{ "best_metric": 0.2769263684749603, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 0.047719884279280624, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0009543976855856124, "grad_norm": 7.5589470863342285, "learning_rate": 5e-05, "loss": 6.5105, "step": 1 }, { "epoch": 0.0009543976855856124, "eval_loss": 6.898464202880859, "eval_runtime": 4.3332, "eval_samples_per_second": 11.539, "eval_steps_per_second": 3.0, "step": 1 }, { "epoch": 0.0019087953711712249, "grad_norm": 7.104386806488037, "learning_rate": 0.0001, "loss": 6.1061, "step": 2 }, { "epoch": 0.0028631930567568375, "grad_norm": 8.571779251098633, "learning_rate": 9.990365154573717e-05, "loss": 5.9668, "step": 3 }, { "epoch": 0.0038175907423424497, "grad_norm": 7.244858741760254, "learning_rate": 9.961501876182148e-05, "loss": 4.2635, "step": 4 }, { "epoch": 0.004771988427928062, "grad_norm": 5.659046649932861, "learning_rate": 9.913533761814537e-05, "loss": 3.2179, "step": 5 }, { "epoch": 0.005726386113513675, "grad_norm": 6.285874366760254, "learning_rate": 9.846666218300807e-05, "loss": 2.3588, "step": 6 }, { "epoch": 0.006680783799099287, "grad_norm": 7.563727855682373, "learning_rate": 9.761185582727977e-05, "loss": 1.6817, "step": 7 }, { "epoch": 0.007635181484684899, "grad_norm": 5.233025074005127, "learning_rate": 9.657457896300791e-05, "loss": 0.8883, "step": 8 }, { "epoch": 0.008589579170270513, "grad_norm": 13.621255874633789, "learning_rate": 9.535927336897098e-05, "loss": 0.9481, "step": 9 }, { "epoch": 0.009543976855856125, "grad_norm": 14.01646900177002, "learning_rate": 9.397114317029975e-05, "loss": 1.0053, "step": 10 }, { "epoch": 0.010498374541441736, "grad_norm": 3.7569971084594727, "learning_rate": 9.241613255361455e-05, "loss": 0.7166, "step": 11 }, { "epoch": 0.01145277222702735, "grad_norm": 3.1396937370300293, "learning_rate": 9.070090031310558e-05, "loss": 0.6126, "step": 12 }, { "epoch": 0.012407169912612962, "grad_norm": 2.981506586074829, "learning_rate": 8.883279133655399e-05, "loss": 0.5468, "step": 13 }, { "epoch": 0.013361567598198574, "grad_norm": 1.8633419275283813, "learning_rate": 8.681980515339464e-05, "loss": 0.4321, "step": 14 }, { "epoch": 0.014315965283784187, "grad_norm": 2.2961695194244385, "learning_rate": 8.467056167950311e-05, "loss": 0.4756, "step": 15 }, { "epoch": 0.015270362969369799, "grad_norm": 1.7233766317367554, "learning_rate": 8.239426430539243e-05, "loss": 0.3876, "step": 16 }, { "epoch": 0.01622476065495541, "grad_norm": 1.6890201568603516, "learning_rate": 8.000066048588211e-05, "loss": 0.3096, "step": 17 }, { "epoch": 0.017179158340541026, "grad_norm": 1.5592209100723267, "learning_rate": 7.75e-05, "loss": 0.3154, "step": 18 }, { "epoch": 0.018133556026126638, "grad_norm": 1.330201268196106, "learning_rate": 7.490299105985507e-05, "loss": 0.3503, "step": 19 }, { "epoch": 0.01908795371171225, "grad_norm": 1.3003387451171875, "learning_rate": 7.222075445642904e-05, "loss": 0.2713, "step": 20 }, { "epoch": 0.02004235139729786, "grad_norm": 1.5680718421936035, "learning_rate": 6.946477593864228e-05, "loss": 0.3378, "step": 21 }, { "epoch": 0.020996749082883473, "grad_norm": 1.3272722959518433, "learning_rate": 6.664685702961344e-05, "loss": 0.2735, "step": 22 }, { "epoch": 0.021951146768469085, "grad_norm": 1.4800026416778564, "learning_rate": 6.377906449072578e-05, "loss": 0.3437, "step": 23 }, { "epoch": 0.0229055444540547, "grad_norm": 1.6576793193817139, "learning_rate": 6.087367864990233e-05, "loss": 0.356, "step": 24 }, { "epoch": 0.023859942139640312, "grad_norm": 1.294888973236084, "learning_rate": 5.794314081535644e-05, "loss": 0.2651, "step": 25 }, { "epoch": 0.023859942139640312, "eval_loss": 0.3292239308357239, "eval_runtime": 4.3786, "eval_samples_per_second": 11.419, "eval_steps_per_second": 2.969, "step": 25 }, { "epoch": 0.024814339825225924, "grad_norm": 1.6082409620285034, "learning_rate": 5.500000000000001e-05, "loss": 0.3021, "step": 26 }, { "epoch": 0.025768737510811535, "grad_norm": 1.1714216470718384, "learning_rate": 5.205685918464356e-05, "loss": 0.2882, "step": 27 }, { "epoch": 0.026723135196397147, "grad_norm": 1.1372226476669312, "learning_rate": 4.912632135009769e-05, "loss": 0.2209, "step": 28 }, { "epoch": 0.027677532881982762, "grad_norm": 0.9055098295211792, "learning_rate": 4.6220935509274235e-05, "loss": 0.1623, "step": 29 }, { "epoch": 0.028631930567568374, "grad_norm": 0.9483652710914612, "learning_rate": 4.3353142970386564e-05, "loss": 0.2163, "step": 30 }, { "epoch": 0.029586328253153986, "grad_norm": 1.1060841083526611, "learning_rate": 4.053522406135775e-05, "loss": 0.2112, "step": 31 }, { "epoch": 0.030540725938739598, "grad_norm": 1.0018855333328247, "learning_rate": 3.777924554357096e-05, "loss": 0.188, "step": 32 }, { "epoch": 0.03149512362432521, "grad_norm": 1.0843490362167358, "learning_rate": 3.509700894014496e-05, "loss": 0.2795, "step": 33 }, { "epoch": 0.03244952130991082, "grad_norm": 1.3921905755996704, "learning_rate": 3.250000000000001e-05, "loss": 0.2683, "step": 34 }, { "epoch": 0.03340391899549643, "grad_norm": 1.2948616743087769, "learning_rate": 2.9999339514117912e-05, "loss": 0.2528, "step": 35 }, { "epoch": 0.03435831668108205, "grad_norm": 1.504824161529541, "learning_rate": 2.760573569460757e-05, "loss": 0.2593, "step": 36 }, { "epoch": 0.035312714366667664, "grad_norm": 1.3747433423995972, "learning_rate": 2.53294383204969e-05, "loss": 0.3509, "step": 37 }, { "epoch": 0.036267112052253275, "grad_norm": 1.1321784257888794, "learning_rate": 2.3180194846605367e-05, "loss": 0.2478, "step": 38 }, { "epoch": 0.03722150973783889, "grad_norm": 0.8461317420005798, "learning_rate": 2.1167208663446025e-05, "loss": 0.1884, "step": 39 }, { "epoch": 0.0381759074234245, "grad_norm": 0.9209880232810974, "learning_rate": 1.9299099686894423e-05, "loss": 0.2451, "step": 40 }, { "epoch": 0.03913030510901011, "grad_norm": 1.097226619720459, "learning_rate": 1.758386744638546e-05, "loss": 0.1921, "step": 41 }, { "epoch": 0.04008470279459572, "grad_norm": 0.9732930660247803, "learning_rate": 1.602885682970026e-05, "loss": 0.231, "step": 42 }, { "epoch": 0.041039100480181334, "grad_norm": 0.8967514038085938, "learning_rate": 1.464072663102903e-05, "loss": 0.2743, "step": 43 }, { "epoch": 0.041993498165766946, "grad_norm": 1.1284832954406738, "learning_rate": 1.3425421036992098e-05, "loss": 0.2349, "step": 44 }, { "epoch": 0.04294789585135256, "grad_norm": 0.908921480178833, "learning_rate": 1.2388144172720251e-05, "loss": 0.1719, "step": 45 }, { "epoch": 0.04390229353693817, "grad_norm": 1.205191731452942, "learning_rate": 1.1533337816991932e-05, "loss": 0.2746, "step": 46 }, { "epoch": 0.04485669122252379, "grad_norm": 1.016750454902649, "learning_rate": 1.0864662381854632e-05, "loss": 0.2213, "step": 47 }, { "epoch": 0.0458110889081094, "grad_norm": 0.8877540826797485, "learning_rate": 1.0384981238178534e-05, "loss": 0.2197, "step": 48 }, { "epoch": 0.04676548659369501, "grad_norm": 1.3043239116668701, "learning_rate": 1.0096348454262845e-05, "loss": 0.3115, "step": 49 }, { "epoch": 0.047719884279280624, "grad_norm": 1.060339331626892, "learning_rate": 1e-05, "loss": 0.2079, "step": 50 }, { "epoch": 0.047719884279280624, "eval_loss": 0.2769263684749603, "eval_runtime": 4.3858, "eval_samples_per_second": 11.4, "eval_steps_per_second": 2.964, "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": 5.968083617316864e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }