| { | |
| "best_metric": 1.3278440237045288, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.0008455980280653986, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6911960561307972e-05, | |
| "grad_norm": 0.5461403131484985, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.6911960561307972e-05, | |
| "eval_loss": 3.3437588214874268, | |
| "eval_runtime": 1805.366, | |
| "eval_samples_per_second": 13.791, | |
| "eval_steps_per_second": 6.896, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.3823921122615945e-05, | |
| "grad_norm": 1.5352400541305542, | |
| "learning_rate": 8e-05, | |
| "loss": 2.567, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.073588168392391e-05, | |
| "grad_norm": 1.80024254322052, | |
| "learning_rate": 0.00012, | |
| "loss": 2.7514, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.764784224523189e-05, | |
| "grad_norm": 1.3233122825622559, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6365, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.455980280653986e-05, | |
| "grad_norm": 1.474558711051941, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8207, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00010147176336784782, | |
| "grad_norm": 1.7245981693267822, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 2.6809, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011838372392915579, | |
| "grad_norm": 2.162684679031372, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 2.6813, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00013529568449046378, | |
| "grad_norm": 1.9564881324768066, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 2.4524, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00015220764505177175, | |
| "grad_norm": 2.0885121822357178, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 2.0998, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016911960561307972, | |
| "grad_norm": 3.7902536392211914, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 2.0842, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00018603156617438767, | |
| "grad_norm": 2.2282345294952393, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 1.9047, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00020294352673569564, | |
| "grad_norm": 1.974695086479187, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 1.5154, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002198554872970036, | |
| "grad_norm": 2.592761278152466, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 1.7882, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00023676744785831159, | |
| "grad_norm": 2.0295674800872803, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 1.6305, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00025367940841961956, | |
| "grad_norm": 1.625274658203125, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 1.473, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00027059136898092756, | |
| "grad_norm": 1.835348129272461, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 1.8893, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002875033295422355, | |
| "grad_norm": 1.6969001293182373, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 1.8415, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0003044152901035435, | |
| "grad_norm": 2.303267002105713, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 1.3015, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00032132725066485145, | |
| "grad_norm": 1.8150877952575684, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 1.2658, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00033823921122615945, | |
| "grad_norm": 2.3673338890075684, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 1.2364, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003551511717874674, | |
| "grad_norm": 2.4632089138031006, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 1.0193, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00037206313234877534, | |
| "grad_norm": 1.3708044290542603, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.9471, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00038897509291008334, | |
| "grad_norm": 2.6031060218811035, | |
| "learning_rate": 0.00018280088311480201, | |
| "loss": 1.0314, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0004058870534713913, | |
| "grad_norm": 0.9620503187179565, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.8515, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0004227990140326993, | |
| "grad_norm": 1.026154637336731, | |
| "learning_rate": 0.00017891405093963938, | |
| "loss": 0.8531, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0004227990140326993, | |
| "eval_loss": 1.3278440237045288, | |
| "eval_runtime": 1805.0632, | |
| "eval_samples_per_second": 13.793, | |
| "eval_steps_per_second": 6.897, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0004397109745940072, | |
| "grad_norm": 1.2110459804534912, | |
| "learning_rate": 0.00017684011108568592, | |
| "loss": 0.895, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0004566229351553152, | |
| "grad_norm": 1.1382213830947876, | |
| "learning_rate": 0.0001746821476984154, | |
| "loss": 0.9614, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.00047353489571662317, | |
| "grad_norm": 1.0368095636367798, | |
| "learning_rate": 0.00017244252047910892, | |
| "loss": 0.8552, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0004904468562779311, | |
| "grad_norm": 1.323333740234375, | |
| "learning_rate": 0.00017012367842724887, | |
| "loss": 1.0692, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0005073588168392391, | |
| "grad_norm": 1.1299031972885132, | |
| "learning_rate": 0.00016772815716257412, | |
| "loss": 1.0273, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0005242707774005471, | |
| "grad_norm": 0.9993110299110413, | |
| "learning_rate": 0.00016525857615241687, | |
| "loss": 0.7862, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0005411827379618551, | |
| "grad_norm": 0.9180406332015991, | |
| "learning_rate": 0.0001627176358473537, | |
| "loss": 0.8503, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.000558094698523163, | |
| "grad_norm": 0.852716863155365, | |
| "learning_rate": 0.00016010811472830252, | |
| "loss": 0.7589, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.000575006659084471, | |
| "grad_norm": 1.1683015823364258, | |
| "learning_rate": 0.00015743286626829437, | |
| "loss": 0.9032, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.000591918619645779, | |
| "grad_norm": 0.8834861516952515, | |
| "learning_rate": 0.00015469481581224272, | |
| "loss": 0.8227, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.000608830580207087, | |
| "grad_norm": 0.788383424282074, | |
| "learning_rate": 0.00015189695737812152, | |
| "loss": 0.8611, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0006257425407683949, | |
| "grad_norm": 0.7765706777572632, | |
| "learning_rate": 0.00014904235038305083, | |
| "loss": 0.8839, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0006426545013297029, | |
| "grad_norm": 0.8954746127128601, | |
| "learning_rate": 0.0001461341162978688, | |
| "loss": 0.7209, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0006595664618910109, | |
| "grad_norm": 0.6842917799949646, | |
| "learning_rate": 0.00014317543523384928, | |
| "loss": 0.644, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0006764784224523189, | |
| "grad_norm": 0.8862132430076599, | |
| "learning_rate": 0.00014016954246529696, | |
| "loss": 0.7262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0006933903830136268, | |
| "grad_norm": 0.8410934805870056, | |
| "learning_rate": 0.00013711972489182208, | |
| "loss": 0.7245, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0007103023435749348, | |
| "grad_norm": 1.1996475458145142, | |
| "learning_rate": 0.00013402931744416433, | |
| "loss": 0.8627, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0007272143041362428, | |
| "grad_norm": 1.1021193265914917, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.887, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0007441262646975507, | |
| "grad_norm": 1.623423457145691, | |
| "learning_rate": 0.00012774029087618446, | |
| "loss": 0.9683, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0007610382252588587, | |
| "grad_norm": 0.932873547077179, | |
| "learning_rate": 0.00012454854871407994, | |
| "loss": 0.882, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0007779501858201667, | |
| "grad_norm": 0.9381756782531738, | |
| "learning_rate": 0.0001213299630743747, | |
| "loss": 0.8824, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0007948621463814747, | |
| "grad_norm": 1.2354497909545898, | |
| "learning_rate": 0.000118088053433211, | |
| "loss": 1.093, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0008117741069427826, | |
| "grad_norm": 1.0774998664855957, | |
| "learning_rate": 0.0001148263647711842, | |
| "loss": 1.032, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0008286860675040906, | |
| "grad_norm": 0.8946607708930969, | |
| "learning_rate": 0.00011154846369695863, | |
| "loss": 0.8654, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0008455980280653986, | |
| "grad_norm": 0.8054470419883728, | |
| "learning_rate": 0.00010825793454723325, | |
| "loss": 0.8106, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0008455980280653986, | |
| "eval_loss": 1.3436920642852783, | |
| "eval_runtime": 1805.0607, | |
| "eval_samples_per_second": 13.793, | |
| "eval_steps_per_second": 6.897, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3604771504128000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |