{ "best_metric": 1.6436538696289062, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.1027221366204417, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.002054442732408834, "grad_norm": 72.63911437988281, "learning_rate": 5e-05, "loss": 38.3589, "step": 1 }, { "epoch": 0.002054442732408834, "eval_loss": 3.0806236267089844, "eval_runtime": 215.2339, "eval_samples_per_second": 15.239, "eval_steps_per_second": 1.905, "step": 1 }, { "epoch": 0.004108885464817668, "grad_norm": 84.75655364990234, "learning_rate": 0.0001, "loss": 41.3745, "step": 2 }, { "epoch": 0.0061633281972265025, "grad_norm": 63.62594223022461, "learning_rate": 9.989294616193017e-05, "loss": 38.5362, "step": 3 }, { "epoch": 0.008217770929635337, "grad_norm": 148.93727111816406, "learning_rate": 9.957224306869053e-05, "loss": 37.302, "step": 4 }, { "epoch": 0.01027221366204417, "grad_norm": 73.28170013427734, "learning_rate": 9.903926402016153e-05, "loss": 34.3173, "step": 5 }, { "epoch": 0.012326656394453005, "grad_norm": 87.36775207519531, "learning_rate": 9.829629131445342e-05, "loss": 34.3255, "step": 6 }, { "epoch": 0.014381099126861838, "grad_norm": 107.49162292480469, "learning_rate": 9.73465064747553e-05, "loss": 31.8931, "step": 7 }, { "epoch": 0.016435541859270673, "grad_norm": 56.272708892822266, "learning_rate": 9.619397662556435e-05, "loss": 31.9466, "step": 8 }, { "epoch": 0.01848998459167951, "grad_norm": 231.95889282226562, "learning_rate": 9.484363707663442e-05, "loss": 31.9671, "step": 9 }, { "epoch": 0.02054442732408834, "grad_norm": 53.92425537109375, "learning_rate": 9.330127018922194e-05, "loss": 29.5999, "step": 10 }, { "epoch": 0.022598870056497175, "grad_norm": 48.65695571899414, "learning_rate": 9.157348061512727e-05, "loss": 28.8132, "step": 11 }, { "epoch": 0.02465331278890601, "grad_norm": 48.8329963684082, "learning_rate": 8.966766701456177e-05, "loss": 29.6056, "step": 12 }, { "epoch": 0.02670775552131484, "grad_norm": 47.05804443359375, "learning_rate": 8.759199037394887e-05, "loss": 30.9364, "step": 13 }, { "epoch": 0.028762198253723677, "grad_norm": 90.31666564941406, "learning_rate": 8.535533905932738e-05, "loss": 30.1931, "step": 14 }, { "epoch": 0.030816640986132512, "grad_norm": 38.44446563720703, "learning_rate": 8.296729075500344e-05, "loss": 28.5989, "step": 15 }, { "epoch": 0.03287108371854135, "grad_norm": 35.618350982666016, "learning_rate": 8.043807145043604e-05, "loss": 28.4939, "step": 16 }, { "epoch": 0.03492552645095018, "grad_norm": 34.55806350708008, "learning_rate": 7.777851165098012e-05, "loss": 27.4811, "step": 17 }, { "epoch": 0.03697996918335902, "grad_norm": 228.94281005859375, "learning_rate": 7.500000000000001e-05, "loss": 28.0385, "step": 18 }, { "epoch": 0.03903441191576785, "grad_norm": 42.987892150878906, "learning_rate": 7.211443451095007e-05, "loss": 26.6212, "step": 19 }, { "epoch": 0.04108885464817668, "grad_norm": 40.11811828613281, "learning_rate": 6.91341716182545e-05, "loss": 27.7546, "step": 20 }, { "epoch": 0.04314329738058552, "grad_norm": 37.71592330932617, "learning_rate": 6.607197326515808e-05, "loss": 27.7426, "step": 21 }, { "epoch": 0.04519774011299435, "grad_norm": 36.94485092163086, "learning_rate": 6.294095225512603e-05, "loss": 27.2242, "step": 22 }, { "epoch": 0.04725218284540318, "grad_norm": 37.85831069946289, "learning_rate": 5.9754516100806423e-05, "loss": 28.0138, "step": 23 }, { "epoch": 0.04930662557781202, "grad_norm": 34.742069244384766, "learning_rate": 5.6526309611002594e-05, "loss": 25.5438, "step": 24 }, { "epoch": 0.05136106831022085, "grad_norm": 41.137718200683594, "learning_rate": 5.327015646150716e-05, "loss": 27.044, "step": 25 }, { "epoch": 0.05136106831022085, "eval_loss": 1.6952250003814697, "eval_runtime": 215.2445, "eval_samples_per_second": 15.238, "eval_steps_per_second": 1.905, "step": 25 }, { "epoch": 0.05341551104262968, "grad_norm": 44.00088882446289, "learning_rate": 5e-05, "loss": 27.7822, "step": 26 }, { "epoch": 0.05546995377503852, "grad_norm": 42.3242073059082, "learning_rate": 4.6729843538492847e-05, "loss": 27.3737, "step": 27 }, { "epoch": 0.05752439650744735, "grad_norm": 38.348670959472656, "learning_rate": 4.347369038899744e-05, "loss": 27.6254, "step": 28 }, { "epoch": 0.05957883923985619, "grad_norm": 37.97185516357422, "learning_rate": 4.0245483899193595e-05, "loss": 27.3671, "step": 29 }, { "epoch": 0.061633281972265024, "grad_norm": 37.6766471862793, "learning_rate": 3.705904774487396e-05, "loss": 27.7831, "step": 30 }, { "epoch": 0.06368772470467386, "grad_norm": 35.792240142822266, "learning_rate": 3.392802673484193e-05, "loss": 26.383, "step": 31 }, { "epoch": 0.0657421674370827, "grad_norm": 30.798736572265625, "learning_rate": 3.086582838174551e-05, "loss": 26.7846, "step": 32 }, { "epoch": 0.06779661016949153, "grad_norm": 34.46708679199219, "learning_rate": 2.7885565489049946e-05, "loss": 26.9403, "step": 33 }, { "epoch": 0.06985105290190036, "grad_norm": 32.722984313964844, "learning_rate": 2.500000000000001e-05, "loss": 25.5387, "step": 34 }, { "epoch": 0.07190549563430919, "grad_norm": 33.066802978515625, "learning_rate": 2.2221488349019903e-05, "loss": 27.3704, "step": 35 }, { "epoch": 0.07395993836671803, "grad_norm": 35.121376037597656, "learning_rate": 1.9561928549563968e-05, "loss": 26.1383, "step": 36 }, { "epoch": 0.07601438109912687, "grad_norm": 32.85065841674805, "learning_rate": 1.703270924499656e-05, "loss": 26.2707, "step": 37 }, { "epoch": 0.0780688238315357, "grad_norm": 34.69348907470703, "learning_rate": 1.4644660940672627e-05, "loss": 27.4932, "step": 38 }, { "epoch": 0.08012326656394453, "grad_norm": 36.420936584472656, "learning_rate": 1.2408009626051137e-05, "loss": 26.7692, "step": 39 }, { "epoch": 0.08217770929635336, "grad_norm": 34.44639587402344, "learning_rate": 1.0332332985438248e-05, "loss": 26.6481, "step": 40 }, { "epoch": 0.08423215202876219, "grad_norm": 30.01451301574707, "learning_rate": 8.426519384872733e-06, "loss": 25.7843, "step": 41 }, { "epoch": 0.08628659476117104, "grad_norm": 25.13599395751953, "learning_rate": 6.698729810778065e-06, "loss": 26.7225, "step": 42 }, { "epoch": 0.08834103749357987, "grad_norm": 26.27276039123535, "learning_rate": 5.156362923365588e-06, "loss": 25.5646, "step": 43 }, { "epoch": 0.0903954802259887, "grad_norm": 24.683252334594727, "learning_rate": 3.8060233744356633e-06, "loss": 25.5756, "step": 44 }, { "epoch": 0.09244992295839753, "grad_norm": 25.751869201660156, "learning_rate": 2.653493525244721e-06, "loss": 26.0279, "step": 45 }, { "epoch": 0.09450436569080636, "grad_norm": 30.72328758239746, "learning_rate": 1.70370868554659e-06, "loss": 24.7662, "step": 46 }, { "epoch": 0.09655880842321521, "grad_norm": 32.1501579284668, "learning_rate": 9.607359798384785e-07, "loss": 26.0407, "step": 47 }, { "epoch": 0.09861325115562404, "grad_norm": 37.73057174682617, "learning_rate": 4.277569313094809e-07, "loss": 25.4584, "step": 48 }, { "epoch": 0.10066769388803287, "grad_norm": 36.1685791015625, "learning_rate": 1.0705383806982606e-07, "loss": 25.6212, "step": 49 }, { "epoch": 0.1027221366204417, "grad_norm": 48.9822883605957, "learning_rate": 0.0, "loss": 28.0915, "step": 50 }, { "epoch": 0.1027221366204417, "eval_loss": 1.6436538696289062, "eval_runtime": 85.2925, "eval_samples_per_second": 38.456, "eval_steps_per_second": 4.807, "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": 5.658027780734976e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }