| { | |
| "best_metric": 0.3631051480770111, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.8398169336384438, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.036613272311212815, | |
| "grad_norm": 0.32250547409057617, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7014, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.036613272311212815, | |
| "eval_loss": 0.9680460095405579, | |
| "eval_runtime": 5.1865, | |
| "eval_samples_per_second": 35.476, | |
| "eval_steps_per_second": 4.435, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07322654462242563, | |
| "grad_norm": 0.4020719826221466, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7634, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.10983981693363844, | |
| "grad_norm": 0.4104273021221161, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.7494, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.14645308924485126, | |
| "grad_norm": 0.28879839181900024, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.6925, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.18306636155606407, | |
| "grad_norm": 0.2854153513908386, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.7343, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.21967963386727687, | |
| "grad_norm": 0.40884876251220703, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.7694, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2562929061784897, | |
| "grad_norm": 0.2876134216785431, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.6223, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2929061784897025, | |
| "grad_norm": 0.20996485650539398, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4902, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3295194508009153, | |
| "grad_norm": 0.2512865364551544, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4585, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.36613272311212813, | |
| "grad_norm": 0.28524497151374817, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.4061, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.40274599542334094, | |
| "grad_norm": 0.27074134349823, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4413, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.43935926773455375, | |
| "grad_norm": 0.28311052918434143, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.4968, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4759725400457666, | |
| "grad_norm": 0.3166552484035492, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5135, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5125858123569794, | |
| "grad_norm": 0.2158898264169693, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4413, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5491990846681922, | |
| "grad_norm": 0.21108894050121307, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4028, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.585812356979405, | |
| "grad_norm": 0.17739154398441315, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3421, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6224256292906178, | |
| "grad_norm": 0.15188650786876678, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3295, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6590389016018307, | |
| "grad_norm": 0.1504863202571869, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3605, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.210085928440094, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4134, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7322654462242563, | |
| "grad_norm": 0.30477142333984375, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4139, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7688787185354691, | |
| "grad_norm": 0.12143126130104065, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3609, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8054919908466819, | |
| "grad_norm": 0.1495080590248108, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.3269, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.1595747321844101, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3066, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.8787185354691075, | |
| "grad_norm": 0.15651889145374298, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.3045, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9153318077803204, | |
| "grad_norm": 0.13724884390830994, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3258, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9153318077803204, | |
| "eval_loss": 0.40415117144584656, | |
| "eval_runtime": 5.1906, | |
| "eval_samples_per_second": 35.448, | |
| "eval_steps_per_second": 4.431, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9519450800915332, | |
| "grad_norm": 0.15927977859973907, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3694, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.988558352402746, | |
| "grad_norm": 0.22202396392822266, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4189, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.034324942791762, | |
| "grad_norm": 0.2729898989200592, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7635, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.070938215102975, | |
| "grad_norm": 0.12082233279943466, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3147, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1075514874141876, | |
| "grad_norm": 0.1213618814945221, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2839, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1441647597254005, | |
| "grad_norm": 0.13045448064804077, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2742, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.1807780320366132, | |
| "grad_norm": 0.15795262157917023, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.3233, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2173913043478262, | |
| "grad_norm": 0.1785769909620285, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.3381, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.2540045766590389, | |
| "grad_norm": 0.16711662709712982, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4122, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.2906178489702518, | |
| "grad_norm": 0.1267433911561966, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.335, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3272311212814645, | |
| "grad_norm": 0.11527062207460403, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2862, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.3638443935926774, | |
| "grad_norm": 0.11933337897062302, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2703, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.40045766590389, | |
| "grad_norm": 0.13421335816383362, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2857, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.437070938215103, | |
| "grad_norm": 0.15082192420959473, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.3248, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.4736842105263157, | |
| "grad_norm": 0.19551853835582733, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.349, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5102974828375286, | |
| "grad_norm": 0.13802577555179596, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.3084, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.5469107551487413, | |
| "grad_norm": 0.12603098154067993, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.3111, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.5835240274599542, | |
| "grad_norm": 0.11855199933052063, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2727, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6201372997711672, | |
| "grad_norm": 0.12961673736572266, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2666, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.6567505720823799, | |
| "grad_norm": 0.13719911873340607, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.3096, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.6933638443935926, | |
| "grad_norm": 0.16374927759170532, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.3387, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.7299771167048055, | |
| "grad_norm": 0.21558819711208344, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.3526, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.7665903890160184, | |
| "grad_norm": 0.11992810666561127, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.3078, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.803203661327231, | |
| "grad_norm": 0.12123319506645203, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.3008, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.8398169336384438, | |
| "grad_norm": 0.11846727877855301, | |
| "learning_rate": 0.0, | |
| "loss": 0.279, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.8398169336384438, | |
| "eval_loss": 0.3631051480770111, | |
| "eval_runtime": 5.1867, | |
| "eval_samples_per_second": 35.476, | |
| "eval_steps_per_second": 4.434, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.6855709765074944e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |