| { | |
| "best_metric": 0.7887606024742126, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.150537634408602, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 9.390022277832031, | |
| "learning_rate": 5e-05, | |
| "loss": 13.6544, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "eval_loss": 13.57972526550293, | |
| "eval_runtime": 7.9896, | |
| "eval_samples_per_second": 19.651, | |
| "eval_steps_per_second": 2.503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 8.494207382202148, | |
| "learning_rate": 0.0001, | |
| "loss": 13.6314, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 6.406372547149658, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 13.4276, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 8.096014976501465, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 12.3224, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.21505376344086022, | |
| "grad_norm": 7.721968650817871, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 9.8171, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 7.150884628295898, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 9.2711, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3010752688172043, | |
| "grad_norm": 11.189762115478516, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.1233, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 6.991576671600342, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.7885, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 6.144765377044678, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.3918, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 14.851336479187012, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.0556, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4731182795698925, | |
| "grad_norm": 11.841018676757812, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 4.6789, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 5.690128803253174, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.1764, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5591397849462365, | |
| "grad_norm": 4.6572041511535645, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.6003, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6021505376344086, | |
| "grad_norm": 4.771907806396484, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2353, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 5.913241863250732, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.3812, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 6.0179443359375, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.3913, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7311827956989247, | |
| "grad_norm": 4.213968276977539, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.2393, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 2.8896896839141846, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.0148, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8172043010752689, | |
| "grad_norm": 3.7044646739959717, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.5697, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 3.8937833309173584, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8261, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 2.872431993484497, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.4156, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.946236559139785, | |
| "grad_norm": 2.7304794788360596, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.2915, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.989247311827957, | |
| "grad_norm": 2.295313835144043, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.3503, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 8.538825988769531, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.7392, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.075268817204301, | |
| "grad_norm": 5.440336227416992, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.7914, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.075268817204301, | |
| "eval_loss": 1.0806931257247925, | |
| "eval_runtime": 7.9548, | |
| "eval_samples_per_second": 19.736, | |
| "eval_steps_per_second": 2.514, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.118279569892473, | |
| "grad_norm": 4.576476097106934, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2379, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.1612903225806452, | |
| "grad_norm": 3.7548060417175293, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0289, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2043010752688172, | |
| "grad_norm": 3.2624807357788086, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9353, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.2473118279569892, | |
| "grad_norm": 5.262892246246338, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.3024, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 3.8155572414398193, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9858, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 4.295482158660889, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0545, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.3763440860215055, | |
| "grad_norm": 2.9629807472229004, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1583, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.4193548387096775, | |
| "grad_norm": 3.3191750049591064, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9557, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.4623655913978495, | |
| "grad_norm": 2.754456043243408, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8508, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5053763440860215, | |
| "grad_norm": 2.761148691177368, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.0884, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 2.2412075996398926, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.702, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.5913978494623655, | |
| "grad_norm": 3.087839365005493, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8207, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.6344086021505375, | |
| "grad_norm": 2.7227118015289307, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.909, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.6774193548387095, | |
| "grad_norm": 2.712979555130005, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.8866, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7204301075268817, | |
| "grad_norm": 2.3975188732147217, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.7952, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.7634408602150538, | |
| "grad_norm": 2.380941152572632, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.8558, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8064516129032258, | |
| "grad_norm": 1.8597089052200317, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.6109, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.849462365591398, | |
| "grad_norm": 3.6962974071502686, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7898, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.89247311827957, | |
| "grad_norm": 3.9587137699127197, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.906, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": 1.634704351425171, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7133, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.978494623655914, | |
| "grad_norm": 2.543936014175415, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.8129, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.021505376344086, | |
| "grad_norm": 5.290590286254883, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3649, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.064516129032258, | |
| "grad_norm": 1.4306670427322388, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.6567, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.10752688172043, | |
| "grad_norm": 2.4674768447875977, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8203, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "grad_norm": 1.742997407913208, | |
| "learning_rate": 0.0, | |
| "loss": 0.8144, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.150537634408602, | |
| "eval_loss": 0.7887606024742126, | |
| "eval_runtime": 7.9519, | |
| "eval_samples_per_second": 19.744, | |
| "eval_steps_per_second": 2.515, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.0627374735425536e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |