| { | |
| "best_metric": 0.7669674754142761, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.1265022137887413, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002530044275774826, | |
| "grad_norm": 0.5878192186355591, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6514, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002530044275774826, | |
| "eval_loss": 1.063130497932434, | |
| "eval_runtime": 182.3575, | |
| "eval_samples_per_second": 14.603, | |
| "eval_steps_per_second": 1.826, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005060088551549652, | |
| "grad_norm": 0.707244336605072, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7736, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007590132827324478, | |
| "grad_norm": 0.6830605864524841, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.8633, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010120177103099304, | |
| "grad_norm": 0.5913272500038147, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.8182, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01265022137887413, | |
| "grad_norm": 0.6596630215644836, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.8601, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015180265654648957, | |
| "grad_norm": 0.5458433032035828, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.8256, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017710309930423784, | |
| "grad_norm": 0.5810830593109131, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.7865, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02024035420619861, | |
| "grad_norm": 0.6840958595275879, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8018, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022770398481973434, | |
| "grad_norm": 0.7228375673294067, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8826, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02530044275774826, | |
| "grad_norm": 0.7571236491203308, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.8623, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.027830487033523088, | |
| "grad_norm": 1.1499253511428833, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9005, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.030360531309297913, | |
| "grad_norm": 1.1630706787109375, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.9637, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03289057558507274, | |
| "grad_norm": 0.5038442611694336, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5401, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03542061986084757, | |
| "grad_norm": 0.44013500213623047, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6083, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03795066413662239, | |
| "grad_norm": 0.5487754344940186, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7349, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04048070841239722, | |
| "grad_norm": 0.45551809668540955, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7123, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.043010752688172046, | |
| "grad_norm": 0.4125840365886688, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7482, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04554079696394687, | |
| "grad_norm": 0.4445502758026123, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8046, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0480708412397217, | |
| "grad_norm": 0.4875430166721344, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7529, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05060088551549652, | |
| "grad_norm": 0.5528565645217896, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7704, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05313092979127135, | |
| "grad_norm": 0.6151865124702454, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.739, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055660974067046176, | |
| "grad_norm": 0.7081171870231628, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.7436, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.058191018342821, | |
| "grad_norm": 0.8696717023849487, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.8288, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06072106261859583, | |
| "grad_norm": 0.9304735660552979, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.919, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06325110689437065, | |
| "grad_norm": 1.3492540121078491, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.942, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06325110689437065, | |
| "eval_loss": 0.7933292388916016, | |
| "eval_runtime": 178.6076, | |
| "eval_samples_per_second": 14.91, | |
| "eval_steps_per_second": 1.864, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06578115117014548, | |
| "grad_norm": 0.3085412085056305, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5028, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0683111954459203, | |
| "grad_norm": 0.4568122923374176, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.709, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07084123972169513, | |
| "grad_norm": 0.4451022148132324, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7108, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07337128399746995, | |
| "grad_norm": 0.44292229413986206, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7233, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07590132827324478, | |
| "grad_norm": 0.5089272856712341, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7952, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 0.4563312828540802, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7415, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08096141682479444, | |
| "grad_norm": 0.4483792185783386, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7205, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08349146110056926, | |
| "grad_norm": 0.48972287774086, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7487, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 0.5764914751052856, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8205, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08855154965211891, | |
| "grad_norm": 0.710080087184906, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.7891, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09108159392789374, | |
| "grad_norm": 0.8010451197624207, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.8268, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09361163820366857, | |
| "grad_norm": 1.0116633176803589, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.8728, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0961416824794434, | |
| "grad_norm": 0.4091106057167053, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5207, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09867172675521822, | |
| "grad_norm": 0.2687011957168579, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5985, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10120177103099304, | |
| "grad_norm": 0.30941206216812134, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6427, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10373181530676787, | |
| "grad_norm": 0.3291284441947937, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.6819, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1062618595825427, | |
| "grad_norm": 0.3654635548591614, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7387, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10879190385831752, | |
| "grad_norm": 0.37484773993492126, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7585, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11132194813409235, | |
| "grad_norm": 0.39777594804763794, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7547, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11385199240986717, | |
| "grad_norm": 0.4498005509376526, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7332, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.116382036685642, | |
| "grad_norm": 0.4953252077102661, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.7556, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11891208096141682, | |
| "grad_norm": 0.5951145887374878, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.7668, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12144212523719165, | |
| "grad_norm": 0.7458454966545105, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.828, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12397216951296648, | |
| "grad_norm": 0.9640898704528809, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9184, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.1265022137887413, | |
| "grad_norm": 1.3981536626815796, | |
| "learning_rate": 0.0, | |
| "loss": 1.0085, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1265022137887413, | |
| "eval_loss": 0.7669674754142761, | |
| "eval_runtime": 176.9953, | |
| "eval_samples_per_second": 15.046, | |
| "eval_steps_per_second": 1.881, | |
| "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": 5.833339884672123e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |