| { | |
| "best_metric": 1.1957429647445679, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13065490772497143, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026130981544994283, | |
| "grad_norm": 30.899654388427734, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1267, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026130981544994283, | |
| "eval_loss": 1.8499661684036255, | |
| "eval_runtime": 167.2588, | |
| "eval_samples_per_second": 15.413, | |
| "eval_steps_per_second": 1.931, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005226196308998857, | |
| "grad_norm": 33.87411880493164, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2228, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007839294463498285, | |
| "grad_norm": 18.999311447143555, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.1836, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010452392617997713, | |
| "grad_norm": 21.47573471069336, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.1927, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013065490772497142, | |
| "grad_norm": 21.85623550415039, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2051, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01567858892699657, | |
| "grad_norm": 17.990365982055664, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2142, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018291687081496, | |
| "grad_norm": 14.827211380004883, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1788, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020904785235995427, | |
| "grad_norm": 22.092012405395508, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2685, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023517883390494855, | |
| "grad_norm": 32.1710319519043, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.4338, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026130981544994283, | |
| "grad_norm": 45.76557540893555, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.566, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02874407969949371, | |
| "grad_norm": 45.74945068359375, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.6296, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03135717785399314, | |
| "grad_norm": 52.03664016723633, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.812, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03397027600849257, | |
| "grad_norm": 54.32783126831055, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.5289, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.036583374162992, | |
| "grad_norm": 25.161073684692383, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.1103, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039196472317491425, | |
| "grad_norm": 24.294761657714844, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.1767, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04180957047199085, | |
| "grad_norm": 19.136260986328125, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.109, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04442266862649028, | |
| "grad_norm": 15.456122398376465, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.1021, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04703576678098971, | |
| "grad_norm": 12.054083824157715, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1288, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04964886493548914, | |
| "grad_norm": 11.738526344299316, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.1676, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05226196308998857, | |
| "grad_norm": 14.183579444885254, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1864, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054875061244487995, | |
| "grad_norm": 18.19736099243164, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.2671, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05748815939898742, | |
| "grad_norm": 25.0335693359375, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.3673, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06010125755348685, | |
| "grad_norm": 36.76613235473633, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5454, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06271435570798628, | |
| "grad_norm": 45.20155715942383, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5598, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "grad_norm": 76.99732971191406, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.9044, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "eval_loss": 1.2333778142929077, | |
| "eval_runtime": 167.251, | |
| "eval_samples_per_second": 15.414, | |
| "eval_steps_per_second": 1.931, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06794055201698514, | |
| "grad_norm": 7.437511920928955, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9982, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07055365017148457, | |
| "grad_norm": 6.7867207527160645, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.0384, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.073166748325984, | |
| "grad_norm": 6.633565902709961, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.0307, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07577984648048343, | |
| "grad_norm": 7.300943851470947, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.0679, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07839294463498285, | |
| "grad_norm": 8.290701866149902, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.0623, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08100604278948229, | |
| "grad_norm": 10.008981704711914, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1515, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0836191409439817, | |
| "grad_norm": 12.658711433410645, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2007, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08623223909848114, | |
| "grad_norm": 17.597726821899414, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.24, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08884533725298056, | |
| "grad_norm": 21.86583709716797, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.3628, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09145843540748, | |
| "grad_norm": 26.087900161743164, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.3616, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09407153356197942, | |
| "grad_norm": 33.14945983886719, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4062, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09668463171647886, | |
| "grad_norm": 39.74778747558594, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.6848, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09929772987097828, | |
| "grad_norm": 36.329551696777344, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.3833, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10191082802547771, | |
| "grad_norm": 6.016417503356934, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0036, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10452392617997713, | |
| "grad_norm": 6.548324108123779, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0207, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10713702433447657, | |
| "grad_norm": 6.872424602508545, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.0523, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10975012248897599, | |
| "grad_norm": 7.7177734375, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.0816, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11236322064347543, | |
| "grad_norm": 8.686575889587402, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.1517, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11497631879797485, | |
| "grad_norm": 9.739227294921875, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.115, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11758941695247428, | |
| "grad_norm": 12.140241622924805, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.1213, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1202025151069737, | |
| "grad_norm": 16.49872398376465, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2322, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12281561326147314, | |
| "grad_norm": 21.253034591674805, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.3385, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12542871141597256, | |
| "grad_norm": 28.797561645507812, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.363, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12804180957047198, | |
| "grad_norm": 35.98500442504883, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.3961, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13065490772497143, | |
| "grad_norm": 53.93410873413086, | |
| "learning_rate": 0.0, | |
| "loss": 1.7542, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13065490772497143, | |
| "eval_loss": 1.1957429647445679, | |
| "eval_runtime": 167.2329, | |
| "eval_samples_per_second": 15.416, | |
| "eval_steps_per_second": 1.931, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |