| { | |
| "best_metric": 3.0068626403808594, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.9564164648910412, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0387409200968523, | |
| "grad_norm": 6.9472174644470215, | |
| "learning_rate": 5e-05, | |
| "loss": 5.0957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0387409200968523, | |
| "eval_loss": 4.447319984436035, | |
| "eval_runtime": 11.9217, | |
| "eval_samples_per_second": 14.595, | |
| "eval_steps_per_second": 1.845, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0774818401937046, | |
| "grad_norm": 6.7599897384643555, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3702, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1162227602905569, | |
| "grad_norm": 6.047508716583252, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.9169, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1549636803874092, | |
| "grad_norm": 8.235490798950195, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.4562, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1937046004842615, | |
| "grad_norm": 2.4021806716918945, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.0775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.2324455205811138, | |
| "grad_norm": 6.199411869049072, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.0516, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 4.084719657897949, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.794, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3099273607748184, | |
| "grad_norm": 2.1793830394744873, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.3725, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.3486682808716707, | |
| "grad_norm": 1.2195143699645996, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.1819, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.387409200968523, | |
| "grad_norm": 1.0480231046676636, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.0885, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4261501210653753, | |
| "grad_norm": 0.7510465979576111, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.9443, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4648910411622276, | |
| "grad_norm": 1.0025348663330078, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.7681, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5036319612590799, | |
| "grad_norm": 0.9004942178726196, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.329, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 1.3278800249099731, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.4889, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5811138014527845, | |
| "grad_norm": 1.0272107124328613, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.1198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6198547215496368, | |
| "grad_norm": 0.7518178224563599, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 3.0856, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6585956416464891, | |
| "grad_norm": 1.1100701093673706, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.0419, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6973365617433414, | |
| "grad_norm": 0.9645322561264038, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.835, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7360774818401937, | |
| "grad_norm": 0.862867534160614, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 3.0389, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.774818401937046, | |
| "grad_norm": 1.1330729722976685, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.5739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 0.8608712553977966, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.0211, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8523002421307506, | |
| "grad_norm": 0.8743544816970825, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.8889, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8910411622276029, | |
| "grad_norm": 0.8329064249992371, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.9673, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9297820823244553, | |
| "grad_norm": 1.6253032684326172, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.9516, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9685230024213075, | |
| "grad_norm": 0.8131842017173767, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.8329, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.9685230024213075, | |
| "eval_loss": 3.0354466438293457, | |
| "eval_runtime": 11.9134, | |
| "eval_samples_per_second": 14.605, | |
| "eval_steps_per_second": 1.847, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.026634382566586, | |
| "grad_norm": 2.9393057823181152, | |
| "learning_rate": 5e-05, | |
| "loss": 5.7408, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0653753026634383, | |
| "grad_norm": 1.3096283674240112, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 3.135, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.1041162227602905, | |
| "grad_norm": 1.031684398651123, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.8978, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 1.2637622356414795, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.9017, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.181598062953995, | |
| "grad_norm": 0.9409626722335815, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8737, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2203389830508475, | |
| "grad_norm": 0.982624888420105, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.819, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2590799031476998, | |
| "grad_norm": 1.4315216541290283, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.1233, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.297820823244552, | |
| "grad_norm": 1.4830853939056396, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 3.335, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3365617433414043, | |
| "grad_norm": 1.272890567779541, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.9649, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3753026634382566, | |
| "grad_norm": 1.2674185037612915, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.9028, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.414043583535109, | |
| "grad_norm": 1.2481498718261719, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.941, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4527845036319613, | |
| "grad_norm": 0.9147533774375916, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.7872, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4915254237288136, | |
| "grad_norm": 1.4051660299301147, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.952, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5302663438256658, | |
| "grad_norm": 2.065242052078247, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 3.4175, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.569007263922518, | |
| "grad_norm": 1.2460421323776245, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.9729, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6077481840193704, | |
| "grad_norm": 0.9894155263900757, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.8412, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6464891041162226, | |
| "grad_norm": 2.462437629699707, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.8047, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.685230024213075, | |
| "grad_norm": 0.9419494867324829, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.8367, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7239709443099274, | |
| "grad_norm": 1.5156563520431519, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.7518, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7627118644067796, | |
| "grad_norm": 1.8598206043243408, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 3.3659, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.801452784503632, | |
| "grad_norm": 1.3871934413909912, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.95, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8401937046004844, | |
| "grad_norm": 1.2430062294006348, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.8985, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8789346246973366, | |
| "grad_norm": 1.2211697101593018, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.8497, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.917675544794189, | |
| "grad_norm": 1.6619465351104736, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.8456, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9564164648910412, | |
| "grad_norm": 0.6423755288124084, | |
| "learning_rate": 0.0, | |
| "loss": 2.7164, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9564164648910412, | |
| "eval_loss": 3.0068626403808594, | |
| "eval_runtime": 11.9198, | |
| "eval_samples_per_second": 14.598, | |
| "eval_steps_per_second": 1.846, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |