| { | |
| "best_metric": 0.595823347568512, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9704433497536946, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03940886699507389, | |
| "grad_norm": 0.2884816527366638, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7061, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03940886699507389, | |
| "eval_loss": 0.9556217193603516, | |
| "eval_runtime": 10.4285, | |
| "eval_samples_per_second": 16.397, | |
| "eval_steps_per_second": 2.11, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07881773399014778, | |
| "grad_norm": 0.4466714560985565, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8296, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11822660098522167, | |
| "grad_norm": 0.5227925181388855, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.791, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15763546798029557, | |
| "grad_norm": 0.49005722999572754, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.6879, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19704433497536947, | |
| "grad_norm": 0.5601417422294617, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9169, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23645320197044334, | |
| "grad_norm": 0.6752742528915405, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7662, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.27586206896551724, | |
| "grad_norm": 0.19960370659828186, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7286, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.31527093596059114, | |
| "grad_norm": 0.3387351334095001, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35467980295566504, | |
| "grad_norm": 0.3576226830482483, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.5311, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.39408866995073893, | |
| "grad_norm": 0.34454867243766785, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4194, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.43349753694581283, | |
| "grad_norm": 0.33091822266578674, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6092, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4729064039408867, | |
| "grad_norm": 0.4191518723964691, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6693, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5123152709359606, | |
| "grad_norm": 0.19716322422027588, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6877, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5517241379310345, | |
| "grad_norm": 0.19261513650417328, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4703, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5911330049261084, | |
| "grad_norm": 0.2257925420999527, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6305418719211823, | |
| "grad_norm": 0.27351778745651245, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5046, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6699507389162561, | |
| "grad_norm": 0.2576059401035309, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5116, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7093596059113301, | |
| "grad_norm": 0.2532605826854706, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6067, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7487684729064039, | |
| "grad_norm": 0.21180546283721924, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7976, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7881773399014779, | |
| "grad_norm": 0.14593924582004547, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5314, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8275862068965517, | |
| "grad_norm": 0.19641239941120148, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5906, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8669950738916257, | |
| "grad_norm": 0.17595908045768738, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3893, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.9064039408866995, | |
| "grad_norm": 0.2203323394060135, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5394, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9458128078817734, | |
| "grad_norm": 0.2296009659767151, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.6099, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9852216748768473, | |
| "grad_norm": 0.3083626329898834, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.6687, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9852216748768473, | |
| "eval_loss": 0.6031047701835632, | |
| "eval_runtime": 10.3852, | |
| "eval_samples_per_second": 16.466, | |
| "eval_steps_per_second": 2.118, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0246305418719213, | |
| "grad_norm": 0.2834261655807495, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9793, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.064039408866995, | |
| "grad_norm": 0.12495367228984833, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4947, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.103448275862069, | |
| "grad_norm": 0.16204771399497986, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.489, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 0.19606707990169525, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.397, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1822660098522166, | |
| "grad_norm": 0.26958799362182617, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.6213, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2216748768472907, | |
| "grad_norm": 0.2792090177536011, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5842, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2610837438423645, | |
| "grad_norm": 0.20217172801494598, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6247, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3004926108374384, | |
| "grad_norm": 0.1565660685300827, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.5037, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3399014778325122, | |
| "grad_norm": 0.13762818276882172, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3797, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3793103448275863, | |
| "grad_norm": 0.16477568447589874, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4446, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4187192118226601, | |
| "grad_norm": 0.18226175010204315, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4642, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.458128078817734, | |
| "grad_norm": 0.2204369157552719, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5166, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4975369458128078, | |
| "grad_norm": 0.17690245807170868, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.438, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5369458128078817, | |
| "grad_norm": 0.17283889651298523, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5826, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5763546798029555, | |
| "grad_norm": 0.13877063989639282, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6157635467980296, | |
| "grad_norm": 0.1638207882642746, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4527, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6551724137931034, | |
| "grad_norm": 0.16349922120571136, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4198, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6945812807881775, | |
| "grad_norm": 0.22082000970840454, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5535, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7339901477832513, | |
| "grad_norm": 0.17473125457763672, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3828, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7733990147783252, | |
| "grad_norm": 0.2006826251745224, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9111, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.812807881773399, | |
| "grad_norm": 0.13559463620185852, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4365, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8522167487684729, | |
| "grad_norm": 0.1571803092956543, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4817, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8916256157635467, | |
| "grad_norm": 0.16777488589286804, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3306, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9310344827586206, | |
| "grad_norm": 0.1940426230430603, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.5166, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9704433497536946, | |
| "grad_norm": 0.2563996911048889, | |
| "learning_rate": 0.0, | |
| "loss": 0.5225, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9704433497536946, | |
| "eval_loss": 0.595823347568512, | |
| "eval_runtime": 10.3871, | |
| "eval_samples_per_second": 16.463, | |
| "eval_steps_per_second": 2.118, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |