| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06265991332045324, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008354655109393765, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008354655109393765, | |
| "eval_loss": NaN, | |
| "eval_runtime": 288.3181, | |
| "eval_samples_per_second": 13.985, | |
| "eval_steps_per_second": 3.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001670931021878753, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025063965328181296, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003341862043757506, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004177327554696883, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005012793065636259, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005848258576575636, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006683724087515012, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007519189598454388, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008354655109393766, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009190120620333142, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010025586131272518, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010861051642211895, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011696517153151271, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012531982664090648, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013367448175030024, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0142029136859694, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015038379196908777, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015873844707848153, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01670931021878753, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017544775729726906, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018380241240666284, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01921570675160566, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.020051172262545037, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020886637773484415, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02172210328442379, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022557568795363168, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.023393034306302542, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02422849981724192, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.025063965328181295, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025899430839120673, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.026734896350060048, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.027570361860999426, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0284058273719388, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.02924129288287818, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.030076758393817554, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03091222390475693, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.031747689415696306, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03258315492663569, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03341862043757506, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03425408594851444, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03508955145945381, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.035925016970393193, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03676048248133257, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03759594799227194, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03843141350321132, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0392668790141507, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.040102344525090074, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04093781003602945, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04177327554696883, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04177327554696883, | |
| "eval_loss": NaN, | |
| "eval_runtime": 288.428, | |
| "eval_samples_per_second": 13.979, | |
| "eval_steps_per_second": 3.495, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.042608741057908205, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04344420656884758, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.044279672079786954, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.045115137590726336, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04595060310166571, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.046786068612605085, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.04762153412354446, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04845699963448384, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.049292465145423216, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.05012793065636259, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05096339616730197, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05179886167824135, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.05263432718918072, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.053469792700120096, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05430525821105948, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.05514072372199885, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05597618923293823, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0568116547438776, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.05764712025481698, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.05848258576575636, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.05931805127669573, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.06015351678763511, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06098898229857449, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06182444780951386, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06265991332045324, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "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": 1.0423143185252352e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |