| { | |
| "best_metric": 2.4847590923309326, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04501969611705121, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009003939223410242, | |
| "grad_norm": 0.2935332953929901, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5246, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009003939223410242, | |
| "eval_loss": 2.7960000038146973, | |
| "eval_runtime": 85.5902, | |
| "eval_samples_per_second": 87.428, | |
| "eval_steps_per_second": 10.936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018007878446820484, | |
| "grad_norm": 0.31910693645477295, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7258, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0027011817670230726, | |
| "grad_norm": 0.33405545353889465, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.7225, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0036015756893640967, | |
| "grad_norm": 0.31301429867744446, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.7345, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004501969611705121, | |
| "grad_norm": 0.2616855204105377, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.5751, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005402363534046145, | |
| "grad_norm": 0.264691025018692, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.5743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006302757456387169, | |
| "grad_norm": 0.28072842955589294, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.6825, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007203151378728193, | |
| "grad_norm": 0.28742966055870056, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.632, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008103545301069218, | |
| "grad_norm": 0.27740779519081116, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.5428, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009003939223410242, | |
| "grad_norm": 0.2890505790710449, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.674, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009904333145751266, | |
| "grad_norm": 0.2683861553668976, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.6376, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01080472706809229, | |
| "grad_norm": 0.3053511381149292, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.6566, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011705120990433315, | |
| "grad_norm": 0.3369949758052826, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.6017, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012605514912774339, | |
| "grad_norm": 0.348676472902298, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4501, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013505908835115363, | |
| "grad_norm": 0.29540905356407166, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.5762, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014406302757456387, | |
| "grad_norm": 0.27232328057289124, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.4559, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.015306696679797411, | |
| "grad_norm": 0.267428994178772, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5221, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.016207090602138437, | |
| "grad_norm": 0.2593449652194977, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.5985, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01710748452447946, | |
| "grad_norm": 0.29024699330329895, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.5037, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.018007878446820485, | |
| "grad_norm": 0.3114057183265686, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4805, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018908272369161507, | |
| "grad_norm": 0.31037384271621704, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.5172, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019808666291502533, | |
| "grad_norm": 0.3149888515472412, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.5971, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020709060213843555, | |
| "grad_norm": 0.3053635060787201, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.616, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02160945413618458, | |
| "grad_norm": 0.3033860921859741, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.4654, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.022509848058525603, | |
| "grad_norm": 0.43421122431755066, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.6261, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022509848058525603, | |
| "eval_loss": 2.515045642852783, | |
| "eval_runtime": 85.3241, | |
| "eval_samples_per_second": 87.701, | |
| "eval_steps_per_second": 10.97, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02341024198086663, | |
| "grad_norm": 0.23387306928634644, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3543, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.024310635903207655, | |
| "grad_norm": 0.2605088949203491, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.5719, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.025211029825548677, | |
| "grad_norm": 0.25959137082099915, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.5124, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.026111423747889703, | |
| "grad_norm": 0.277042955160141, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.4706, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.027011817670230726, | |
| "grad_norm": 0.33254826068878174, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.4795, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02791221159257175, | |
| "grad_norm": 0.2666430175304413, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.3948, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.028812605514912774, | |
| "grad_norm": 0.2859417498111725, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3231, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0297129994372538, | |
| "grad_norm": 0.2585482597351074, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.4618, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.030613393359594822, | |
| "grad_norm": 0.27401846647262573, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.4809, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.031513787281935844, | |
| "grad_norm": 0.2689136862754822, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.5238, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03241418120427687, | |
| "grad_norm": 0.28383877873420715, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.5349, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.033314575126617896, | |
| "grad_norm": 0.3058584928512573, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.5093, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03421496904895892, | |
| "grad_norm": 0.2748225927352905, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4525, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03511536297129994, | |
| "grad_norm": 0.2352573424577713, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.4571, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03601575689364097, | |
| "grad_norm": 0.24772126972675323, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.4815, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03691615081598199, | |
| "grad_norm": 0.2468077391386032, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.3734, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.037816544738323014, | |
| "grad_norm": 0.25353872776031494, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.4168, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.038716938660664044, | |
| "grad_norm": 0.2523353099822998, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.4197, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.039617332583005066, | |
| "grad_norm": 0.2582724988460541, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.492, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04051772650534609, | |
| "grad_norm": 0.25668585300445557, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.4805, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04141812042768711, | |
| "grad_norm": 0.2525278329849243, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.4749, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04231851435002814, | |
| "grad_norm": 0.2551382780075073, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.4707, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04321890827236916, | |
| "grad_norm": 0.2634233236312866, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.4281, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.044119302194710185, | |
| "grad_norm": 0.25443539023399353, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.434, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04501969611705121, | |
| "grad_norm": 0.37525126338005066, | |
| "learning_rate": 0.0, | |
| "loss": 2.6176, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04501969611705121, | |
| "eval_loss": 2.4847590923309326, | |
| "eval_runtime": 85.0851, | |
| "eval_samples_per_second": 87.947, | |
| "eval_steps_per_second": 11.001, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |