| { | |
| "best_metric": 0.4174307584762573, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04538852578068264, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009077705156136529, | |
| "grad_norm": 19.090673446655273, | |
| "learning_rate": 0.00015, | |
| "loss": 9.7116, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009077705156136529, | |
| "eval_loss": 9.237911224365234, | |
| "eval_runtime": 0.5515, | |
| "eval_samples_per_second": 90.658, | |
| "eval_steps_per_second": 5.439, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018155410312273058, | |
| "grad_norm": 21.541793823242188, | |
| "learning_rate": 0.0003, | |
| "loss": 9.5187, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027233115468409588, | |
| "grad_norm": 16.640724182128906, | |
| "learning_rate": 0.0002998600959423082, | |
| "loss": 7.2173, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0036310820624546117, | |
| "grad_norm": 172.39108276367188, | |
| "learning_rate": 0.0002994406737417567, | |
| "loss": 6.3391, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004538852578068265, | |
| "grad_norm": 9.659110069274902, | |
| "learning_rate": 0.00029874260271490463, | |
| "loss": 3.7329, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0054466230936819175, | |
| "grad_norm": 11.84581470489502, | |
| "learning_rate": 0.00029776732972055516, | |
| "loss": 2.0967, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0063543936092955704, | |
| "grad_norm": 35.30651092529297, | |
| "learning_rate": 0.0002965168761609197, | |
| "loss": 1.4312, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007262164124909223, | |
| "grad_norm": 8.859146118164062, | |
| "learning_rate": 0.0002949938337919529, | |
| "loss": 0.8472, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008169934640522876, | |
| "grad_norm": 9.34030532836914, | |
| "learning_rate": 0.0002932013593515431, | |
| "loss": 0.8184, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00907770515613653, | |
| "grad_norm": 7.431899070739746, | |
| "learning_rate": 0.00029114316801669057, | |
| "loss": 0.7907, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009985475671750182, | |
| "grad_norm": 8.734899520874023, | |
| "learning_rate": 0.00028882352570323616, | |
| "loss": 0.7096, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010893246187363835, | |
| "grad_norm": 8.801371574401855, | |
| "learning_rate": 0.00028624724022409897, | |
| "loss": 0.8588, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011801016702977488, | |
| "grad_norm": 7.757359981536865, | |
| "learning_rate": 0.0002834196513243502, | |
| "loss": 0.8325, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012708787218591141, | |
| "grad_norm": 5.052784442901611, | |
| "learning_rate": 0.0002803466196137759, | |
| "loss": 0.5601, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013616557734204794, | |
| "grad_norm": 3.7386362552642822, | |
| "learning_rate": 0.00027703451441986836, | |
| "loss": 0.5656, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014524328249818447, | |
| "grad_norm": 4.285150527954102, | |
| "learning_rate": 0.000273490200586422, | |
| "loss": 0.5889, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015432098765432098, | |
| "grad_norm": 1.7297357320785522, | |
| "learning_rate": 0.00026972102424509665, | |
| "loss": 0.5514, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016339869281045753, | |
| "grad_norm": 4.028224468231201, | |
| "learning_rate": 0.00026573479758943753, | |
| "loss": 0.622, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.017247639796659404, | |
| "grad_norm": 3.1785671710968018, | |
| "learning_rate": 0.0002615397826829114, | |
| "loss": 0.6005, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01815541031227306, | |
| "grad_norm": 2.6770856380462646, | |
| "learning_rate": 0.0002571446743345183, | |
| "loss": 0.5465, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01906318082788671, | |
| "grad_norm": 1.3410382270812988, | |
| "learning_rate": 0.00025255858207747205, | |
| "loss": 0.4898, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019970951343500364, | |
| "grad_norm": 6.422758102416992, | |
| "learning_rate": 0.0002477910112883017, | |
| "loss": 0.6803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020878721859114015, | |
| "grad_norm": 4.62112283706665, | |
| "learning_rate": 0.00024285184348550706, | |
| "loss": 0.5983, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02178649237472767, | |
| "grad_norm": 1.9435359239578247, | |
| "learning_rate": 0.0002377513158486027, | |
| "loss": 0.5102, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02269426289034132, | |
| "grad_norm": 1.9337120056152344, | |
| "learning_rate": 0.00023249999999999999, | |
| "loss": 0.5099, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02269426289034132, | |
| "eval_loss": 0.6093809008598328, | |
| "eval_runtime": 0.5517, | |
| "eval_samples_per_second": 90.623, | |
| "eval_steps_per_second": 5.437, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023602033405954976, | |
| "grad_norm": 4.949934959411621, | |
| "learning_rate": 0.00022710878009370554, | |
| "loss": 0.6187, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024509803921568627, | |
| "grad_norm": 3.945021390914917, | |
| "learning_rate": 0.00022158883025624965, | |
| "loss": 0.5797, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.025417574437182282, | |
| "grad_norm": 2.5016119480133057, | |
| "learning_rate": 0.0002159515914266029, | |
| "loss": 0.5343, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026325344952795933, | |
| "grad_norm": 1.574798345565796, | |
| "learning_rate": 0.0002102087476430831, | |
| "loss": 0.5074, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027233115468409588, | |
| "grad_norm": 1.7340073585510254, | |
| "learning_rate": 0.00020437220182640135, | |
| "loss": 0.4987, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02814088598402324, | |
| "grad_norm": 1.8289647102355957, | |
| "learning_rate": 0.00019845405110904146, | |
| "loss": 0.522, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.029048656499636893, | |
| "grad_norm": 1.8377400636672974, | |
| "learning_rate": 0.00019246656176210558, | |
| "loss": 0.4699, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.029956427015250545, | |
| "grad_norm": 2.042335271835327, | |
| "learning_rate": 0.0001864221437715939, | |
| "loss": 0.4408, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030864197530864196, | |
| "grad_norm": 2.779773712158203, | |
| "learning_rate": 0.0001803333251168141, | |
| "loss": 0.5595, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03177196804647785, | |
| "grad_norm": 2.2879557609558105, | |
| "learning_rate": 0.00017421272580423058, | |
| "loss": 0.5574, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.032679738562091505, | |
| "grad_norm": 2.1511833667755127, | |
| "learning_rate": 0.00016807303171057425, | |
| "loss": 0.5359, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.033587509077705156, | |
| "grad_norm": 1.0012569427490234, | |
| "learning_rate": 0.00016192696828942573, | |
| "loss": 0.4326, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03449527959331881, | |
| "grad_norm": 2.745234489440918, | |
| "learning_rate": 0.00015578727419576942, | |
| "loss": 0.5126, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03540305010893246, | |
| "grad_norm": 2.2056078910827637, | |
| "learning_rate": 0.00014966667488318586, | |
| "loss": 0.4623, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03631082062454612, | |
| "grad_norm": 1.4716527462005615, | |
| "learning_rate": 0.00014357785622840606, | |
| "loss": 0.4342, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03721859114015977, | |
| "grad_norm": 1.3762019872665405, | |
| "learning_rate": 0.00013753343823789445, | |
| "loss": 0.4361, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03812636165577342, | |
| "grad_norm": 2.7313358783721924, | |
| "learning_rate": 0.00013154594889095854, | |
| "loss": 0.4984, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03903413217138707, | |
| "grad_norm": 2.4179422855377197, | |
| "learning_rate": 0.00012562779817359865, | |
| "loss": 0.4451, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03994190268700073, | |
| "grad_norm": 2.6130852699279785, | |
| "learning_rate": 0.00011979125235691685, | |
| "loss": 0.5173, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04084967320261438, | |
| "grad_norm": 2.8871238231658936, | |
| "learning_rate": 0.00011404840857339706, | |
| "loss": 0.4606, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04175744371822803, | |
| "grad_norm": 2.950117826461792, | |
| "learning_rate": 0.0001084111697437504, | |
| "loss": 0.4586, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04266521423384168, | |
| "grad_norm": 0.984398365020752, | |
| "learning_rate": 0.00010289121990629447, | |
| "loss": 0.4926, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04357298474945534, | |
| "grad_norm": 2.0302248001098633, | |
| "learning_rate": 9.750000000000003e-05, | |
| "loss": 0.4309, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04448075526506899, | |
| "grad_norm": 1.1805931329727173, | |
| "learning_rate": 9.22486841513973e-05, | |
| "loss": 0.4593, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04538852578068264, | |
| "grad_norm": 1.6091700792312622, | |
| "learning_rate": 8.714815651449293e-05, | |
| "loss": 0.4697, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04538852578068264, | |
| "eval_loss": 0.4174307584762573, | |
| "eval_runtime": 0.5516, | |
| "eval_samples_per_second": 90.651, | |
| "eval_steps_per_second": 5.439, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 71, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.81327834021888e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |