| { | |
| "best_metric": 0.00023969815811142325, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.383399209486166, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03162055335968379, | |
| "grad_norm": 2.1013476848602295, | |
| "learning_rate": 5e-06, | |
| "loss": 0.2918, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03162055335968379, | |
| "eval_loss": 0.2833981215953827, | |
| "eval_runtime": 5.6957, | |
| "eval_samples_per_second": 18.786, | |
| "eval_steps_per_second": 4.74, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06324110671936758, | |
| "grad_norm": 2.068596601486206, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2797, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09486166007905138, | |
| "grad_norm": 2.0080692768096924, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.2867, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12648221343873517, | |
| "grad_norm": 2.110651969909668, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3163, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15810276679841898, | |
| "grad_norm": 1.4501609802246094, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2454, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18972332015810275, | |
| "grad_norm": 1.193555474281311, | |
| "learning_rate": 3e-05, | |
| "loss": 0.19, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.22134387351778656, | |
| "grad_norm": 0.9181650876998901, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.1517, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.25296442687747034, | |
| "grad_norm": 0.7230370044708252, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1241, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2845849802371542, | |
| "grad_norm": 0.5991852283477783, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.1057, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.31620553359683795, | |
| "grad_norm": 0.6482350826263428, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1023, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.5091797113418579, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0694, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3794466403162055, | |
| "grad_norm": 0.3836430013179779, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0564, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.41106719367588934, | |
| "grad_norm": 0.29540184140205383, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4426877470355731, | |
| "grad_norm": 0.48722681403160095, | |
| "learning_rate": 7e-05, | |
| "loss": 0.044, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4743083003952569, | |
| "grad_norm": 0.4131571352481842, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0286, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5059288537549407, | |
| "grad_norm": 0.3438633978366852, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0199, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5375494071146245, | |
| "grad_norm": 0.16885609924793243, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0114, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5691699604743083, | |
| "grad_norm": 0.16992968320846558, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0115, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6007905138339921, | |
| "grad_norm": 0.23753099143505096, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0142, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6324110671936759, | |
| "grad_norm": 0.3303862512111664, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0103, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6640316205533597, | |
| "grad_norm": 0.14659832417964935, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0094, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.26171669363975525, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.0063, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.08080412447452545, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0026, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.758893280632411, | |
| "grad_norm": 0.05177770555019379, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0018, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7905138339920948, | |
| "grad_norm": 0.07171144336462021, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0035, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8221343873517787, | |
| "grad_norm": 0.03390180692076683, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0009, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8537549407114624, | |
| "grad_norm": 0.09451759606599808, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0053, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8853754940711462, | |
| "grad_norm": 0.12461254745721817, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0033, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9169960474308301, | |
| "grad_norm": 0.10362528264522552, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0054, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9486166007905138, | |
| "grad_norm": 0.013774733059108257, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0006, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9802371541501976, | |
| "grad_norm": 0.04352792352437973, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.006, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.017786561264822, | |
| "grad_norm": 0.014139426872134209, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0006, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0494071146245059, | |
| "grad_norm": 0.03587684407830238, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0043, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0810276679841897, | |
| "grad_norm": 0.17202265560626984, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0009, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.1126482213438735, | |
| "grad_norm": 0.07799206674098969, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0011, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1442687747035574, | |
| "grad_norm": 0.05983465537428856, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.002, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1758893280632412, | |
| "grad_norm": 0.005408214405179024, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0003, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2075098814229248, | |
| "grad_norm": 0.07063424587249756, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.007, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2391304347826086, | |
| "grad_norm": 0.007456331979483366, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0003, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2707509881422925, | |
| "grad_norm": 0.012253080494701862, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0003, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3023715415019763, | |
| "grad_norm": 0.006279624532908201, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0003, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3339920948616601, | |
| "grad_norm": 0.09158781915903091, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.002, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3656126482213438, | |
| "grad_norm": 0.016019077971577644, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.0004, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3972332015810276, | |
| "grad_norm": 0.02001301385462284, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0004, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4288537549407114, | |
| "grad_norm": 0.05574377253651619, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0011, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4604743083003953, | |
| "grad_norm": 0.00605006841942668, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0003, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.492094861660079, | |
| "grad_norm": 0.006872722413390875, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0003, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5237154150197627, | |
| "grad_norm": 0.03212732821702957, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0003, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5553359683794468, | |
| "grad_norm": 0.09686794131994247, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0009, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5869565217391304, | |
| "grad_norm": 0.049275122582912445, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0014, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5869565217391304, | |
| "eval_loss": 0.00023969815811142325, | |
| "eval_runtime": 5.3058, | |
| "eval_samples_per_second": 20.166, | |
| "eval_steps_per_second": 5.089, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6185770750988142, | |
| "grad_norm": 0.007441387511789799, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0003, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.650197628458498, | |
| "grad_norm": 0.004175810143351555, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0003, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.6818181818181817, | |
| "grad_norm": 0.025354648008942604, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.003, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.7134387351778657, | |
| "grad_norm": 0.0125960111618042, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0004, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.7450592885375493, | |
| "grad_norm": 0.004288897849619389, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0003, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.7766798418972332, | |
| "grad_norm": 0.13706451654434204, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0044, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.808300395256917, | |
| "grad_norm": 0.13290545344352722, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0016, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.8399209486166008, | |
| "grad_norm": 0.004434171598404646, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0002, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.8715415019762847, | |
| "grad_norm": 0.004509397316724062, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0003, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.9031620553359683, | |
| "grad_norm": 0.03684943914413452, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0024, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.9347826086956523, | |
| "grad_norm": 0.004858649801462889, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.0003, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.966403162055336, | |
| "grad_norm": 0.033181995153427124, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0036, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.0039525691699605, | |
| "grad_norm": 0.007152313366532326, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0004, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.035573122529644, | |
| "grad_norm": 0.053472116589546204, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0011, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.067193675889328, | |
| "grad_norm": 0.0040871379896998405, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0003, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.0988142292490117, | |
| "grad_norm": 0.0035609269980341196, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0002, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.130434782608696, | |
| "grad_norm": 0.02019282802939415, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0013, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.1620553359683794, | |
| "grad_norm": 0.004724355414509773, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0002, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.1936758893280635, | |
| "grad_norm": 0.0054779378697276115, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0003, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.225296442687747, | |
| "grad_norm": 0.004262240137904882, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0002, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.2569169960474307, | |
| "grad_norm": 0.09871349483728409, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0012, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.2885375494071147, | |
| "grad_norm": 0.014313112944364548, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0005, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.3201581027667983, | |
| "grad_norm": 0.03431084752082825, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0006, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.3517786561264824, | |
| "grad_norm": 0.004373958334326744, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0003, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.383399209486166, | |
| "grad_norm": 0.05674320086836815, | |
| "learning_rate": 0.0, | |
| "loss": 0.0059, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 3.134618974814208e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |