{ "best_metric": 0.3099195957183838, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.06986899563318777, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0013973799126637554, "grad_norm": 7.820697784423828, "learning_rate": 5e-05, "loss": 3.1805, "step": 1 }, { "epoch": 0.0013973799126637554, "eval_loss": 4.933597087860107, "eval_runtime": 375.1559, "eval_samples_per_second": 12.851, "eval_steps_per_second": 1.607, "step": 1 }, { "epoch": 0.0027947598253275107, "grad_norm": 9.600098609924316, "learning_rate": 0.0001, "loss": 3.7853, "step": 2 }, { "epoch": 0.004192139737991266, "grad_norm": 8.434110641479492, "learning_rate": 9.989294616193017e-05, "loss": 3.0426, "step": 3 }, { "epoch": 0.0055895196506550214, "grad_norm": 8.16626262664795, "learning_rate": 9.957224306869053e-05, "loss": 1.6923, "step": 4 }, { "epoch": 0.0069868995633187774, "grad_norm": 5.467092514038086, "learning_rate": 9.903926402016153e-05, "loss": 0.9109, "step": 5 }, { "epoch": 0.008384279475982533, "grad_norm": 2.6859490871429443, "learning_rate": 9.829629131445342e-05, "loss": 0.4587, "step": 6 }, { "epoch": 0.009781659388646289, "grad_norm": 1.7486851215362549, "learning_rate": 9.73465064747553e-05, "loss": 0.4249, "step": 7 }, { "epoch": 0.011179039301310043, "grad_norm": 2.7364816665649414, "learning_rate": 9.619397662556435e-05, "loss": 0.4906, "step": 8 }, { "epoch": 0.012576419213973799, "grad_norm": 1.3542873859405518, "learning_rate": 9.484363707663442e-05, "loss": 0.3368, "step": 9 }, { "epoch": 0.013973799126637555, "grad_norm": 1.4736709594726562, "learning_rate": 9.330127018922194e-05, "loss": 0.3635, "step": 10 }, { "epoch": 0.015371179039301311, "grad_norm": 1.2249358892440796, "learning_rate": 9.157348061512727e-05, "loss": 0.4126, "step": 11 }, { "epoch": 0.016768558951965065, "grad_norm": 1.3233370780944824, "learning_rate": 8.966766701456177e-05, "loss": 0.5093, "step": 12 }, { "epoch": 0.01816593886462882, "grad_norm": 1.3505288362503052, "learning_rate": 8.759199037394887e-05, "loss": 0.4471, "step": 13 }, { "epoch": 0.019563318777292577, "grad_norm": 1.5364714860916138, "learning_rate": 8.535533905932738e-05, "loss": 0.3427, "step": 14 }, { "epoch": 0.02096069868995633, "grad_norm": 1.421094536781311, "learning_rate": 8.296729075500344e-05, "loss": 0.3317, "step": 15 }, { "epoch": 0.022358078602620086, "grad_norm": 0.996880292892456, "learning_rate": 8.043807145043604e-05, "loss": 0.3136, "step": 16 }, { "epoch": 0.023755458515283844, "grad_norm": 0.9842157363891602, "learning_rate": 7.777851165098012e-05, "loss": 0.3173, "step": 17 }, { "epoch": 0.025152838427947598, "grad_norm": 0.9777435064315796, "learning_rate": 7.500000000000001e-05, "loss": 0.2663, "step": 18 }, { "epoch": 0.026550218340611352, "grad_norm": 0.8460299372673035, "learning_rate": 7.211443451095007e-05, "loss": 0.3064, "step": 19 }, { "epoch": 0.02794759825327511, "grad_norm": 1.1061911582946777, "learning_rate": 6.91341716182545e-05, "loss": 0.4295, "step": 20 }, { "epoch": 0.029344978165938864, "grad_norm": 0.8015987277030945, "learning_rate": 6.607197326515808e-05, "loss": 0.2112, "step": 21 }, { "epoch": 0.030742358078602622, "grad_norm": 0.916122317314148, "learning_rate": 6.294095225512603e-05, "loss": 0.3314, "step": 22 }, { "epoch": 0.032139737991266376, "grad_norm": 1.1163928508758545, "learning_rate": 5.9754516100806423e-05, "loss": 0.3573, "step": 23 }, { "epoch": 0.03353711790393013, "grad_norm": 1.1232202053070068, "learning_rate": 5.6526309611002594e-05, "loss": 0.3437, "step": 24 }, { "epoch": 0.034934497816593885, "grad_norm": 1.200721263885498, "learning_rate": 5.327015646150716e-05, "loss": 0.4829, "step": 25 }, { "epoch": 0.034934497816593885, "eval_loss": 0.32214125990867615, "eval_runtime": 374.0514, "eval_samples_per_second": 12.889, "eval_steps_per_second": 1.612, "step": 25 }, { "epoch": 0.03633187772925764, "grad_norm": 0.9103572368621826, "learning_rate": 5e-05, "loss": 0.2798, "step": 26 }, { "epoch": 0.0377292576419214, "grad_norm": 1.0263386964797974, "learning_rate": 4.6729843538492847e-05, "loss": 0.361, "step": 27 }, { "epoch": 0.039126637554585154, "grad_norm": 0.8997160792350769, "learning_rate": 4.347369038899744e-05, "loss": 0.3359, "step": 28 }, { "epoch": 0.04052401746724891, "grad_norm": 0.7481948137283325, "learning_rate": 4.0245483899193595e-05, "loss": 0.3187, "step": 29 }, { "epoch": 0.04192139737991266, "grad_norm": 0.873487114906311, "learning_rate": 3.705904774487396e-05, "loss": 0.2788, "step": 30 }, { "epoch": 0.04331877729257642, "grad_norm": 1.0412384271621704, "learning_rate": 3.392802673484193e-05, "loss": 0.3317, "step": 31 }, { "epoch": 0.04471615720524017, "grad_norm": 0.9272012710571289, "learning_rate": 3.086582838174551e-05, "loss": 0.2985, "step": 32 }, { "epoch": 0.04611353711790393, "grad_norm": 1.0352059602737427, "learning_rate": 2.7885565489049946e-05, "loss": 0.3057, "step": 33 }, { "epoch": 0.04751091703056769, "grad_norm": 1.1511657238006592, "learning_rate": 2.500000000000001e-05, "loss": 0.274, "step": 34 }, { "epoch": 0.04890829694323144, "grad_norm": 0.9687528610229492, "learning_rate": 2.2221488349019903e-05, "loss": 0.2793, "step": 35 }, { "epoch": 0.050305676855895196, "grad_norm": 1.0364540815353394, "learning_rate": 1.9561928549563968e-05, "loss": 0.3161, "step": 36 }, { "epoch": 0.05170305676855895, "grad_norm": 1.1564514636993408, "learning_rate": 1.703270924499656e-05, "loss": 0.4427, "step": 37 }, { "epoch": 0.053100436681222704, "grad_norm": 1.0043615102767944, "learning_rate": 1.4644660940672627e-05, "loss": 0.4424, "step": 38 }, { "epoch": 0.054497816593886465, "grad_norm": 0.9488585591316223, "learning_rate": 1.2408009626051137e-05, "loss": 0.2808, "step": 39 }, { "epoch": 0.05589519650655022, "grad_norm": 0.8899033069610596, "learning_rate": 1.0332332985438248e-05, "loss": 0.2916, "step": 40 }, { "epoch": 0.057292576419213974, "grad_norm": 1.040342926979065, "learning_rate": 8.426519384872733e-06, "loss": 0.3335, "step": 41 }, { "epoch": 0.05868995633187773, "grad_norm": 1.0307811498641968, "learning_rate": 6.698729810778065e-06, "loss": 0.2772, "step": 42 }, { "epoch": 0.06008733624454148, "grad_norm": 1.0109599828720093, "learning_rate": 5.156362923365588e-06, "loss": 0.3653, "step": 43 }, { "epoch": 0.061484716157205244, "grad_norm": 0.6494663953781128, "learning_rate": 3.8060233744356633e-06, "loss": 0.1998, "step": 44 }, { "epoch": 0.062882096069869, "grad_norm": 0.838367760181427, "learning_rate": 2.653493525244721e-06, "loss": 0.2945, "step": 45 }, { "epoch": 0.06427947598253275, "grad_norm": 0.8463190197944641, "learning_rate": 1.70370868554659e-06, "loss": 0.3269, "step": 46 }, { "epoch": 0.0656768558951965, "grad_norm": 0.968761146068573, "learning_rate": 9.607359798384785e-07, "loss": 0.2588, "step": 47 }, { "epoch": 0.06707423580786026, "grad_norm": 0.9924123883247375, "learning_rate": 4.277569313094809e-07, "loss": 0.3954, "step": 48 }, { "epoch": 0.06847161572052402, "grad_norm": 1.1434500217437744, "learning_rate": 1.0705383806982606e-07, "loss": 0.3334, "step": 49 }, { "epoch": 0.06986899563318777, "grad_norm": 1.3751486539840698, "learning_rate": 0.0, "loss": 0.4089, "step": 50 }, { "epoch": 0.06986899563318777, "eval_loss": 0.3099195957183838, "eval_runtime": 372.952, "eval_samples_per_second": 12.927, "eval_steps_per_second": 1.617, "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": 6.631381723512832e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }