| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1359773371104816, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018130311614730878, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018130311614730878, | |
| "eval_loss": NaN, | |
| "eval_runtime": 167.6461, | |
| "eval_samples_per_second": 11.083, | |
| "eval_steps_per_second": 2.774, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036260623229461757, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005439093484419263, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007252124645892351, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009065155807365438, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010878186968838527, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012691218130311615, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014504249291784703, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01631728045325779, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018130311614730877, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019943342776203965, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.021756373937677053, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02356940509915014, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02538243626062323, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.027195467422096317, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029008498583569405, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.030821529745042493, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03263456090651558, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03444759206798867, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.036260623229461754, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.038073654390934845, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03988668555240793, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04169971671388102, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.043512747875354106, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0453257790368272, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04713881019830028, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.048951841359773374, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05076487252124646, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05257790368271955, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.054390934844192634, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05620396600566572, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05801699716713881, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.059830028328611895, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.061643059490084987, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06345609065155808, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06526912181303116, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06708215297450425, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06889518413597734, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07070821529745043, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07252124645892351, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0743342776203966, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07614730878186969, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07796033994334278, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07977337110481586, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08158640226628895, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08339943342776204, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08521246458923512, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08702549575070821, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0888385269121813, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0906515580736544, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0906515580736544, | |
| "eval_loss": NaN, | |
| "eval_runtime": 167.2999, | |
| "eval_samples_per_second": 11.106, | |
| "eval_steps_per_second": 2.779, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09246458923512747, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.09427762039660056, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.09609065155807366, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.09790368271954675, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09971671388101983, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.10152974504249292, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.10334277620396601, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1051558073654391, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.10696883852691218, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10878186968838527, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11059490084985836, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.11240793201133144, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.11422096317280453, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.11603399433427762, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.11784702549575071, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11966005665722379, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.12147308781869688, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.12328611898016997, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.12509915014164305, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.12691218130311616, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12872521246458923, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.1305382436260623, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.13235127478753542, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.1341643059490085, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.1359773371104816, | |
| "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": 1.707250305466368e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |