| { | |
| "best_metric": 2.2995645999908447, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09193288899103655, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018386577798207308, | |
| "grad_norm": 1.081779956817627, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3372, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018386577798207308, | |
| "eval_loss": 3.488497734069824, | |
| "eval_runtime": 91.0592, | |
| "eval_samples_per_second": 40.238, | |
| "eval_steps_per_second": 5.03, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036773155596414617, | |
| "grad_norm": 1.0725606679916382, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4139, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005515973339462192, | |
| "grad_norm": 1.062793493270874, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.3681, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007354631119282923, | |
| "grad_norm": 0.917945921421051, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.2476, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009193288899103653, | |
| "grad_norm": 0.8048112392425537, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.1506, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011031946678924385, | |
| "grad_norm": 0.869051992893219, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.119, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012870604458745116, | |
| "grad_norm": 0.8979360461235046, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.0601, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014709262238565847, | |
| "grad_norm": 0.8364057540893555, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.0116, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016547920018386578, | |
| "grad_norm": 0.7612777352333069, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.9686, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018386577798207307, | |
| "grad_norm": 0.6910287141799927, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.8914, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02022523557802804, | |
| "grad_norm": 0.6527714729309082, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.8909, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02206389335784877, | |
| "grad_norm": 0.6930609345436096, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.7853, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.023902551137669502, | |
| "grad_norm": 0.72305828332901, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.7206, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02574120891749023, | |
| "grad_norm": 0.5932046175003052, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7581, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.027579866697310964, | |
| "grad_norm": 0.58180832862854, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.6843, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029418524477131693, | |
| "grad_norm": 0.5187463164329529, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.6549, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.031257182256952426, | |
| "grad_norm": 0.47566890716552734, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.6104, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.033095840036773155, | |
| "grad_norm": 0.5077899694442749, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.5966, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.034934497816593885, | |
| "grad_norm": 0.47106459736824036, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.5941, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.036773155596414614, | |
| "grad_norm": 0.438539057970047, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.5589, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03861181337623535, | |
| "grad_norm": 0.45031824707984924, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.5078, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04045047115605608, | |
| "grad_norm": 0.5081450343132019, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.5141, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04228912893587681, | |
| "grad_norm": 0.49454426765441895, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.531, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.04412778671569754, | |
| "grad_norm": 0.4849998652935028, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.4787, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.045966444495518274, | |
| "grad_norm": 0.6349493265151978, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.3678, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.045966444495518274, | |
| "eval_loss": 2.43084979057312, | |
| "eval_runtime": 91.222, | |
| "eval_samples_per_second": 40.166, | |
| "eval_steps_per_second": 5.021, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.047805102275339004, | |
| "grad_norm": 0.6615458130836487, | |
| "learning_rate": 5e-05, | |
| "loss": 2.457, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04964376005515973, | |
| "grad_norm": 0.495445191860199, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.4575, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05148241783498046, | |
| "grad_norm": 0.4795641601085663, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.4228, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0533210756148012, | |
| "grad_norm": 0.4803744852542877, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.4151, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05515973339462193, | |
| "grad_norm": 0.5404251217842102, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.4128, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05699839117444266, | |
| "grad_norm": 0.5260909795761108, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.4072, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.058837048954263386, | |
| "grad_norm": 0.5466575622558594, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.428, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.060675706734084116, | |
| "grad_norm": 0.47617822885513306, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.4066, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06251436451390485, | |
| "grad_norm": 0.5196675658226013, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3135, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06435302229372558, | |
| "grad_norm": 0.6534458994865417, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.3918, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06619168007354631, | |
| "grad_norm": 0.5190359950065613, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.3302, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06803033785336704, | |
| "grad_norm": 0.5105009078979492, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.2812, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06986899563318777, | |
| "grad_norm": 0.622005045413971, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3611, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0717076534130085, | |
| "grad_norm": 0.6437798738479614, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.3768, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07354631119282923, | |
| "grad_norm": 0.6086359024047852, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3218, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07538496897264997, | |
| "grad_norm": 0.4965401887893677, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.3161, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0772236267524707, | |
| "grad_norm": 0.4839130640029907, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.319, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07906228453229143, | |
| "grad_norm": 0.4947792589664459, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.305, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08090094231211216, | |
| "grad_norm": 0.5204262137413025, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.3355, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08273960009193289, | |
| "grad_norm": 0.6242971420288086, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.3654, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08457825787175362, | |
| "grad_norm": 0.5766761302947998, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.3287, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08641691565157435, | |
| "grad_norm": 0.5085965991020203, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.3468, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08825557343139508, | |
| "grad_norm": 0.5474885106086731, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.3602, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0900942312112158, | |
| "grad_norm": 0.677193820476532, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.2757, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09193288899103655, | |
| "grad_norm": 0.827997088432312, | |
| "learning_rate": 0.0, | |
| "loss": 2.2033, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09193288899103655, | |
| "eval_loss": 2.2995645999908447, | |
| "eval_runtime": 91.2388, | |
| "eval_samples_per_second": 40.158, | |
| "eval_steps_per_second": 5.02, | |
| "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": 5.305284264198144e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |