| { | |
| "best_metric": 0.6340692639350891, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8519701810436635, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01703940362087327, | |
| "grad_norm": 1.1253975629806519, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7304, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01703940362087327, | |
| "eval_loss": 1.23331880569458, | |
| "eval_runtime": 2.7252, | |
| "eval_samples_per_second": 144.945, | |
| "eval_steps_per_second": 18.348, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03407880724174654, | |
| "grad_norm": 1.4747626781463623, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9722, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.051118210862619806, | |
| "grad_norm": 1.5503989458084106, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.9206, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06815761448349308, | |
| "grad_norm": 1.3072794675827026, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.9335, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08519701810436635, | |
| "grad_norm": 1.7780901193618774, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9484, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10223642172523961, | |
| "grad_norm": 1.6759884357452393, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8925, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.11927582534611289, | |
| "grad_norm": 1.150227665901184, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9145, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13631522896698617, | |
| "grad_norm": 1.083517074584961, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7482, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15335463258785942, | |
| "grad_norm": 1.2330025434494019, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.798, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1703940362087327, | |
| "grad_norm": 1.149918556213379, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8889, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18743343982960597, | |
| "grad_norm": 1.3855211734771729, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9212, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20447284345047922, | |
| "grad_norm": 2.3649160861968994, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.045, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2215122470713525, | |
| "grad_norm": 0.8039005398750305, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6179, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23855165069222578, | |
| "grad_norm": 0.759940505027771, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6646, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.25559105431309903, | |
| "grad_norm": 0.6969624757766724, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27263045793397234, | |
| "grad_norm": 0.6444242596626282, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.6824, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2896698615548456, | |
| "grad_norm": 0.6221126317977905, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6962, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.30670926517571884, | |
| "grad_norm": 0.6093760132789612, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7194, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.32374866879659214, | |
| "grad_norm": 0.7189542055130005, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.835, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3407880724174654, | |
| "grad_norm": 0.8055925369262695, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.779, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.35782747603833864, | |
| "grad_norm": 0.7645823955535889, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7841, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.37486687965921195, | |
| "grad_norm": 0.8412889242172241, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7011, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3919062832800852, | |
| "grad_norm": 0.8904260396957397, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8003, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.40894568690095845, | |
| "grad_norm": 1.0720586776733398, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.708, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.42598509052183176, | |
| "grad_norm": 2.1021010875701904, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.8147, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.42598509052183176, | |
| "eval_loss": 0.6534027457237244, | |
| "eval_runtime": 2.7241, | |
| "eval_samples_per_second": 145.0, | |
| "eval_steps_per_second": 18.354, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.443024494142705, | |
| "grad_norm": 0.4085734486579895, | |
| "learning_rate": 5e-05, | |
| "loss": 0.489, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.46006389776357826, | |
| "grad_norm": 0.5824640989303589, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5703, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.47710330138445156, | |
| "grad_norm": 0.5090480446815491, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.6093, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4941427050053248, | |
| "grad_norm": 0.581184983253479, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.6804, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5111821086261981, | |
| "grad_norm": 0.5396629571914673, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5947, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5282215122470714, | |
| "grad_norm": 0.6579256653785706, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.739, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5452609158679447, | |
| "grad_norm": 0.8383941650390625, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.777, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5623003194888179, | |
| "grad_norm": 0.760420560836792, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.648, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5793397231096912, | |
| "grad_norm": 0.8806910514831543, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.7601, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5963791267305645, | |
| "grad_norm": 0.8053391575813293, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.684, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6134185303514377, | |
| "grad_norm": 0.9814860820770264, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.7502, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.630457933972311, | |
| "grad_norm": 1.2074640989303589, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.7318, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6474973375931843, | |
| "grad_norm": 0.5072846412658691, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4753, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6645367412140575, | |
| "grad_norm": 0.528431236743927, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.655, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6815761448349308, | |
| "grad_norm": 0.5640473365783691, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6813, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6986155484558041, | |
| "grad_norm": 0.5057714581489563, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4823, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7156549520766773, | |
| "grad_norm": 0.6331304311752319, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5428, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7326943556975506, | |
| "grad_norm": 0.6265454888343811, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6965, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7497337593184239, | |
| "grad_norm": 0.7418725490570068, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8041, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7667731629392971, | |
| "grad_norm": 0.681201696395874, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7309, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7838125665601704, | |
| "grad_norm": 0.6290284395217896, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5944, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8008519701810437, | |
| "grad_norm": 0.8113570809364319, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.6793, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8178913738019169, | |
| "grad_norm": 0.9687185287475586, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.7957, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8349307774227902, | |
| "grad_norm": 1.0296266078948975, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.7558, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8519701810436635, | |
| "grad_norm": 1.4596647024154663, | |
| "learning_rate": 0.0, | |
| "loss": 0.8699, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8519701810436635, | |
| "eval_loss": 0.6340692639350891, | |
| "eval_runtime": 2.7254, | |
| "eval_samples_per_second": 144.935, | |
| "eval_steps_per_second": 18.346, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |