| { | |
| "best_metric": 1.338729977607727, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06685050555694827, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013370101111389655, | |
| "grad_norm": 47.35528564453125, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8975, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013370101111389655, | |
| "eval_loss": 2.1031837463378906, | |
| "eval_runtime": 325.2439, | |
| "eval_samples_per_second": 15.493, | |
| "eval_steps_per_second": 1.937, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002674020222277931, | |
| "grad_norm": 63.3394775390625, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8337, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004011030333416896, | |
| "grad_norm": 48.00395584106445, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7147, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005348040444555862, | |
| "grad_norm": 42.88739013671875, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.5729, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0066850505556948275, | |
| "grad_norm": 38.311214447021484, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.3787, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008022060666833792, | |
| "grad_norm": 39.439857482910156, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4194, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009359070777972758, | |
| "grad_norm": 38.344337463378906, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3047, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010696080889111724, | |
| "grad_norm": 37.76652145385742, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3024, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01203309100025069, | |
| "grad_norm": 36.00216293334961, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4223, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013370101111389655, | |
| "grad_norm": 38.224220275878906, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.3393, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01470711122252862, | |
| "grad_norm": 43.11362838745117, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.28, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016044121333667585, | |
| "grad_norm": 44.510921478271484, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.3893, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01738113144480655, | |
| "grad_norm": 45.711830139160156, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5649, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.018718141555945516, | |
| "grad_norm": 28.458812713623047, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6861, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02005515166708448, | |
| "grad_norm": 23.017732620239258, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.4792, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021392161778223447, | |
| "grad_norm": 23.308353424072266, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.4659, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.022729171889362413, | |
| "grad_norm": 26.601207733154297, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.3869, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02406618200050138, | |
| "grad_norm": 28.621337890625, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.3742, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.025403192111640344, | |
| "grad_norm": 28.959524154663086, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1588, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02674020222277931, | |
| "grad_norm": 30.923385620117188, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3067, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028077212333918276, | |
| "grad_norm": 32.88140106201172, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3788, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02941422244505724, | |
| "grad_norm": 32.66322708129883, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3399, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.030751232556196207, | |
| "grad_norm": 34.90681457519531, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.258, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03208824266733517, | |
| "grad_norm": 45.44039535522461, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.3289, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.033425252778474135, | |
| "grad_norm": 45.168724060058594, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.2498, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.033425252778474135, | |
| "eval_loss": 1.3723218441009521, | |
| "eval_runtime": 226.223, | |
| "eval_samples_per_second": 22.274, | |
| "eval_steps_per_second": 2.785, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0347622628896131, | |
| "grad_norm": 27.988006591796875, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5653, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.036099273000752066, | |
| "grad_norm": 23.9869384765625, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5689, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03743628311189103, | |
| "grad_norm": 23.481412887573242, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.428, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03877329322303, | |
| "grad_norm": 23.574743270874023, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.4138, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04011030333416896, | |
| "grad_norm": 24.408958435058594, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.3259, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04144731344530793, | |
| "grad_norm": 25.739273071289062, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3485, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.042784323556446895, | |
| "grad_norm": 26.332134246826172, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3323, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04412133366758586, | |
| "grad_norm": 27.37655258178711, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.3009, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.045458343778724826, | |
| "grad_norm": 29.02335548400879, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.4547, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04679535388986379, | |
| "grad_norm": 30.307477951049805, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.32, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04813236400100276, | |
| "grad_norm": 29.861248016357422, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.1157, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.04946937411214172, | |
| "grad_norm": 37.60776138305664, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.2336, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.05080638422328069, | |
| "grad_norm": 31.587434768676758, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3959, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.052143394334419654, | |
| "grad_norm": 19.443872451782227, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5545, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05348040444555862, | |
| "grad_norm": 20.82927894592285, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.5071, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.054817414556697586, | |
| "grad_norm": 21.544597625732422, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.4133, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.05615442466783655, | |
| "grad_norm": 22.356794357299805, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3494, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05749143477897552, | |
| "grad_norm": 22.970012664794922, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.2914, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.05882844489011448, | |
| "grad_norm": 25.380735397338867, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2244, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.06016545500125345, | |
| "grad_norm": 25.606966018676758, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.2434, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.061502465112392414, | |
| "grad_norm": 26.491294860839844, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2931, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06283947522353138, | |
| "grad_norm": 29.655942916870117, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3152, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06417648533467034, | |
| "grad_norm": 29.71782875061035, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.1351, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06551349544580931, | |
| "grad_norm": 34.75334548950195, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.2264, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06685050555694827, | |
| "grad_norm": 47.528446197509766, | |
| "learning_rate": 0.0, | |
| "loss": 1.2762, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06685050555694827, | |
| "eval_loss": 1.338729977607727, | |
| "eval_runtime": 145.7924, | |
| "eval_samples_per_second": 34.563, | |
| "eval_steps_per_second": 4.321, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |