| { | |
| "best_metric": 1.0520539283752441, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.238390092879257, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02476780185758514, | |
| "grad_norm": 1.401563286781311, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9909, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02476780185758514, | |
| "eval_loss": 3.172659397125244, | |
| "eval_runtime": 7.8105, | |
| "eval_samples_per_second": 34.825, | |
| "eval_steps_per_second": 4.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04953560371517028, | |
| "grad_norm": 1.5852631330490112, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3205, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07430340557275542, | |
| "grad_norm": 1.8465495109558105, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.3424, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.09907120743034056, | |
| "grad_norm": 2.3970329761505127, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.2712, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1238390092879257, | |
| "grad_norm": 1.5857042074203491, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0623, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.14860681114551083, | |
| "grad_norm": 1.590824007987976, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.0058, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17337461300309598, | |
| "grad_norm": 2.000732660293579, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.171, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.19814241486068113, | |
| "grad_norm": 1.7148714065551758, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3005, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22291021671826625, | |
| "grad_norm": 1.9383009672164917, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.1251, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2476780185758514, | |
| "grad_norm": 3.4579310417175293, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.4977, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2724458204334365, | |
| "grad_norm": 3.3259365558624268, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.665, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.29721362229102166, | |
| "grad_norm": 1.825563669204712, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.5272, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3219814241486068, | |
| "grad_norm": 1.6385694742202759, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4618, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.34674922600619196, | |
| "grad_norm": 1.5010485649108887, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.5331, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3715170278637771, | |
| "grad_norm": 1.4281823635101318, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.5566, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.39628482972136225, | |
| "grad_norm": 1.4791179895401, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.5582, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 1.4600080251693726, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.5372, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4458204334365325, | |
| "grad_norm": 1.661367416381836, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.777, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 1.865303635597229, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7801, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4953560371517028, | |
| "grad_norm": 3.176959276199341, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.2092, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5201238390092879, | |
| "grad_norm": 1.5191824436187744, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.1579, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.544891640866873, | |
| "grad_norm": 1.5453227758407593, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0815, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5696594427244582, | |
| "grad_norm": 1.351405382156372, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.1604, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5944272445820433, | |
| "grad_norm": 1.3701266050338745, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.1426, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6191950464396285, | |
| "grad_norm": 1.4790074825286865, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2818, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6191950464396285, | |
| "eval_loss": 1.3508119583129883, | |
| "eval_runtime": 7.808, | |
| "eval_samples_per_second": 34.836, | |
| "eval_steps_per_second": 4.354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6439628482972136, | |
| "grad_norm": 1.4686107635498047, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1942, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6687306501547987, | |
| "grad_norm": 1.8817143440246582, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4641, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6934984520123839, | |
| "grad_norm": 1.7228407859802246, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.2089, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.718266253869969, | |
| "grad_norm": 1.8622612953186035, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.2837, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7430340557275542, | |
| "grad_norm": 2.548654079437256, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.5451, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.7678018575851393, | |
| "grad_norm": 1.872255802154541, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0789, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.7925696594427245, | |
| "grad_norm": 1.6402901411056519, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1032, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8173374613003096, | |
| "grad_norm": 1.6358095407485962, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8919, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 1.5518550872802734, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9096, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.8668730650154799, | |
| "grad_norm": 1.5421191453933716, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0869, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.891640866873065, | |
| "grad_norm": 1.6059826612472534, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.9879, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9164086687306502, | |
| "grad_norm": 1.7333624362945557, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.2627, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 1.703264594078064, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0225, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.9659442724458205, | |
| "grad_norm": 2.474355936050415, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3612, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.9907120743034056, | |
| "grad_norm": 2.699963331222534, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3391, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0154798761609907, | |
| "grad_norm": 2.305959701538086, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.606, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.0402476780185759, | |
| "grad_norm": 1.233525037765503, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.866, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.065015479876161, | |
| "grad_norm": 1.2345691919326782, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.8087, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.089783281733746, | |
| "grad_norm": 1.2370696067810059, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7829, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.1145510835913313, | |
| "grad_norm": 1.2401882410049438, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7784, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.1393188854489165, | |
| "grad_norm": 1.3323066234588623, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7661, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.1640866873065017, | |
| "grad_norm": 1.449929118156433, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.9979, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.1888544891640866, | |
| "grad_norm": 1.6287673711776733, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8577, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.2136222910216719, | |
| "grad_norm": 1.9859602451324463, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.0143, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.238390092879257, | |
| "grad_norm": 2.370694637298584, | |
| "learning_rate": 0.0, | |
| "loss": 1.0756, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.238390092879257, | |
| "eval_loss": 1.0520539283752441, | |
| "eval_runtime": 16.2636, | |
| "eval_samples_per_second": 16.724, | |
| "eval_steps_per_second": 2.091, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |