| { | |
| "best_metric": 1.945392370223999, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0564214683687143, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001128429367374286, | |
| "grad_norm": 0.7965163588523865, | |
| "learning_rate": 5e-05, | |
| "loss": 4.7446, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001128429367374286, | |
| "eval_loss": 4.968631744384766, | |
| "eval_runtime": 70.9174, | |
| "eval_samples_per_second": 84.182, | |
| "eval_steps_per_second": 10.533, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002256858734748572, | |
| "grad_norm": 0.8478525876998901, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2602, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033852881021228577, | |
| "grad_norm": 0.7976023554801941, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.3485, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004513717469497144, | |
| "grad_norm": 0.8236644268035889, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.5825, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00564214683687143, | |
| "grad_norm": 0.8460699319839478, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.5347, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006770576204245715, | |
| "grad_norm": 0.8713262677192688, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.2832, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.007899005571620002, | |
| "grad_norm": 1.017778992652893, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.6521, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009027434938994288, | |
| "grad_norm": 1.022419810295105, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.4763, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010155864306368573, | |
| "grad_norm": 1.1128177642822266, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 4.371, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01128429367374286, | |
| "grad_norm": 1.1345161199569702, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 4.2976, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012412723041117145, | |
| "grad_norm": 1.262861967086792, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.7078, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01354115240849143, | |
| "grad_norm": 1.4134832620620728, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.9068, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.014669581775865716, | |
| "grad_norm": 0.8951296210289001, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.3457, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.015798011143240004, | |
| "grad_norm": 0.9138154983520508, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.9106, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.016926440510614288, | |
| "grad_norm": 0.9040340185165405, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.8029, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018054869877988575, | |
| "grad_norm": 0.913700520992279, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.7255, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01918329924536286, | |
| "grad_norm": 0.9434831738471985, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.6498, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.020311728612737147, | |
| "grad_norm": 0.9711361527442932, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.6076, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02144015798011143, | |
| "grad_norm": 1.200960397720337, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.5892, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02256858734748572, | |
| "grad_norm": 0.899029016494751, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4848, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023697016714860006, | |
| "grad_norm": 0.8277913331985474, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.4131, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02482544608223429, | |
| "grad_norm": 0.9887898564338684, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.4374, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.025953875449608577, | |
| "grad_norm": 0.9525907635688782, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.3974, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02708230481698286, | |
| "grad_norm": 1.0320286750793457, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.6008, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02821073418435715, | |
| "grad_norm": 2.0822911262512207, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.292, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02821073418435715, | |
| "eval_loss": 2.3916566371917725, | |
| "eval_runtime": 71.0407, | |
| "eval_samples_per_second": 84.036, | |
| "eval_steps_per_second": 10.515, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.029339163551731433, | |
| "grad_norm": 3.504126787185669, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4901, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03046759291910572, | |
| "grad_norm": 3.6115365028381348, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.4891, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03159602228648001, | |
| "grad_norm": 2.7637460231781006, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.4113, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03272445165385429, | |
| "grad_norm": 2.168766498565674, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.1962, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.033852881021228576, | |
| "grad_norm": 1.980033278465271, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.0595, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03498131038860287, | |
| "grad_norm": 1.4205628633499146, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.1121, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03610973975597715, | |
| "grad_norm": 0.9236843585968018, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.0293, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.037238169123351435, | |
| "grad_norm": 0.7254409193992615, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.9481, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03836659849072572, | |
| "grad_norm": 0.6937389373779297, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.8681, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03949502785810001, | |
| "grad_norm": 1.0558534860610962, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.0303, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.040623457225474294, | |
| "grad_norm": 1.1168228387832642, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.0258, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04175188659284858, | |
| "grad_norm": 1.3629978895187378, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.1237, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.04288031596022286, | |
| "grad_norm": 2.2949774265289307, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.5624, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.04400874532759715, | |
| "grad_norm": 1.6233364343643188, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.1684, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04513717469497144, | |
| "grad_norm": 1.2072439193725586, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.0256, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04626560406234572, | |
| "grad_norm": 0.8051478862762451, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.8961, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04739403342972001, | |
| "grad_norm": 0.7268571257591248, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.8805, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.048522462797094296, | |
| "grad_norm": 0.6507890224456787, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8469, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.04965089216446858, | |
| "grad_norm": 0.6056588292121887, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7449, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.050779321531842864, | |
| "grad_norm": 0.6091510057449341, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.7524, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.051907750899217155, | |
| "grad_norm": 0.7476862072944641, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8226, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05303618026659144, | |
| "grad_norm": 0.7714654207229614, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.8503, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05416460963396572, | |
| "grad_norm": 1.0077050924301147, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.851, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05529303900134001, | |
| "grad_norm": 0.9173092842102051, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.8596, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0564214683687143, | |
| "grad_norm": 2.0996921062469482, | |
| "learning_rate": 0.0, | |
| "loss": 2.6004, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0564214683687143, | |
| "eval_loss": 1.945392370223999, | |
| "eval_runtime": 71.2097, | |
| "eval_samples_per_second": 83.837, | |
| "eval_steps_per_second": 10.49, | |
| "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": 1.2955709175182131e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |