{ "best_metric": 0.1470915526151657, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.011516756881262236, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00023033513762524472, "grad_norm": 6.441722869873047, "learning_rate": 5e-05, "loss": 10.7989, "step": 1 }, { "epoch": 0.00023033513762524472, "eval_loss": 10.981081008911133, "eval_runtime": 741.395, "eval_samples_per_second": 39.45, "eval_steps_per_second": 4.931, "step": 1 }, { "epoch": 0.00046067027525048944, "grad_norm": 6.788846969604492, "learning_rate": 0.0001, "loss": 10.5669, "step": 2 }, { "epoch": 0.0006910054128757342, "grad_norm": 7.299288749694824, "learning_rate": 9.989294616193017e-05, "loss": 10.379, "step": 3 }, { "epoch": 0.0009213405505009789, "grad_norm": 8.674383163452148, "learning_rate": 9.957224306869053e-05, "loss": 8.2603, "step": 4 }, { "epoch": 0.0011516756881262238, "grad_norm": 5.056308269500732, "learning_rate": 9.903926402016153e-05, "loss": 6.6139, "step": 5 }, { "epoch": 0.0013820108257514684, "grad_norm": 5.52695369720459, "learning_rate": 9.829629131445342e-05, "loss": 5.7284, "step": 6 }, { "epoch": 0.001612345963376713, "grad_norm": 7.320567607879639, "learning_rate": 9.73465064747553e-05, "loss": 4.8653, "step": 7 }, { "epoch": 0.0018426811010019578, "grad_norm": 8.6433744430542, "learning_rate": 9.619397662556435e-05, "loss": 3.7052, "step": 8 }, { "epoch": 0.0020730162386272026, "grad_norm": 7.532520294189453, "learning_rate": 9.484363707663442e-05, "loss": 2.6623, "step": 9 }, { "epoch": 0.0023033513762524475, "grad_norm": 5.737761497497559, "learning_rate": 9.330127018922194e-05, "loss": 1.8973, "step": 10 }, { "epoch": 0.002533686513877692, "grad_norm": 4.132571220397949, "learning_rate": 9.157348061512727e-05, "loss": 1.015, "step": 11 }, { "epoch": 0.002764021651502937, "grad_norm": 6.932968616485596, "learning_rate": 8.966766701456177e-05, "loss": 1.2044, "step": 12 }, { "epoch": 0.0029943567891281813, "grad_norm": 3.8923416137695312, "learning_rate": 8.759199037394887e-05, "loss": 0.9463, "step": 13 }, { "epoch": 0.003224691926753426, "grad_norm": 4.9294328689575195, "learning_rate": 8.535533905932738e-05, "loss": 0.4456, "step": 14 }, { "epoch": 0.003455027064378671, "grad_norm": 2.0760934352874756, "learning_rate": 8.296729075500344e-05, "loss": 0.2602, "step": 15 }, { "epoch": 0.0036853622020039155, "grad_norm": 2.9317197799682617, "learning_rate": 8.043807145043604e-05, "loss": 0.193, "step": 16 }, { "epoch": 0.003915697339629161, "grad_norm": 0.7616105079650879, "learning_rate": 7.777851165098012e-05, "loss": 0.1803, "step": 17 }, { "epoch": 0.004146032477254405, "grad_norm": 1.914324164390564, "learning_rate": 7.500000000000001e-05, "loss": 0.2119, "step": 18 }, { "epoch": 0.00437636761487965, "grad_norm": 0.567974865436554, "learning_rate": 7.211443451095007e-05, "loss": 0.1551, "step": 19 }, { "epoch": 0.004606702752504895, "grad_norm": 2.842289447784424, "learning_rate": 6.91341716182545e-05, "loss": 0.2003, "step": 20 }, { "epoch": 0.0048370378901301395, "grad_norm": 0.9154838919639587, "learning_rate": 6.607197326515808e-05, "loss": 0.1792, "step": 21 }, { "epoch": 0.005067373027755384, "grad_norm": 1.3151744604110718, "learning_rate": 6.294095225512603e-05, "loss": 0.1525, "step": 22 }, { "epoch": 0.005297708165380628, "grad_norm": 0.6900270581245422, "learning_rate": 5.9754516100806423e-05, "loss": 0.1775, "step": 23 }, { "epoch": 0.005528043303005874, "grad_norm": 2.370558977127075, "learning_rate": 5.6526309611002594e-05, "loss": 0.2278, "step": 24 }, { "epoch": 0.005758378440631118, "grad_norm": 2.0755105018615723, "learning_rate": 5.327015646150716e-05, "loss": 0.1925, "step": 25 }, { "epoch": 0.005758378440631118, "eval_loss": 0.1751675307750702, "eval_runtime": 743.5196, "eval_samples_per_second": 39.337, "eval_steps_per_second": 4.917, "step": 25 }, { "epoch": 0.005988713578256363, "grad_norm": 2.5409257411956787, "learning_rate": 5e-05, "loss": 0.1806, "step": 26 }, { "epoch": 0.006219048715881608, "grad_norm": 2.210583209991455, "learning_rate": 4.6729843538492847e-05, "loss": 0.1523, "step": 27 }, { "epoch": 0.006449383853506852, "grad_norm": 1.9195382595062256, "learning_rate": 4.347369038899744e-05, "loss": 0.1316, "step": 28 }, { "epoch": 0.006679718991132097, "grad_norm": 0.559723973274231, "learning_rate": 4.0245483899193595e-05, "loss": 0.1446, "step": 29 }, { "epoch": 0.006910054128757342, "grad_norm": 1.172306776046753, "learning_rate": 3.705904774487396e-05, "loss": 0.1375, "step": 30 }, { "epoch": 0.007140389266382587, "grad_norm": 1.8723504543304443, "learning_rate": 3.392802673484193e-05, "loss": 0.15, "step": 31 }, { "epoch": 0.007370724404007831, "grad_norm": 1.3572112321853638, "learning_rate": 3.086582838174551e-05, "loss": 0.1517, "step": 32 }, { "epoch": 0.007601059541633076, "grad_norm": 2.47939133644104, "learning_rate": 2.7885565489049946e-05, "loss": 0.1438, "step": 33 }, { "epoch": 0.007831394679258322, "grad_norm": 0.7293671369552612, "learning_rate": 2.500000000000001e-05, "loss": 0.1507, "step": 34 }, { "epoch": 0.008061729816883566, "grad_norm": 0.6658552289009094, "learning_rate": 2.2221488349019903e-05, "loss": 0.1605, "step": 35 }, { "epoch": 0.00829206495450881, "grad_norm": 1.1873992681503296, "learning_rate": 1.9561928549563968e-05, "loss": 0.1671, "step": 36 }, { "epoch": 0.008522400092134055, "grad_norm": 0.4208405613899231, "learning_rate": 1.703270924499656e-05, "loss": 0.1378, "step": 37 }, { "epoch": 0.0087527352297593, "grad_norm": 1.3051728010177612, "learning_rate": 1.4644660940672627e-05, "loss": 0.1977, "step": 38 }, { "epoch": 0.008983070367384544, "grad_norm": 1.1391668319702148, "learning_rate": 1.2408009626051137e-05, "loss": 0.1189, "step": 39 }, { "epoch": 0.00921340550500979, "grad_norm": 1.6376707553863525, "learning_rate": 1.0332332985438248e-05, "loss": 0.129, "step": 40 }, { "epoch": 0.009443740642635035, "grad_norm": 1.3044697046279907, "learning_rate": 8.426519384872733e-06, "loss": 0.1299, "step": 41 }, { "epoch": 0.009674075780260279, "grad_norm": 0.4298762083053589, "learning_rate": 6.698729810778065e-06, "loss": 0.1216, "step": 42 }, { "epoch": 0.009904410917885523, "grad_norm": 0.23566682636737823, "learning_rate": 5.156362923365588e-06, "loss": 0.1304, "step": 43 }, { "epoch": 0.010134746055510768, "grad_norm": 0.6235781908035278, "learning_rate": 3.8060233744356633e-06, "loss": 0.1465, "step": 44 }, { "epoch": 0.010365081193136012, "grad_norm": 1.3741854429244995, "learning_rate": 2.653493525244721e-06, "loss": 0.1644, "step": 45 }, { "epoch": 0.010595416330761257, "grad_norm": 0.7963533401489258, "learning_rate": 1.70370868554659e-06, "loss": 0.1392, "step": 46 }, { "epoch": 0.010825751468386503, "grad_norm": 1.312923550605774, "learning_rate": 9.607359798384785e-07, "loss": 0.1589, "step": 47 }, { "epoch": 0.011056086606011747, "grad_norm": 1.262929081916809, "learning_rate": 4.277569313094809e-07, "loss": 0.1641, "step": 48 }, { "epoch": 0.011286421743636992, "grad_norm": 3.1545238494873047, "learning_rate": 1.0705383806982606e-07, "loss": 0.2133, "step": 49 }, { "epoch": 0.011516756881262236, "grad_norm": 2.1335887908935547, "learning_rate": 0.0, "loss": 0.1899, "step": 50 }, { "epoch": 0.011516756881262236, "eval_loss": 0.1470915526151657, "eval_runtime": 742.2522, "eval_samples_per_second": 39.404, "eval_steps_per_second": 4.926, "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": 5.629330376926167e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }