| { | |
| "best_metric": 0.7709798812866211, | |
| "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": 31.345754623413086, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7757, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026130981544994283, | |
| "eval_loss": 1.1999441385269165, | |
| "eval_runtime": 80.8412, | |
| "eval_samples_per_second": 31.89, | |
| "eval_steps_per_second": 3.995, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005226196308998857, | |
| "grad_norm": 38.250240325927734, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9545, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007839294463498285, | |
| "grad_norm": 17.965593338012695, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.8977, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010452392617997713, | |
| "grad_norm": 52.536643981933594, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.0126, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013065490772497142, | |
| "grad_norm": 34.53886032104492, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.9639, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01567858892699657, | |
| "grad_norm": 21.341968536376953, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.9108, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018291687081496, | |
| "grad_norm": 15.834890365600586, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8092, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020904785235995427, | |
| "grad_norm": 15.896698951721191, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8259, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023517883390494855, | |
| "grad_norm": 24.83303451538086, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8807, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026130981544994283, | |
| "grad_norm": 36.16289520263672, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.9436, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02874407969949371, | |
| "grad_norm": 48.6241455078125, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.9755, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03135717785399314, | |
| "grad_norm": 91.8714828491211, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.1704, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03397027600849257, | |
| "grad_norm": 52.59507369995117, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0213, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.036583374162992, | |
| "grad_norm": 27.812883377075195, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7753, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.039196472317491425, | |
| "grad_norm": 18.69647979736328, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.7847, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04180957047199085, | |
| "grad_norm": 12.70093822479248, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.7982, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04442266862649028, | |
| "grad_norm": 10.31103229522705, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.7916, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04703576678098971, | |
| "grad_norm": 10.175467491149902, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.8207, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04964886493548914, | |
| "grad_norm": 10.68921184539795, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.7828, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05226196308998857, | |
| "grad_norm": 12.193572998046875, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7737, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.054875061244487995, | |
| "grad_norm": 12.889281272888184, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.7253, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05748815939898742, | |
| "grad_norm": 19.57475471496582, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.8299, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06010125755348685, | |
| "grad_norm": 27.88360023498535, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.948, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06271435570798628, | |
| "grad_norm": 31.01333999633789, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.0057, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "grad_norm": 70.52838897705078, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.1215, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06532745386248572, | |
| "eval_loss": 0.8273301720619202, | |
| "eval_runtime": 80.6629, | |
| "eval_samples_per_second": 31.96, | |
| "eval_steps_per_second": 4.004, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06794055201698514, | |
| "grad_norm": 25.535202026367188, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6198, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07055365017148457, | |
| "grad_norm": 21.482892990112305, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.732, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.073166748325984, | |
| "grad_norm": 11.607685089111328, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.7445, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07577984648048343, | |
| "grad_norm": 9.2691068649292, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7646, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07839294463498285, | |
| "grad_norm": 8.74544906616211, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.7796, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08100604278948229, | |
| "grad_norm": 9.21976375579834, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.7569, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0836191409439817, | |
| "grad_norm": 10.738837242126465, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7304, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08623223909848114, | |
| "grad_norm": 14.570478439331055, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.7622, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08884533725298056, | |
| "grad_norm": 21.41011619567871, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.8185, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09145843540748, | |
| "grad_norm": 29.7635498046875, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.8513, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09407153356197942, | |
| "grad_norm": 29.27798843383789, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.947, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09668463171647886, | |
| "grad_norm": 36.1460075378418, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9927, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09929772987097828, | |
| "grad_norm": 36.24226760864258, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7823, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10191082802547771, | |
| "grad_norm": 6.356374740600586, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6502, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10452392617997713, | |
| "grad_norm": 6.381150722503662, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.6938, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10713702433447657, | |
| "grad_norm": 6.29508638381958, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.7362, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10975012248897599, | |
| "grad_norm": 6.889440059661865, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.7619, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11236322064347543, | |
| "grad_norm": 7.852916240692139, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.7662, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11497631879797485, | |
| "grad_norm": 9.296074867248535, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7466, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11758941695247428, | |
| "grad_norm": 11.581921577453613, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.7248, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1202025151069737, | |
| "grad_norm": 17.06822967529297, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.6999, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12281561326147314, | |
| "grad_norm": 26.341707229614258, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.8121, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12542871141597256, | |
| "grad_norm": 38.58266830444336, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.8942, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12804180957047198, | |
| "grad_norm": 56.36668395996094, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.8407, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13065490772497143, | |
| "grad_norm": 60.980892181396484, | |
| "learning_rate": 0.0, | |
| "loss": 1.0831, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13065490772497143, | |
| "eval_loss": 0.7709798812866211, | |
| "eval_runtime": 80.9399, | |
| "eval_samples_per_second": 31.851, | |
| "eval_steps_per_second": 3.991, | |
| "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": 5.727082812528394e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |