| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08736803785948308, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011649071714597743, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011649071714597743, | |
| "eval_loss": NaN, | |
| "eval_runtime": 426.668, | |
| "eval_samples_per_second": 6.778, | |
| "eval_steps_per_second": 1.695, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023298143429195486, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003494721514379323, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004659628685839097, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005824535857298871, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006989443028758646, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00815435020021842, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009319257371678194, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01048416454313797, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011649071714597743, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.012813978886057517, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.013978886057517292, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.015143793228977066, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01630870040043684, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.017473607571896616, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01863851474335639, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019803421914816162, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02096832908627594, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022133236257735712, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.023298143429195485, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02446305060065526, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025627957772115035, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.026792864943574808, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.027957772115034585, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029122679286494358, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03028758645795413, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03145249362941391, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03261740080087368, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.033782307972333454, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03494721514379323, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.036112122315253, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.03727702948671278, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.038441936658172554, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.039606843829632324, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0407717510010921, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04193665817255188, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04310156534401165, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.044266472515471424, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0454313796869312, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.04659628685839097, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04776119402985075, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.04892610120131052, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05009100837277029, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05125591554423007, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.052420822715689847, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.053585729887149616, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.05475063705860939, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.05591554423006917, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.05708045140152894, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.058245358572988716, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.058245358572988716, | |
| "eval_loss": NaN, | |
| "eval_runtime": 427.0525, | |
| "eval_samples_per_second": 6.772, | |
| "eval_steps_per_second": 1.693, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.059410265744448486, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.06057517291590826, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.06174008008736804, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.06290498725882782, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.06406989443028759, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.06523480160174736, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.06639970877320714, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.06756461594466691, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.06872952311612668, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.06989443028758646, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07105933745904623, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.072224244630506, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.07338915180196579, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.07455405897342555, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.07571896614488532, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.07688387331634511, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.07921368765926465, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.08037859483072443, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.0815435020021842, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08270840917364397, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.08387331634510375, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.08503822351656352, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.0862031306880233, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.08736803785948308, | |
| "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": 3.991489738702848e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |