| { | |
| "best_metric": 0.8260481357574463, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7162041181736795, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01432408236347359, | |
| "grad_norm": 0.09537966549396515, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01432408236347359, | |
| "eval_loss": 1.2682228088378906, | |
| "eval_runtime": 26.3318, | |
| "eval_samples_per_second": 17.849, | |
| "eval_steps_per_second": 2.241, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02864816472694718, | |
| "grad_norm": 0.10723049938678741, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8215, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.04297224709042077, | |
| "grad_norm": 0.11505736410617828, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.788, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05729632945389436, | |
| "grad_norm": 0.10366005450487137, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.853, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07162041181736795, | |
| "grad_norm": 0.1099310964345932, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9151, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08594449418084155, | |
| "grad_norm": 0.13684609532356262, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8355, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.10026857654431513, | |
| "grad_norm": 0.17738723754882812, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9252, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.11459265890778872, | |
| "grad_norm": 0.18676184117794037, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9054, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.12891674127126232, | |
| "grad_norm": 0.16536663472652435, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8355, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1432408236347359, | |
| "grad_norm": 0.1593295782804489, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8895, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1575649059982095, | |
| "grad_norm": 0.19863909482955933, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0104, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1718889883616831, | |
| "grad_norm": 0.23164160549640656, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0904, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.18621307072515667, | |
| "grad_norm": 0.09914696961641312, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.7302, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.20053715308863027, | |
| "grad_norm": 0.11318004876375198, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8218, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.21486123545210384, | |
| "grad_norm": 0.1315881907939911, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7987, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.22918531781557744, | |
| "grad_norm": 0.12444476038217545, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.8093, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.24350940017905104, | |
| "grad_norm": 0.1274099349975586, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7724, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.25783348254252464, | |
| "grad_norm": 0.11214341968297958, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.7323, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2721575649059982, | |
| "grad_norm": 0.12426099181175232, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.876, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2864816472694718, | |
| "grad_norm": 0.12057890743017197, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7956, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3008057296329454, | |
| "grad_norm": 0.14142070710659027, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.833, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.315129811996419, | |
| "grad_norm": 0.14428313076496124, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8417, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3294538943598926, | |
| "grad_norm": 0.18170873820781708, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9364, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.3437779767233662, | |
| "grad_norm": 0.21552841365337372, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0173, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.35810205908683973, | |
| "grad_norm": 0.34762731194496155, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1559, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35810205908683973, | |
| "eval_loss": 0.8497164845466614, | |
| "eval_runtime": 26.2821, | |
| "eval_samples_per_second": 17.883, | |
| "eval_steps_per_second": 2.245, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.37242614145031333, | |
| "grad_norm": 0.06810956448316574, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7427, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.38675022381378693, | |
| "grad_norm": 0.07532549649477005, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.844, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.40107430617726053, | |
| "grad_norm": 0.08530668914318085, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7301, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.41539838854073413, | |
| "grad_norm": 0.09383714199066162, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.746, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.4297224709042077, | |
| "grad_norm": 0.10356415808200836, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7789, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4440465532676813, | |
| "grad_norm": 0.137028768658638, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7823, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.4583706356311549, | |
| "grad_norm": 0.1444852352142334, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8793, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4726947179946285, | |
| "grad_norm": 0.14780306816101074, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.8477, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.4870188003581021, | |
| "grad_norm": 0.16937947273254395, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8519, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.5013428827215757, | |
| "grad_norm": 0.16218450665473938, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8925, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5156669650850493, | |
| "grad_norm": 0.1833808720111847, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8988, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5299910474485229, | |
| "grad_norm": 0.22939519584178925, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9816, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5443151298119964, | |
| "grad_norm": 0.08518178761005402, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8183, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.55863921217547, | |
| "grad_norm": 0.07068660110235214, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8179, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5729632945389436, | |
| "grad_norm": 0.08099059760570526, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.8127, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5872873769024172, | |
| "grad_norm": 0.08545270562171936, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7382, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6016114592658908, | |
| "grad_norm": 0.09283125400543213, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7788, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6159355416293644, | |
| "grad_norm": 0.10766535252332687, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7369, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.630259623992838, | |
| "grad_norm": 0.13231581449508667, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.788, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.6445837063563116, | |
| "grad_norm": 0.1386619359254837, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7723, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.6589077887197852, | |
| "grad_norm": 0.14434082806110382, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7922, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6732318710832588, | |
| "grad_norm": 0.16179312765598297, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8169, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6875559534467324, | |
| "grad_norm": 0.1684214323759079, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8452, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7018800358102059, | |
| "grad_norm": 0.19974979758262634, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9585, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7162041181736795, | |
| "grad_norm": 0.3124803304672241, | |
| "learning_rate": 0.0, | |
| "loss": 1.142, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7162041181736795, | |
| "eval_loss": 0.8260481357574463, | |
| "eval_runtime": 26.2734, | |
| "eval_samples_per_second": 17.889, | |
| "eval_steps_per_second": 2.246, | |
| "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": 1.1160183123759596e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |