| { | |
| "best_metric": 1.6356873512268066, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03311806590495115, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000662361318099023, | |
| "grad_norm": 40.82220458984375, | |
| "learning_rate": 5e-05, | |
| "loss": 27.5824, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000662361318099023, | |
| "eval_loss": 2.2696444988250732, | |
| "eval_runtime": 432.347, | |
| "eval_samples_per_second": 23.525, | |
| "eval_steps_per_second": 2.942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001324722636198046, | |
| "grad_norm": 36.23447799682617, | |
| "learning_rate": 0.0001, | |
| "loss": 27.0301, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001987083954297069, | |
| "grad_norm": 41.014190673828125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 29.9936, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002649445272396092, | |
| "grad_norm": 36.32714080810547, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 27.1201, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003311806590495115, | |
| "grad_norm": 36.35200500488281, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 30.1767, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003974167908594138, | |
| "grad_norm": 34.66734313964844, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 32.16, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004636529226693161, | |
| "grad_norm": 27.75533103942871, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 28.1419, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005298890544792184, | |
| "grad_norm": 39.82036209106445, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 31.4935, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005961251862891207, | |
| "grad_norm": 32.18791198730469, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 29.9285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00662361318099023, | |
| "grad_norm": 33.4499626159668, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 29.7212, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007285974499089253, | |
| "grad_norm": 38.62579345703125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 33.2777, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007948335817188276, | |
| "grad_norm": 36.961639404296875, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 31.1595, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0086106971352873, | |
| "grad_norm": 37.11787414550781, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 30.9798, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009273058453386322, | |
| "grad_norm": 35.7690315246582, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 26.4066, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009935419771485345, | |
| "grad_norm": 25.68424415588379, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 26.8711, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010597781089584368, | |
| "grad_norm": 20.35919189453125, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 24.8348, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.011260142407683391, | |
| "grad_norm": 20.65962028503418, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 24.6985, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011922503725782414, | |
| "grad_norm": 20.867441177368164, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 26.0421, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012584865043881437, | |
| "grad_norm": 23.38364028930664, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 25.5464, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01324722636198046, | |
| "grad_norm": 24.096189498901367, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 26.3065, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013909587680079483, | |
| "grad_norm": 25.358400344848633, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 27.5427, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014571948998178506, | |
| "grad_norm": 25.04808235168457, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 27.4076, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01523431031627753, | |
| "grad_norm": 29.721607208251953, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 27.733, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015896671634376552, | |
| "grad_norm": 34.963172912597656, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 29.4103, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.016559032952475575, | |
| "grad_norm": 36.04214096069336, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 29.9496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016559032952475575, | |
| "eval_loss": 1.6913299560546875, | |
| "eval_runtime": 435.6417, | |
| "eval_samples_per_second": 23.347, | |
| "eval_steps_per_second": 2.92, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0172213942705746, | |
| "grad_norm": 23.54070472717285, | |
| "learning_rate": 5e-05, | |
| "loss": 22.5009, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.01788375558867362, | |
| "grad_norm": 20.027286529541016, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 23.1153, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018546116906772644, | |
| "grad_norm": 18.963481903076172, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 23.7903, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.019208478224871667, | |
| "grad_norm": 26.33202362060547, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 27.938, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01987083954297069, | |
| "grad_norm": 21.261442184448242, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 25.7281, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020533200861069714, | |
| "grad_norm": 20.291833877563477, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 24.2849, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.021195562179168737, | |
| "grad_norm": 22.858013153076172, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 25.7152, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02185792349726776, | |
| "grad_norm": 23.46312713623047, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 26.8651, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.022520284815366783, | |
| "grad_norm": 23.533655166625977, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 26.9475, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.023182646133465806, | |
| "grad_norm": 23.187999725341797, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 25.6272, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02384500745156483, | |
| "grad_norm": 26.695240020751953, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 28.5214, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02450736876966385, | |
| "grad_norm": 27.083887100219727, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 31.241, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.025169730087762875, | |
| "grad_norm": 33.784095764160156, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 27.0767, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025832091405861898, | |
| "grad_norm": 17.89984130859375, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 23.7762, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02649445272396092, | |
| "grad_norm": 25.040252685546875, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 26.2669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.027156814042059944, | |
| "grad_norm": 17.308666229248047, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 22.8648, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027819175360158967, | |
| "grad_norm": 17.806684494018555, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 25.445, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02848153667825799, | |
| "grad_norm": 18.2435359954834, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 25.0637, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.029143897996357013, | |
| "grad_norm": 22.409690856933594, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 28.0825, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.029806259314456036, | |
| "grad_norm": 18.422311782836914, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 26.1024, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03046862063255506, | |
| "grad_norm": 21.495967864990234, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 25.523, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.031130981950654082, | |
| "grad_norm": 22.34445571899414, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 25.1083, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.031793343268753105, | |
| "grad_norm": 24.14988136291504, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 26.1674, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03245570458685213, | |
| "grad_norm": 24.39285659790039, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 27.8474, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03311806590495115, | |
| "grad_norm": 28.339920043945312, | |
| "learning_rate": 0.0, | |
| "loss": 28.8547, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03311806590495115, | |
| "eval_loss": 1.6356873512268066, | |
| "eval_runtime": 431.7917, | |
| "eval_samples_per_second": 23.555, | |
| "eval_steps_per_second": 2.946, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 8.435490789261312e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |