| { | |
| "best_metric": 0.08695371448993683, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1759788825340959, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0035195776506819184, | |
| "grad_norm": 0.7145345211029053, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4861, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0035195776506819184, | |
| "eval_loss": 0.6669037342071533, | |
| "eval_runtime": 2.4691, | |
| "eval_samples_per_second": 20.25, | |
| "eval_steps_per_second": 5.265, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007039155301363837, | |
| "grad_norm": 0.7979465126991272, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5478, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010558732952045754, | |
| "grad_norm": 0.7627394795417786, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.5323, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014078310602727673, | |
| "grad_norm": 0.47743260860443115, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.3732, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01759788825340959, | |
| "grad_norm": 0.5068439841270447, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.2793, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02111746590409151, | |
| "grad_norm": 0.5551760196685791, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.1954, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024637043554773426, | |
| "grad_norm": 0.2108476608991623, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.1348, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.028156621205455347, | |
| "grad_norm": 0.1400616466999054, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.1213, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03167619885613726, | |
| "grad_norm": 0.13035763800144196, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.1176, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03519577650681918, | |
| "grad_norm": 0.09439640492200851, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.1127, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0387153541575011, | |
| "grad_norm": 0.129567950963974, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.1069, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04223493180818302, | |
| "grad_norm": 0.5033031105995178, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.1186, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04575450945886494, | |
| "grad_norm": 0.20445086061954498, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.1114, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04927408710954685, | |
| "grad_norm": 0.5134371519088745, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.1248, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05279366476022877, | |
| "grad_norm": 0.25513920187950134, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.1187, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.056313242410910694, | |
| "grad_norm": 0.36205729842185974, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.1169, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05983282006159261, | |
| "grad_norm": 0.2975631058216095, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.1144, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06335239771227452, | |
| "grad_norm": 0.09141319990158081, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.1056, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06687197536295644, | |
| "grad_norm": 0.2522970139980316, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.1038, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.07039155301363836, | |
| "grad_norm": 0.1794099658727646, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.1071, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07391113066432028, | |
| "grad_norm": 0.08568066358566284, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.1061, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0774307083150022, | |
| "grad_norm": 0.24917910993099213, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.1078, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.08095028596568411, | |
| "grad_norm": 0.13816817104816437, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.0968, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.08446986361636603, | |
| "grad_norm": 0.25170326232910156, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.0961, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08798944126704795, | |
| "grad_norm": 0.23660145699977875, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0986, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08798944126704795, | |
| "eval_loss": 0.09295430034399033, | |
| "eval_runtime": 1.8366, | |
| "eval_samples_per_second": 27.224, | |
| "eval_steps_per_second": 7.078, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.09150901891772988, | |
| "grad_norm": 0.40268394351005554, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.1017, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0950285965684118, | |
| "grad_norm": 0.3160291016101837, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.1101, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0985481742190937, | |
| "grad_norm": 0.07668313384056091, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.1038, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.10206775186977562, | |
| "grad_norm": 0.24542756378650665, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.1077, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.10558732952045755, | |
| "grad_norm": 0.2892981767654419, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.108, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10910690717113947, | |
| "grad_norm": 0.1468868851661682, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.0987, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.11262648482182139, | |
| "grad_norm": 0.06367430090904236, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1001, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1161460624725033, | |
| "grad_norm": 0.13880383968353271, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.0972, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11966564012318522, | |
| "grad_norm": 0.07297297567129135, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.0942, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.12318521777386714, | |
| "grad_norm": 0.09036003053188324, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.0938, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.12670479542454904, | |
| "grad_norm": 0.06856901943683624, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.0921, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.13022437307523096, | |
| "grad_norm": 0.15229707956314087, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.088, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.13374395072591289, | |
| "grad_norm": 0.14902161061763763, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.0885, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.1372635283765948, | |
| "grad_norm": 0.18551306426525116, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1012, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.14078310602727673, | |
| "grad_norm": 0.17542138695716858, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.0988, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14430268367795865, | |
| "grad_norm": 0.05021262913942337, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.098, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.14782226132864057, | |
| "grad_norm": 0.07619772106409073, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.1022, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1513418389793225, | |
| "grad_norm": 0.08549729734659195, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.0973, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1548614166300044, | |
| "grad_norm": 0.16657781600952148, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.1013, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1583809942806863, | |
| "grad_norm": 0.06948012858629227, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.0929, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.16190057193136823, | |
| "grad_norm": 0.13890503346920013, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.0926, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.16542014958205015, | |
| "grad_norm": 0.14210690557956696, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0889, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.16893972723273207, | |
| "grad_norm": 0.19957098364830017, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0907, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.172459304883414, | |
| "grad_norm": 0.1634853184223175, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0877, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1759788825340959, | |
| "grad_norm": 0.17324256896972656, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0856, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1759788825340959, | |
| "eval_loss": 0.08695371448993683, | |
| "eval_runtime": 1.8302, | |
| "eval_samples_per_second": 27.319, | |
| "eval_steps_per_second": 7.103, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |