| { | |
| "best_global_step": 1384, | |
| "best_metric": 0.7932960893854749, | |
| "best_model_checkpoint": "./bert-tiny-heading-classifier\\checkpoint-1384", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 1384, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.036127167630057806, | |
| "grad_norm": 3.7394230365753174, | |
| "learning_rate": 2.45e-05, | |
| "loss": 0.484, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07225433526011561, | |
| "grad_norm": 2.0182766914367676, | |
| "learning_rate": 4.9500000000000004e-05, | |
| "loss": 0.3104, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10838150289017341, | |
| "grad_norm": 1.2229622602462769, | |
| "learning_rate": 4.9549300956585726e-05, | |
| "loss": 0.2133, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.14450867052023122, | |
| "grad_norm": 0.9460026025772095, | |
| "learning_rate": 4.9089403973509935e-05, | |
| "loss": 0.2163, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18063583815028902, | |
| "grad_norm": 0.7926827073097229, | |
| "learning_rate": 4.8629506990434144e-05, | |
| "loss": 0.182, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.21676300578034682, | |
| "grad_norm": 0.5686139464378357, | |
| "learning_rate": 4.816961000735836e-05, | |
| "loss": 0.1811, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.25289017341040465, | |
| "grad_norm": 1.6547473669052124, | |
| "learning_rate": 4.770971302428257e-05, | |
| "loss": 0.121, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.28901734104046245, | |
| "grad_norm": 0.47385355830192566, | |
| "learning_rate": 4.724981604120677e-05, | |
| "loss": 0.1834, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.32514450867052025, | |
| "grad_norm": 0.9103878140449524, | |
| "learning_rate": 4.678991905813098e-05, | |
| "loss": 0.1099, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.36127167630057805, | |
| "grad_norm": 0.30629491806030273, | |
| "learning_rate": 4.633002207505519e-05, | |
| "loss": 0.1169, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.39739884393063585, | |
| "grad_norm": 3.804182291030884, | |
| "learning_rate": 4.58701250919794e-05, | |
| "loss": 0.151, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.43352601156069365, | |
| "grad_norm": 0.23083843290805817, | |
| "learning_rate": 4.5410228108903606e-05, | |
| "loss": 0.0816, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.46965317919075145, | |
| "grad_norm": 0.31194067001342773, | |
| "learning_rate": 4.4950331125827815e-05, | |
| "loss": 0.1238, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.5057803468208093, | |
| "grad_norm": 0.18349987268447876, | |
| "learning_rate": 4.4490434142752024e-05, | |
| "loss": 0.0834, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.541907514450867, | |
| "grad_norm": 2.0543556213378906, | |
| "learning_rate": 4.403053715967623e-05, | |
| "loss": 0.1476, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.5780346820809249, | |
| "grad_norm": 3.1080751419067383, | |
| "learning_rate": 4.357064017660044e-05, | |
| "loss": 0.1217, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6141618497109826, | |
| "grad_norm": 13.235072135925293, | |
| "learning_rate": 4.311074319352466e-05, | |
| "loss": 0.1886, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.6502890173410405, | |
| "grad_norm": 0.290387362241745, | |
| "learning_rate": 4.265084621044887e-05, | |
| "loss": 0.1246, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.6864161849710982, | |
| "grad_norm": 3.8590610027313232, | |
| "learning_rate": 4.219094922737307e-05, | |
| "loss": 0.079, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.7225433526011561, | |
| "grad_norm": 0.1421326994895935, | |
| "learning_rate": 4.173105224429728e-05, | |
| "loss": 0.0346, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.7586705202312138, | |
| "grad_norm": 0.1293569654226303, | |
| "learning_rate": 4.127115526122149e-05, | |
| "loss": 0.0552, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.7947976878612717, | |
| "grad_norm": 0.11882981657981873, | |
| "learning_rate": 4.0811258278145696e-05, | |
| "loss": 0.1326, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.8309248554913294, | |
| "grad_norm": 0.12036094069480896, | |
| "learning_rate": 4.0351361295069905e-05, | |
| "loss": 0.0938, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.8670520231213873, | |
| "grad_norm": 3.4779465198516846, | |
| "learning_rate": 3.9891464311994114e-05, | |
| "loss": 0.088, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.903179190751445, | |
| "grad_norm": 0.17521940171718597, | |
| "learning_rate": 3.943156732891832e-05, | |
| "loss": 0.0692, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.9393063583815029, | |
| "grad_norm": 4.401475429534912, | |
| "learning_rate": 3.897167034584253e-05, | |
| "loss": 0.067, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.9754335260115607, | |
| "grad_norm": 18.098052978515625, | |
| "learning_rate": 3.851177336276674e-05, | |
| "loss": 0.0704, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.981064483111566, | |
| "eval_f1": 0.7932960893854749, | |
| "eval_loss": 0.08416279405355453, | |
| "eval_runtime": 1.6656, | |
| "eval_samples_per_second": 1173.183, | |
| "eval_steps_per_second": 147.098, | |
| "step": 1384 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 5536, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7031510522880.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |