| { | |
| "best_metric": 0.3578774929046631, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.644468313641246, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 24.527587890625, | |
| "learning_rate": 5e-06, | |
| "loss": 26.7779, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "eval_loss": 1.7484409809112549, | |
| "eval_runtime": 49.6443, | |
| "eval_samples_per_second": 7.896, | |
| "eval_steps_per_second": 1.974, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 37.25108337402344, | |
| "learning_rate": 1e-05, | |
| "loss": 30.2279, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 26.99140167236328, | |
| "learning_rate": 1.5e-05, | |
| "loss": 30.4207, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 36.530818939208984, | |
| "learning_rate": 2e-05, | |
| "loss": 32.068, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 21.84710693359375, | |
| "learning_rate": 2.5e-05, | |
| "loss": 26.86, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05155746509129968, | |
| "grad_norm": 28.68981170654297, | |
| "learning_rate": 3e-05, | |
| "loss": 28.5753, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06015037593984962, | |
| "grad_norm": 24.717876434326172, | |
| "learning_rate": 3.5e-05, | |
| "loss": 23.4737, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06874328678839957, | |
| "grad_norm": 31.985191345214844, | |
| "learning_rate": 4e-05, | |
| "loss": 23.7119, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07733619763694952, | |
| "grad_norm": 24.535207748413086, | |
| "learning_rate": 4.5e-05, | |
| "loss": 21.2995, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08592910848549946, | |
| "grad_norm": 20.784114837646484, | |
| "learning_rate": 5e-05, | |
| "loss": 19.4062, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09452201933404941, | |
| "grad_norm": 22.949960708618164, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 19.894, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10311493018259936, | |
| "grad_norm": 18.90312957763672, | |
| "learning_rate": 6e-05, | |
| "loss": 15.6992, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11170784103114931, | |
| "grad_norm": 12.863642692565918, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 13.7171, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12030075187969924, | |
| "grad_norm": 10.37125015258789, | |
| "learning_rate": 7e-05, | |
| "loss": 13.0682, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.1288936627282492, | |
| "grad_norm": 11.138198852539062, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 12.1682, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.13748657357679914, | |
| "grad_norm": 14.989235877990723, | |
| "learning_rate": 8e-05, | |
| "loss": 11.8289, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1460794844253491, | |
| "grad_norm": 11.183653831481934, | |
| "learning_rate": 8.5e-05, | |
| "loss": 9.9752, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.15467239527389903, | |
| "grad_norm": 10.320233345031738, | |
| "learning_rate": 9e-05, | |
| "loss": 8.4, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 7.7508039474487305, | |
| "learning_rate": 9.5e-05, | |
| "loss": 8.694, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17185821697099893, | |
| "grad_norm": 8.021259307861328, | |
| "learning_rate": 0.0001, | |
| "loss": 8.0313, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18045112781954886, | |
| "grad_norm": 7.663169860839844, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 10.0139, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.18904403866809882, | |
| "grad_norm": 7.0549798011779785, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 8.3892, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.19763694951664876, | |
| "grad_norm": 6.753633975982666, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 7.8297, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.20622986036519872, | |
| "grad_norm": 7.454422950744629, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 7.9531, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.21482277121374865, | |
| "grad_norm": 4.801022052764893, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 7.3965, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22341568206229862, | |
| "grad_norm": 5.871040344238281, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 8.6411, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.23200859291084855, | |
| "grad_norm": 6.431129455566406, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 6.2586, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24060150375939848, | |
| "grad_norm": 4.8356032371521, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 6.9354, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.24919441460794844, | |
| "grad_norm": 4.676732540130615, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 7.0826, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.2577873254564984, | |
| "grad_norm": 4.927655220031738, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 6.9211, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2663802363050483, | |
| "grad_norm": 5.393516540527344, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 6.5549, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2749731471535983, | |
| "grad_norm": 5.347249984741211, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 7.0554, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.28356605800214824, | |
| "grad_norm": 5.3050312995910645, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 6.4794, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2921589688506982, | |
| "grad_norm": 5.1706037521362305, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 6.7291, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3007518796992481, | |
| "grad_norm": 5.202975749969482, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 6.4802, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.30934479054779807, | |
| "grad_norm": 5.066944599151611, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 5.5754, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.317937701396348, | |
| "grad_norm": 5.513393878936768, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 5.9398, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 6.0009565353393555, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 6.3022, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3351235230934479, | |
| "grad_norm": 5.408257007598877, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 5.3976, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.34371643394199786, | |
| "grad_norm": 6.3030195236206055, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 6.669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3523093447905478, | |
| "grad_norm": 4.973893642425537, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 6.0552, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3609022556390977, | |
| "grad_norm": 5.095200061798096, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 5.2656, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3694951664876477, | |
| "grad_norm": 5.441334247589111, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 6.0926, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.37808807733619765, | |
| "grad_norm": 5.907732009887695, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 6.2611, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.3866809881847476, | |
| "grad_norm": 5.2476348876953125, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 5.114, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.3952738990332975, | |
| "grad_norm": 4.924515724182129, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 4.9915, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4038668098818475, | |
| "grad_norm": 5.901587963104248, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 5.8679, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.41245972073039744, | |
| "grad_norm": 4.880833625793457, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 5.1338, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 5.361891746520996, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 5.8578, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4296455424274973, | |
| "grad_norm": 5.202010631561279, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 5.4502, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4296455424274973, | |
| "eval_loss": 0.3578774929046631, | |
| "eval_runtime": 50.006, | |
| "eval_samples_per_second": 7.839, | |
| "eval_steps_per_second": 1.96, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.43823845327604727, | |
| "grad_norm": 5.766439914703369, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 4.9625, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.44683136412459723, | |
| "grad_norm": 5.521291255950928, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 4.9848, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.45542427497314714, | |
| "grad_norm": 6.785717487335205, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 5.913, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.4640171858216971, | |
| "grad_norm": 6.411205768585205, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 5.3654, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.47261009667024706, | |
| "grad_norm": 5.137513637542725, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 4.7431, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.48120300751879697, | |
| "grad_norm": 6.2091755867004395, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 4.7387, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 6.7059173583984375, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 5.7861, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4983888292158969, | |
| "grad_norm": 7.024590969085693, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 5.8263, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.5069817400644469, | |
| "grad_norm": 6.100332736968994, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 4.9064, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.5155746509129968, | |
| "grad_norm": 5.492628574371338, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 4.977, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5241675617615468, | |
| "grad_norm": 6.51470947265625, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 4.8705, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.5327604726100966, | |
| "grad_norm": 5.699104309082031, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 5.0406, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.5413533834586466, | |
| "grad_norm": 5.825130939483643, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 5.1809, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5499462943071965, | |
| "grad_norm": 6.401869773864746, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 6.0405, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.5585392051557465, | |
| "grad_norm": 6.119671821594238, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 5.5007, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5671321160042965, | |
| "grad_norm": 6.092080593109131, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 4.8658, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.5757250268528464, | |
| "grad_norm": 5.349208831787109, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 4.3778, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.5843179377013964, | |
| "grad_norm": 5.576518535614014, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 4.7543, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.5929108485499462, | |
| "grad_norm": 5.412608623504639, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 4.2394, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6015037593984962, | |
| "grad_norm": 5.888413906097412, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 5.4023, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6100966702470462, | |
| "grad_norm": 5.344703197479248, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 4.2625, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.6186895810955961, | |
| "grad_norm": 5.677237033843994, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 4.9872, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6272824919441461, | |
| "grad_norm": 6.14519739151001, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 4.9022, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.635875402792696, | |
| "grad_norm": 5.074471950531006, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 4.4077, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.644468313641246, | |
| "grad_norm": 5.900351047515869, | |
| "learning_rate": 0.0, | |
| "loss": 5.002, | |
| "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": 3.991525977489408e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |