| { | |
| "best_metric": 11.923681259155273, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.37174721189591076, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004956629491945477, | |
| "grad_norm": 0.029702121391892433, | |
| "learning_rate": 5e-06, | |
| "loss": 11.9338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004956629491945477, | |
| "eval_loss": 11.932662010192871, | |
| "eval_runtime": 3.4335, | |
| "eval_samples_per_second": 99.025, | |
| "eval_steps_per_second": 24.756, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009913258983890954, | |
| "grad_norm": 0.029551642015576363, | |
| "learning_rate": 1e-05, | |
| "loss": 11.933, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01486988847583643, | |
| "grad_norm": 0.02150936797261238, | |
| "learning_rate": 1.5e-05, | |
| "loss": 11.9333, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01982651796778191, | |
| "grad_norm": 0.031518660485744476, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9315, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.024783147459727387, | |
| "grad_norm": 0.01814820058643818, | |
| "learning_rate": 2.5e-05, | |
| "loss": 11.9329, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02973977695167286, | |
| "grad_norm": 0.022795800119638443, | |
| "learning_rate": 3e-05, | |
| "loss": 11.9295, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03469640644361834, | |
| "grad_norm": 0.02691086195409298, | |
| "learning_rate": 3.5e-05, | |
| "loss": 11.9328, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03965303593556382, | |
| "grad_norm": 0.021017029881477356, | |
| "learning_rate": 4e-05, | |
| "loss": 11.9363, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04460966542750929, | |
| "grad_norm": 0.02902752347290516, | |
| "learning_rate": 4.5e-05, | |
| "loss": 11.9329, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04956629491945477, | |
| "grad_norm": 0.025535089895129204, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9316, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05452292441140025, | |
| "grad_norm": 0.018343951553106308, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.9298, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05947955390334572, | |
| "grad_norm": 0.028216585516929626, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9309, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0644361833952912, | |
| "grad_norm": 0.04306847229599953, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 11.9312, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06939281288723669, | |
| "grad_norm": 0.032149795442819595, | |
| "learning_rate": 7e-05, | |
| "loss": 11.9318, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.07434944237918216, | |
| "grad_norm": 0.031103266403079033, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9308, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07930607187112763, | |
| "grad_norm": 0.023666374385356903, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9331, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08426270136307311, | |
| "grad_norm": 0.04397472366690636, | |
| "learning_rate": 8.5e-05, | |
| "loss": 11.9318, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08921933085501858, | |
| "grad_norm": 0.03761634603142738, | |
| "learning_rate": 9e-05, | |
| "loss": 11.9327, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09417596034696406, | |
| "grad_norm": 0.03000902198255062, | |
| "learning_rate": 9.5e-05, | |
| "loss": 11.9312, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09913258983890955, | |
| "grad_norm": 0.04588532820343971, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9285, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10408921933085502, | |
| "grad_norm": 0.05068815499544144, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 11.9334, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1090458488228005, | |
| "grad_norm": 0.0575312003493309, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 11.9303, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.11400247831474597, | |
| "grad_norm": 0.05008804053068161, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 11.9305, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11895910780669144, | |
| "grad_norm": 0.04055539891123772, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 11.9322, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.12391573729863693, | |
| "grad_norm": 0.05720638111233711, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 11.928, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1288723667905824, | |
| "grad_norm": 0.06328973174095154, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 11.9308, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.13382899628252787, | |
| "grad_norm": 0.05939590185880661, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 11.9294, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.13878562577447337, | |
| "grad_norm": 0.0752195417881012, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 11.9302, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.14374225526641884, | |
| "grad_norm": 0.04964336380362511, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 11.9312, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.14869888475836432, | |
| "grad_norm": 0.07646752148866653, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 11.9305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1536555142503098, | |
| "grad_norm": 0.08100369572639465, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 11.9292, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.15861214374225527, | |
| "grad_norm": 0.05317220091819763, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 11.9305, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.16356877323420074, | |
| "grad_norm": 0.11869339644908905, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 11.9257, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.16852540272614622, | |
| "grad_norm": 0.07948697358369827, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 11.9298, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.1734820322180917, | |
| "grad_norm": 0.08774244040250778, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 11.9288, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17843866171003717, | |
| "grad_norm": 0.13008320331573486, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 11.9263, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.18339529120198264, | |
| "grad_norm": 0.0970505028963089, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 11.9288, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.18835192069392812, | |
| "grad_norm": 0.12324848026037216, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 11.9239, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.19330855018587362, | |
| "grad_norm": 0.08435509353876114, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 11.9262, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1982651796778191, | |
| "grad_norm": 0.07982442528009415, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 11.9263, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.20322180916976457, | |
| "grad_norm": 0.08218646049499512, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 11.9271, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.20817843866171004, | |
| "grad_norm": 0.10249483585357666, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 11.9276, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.21313506815365552, | |
| "grad_norm": 0.09215902537107468, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 11.9282, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.218091697645601, | |
| "grad_norm": 0.09024009853601456, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 11.925, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.22304832713754646, | |
| "grad_norm": 0.06474387645721436, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 11.9266, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22800495662949194, | |
| "grad_norm": 0.08036696910858154, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 11.9252, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.23296158612143741, | |
| "grad_norm": 0.07694265991449356, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 11.9237, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2379182156133829, | |
| "grad_norm": 0.05151360481977463, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 11.9229, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.24287484510532836, | |
| "grad_norm": 0.09331781417131424, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 11.9232, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.24783147459727387, | |
| "grad_norm": 0.09337204694747925, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 11.9223, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24783147459727387, | |
| "eval_loss": 11.923681259155273, | |
| "eval_runtime": 3.4546, | |
| "eval_samples_per_second": 98.419, | |
| "eval_steps_per_second": 24.605, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2527881040892193, | |
| "grad_norm": 0.06785538047552109, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 11.9238, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2577447335811648, | |
| "grad_norm": 0.06856627762317657, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 11.9219, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.26270136307311026, | |
| "grad_norm": 0.08525048196315765, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 11.9235, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.26765799256505574, | |
| "grad_norm": 0.06322482973337173, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 11.9243, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.27261462205700127, | |
| "grad_norm": 0.07685398310422897, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 11.9228, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.27757125154894674, | |
| "grad_norm": 0.06677208840847015, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 11.9268, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2825278810408922, | |
| "grad_norm": 0.06735136359930038, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 11.9235, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2874845105328377, | |
| "grad_norm": 0.0659952163696289, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 11.9245, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.29244114002478316, | |
| "grad_norm": 0.08097010850906372, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 11.9218, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.29739776951672864, | |
| "grad_norm": 0.07043331116437912, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 11.9238, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3023543990086741, | |
| "grad_norm": 0.07436829805374146, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 11.9221, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3073110285006196, | |
| "grad_norm": 0.07238686829805374, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 11.9243, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.31226765799256506, | |
| "grad_norm": 0.06303081661462784, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 11.924, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.31722428748451054, | |
| "grad_norm": 0.050584156066179276, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 11.9225, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.322180916976456, | |
| "grad_norm": 0.06821806728839874, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 11.9226, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3271375464684015, | |
| "grad_norm": 0.07609910517930984, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 11.9227, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.33209417596034696, | |
| "grad_norm": 0.09269632399082184, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 11.9239, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.33705080545229243, | |
| "grad_norm": 0.07459668070077896, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 11.9219, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3420074349442379, | |
| "grad_norm": 0.054816748946905136, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 11.9238, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.3469640644361834, | |
| "grad_norm": 0.07526088505983353, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 11.9224, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.35192069392812886, | |
| "grad_norm": 0.06288407742977142, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 11.9252, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.35687732342007433, | |
| "grad_norm": 0.07722307741641998, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 11.9235, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3618339529120198, | |
| "grad_norm": 0.0703897774219513, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 11.9213, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.3667905824039653, | |
| "grad_norm": 0.06519778072834015, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 11.9269, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.37174721189591076, | |
| "grad_norm": 0.05321093648672104, | |
| "learning_rate": 0.0, | |
| "loss": 11.9229, | |
| "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": 723124224000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |