| { | |
| "best_metric": 0.3696126937866211, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4444444444444444, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008888888888888889, | |
| "grad_norm": 5.546084403991699, | |
| "learning_rate": 0.0001, | |
| "loss": 7.1758, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008888888888888889, | |
| "eval_loss": 7.330979824066162, | |
| "eval_runtime": 3.4496, | |
| "eval_samples_per_second": 13.914, | |
| "eval_steps_per_second": 6.957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017777777777777778, | |
| "grad_norm": 5.357749938964844, | |
| "learning_rate": 0.0002, | |
| "loss": 7.0917, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.02666666666666667, | |
| "grad_norm": 4.400688648223877, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 7.5881, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.035555555555555556, | |
| "grad_norm": 5.9483561515808105, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.748, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 8.287385940551758, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 6.1399, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05333333333333334, | |
| "grad_norm": 8.510035514831543, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 4.7425, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.06222222222222222, | |
| "grad_norm": 7.661823749542236, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 3.1506, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.07111111111111111, | |
| "grad_norm": 7.301525115966797, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 2.9865, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 4.330402851104736, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 1.526, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 5.074550151824951, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.3981, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09777777777777778, | |
| "grad_norm": 3.7569286823272705, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.7422, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.10666666666666667, | |
| "grad_norm": 3.5919718742370605, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.7367, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.11555555555555555, | |
| "grad_norm": 2.3541793823242188, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.4833, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.12444444444444444, | |
| "grad_norm": 1.313127875328064, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.4141, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 1.5438507795333862, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.3956, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.14222222222222222, | |
| "grad_norm": 4.521699905395508, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.3996, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1511111111111111, | |
| "grad_norm": 1.5206464529037476, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.3195, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 1.1479847431182861, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.2795, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1688888888888889, | |
| "grad_norm": 6.164490222930908, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.5428, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 3.505394458770752, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.4271, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18666666666666668, | |
| "grad_norm": 1.352529525756836, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.3857, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.19555555555555557, | |
| "grad_norm": 2.4588797092437744, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.3894, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.20444444444444446, | |
| "grad_norm": 6.47442102432251, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.4564, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.21333333333333335, | |
| "grad_norm": 5.257223606109619, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.4425, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.8862743973731995, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 0.3077, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "eval_loss": 0.38192471861839294, | |
| "eval_runtime": 3.4584, | |
| "eval_samples_per_second": 13.879, | |
| "eval_steps_per_second": 6.94, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2311111111111111, | |
| "grad_norm": 2.0117669105529785, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3888, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 6.946228504180908, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.5364, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.24888888888888888, | |
| "grad_norm": 2.2014853954315186, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.3977, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.2577777777777778, | |
| "grad_norm": 4.625939846038818, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.366, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 2.8562731742858887, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.4198, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.27555555555555555, | |
| "grad_norm": 0.6394229531288147, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.3234, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.28444444444444444, | |
| "grad_norm": 2.782531976699829, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.2482, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.29333333333333333, | |
| "grad_norm": 5.685042858123779, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.5143, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3022222222222222, | |
| "grad_norm": 2.0438950061798096, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.3339, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 3.337780237197876, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.4482, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 1.1531790494918823, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.3529, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3288888888888889, | |
| "grad_norm": 1.931061863899231, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.3628, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.3377777777777778, | |
| "grad_norm": 1.7695353031158447, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.3906, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3466666666666667, | |
| "grad_norm": 2.8632524013519287, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 0.3458, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 2.9647114276885986, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.334, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.36444444444444446, | |
| "grad_norm": 0.7860206961631775, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.345, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.37333333333333335, | |
| "grad_norm": 0.9671415686607361, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.3785, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.38222222222222224, | |
| "grad_norm": 2.243291139602661, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.3267, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.39111111111111113, | |
| "grad_norm": 1.4092743396759033, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.3687, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 2.9342949390411377, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.3915, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4088888888888889, | |
| "grad_norm": 1.2684597969055176, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.3857, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.4177777777777778, | |
| "grad_norm": 0.8089708089828491, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.3436, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.4266666666666667, | |
| "grad_norm": 1.3409976959228516, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.3426, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.43555555555555553, | |
| "grad_norm": 2.8692626953125, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.3069, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.4735819101333618, | |
| "learning_rate": 0.0, | |
| "loss": 0.368, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "eval_loss": 0.3696126937866211, | |
| "eval_runtime": 3.4698, | |
| "eval_samples_per_second": 13.834, | |
| "eval_steps_per_second": 6.917, | |
| "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": 1.02936877203456e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |