| { | |
| "best_metric": 0.020438848063349724, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06781385097906248, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013562770195812495, | |
| "grad_norm": 8.829853057861328, | |
| "learning_rate": 5e-05, | |
| "loss": 5.48, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013562770195812495, | |
| "eval_loss": 5.35487174987793, | |
| "eval_runtime": 178.9569, | |
| "eval_samples_per_second": 27.755, | |
| "eval_steps_per_second": 3.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002712554039162499, | |
| "grad_norm": 8.493329048156738, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3874, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004068831058743749, | |
| "grad_norm": 8.060304641723633, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.1312, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005425108078324998, | |
| "grad_norm": 7.588632106781006, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.652, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006781385097906247, | |
| "grad_norm": 8.079386711120605, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.3827, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008137662117487498, | |
| "grad_norm": 13.640036582946777, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.1052, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009493939137068747, | |
| "grad_norm": 3.801544189453125, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.209, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010850216156649996, | |
| "grad_norm": 4.697356224060059, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1661, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.012206493176231245, | |
| "grad_norm": 2.2616631984710693, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1281, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013562770195812495, | |
| "grad_norm": 1.0779037475585938, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.0734, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014919047215393744, | |
| "grad_norm": 1.0886865854263306, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.057, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016275324234974995, | |
| "grad_norm": 1.1330660581588745, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.0881, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017631601254556244, | |
| "grad_norm": 2.9014949798583984, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.2475, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018987878274137494, | |
| "grad_norm": 2.011962413787842, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0849, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020344155293718743, | |
| "grad_norm": 1.3376178741455078, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0453, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021700432313299992, | |
| "grad_norm": 1.0635402202606201, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.044, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02305670933288124, | |
| "grad_norm": 0.9886969327926636, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0533, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02441298635246249, | |
| "grad_norm": 0.8168627619743347, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0379, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02576926337204374, | |
| "grad_norm": 0.34220975637435913, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0313, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02712554039162499, | |
| "grad_norm": 0.5813488960266113, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0297, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02848181741120624, | |
| "grad_norm": 0.6970713138580322, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0564, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.029838094430787488, | |
| "grad_norm": 0.5031370520591736, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0281, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.031194371450368737, | |
| "grad_norm": 0.43404918909072876, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0374, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03255064846994999, | |
| "grad_norm": 0.3055057227611542, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.0205, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03390692548953124, | |
| "grad_norm": 0.399833083152771, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0298, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03390692548953124, | |
| "eval_loss": 0.025279613211750984, | |
| "eval_runtime": 178.8888, | |
| "eval_samples_per_second": 27.766, | |
| "eval_steps_per_second": 3.471, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03526320250911249, | |
| "grad_norm": 0.3740287125110626, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0167, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03661947952869374, | |
| "grad_norm": 0.30993032455444336, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0169, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03797575654827499, | |
| "grad_norm": 0.3844718337059021, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0158, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03933203356785624, | |
| "grad_norm": 0.3056732416152954, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0124, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.040688310587437486, | |
| "grad_norm": 0.46882057189941406, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0295, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042044587607018735, | |
| "grad_norm": 0.47933128476142883, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0223, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.043400864626599985, | |
| "grad_norm": 0.3894636631011963, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0163, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.044757141646181234, | |
| "grad_norm": 0.48748522996902466, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.03, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04611341866576248, | |
| "grad_norm": 0.5438624620437622, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0283, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04746969568534373, | |
| "grad_norm": 0.44844117760658264, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0278, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04882597270492498, | |
| "grad_norm": 0.41513577103614807, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0196, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05018224972450623, | |
| "grad_norm": 0.3627379834651947, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0118, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05153852674408748, | |
| "grad_norm": 0.43544554710388184, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0275, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05289480376366873, | |
| "grad_norm": 0.37630170583724976, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0214, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05425108078324998, | |
| "grad_norm": 0.3092811405658722, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0107, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05560735780283123, | |
| "grad_norm": 0.4349355697631836, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0108, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05696363482241248, | |
| "grad_norm": 0.15674984455108643, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0062, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05831991184199373, | |
| "grad_norm": 0.3282619118690491, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0108, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.059676188861574976, | |
| "grad_norm": 0.4003311097621918, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0231, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.061032465881156225, | |
| "grad_norm": 0.36832916736602783, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0218, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.062388742900737475, | |
| "grad_norm": 0.4607793390750885, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0355, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06374501992031872, | |
| "grad_norm": 0.25370919704437256, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0056, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06510129693989998, | |
| "grad_norm": 0.3585875928401947, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.019, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06645757395948122, | |
| "grad_norm": 0.38194748759269714, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0152, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06781385097906248, | |
| "grad_norm": 0.5131410956382751, | |
| "learning_rate": 0.0, | |
| "loss": 0.0307, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06781385097906248, | |
| "eval_loss": 0.020438848063349724, | |
| "eval_runtime": 179.7145, | |
| "eval_samples_per_second": 27.638, | |
| "eval_steps_per_second": 3.455, | |
| "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": 6.823228785819648e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |