| { | |
| "best_metric": 0.05362105742096901, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.47206923682140045, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006294256490952006, | |
| "grad_norm": 3.8400495052337646, | |
| "learning_rate": 5e-06, | |
| "loss": 3.0839, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006294256490952006, | |
| "eval_loss": 3.1272127628326416, | |
| "eval_runtime": 84.4157, | |
| "eval_samples_per_second": 6.35, | |
| "eval_steps_per_second": 0.794, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012588512981904013, | |
| "grad_norm": 3.7963645458221436, | |
| "learning_rate": 1e-05, | |
| "loss": 3.289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01888276947285602, | |
| "grad_norm": 3.8076391220092773, | |
| "learning_rate": 1.5e-05, | |
| "loss": 3.2079, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.025177025963808025, | |
| "grad_norm": 3.608992099761963, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0601, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03147128245476003, | |
| "grad_norm": 3.9987127780914307, | |
| "learning_rate": 2.5e-05, | |
| "loss": 3.2286, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03776553894571204, | |
| "grad_norm": 3.7046732902526855, | |
| "learning_rate": 3e-05, | |
| "loss": 3.1094, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.044059795436664044, | |
| "grad_norm": 3.8715567588806152, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.9081, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05035405192761605, | |
| "grad_norm": 3.759075403213501, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7651, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05664830841856806, | |
| "grad_norm": 3.834105968475342, | |
| "learning_rate": 4.5e-05, | |
| "loss": 2.5933, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06294256490952006, | |
| "grad_norm": 3.9589412212371826, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3404, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06923682140047208, | |
| "grad_norm": 4.193765163421631, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.3012, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07553107789142408, | |
| "grad_norm": 5.016157627105713, | |
| "learning_rate": 6e-05, | |
| "loss": 2.025, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08182533438237609, | |
| "grad_norm": 4.501615524291992, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.8619, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08811959087332809, | |
| "grad_norm": 4.059515953063965, | |
| "learning_rate": 7e-05, | |
| "loss": 1.7482, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0944138473642801, | |
| "grad_norm": 3.349575996398926, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4586, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1007081038552321, | |
| "grad_norm": 3.5398507118225098, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3738, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10700236034618411, | |
| "grad_norm": 2.90134859085083, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.2573, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11329661683713611, | |
| "grad_norm": 2.85213303565979, | |
| "learning_rate": 9e-05, | |
| "loss": 1.2735, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11959087332808813, | |
| "grad_norm": 2.873847007751465, | |
| "learning_rate": 9.5e-05, | |
| "loss": 1.0826, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12588512981904013, | |
| "grad_norm": 2.7670559883117676, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1229, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13217938630999213, | |
| "grad_norm": 3.1859798431396484, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 1.0617, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13847364280094415, | |
| "grad_norm": 2.4608633518218994, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.8707, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14476789929189615, | |
| "grad_norm": 2.742429256439209, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.852, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15106215578284815, | |
| "grad_norm": 2.2563023567199707, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.7373, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15735641227380015, | |
| "grad_norm": 2.2105352878570557, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.7149, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16365066876475218, | |
| "grad_norm": 2.4090940952301025, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.7451, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16994492525570418, | |
| "grad_norm": 2.5231480598449707, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.6176, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17623918174665618, | |
| "grad_norm": 2.0671744346618652, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.4402, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18253343823760818, | |
| "grad_norm": 2.357484817504883, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.4541, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1888276947285602, | |
| "grad_norm": 2.6663615703582764, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.3951, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 2.5575287342071533, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3535, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2014162077104642, | |
| "grad_norm": 2.6381635665893555, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.3087, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2077104642014162, | |
| "grad_norm": 2.8394503593444824, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.2934, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21400472069236823, | |
| "grad_norm": 2.78173565864563, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.2449, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.22029897718332023, | |
| "grad_norm": 2.9417877197265625, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.2123, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22659323367427223, | |
| "grad_norm": 2.85414981842041, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.2024, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23288749016522423, | |
| "grad_norm": 2.734037160873413, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.1753, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.23918174665617625, | |
| "grad_norm": 4.297616958618164, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.2276, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24547600314712825, | |
| "grad_norm": 2.606386184692383, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.1276, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.25177025963808025, | |
| "grad_norm": 1.5647878646850586, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0612, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 2.8499035835266113, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0934, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.26435877261998425, | |
| "grad_norm": 2.563603162765503, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.1466, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.27065302911093625, | |
| "grad_norm": 1.9947185516357422, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.057, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.2769472856018883, | |
| "grad_norm": 2.5543155670166016, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.062, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2832415420928403, | |
| "grad_norm": 1.8335676193237305, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0785, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2895357985837923, | |
| "grad_norm": 1.778093695640564, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0491, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2958300550747443, | |
| "grad_norm": 1.2079533338546753, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0373, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3021243115656963, | |
| "grad_norm": 1.9942814111709595, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0423, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3084185680566483, | |
| "grad_norm": 1.2081289291381836, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0258, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3147128245476003, | |
| "grad_norm": 2.220339059829712, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0285, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3147128245476003, | |
| "eval_loss": 0.05362105742096901, | |
| "eval_runtime": 85.2365, | |
| "eval_samples_per_second": 6.288, | |
| "eval_steps_per_second": 0.786, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3210070810385523, | |
| "grad_norm": 3.1018424034118652, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0904, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.32730133752950435, | |
| "grad_norm": 2.7917895317077637, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0776, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.33359559402045635, | |
| "grad_norm": 1.141679048538208, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0297, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.33988985051140835, | |
| "grad_norm": 1.4085471630096436, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0158, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.34618410700236035, | |
| "grad_norm": 2.6473264694213867, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0374, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.35247836349331235, | |
| "grad_norm": 2.7476418018341064, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0185, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.35877261998426435, | |
| "grad_norm": 1.146089792251587, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0159, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.36506687647521635, | |
| "grad_norm": 1.5934761762619019, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0249, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.37136113296616835, | |
| "grad_norm": 1.0182127952575684, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0249, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.3776553894571204, | |
| "grad_norm": 1.0180975198745728, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0168, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3839496459480724, | |
| "grad_norm": 1.1062073707580566, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.0155, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 0.5176264643669128, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0067, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3965381589299764, | |
| "grad_norm": 0.4311802387237549, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0103, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4028324154209284, | |
| "grad_norm": 0.7234724760055542, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.011, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4091266719118804, | |
| "grad_norm": 0.7512171864509583, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0119, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.4154209284028324, | |
| "grad_norm": 0.8448026180267334, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0143, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.4217151848937844, | |
| "grad_norm": 0.37998679280281067, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.004, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.42800944138473646, | |
| "grad_norm": 0.6252229809761047, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0072, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.43430369787568845, | |
| "grad_norm": 0.4169199466705322, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0064, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.44059795436664045, | |
| "grad_norm": 0.2969546318054199, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.005, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44689221085759245, | |
| "grad_norm": 0.6241343021392822, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0097, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.45318646734854445, | |
| "grad_norm": 0.4060995578765869, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0054, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.45948072383949645, | |
| "grad_norm": 0.5652337670326233, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0094, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.46577498033044845, | |
| "grad_norm": 0.6753122806549072, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0068, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.47206923682140045, | |
| "grad_norm": 0.3501550257205963, | |
| "learning_rate": 0.0, | |
| "loss": 0.004, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 4.451401010774016e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |