| { | |
| "best_metric": 0.22318783402442932, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.06389266033064452, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012778532066128904, | |
| "grad_norm": 2.9149091243743896, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1476, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012778532066128904, | |
| "eval_loss": 5.142962455749512, | |
| "eval_runtime": 260.5184, | |
| "eval_samples_per_second": 20.237, | |
| "eval_steps_per_second": 2.53, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002555706413225781, | |
| "grad_norm": 3.029045581817627, | |
| "learning_rate": 0.0001, | |
| "loss": 5.5751, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003833559619838671, | |
| "grad_norm": 3.0204575061798096, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.377, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005111412826451562, | |
| "grad_norm": 3.8094005584716797, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.4789, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006389266033064452, | |
| "grad_norm": 4.571749210357666, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.6771, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.007667119239677342, | |
| "grad_norm": 4.94711971282959, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.3963, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008944972446290233, | |
| "grad_norm": 3.147123336791992, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.463, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010222825652903124, | |
| "grad_norm": 2.149303436279297, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8673, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.011500678859516012, | |
| "grad_norm": 1.475569486618042, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6686, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012778532066128903, | |
| "grad_norm": 0.9012019038200378, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.516, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014056385272741794, | |
| "grad_norm": 0.5875328183174133, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.242, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.015334238479354684, | |
| "grad_norm": 0.9414550065994263, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.2606, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016612091685967573, | |
| "grad_norm": 1.3743778467178345, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6511, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.017889944892580466, | |
| "grad_norm": 1.4236531257629395, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6336, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.019167798099193355, | |
| "grad_norm": 1.0116318464279175, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.504, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.020445651305806247, | |
| "grad_norm": 0.8130444288253784, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.411, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.021723504512419136, | |
| "grad_norm": 0.7510324120521545, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3096, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.023001357719032025, | |
| "grad_norm": 0.6893289685249329, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.3072, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024279210925644917, | |
| "grad_norm": 0.6318802833557129, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.2202, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.025557064132257806, | |
| "grad_norm": 0.7694609761238098, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2574, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0268349173388707, | |
| "grad_norm": 0.5977926254272461, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.2059, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.028112770545483588, | |
| "grad_norm": 0.47472697496414185, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.175, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.029390623752096477, | |
| "grad_norm": 0.41430801153182983, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1163, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03066847695870937, | |
| "grad_norm": 0.40955567359924316, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.1113, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03194633016532226, | |
| "grad_norm": 0.5556414127349854, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0941, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03194633016532226, | |
| "eval_loss": 0.27160951495170593, | |
| "eval_runtime": 261.4147, | |
| "eval_samples_per_second": 20.167, | |
| "eval_steps_per_second": 2.521, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03322418337193515, | |
| "grad_norm": 1.3373982906341553, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7826, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03450203657854804, | |
| "grad_norm": 0.9719566702842712, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4262, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03577988978516093, | |
| "grad_norm": 0.765075147151947, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.3854, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.03705774299177382, | |
| "grad_norm": 0.6298338770866394, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2725, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.03833559619838671, | |
| "grad_norm": 0.47626811265945435, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2295, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0396134494049996, | |
| "grad_norm": 0.5751525163650513, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.1672, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.040891302611612494, | |
| "grad_norm": 0.5069852471351624, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1841, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.04216915581822538, | |
| "grad_norm": 0.41022780537605286, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.1478, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04344700902483827, | |
| "grad_norm": 0.38475725054740906, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.145, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.04472486223145116, | |
| "grad_norm": 0.373092919588089, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.1286, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04600271543806405, | |
| "grad_norm": 0.4084884822368622, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1228, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.047280568644676946, | |
| "grad_norm": 0.27328649163246155, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0774, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.048558421851289835, | |
| "grad_norm": 0.801368236541748, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4248, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.049836275057902724, | |
| "grad_norm": 0.6625673770904541, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4589, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05111412826451561, | |
| "grad_norm": 0.5224865674972534, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.3141, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0523919814711285, | |
| "grad_norm": 0.43287745118141174, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2324, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0536698346777414, | |
| "grad_norm": 0.5098556876182556, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2153, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.054947687884354286, | |
| "grad_norm": 0.3898968994617462, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.1755, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.056225541090967175, | |
| "grad_norm": 0.42298492789268494, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2038, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.057503394297580064, | |
| "grad_norm": 0.3861464262008667, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.1561, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.05878124750419295, | |
| "grad_norm": 0.47179993987083435, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1717, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06005910071080585, | |
| "grad_norm": 0.46367916464805603, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1962, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06133695391741874, | |
| "grad_norm": 0.4226861298084259, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.1628, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.06261480712403163, | |
| "grad_norm": 0.2117103934288025, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0521, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06389266033064452, | |
| "grad_norm": 0.3646078109741211, | |
| "learning_rate": 0.0, | |
| "loss": 0.0666, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06389266033064452, | |
| "eval_loss": 0.22318783402442932, | |
| "eval_runtime": 262.3219, | |
| "eval_samples_per_second": 20.097, | |
| "eval_steps_per_second": 2.512, | |
| "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": 1.0282699722976133e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |