9457, "step": 30 }, { "epoch": 0.027610777109775105, "grad_norm": 1.3264373540878296, "learning_rate": 3.392802673484193e-05, "loss": 0.9195, "step": 31 }, { "epoch": 0.02850144733912269, "grad_norm": 1.186482548713684, "learning_rate": 3.086582838174551e-05, "loss": 0.8382, "step": 32 }, { "epoch": 0.029392117568470273, "grad_norm": 1.2447603940963745, "learning_rate": 2.7885565489049946e-05, "loss": 0.7952, "step": 33 }, { "epoch": 0.03028278779781786, "grad_norm": 1.3419549465179443, "learning_rate": 2.500000000000001e-05, "loss": 0.8876, "step": 34 }, { "epoch": 0.03117345802716544, "grad_norm": 1.4486920833587646, "learning_rate": 2.2221488349019903e-05, "loss": 0.928, "step": 35 }, { "epoch": 0.03206412825651302, "grad_norm": 1.4917124509811401, "learning_rate": 1.9561928549563968e-05, "loss": 0.9708, "step": 36 }, { "epoch": 0.03295479848586061, "grad_norm": 1.4312398433685303, "learning_rate": 1.703270924499656e-05, "loss": 0.9126, "step": 37 }, { "epoch": 0.033845468715208195, "grad_norm": 1.4668188095092773, "learning_rate": 1.4644660940672627e-05, "loss": 1.0575, "step": 38 }, { "epoch": 0.03473613894455578, "grad_norm": 1.0228489637374878, "learning_rate": 1.2408009626051137e-05, "loss": 1.1165, "step": 39 }, { "epoch": 0.03562680917390336, "grad_norm": 1.1922171115875244, "learning_rate": 1.0332332985438248e-05, "loss": 0.876, "step": 40 }, { "epoch": 0.036517479403250945, "grad_norm": 1.4448883533477783, "learning_rate": 8.426519384872733e-06, "loss": 0.8162, "step": 41 }, { "epoch": 0.03740814963259853, "grad_norm": 1.309898853302002, "learning_rate": 6.698729810778065e-06, "loss": 0.8612, "step": 42 }, { "epoch": 0.038298819861946116, "grad_norm": 1.1799569129943848, "learning_rate": 5.156362923365588e-06, "loss": 0.7556, "step": 43 }, { "epoch": 0.039189490091293695, "grad_norm": 1.1924082040786743, "learning_rate": 3.8060233744356633e-06, "loss": 0.7998, "step": 44 }, { "epoch": 0.04008016032064128, "grad_norm": 1.1871657371520996, "learning_rate": 2.653493525244721e-06, "loss": 0.7922, "step": 45 }, { "epoch": 0.04097083054998887, "grad_norm": 1.3861472606658936, "learning_rate": 1.70370868554659e-06, "loss": 0.8351, "step": 46 }, { "epoch": 0.04186150077933645, "grad_norm": 1.3767911195755005, "learning_rate": 9.607359798384785e-07, "loss": 0.8327, "step": 47 }, { "epoch": 0.04275217100868404, "grad_norm": 1.8437672853469849, "learning_rate": 4.277569313094809e-07, "loss": 0.9629, "step": 48 }, { "epoch": 0.04364284123803162, "grad_norm": 1.6834858655929565, "learning_rate": 1.0705383806982606e-07, "loss": 1.0285, "step": 49 }, { "epoch": 0.0445335114673792, "grad_norm": 1.8425227403640747, "learning_rate": 0.0, "loss": 0.9625, "step": 50 }, { "epoch": 0.0445335114673792, "eval_loss": 0.913843035697937, "eval_runtime": 685.0025, "eval_samples_per_second": 22.085, "eval_steps_per_second": 1.381, "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": 2.0456723072417792e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }