| { | |
| "best_metric": 0.021467845886945724, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.011894142134998514, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00023788284269997027, | |
| "grad_norm": 17.393367767333984, | |
| "learning_rate": 5e-05, | |
| "loss": 5.2482, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023788284269997027, | |
| "eval_loss": 5.099360942840576, | |
| "eval_runtime": 694.2171, | |
| "eval_samples_per_second": 40.794, | |
| "eval_steps_per_second": 5.099, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00047576568539994053, | |
| "grad_norm": 17.811248779296875, | |
| "learning_rate": 0.0001, | |
| "loss": 5.0626, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007136485280999108, | |
| "grad_norm": 13.558974266052246, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.3489, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009515313707998811, | |
| "grad_norm": 9.048644065856934, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.0027, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011894142134998512, | |
| "grad_norm": 10.191452026367188, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.2289, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014272970561998216, | |
| "grad_norm": 14.056161880493164, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.37, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016651798988997918, | |
| "grad_norm": 7.206189155578613, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8693, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019030627415997621, | |
| "grad_norm": 7.198247909545898, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4755, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0021409455842997323, | |
| "grad_norm": 3.900367021560669, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1787, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0023788284269997025, | |
| "grad_norm": 15.934491157531738, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.3333, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002616711269699673, | |
| "grad_norm": 10.015689849853516, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1937, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.002854594112399643, | |
| "grad_norm": 2.416588544845581, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0905, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0030924769550996134, | |
| "grad_norm": 5.22405481338501, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.1421, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0033303597977995835, | |
| "grad_norm": 1.8864647150039673, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0978, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003568242640499554, | |
| "grad_norm": 0.7159560918807983, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0038061254831995243, | |
| "grad_norm": 1.7144348621368408, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0572, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004044008325899495, | |
| "grad_norm": 5.09656286239624, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0567, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004281891168599465, | |
| "grad_norm": 1.1702532768249512, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0397, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004519774011299435, | |
| "grad_norm": 0.7027019262313843, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0109, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004757656853999405, | |
| "grad_norm": 0.7570264935493469, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.022, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0049955396966993755, | |
| "grad_norm": 1.3122613430023193, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0611, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005233422539399346, | |
| "grad_norm": 0.8826402425765991, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0384, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005471305382099316, | |
| "grad_norm": 5.429707050323486, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0704, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005709188224799286, | |
| "grad_norm": 4.846289157867432, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0787, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005947071067499257, | |
| "grad_norm": 2.3819010257720947, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0484, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005947071067499257, | |
| "eval_loss": 0.03744269162416458, | |
| "eval_runtime": 694.1415, | |
| "eval_samples_per_second": 40.799, | |
| "eval_steps_per_second": 5.1, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006184953910199227, | |
| "grad_norm": 5.12270975112915, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0628, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006422836752899197, | |
| "grad_norm": 0.4506359100341797, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0383, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006660719595599167, | |
| "grad_norm": 0.2883658707141876, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0116, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.006898602438299138, | |
| "grad_norm": 0.3664928376674652, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0157, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007136485280999108, | |
| "grad_norm": 0.5137994289398193, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0344, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007374368123699078, | |
| "grad_norm": 0.3177562952041626, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0086, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0076122509663990486, | |
| "grad_norm": 0.3575591742992401, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0141, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.00785013380909902, | |
| "grad_norm": 0.6437414288520813, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0474, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00808801665179899, | |
| "grad_norm": 0.5256926417350769, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0398, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008325899494498959, | |
| "grad_norm": 0.528218150138855, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0182, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00856378233719893, | |
| "grad_norm": 0.4154456853866577, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0144, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0088016651798989, | |
| "grad_norm": 0.2326408475637436, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0052, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.00903954802259887, | |
| "grad_norm": 0.6743408441543579, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0477, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.009277430865298841, | |
| "grad_norm": 0.47138625383377075, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0158, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00951531370799881, | |
| "grad_norm": 0.7161089181900024, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0229, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00975319655069878, | |
| "grad_norm": 0.5954609513282776, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0255, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.009991079393398751, | |
| "grad_norm": 0.6990079283714294, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0256, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010228962236098722, | |
| "grad_norm": 0.3620032072067261, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0108, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.010466845078798692, | |
| "grad_norm": 0.24278657138347626, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0361, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.010704727921498661, | |
| "grad_norm": 0.24923881888389587, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0229, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.010942610764198632, | |
| "grad_norm": 0.18173465132713318, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0215, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.011180493606898602, | |
| "grad_norm": 0.14647623896598816, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0184, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.011418376449598573, | |
| "grad_norm": 0.18817275762557983, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0171, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.011656259292298543, | |
| "grad_norm": 0.2422836571931839, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0185, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.011894142134998514, | |
| "grad_norm": 0.5552806258201599, | |
| "learning_rate": 0.0, | |
| "loss": 0.0471, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.011894142134998514, | |
| "eval_loss": 0.021467845886945724, | |
| "eval_runtime": 693.0444, | |
| "eval_samples_per_second": 40.863, | |
| "eval_steps_per_second": 5.108, | |
| "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": 7.842663714573517e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |