| { | |
| "best_metric": 0.03780783340334892, | |
| "best_model_checkpoint": "./results3/checkpoint-2400", | |
| "epoch": 3.864734299516908, | |
| "eval_steps": 200, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.322061191626409, | |
| "grad_norm": 7.461069583892822, | |
| "learning_rate": 6.666666666666667e-07, | |
| "loss": 1.8012, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.322061191626409, | |
| "eval_accuracy": 0.18971061093247588, | |
| "eval_f1": 0.10189049057972092, | |
| "eval_loss": 1.7812345027923584, | |
| "eval_precision": 0.12844515990912814, | |
| "eval_recall": 0.18971061093247588, | |
| "eval_runtime": 5.7225, | |
| "eval_samples_per_second": 108.693, | |
| "eval_steps_per_second": 27.261, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.644122383252818, | |
| "grad_norm": 6.918825149536133, | |
| "learning_rate": 1.3333333333333334e-06, | |
| "loss": 1.7688, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.644122383252818, | |
| "eval_accuracy": 0.26688102893890675, | |
| "eval_f1": 0.21143076934540506, | |
| "eval_loss": 1.7484790086746216, | |
| "eval_precision": 0.48251637799958924, | |
| "eval_recall": 0.26688102893890675, | |
| "eval_runtime": 5.841, | |
| "eval_samples_per_second": 106.489, | |
| "eval_steps_per_second": 26.708, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "grad_norm": 6.153536319732666, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 1.7475, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.966183574879227, | |
| "eval_accuracy": 0.5353697749196141, | |
| "eval_f1": 0.5292630942880905, | |
| "eval_loss": 1.6678913831710815, | |
| "eval_precision": 0.5777595640628179, | |
| "eval_recall": 0.5353697749196141, | |
| "eval_runtime": 5.7676, | |
| "eval_samples_per_second": 107.844, | |
| "eval_steps_per_second": 27.048, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.288244766505636, | |
| "grad_norm": 10.906112670898438, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 1.6323, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.288244766505636, | |
| "eval_accuracy": 0.6109324758842444, | |
| "eval_f1": 0.584022217728586, | |
| "eval_loss": 1.4518650770187378, | |
| "eval_precision": 0.6770832871589993, | |
| "eval_recall": 0.6109324758842444, | |
| "eval_runtime": 5.7252, | |
| "eval_samples_per_second": 108.643, | |
| "eval_steps_per_second": 27.248, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.6103059581320451, | |
| "grad_norm": 11.212413787841797, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 1.3569, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6103059581320451, | |
| "eval_accuracy": 0.6672025723472669, | |
| "eval_f1": 0.6448086526662313, | |
| "eval_loss": 1.0713452100753784, | |
| "eval_precision": 0.7227579722788608, | |
| "eval_recall": 0.6672025723472669, | |
| "eval_runtime": 5.8441, | |
| "eval_samples_per_second": 106.433, | |
| "eval_steps_per_second": 26.694, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "grad_norm": 10.077208518981934, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.9744, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.9323671497584543, | |
| "eval_accuracy": 0.8360128617363344, | |
| "eval_f1": 0.8313516450563994, | |
| "eval_loss": 0.6114147901535034, | |
| "eval_precision": 0.8485064229080279, | |
| "eval_recall": 0.8360128617363344, | |
| "eval_runtime": 5.7667, | |
| "eval_samples_per_second": 107.861, | |
| "eval_steps_per_second": 27.052, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.2544283413848634, | |
| "grad_norm": 3.6660408973693848, | |
| "learning_rate": 4.666666666666667e-06, | |
| "loss": 0.5969, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.2544283413848634, | |
| "eval_accuracy": 0.9180064308681672, | |
| "eval_f1": 0.9171911311305204, | |
| "eval_loss": 0.29916083812713623, | |
| "eval_precision": 0.9217784712222669, | |
| "eval_recall": 0.9180064308681672, | |
| "eval_runtime": 5.8166, | |
| "eval_samples_per_second": 106.936, | |
| "eval_steps_per_second": 26.82, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.576489533011272, | |
| "grad_norm": 3.6452574729919434, | |
| "learning_rate": 4.994440868783523e-06, | |
| "loss": 0.3187, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.576489533011272, | |
| "eval_accuracy": 0.9453376205787781, | |
| "eval_f1": 0.94523522766866, | |
| "eval_loss": 0.1684405654668808, | |
| "eval_precision": 0.951570696538466, | |
| "eval_recall": 0.9453376205787781, | |
| "eval_runtime": 5.7215, | |
| "eval_samples_per_second": 108.712, | |
| "eval_steps_per_second": 27.265, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.898550724637681, | |
| "grad_norm": 0.2801424562931061, | |
| "learning_rate": 4.950116048011739e-06, | |
| "loss": 0.1856, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.898550724637681, | |
| "eval_accuracy": 0.9726688102893891, | |
| "eval_f1": 0.9726543269299354, | |
| "eval_loss": 0.0953439399600029, | |
| "eval_precision": 0.9736809257583791, | |
| "eval_recall": 0.9726688102893891, | |
| "eval_runtime": 5.7237, | |
| "eval_samples_per_second": 108.672, | |
| "eval_steps_per_second": 27.255, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 3.2206119162640903, | |
| "grad_norm": 0.754078209400177, | |
| "learning_rate": 4.862254033772164e-06, | |
| "loss": 0.1113, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.2206119162640903, | |
| "eval_accuracy": 0.9823151125401929, | |
| "eval_f1": 0.9823107313578804, | |
| "eval_loss": 0.05166807398200035, | |
| "eval_precision": 0.9823692945184218, | |
| "eval_recall": 0.9823151125401929, | |
| "eval_runtime": 5.6315, | |
| "eval_samples_per_second": 110.451, | |
| "eval_steps_per_second": 27.702, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 3.542673107890499, | |
| "grad_norm": 0.2094874083995819, | |
| "learning_rate": 4.7324160849755856e-06, | |
| "loss": 0.0492, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.542673107890499, | |
| "eval_accuracy": 0.9855305466237942, | |
| "eval_f1": 0.9855078289074475, | |
| "eval_loss": 0.04900892823934555, | |
| "eval_precision": 0.9855788271208662, | |
| "eval_recall": 0.9855305466237942, | |
| "eval_runtime": 5.7859, | |
| "eval_samples_per_second": 107.503, | |
| "eval_steps_per_second": 26.962, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 3.864734299516908, | |
| "grad_norm": 0.26868194341659546, | |
| "learning_rate": 4.562909349440899e-06, | |
| "loss": 0.0584, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 3.864734299516908, | |
| "eval_accuracy": 0.9855305466237942, | |
| "eval_f1": 0.9855183714453405, | |
| "eval_loss": 0.03780783340334892, | |
| "eval_precision": 0.9856657355462896, | |
| "eval_recall": 0.9855305466237942, | |
| "eval_runtime": 5.7375, | |
| "eval_samples_per_second": 108.409, | |
| "eval_steps_per_second": 27.189, | |
| "step": 2400 | |
| } | |
| ], | |
| "logging_steps": 200, | |
| "max_steps": 6210, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 383614021649664.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |