| { | |
| "best_metric": 0.29814502596855164, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.041322314049587, | |
| "eval_steps": 25, | |
| "global_step": 46, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 1.2821037769317627, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "eval_loss": 0.8276475667953491, | |
| "eval_runtime": 4.7766, | |
| "eval_samples_per_second": 10.468, | |
| "eval_steps_per_second": 2.722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1322314049586777, | |
| "grad_norm": 1.515925407409668, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6771, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.19834710743801653, | |
| "grad_norm": 1.3467015027999878, | |
| "learning_rate": 9.98853451574614e-05, | |
| "loss": 0.6128, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2644628099173554, | |
| "grad_norm": 0.8077853918075562, | |
| "learning_rate": 9.954196488464198e-05, | |
| "loss": 0.4131, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.3305785123966942, | |
| "grad_norm": 0.7690338492393494, | |
| "learning_rate": 9.897160896870218e-05, | |
| "loss": 0.3669, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.39669421487603307, | |
| "grad_norm": 0.9872344136238098, | |
| "learning_rate": 9.81771838126524e-05, | |
| "loss": 0.3699, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.4628099173553719, | |
| "grad_norm": 0.543779730796814, | |
| "learning_rate": 9.716273762498929e-05, | |
| "loss": 0.3246, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.5289256198347108, | |
| "grad_norm": 0.5106104016304016, | |
| "learning_rate": 9.593343979095333e-05, | |
| "loss": 0.3045, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5950413223140496, | |
| "grad_norm": 0.4468647539615631, | |
| "learning_rate": 9.449555453052651e-05, | |
| "loss": 0.3354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.6611570247933884, | |
| "grad_norm": 0.48299410939216614, | |
| "learning_rate": 9.285640897740315e-05, | |
| "loss": 0.3475, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 0.5404636263847351, | |
| "learning_rate": 9.102435584159622e-05, | |
| "loss": 0.3114, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.7933884297520661, | |
| "grad_norm": 0.3328273296356201, | |
| "learning_rate": 8.900873084594164e-05, | |
| "loss": 0.2682, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.859504132231405, | |
| "grad_norm": 0.36546558141708374, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.2919, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.9256198347107438, | |
| "grad_norm": 0.38495934009552, | |
| "learning_rate": 8.446873302753784e-05, | |
| "loss": 0.2714, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.9917355371900827, | |
| "grad_norm": 0.4691920876502991, | |
| "learning_rate": 8.19674949930106e-05, | |
| "loss": 0.2495, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.0578512396694215, | |
| "grad_norm": 0.6476026177406311, | |
| "learning_rate": 7.93288367855019e-05, | |
| "loss": 0.3272, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.1239669421487604, | |
| "grad_norm": 0.3131757080554962, | |
| "learning_rate": 7.656620440240257e-05, | |
| "loss": 0.2197, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.1900826446280992, | |
| "grad_norm": 0.3334848880767822, | |
| "learning_rate": 7.369367558508489e-05, | |
| "loss": 0.2098, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.256198347107438, | |
| "grad_norm": 0.3057920038700104, | |
| "learning_rate": 7.072588808195944e-05, | |
| "loss": 0.1671, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.322314049586777, | |
| "grad_norm": 0.31117555499076843, | |
| "learning_rate": 6.767796505786435e-05, | |
| "loss": 0.2383, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.3884297520661157, | |
| "grad_norm": 0.32219311594963074, | |
| "learning_rate": 6.456543802988395e-05, | |
| "loss": 0.1966, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.4545454545454546, | |
| "grad_norm": 0.3343944847583771, | |
| "learning_rate": 6.140416772229784e-05, | |
| "loss": 0.1738, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.5206611570247934, | |
| "grad_norm": 0.30831432342529297, | |
| "learning_rate": 5.821026324396546e-05, | |
| "loss": 0.1812, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.5867768595041323, | |
| "grad_norm": 0.3504087030887604, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.217, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.6528925619834711, | |
| "grad_norm": 0.3314357101917267, | |
| "learning_rate": 5.178973675603456e-05, | |
| "loss": 0.2003, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.6528925619834711, | |
| "eval_loss": 0.29814502596855164, | |
| "eval_runtime": 4.8436, | |
| "eval_samples_per_second": 10.323, | |
| "eval_steps_per_second": 2.684, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.71900826446281, | |
| "grad_norm": 0.38563114404678345, | |
| "learning_rate": 4.859583227770218e-05, | |
| "loss": 0.1666, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.7851239669421488, | |
| "grad_norm": 0.32108181715011597, | |
| "learning_rate": 4.543456197011605e-05, | |
| "loss": 0.185, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.8512396694214877, | |
| "grad_norm": 0.3681396245956421, | |
| "learning_rate": 4.232203494213567e-05, | |
| "loss": 0.2199, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.9173553719008265, | |
| "grad_norm": 0.37222185730934143, | |
| "learning_rate": 3.927411191804058e-05, | |
| "loss": 0.2032, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.9834710743801653, | |
| "grad_norm": 0.4296535551548004, | |
| "learning_rate": 3.630632441491512e-05, | |
| "loss": 0.1851, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.049586776859504, | |
| "grad_norm": 0.8122077584266663, | |
| "learning_rate": 3.343379559759746e-05, | |
| "loss": 0.2605, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.115702479338843, | |
| "grad_norm": 0.29376327991485596, | |
| "learning_rate": 3.067116321449813e-05, | |
| "loss": 0.1641, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.1818181818181817, | |
| "grad_norm": 0.3262518048286438, | |
| "learning_rate": 2.803250500698939e-05, | |
| "loss": 0.1464, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 2.2479338842975207, | |
| "grad_norm": 0.2500488758087158, | |
| "learning_rate": 2.5531266972462177e-05, | |
| "loss": 0.0992, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.3140495867768593, | |
| "grad_norm": 0.3410912752151489, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1822, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.3801652892561984, | |
| "grad_norm": 0.28179067373275757, | |
| "learning_rate": 2.0991269154058385e-05, | |
| "loss": 0.1224, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.446280991735537, | |
| "grad_norm": 0.30862489342689514, | |
| "learning_rate": 1.897564415840379e-05, | |
| "loss": 0.1116, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.512396694214876, | |
| "grad_norm": 0.2770218253135681, | |
| "learning_rate": 1.7143591022596845e-05, | |
| "loss": 0.1074, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.5785123966942147, | |
| "grad_norm": 0.3372029662132263, | |
| "learning_rate": 1.5504445469473496e-05, | |
| "loss": 0.1526, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.644628099173554, | |
| "grad_norm": 0.3446227014064789, | |
| "learning_rate": 1.4066560209046673e-05, | |
| "loss": 0.1372, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.7107438016528924, | |
| "grad_norm": 0.34640777111053467, | |
| "learning_rate": 1.2837262375010731e-05, | |
| "loss": 0.1075, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.7768595041322315, | |
| "grad_norm": 0.30039989948272705, | |
| "learning_rate": 1.1822816187347623e-05, | |
| "loss": 0.1153, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.84297520661157, | |
| "grad_norm": 0.34811943769454956, | |
| "learning_rate": 1.1028391031297826e-05, | |
| "loss": 0.1557, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.909090909090909, | |
| "grad_norm": 0.34190842509269714, | |
| "learning_rate": 1.0458035115358032e-05, | |
| "loss": 0.1301, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.975206611570248, | |
| "grad_norm": 0.3699391782283783, | |
| "learning_rate": 1.0114654842538593e-05, | |
| "loss": 0.0992, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 3.041322314049587, | |
| "grad_norm": 0.8737526535987854, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2512, | |
| "step": 46 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 46, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 5.6805209969105306e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |