| { | |
| "best_metric": 0.6368208527565002, | |
| "best_model_checkpoint": "../experiments/attribute_minig_mslacerda/run-1/checkpoint-473", | |
| "epoch": 11.0, | |
| "eval_steps": 500, | |
| "global_step": 473, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.03543543543543543, | |
| "eval_f1": 0.004940711462450594, | |
| "eval_loss": 4.673229217529297, | |
| "eval_precision": 0.004108463434675432, | |
| "eval_recall": 0.006195786864931847, | |
| "eval_runtime": 0.3918, | |
| "eval_samples_per_second": 742.66, | |
| "eval_steps_per_second": 94.428, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.12612612612612611, | |
| "eval_f1": 0.019381056580181303, | |
| "eval_loss": 4.209076881408691, | |
| "eval_precision": 0.019558359621451103, | |
| "eval_recall": 0.019206939281288724, | |
| "eval_runtime": 0.3924, | |
| "eval_samples_per_second": 741.507, | |
| "eval_steps_per_second": 94.281, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3282282282282282, | |
| "eval_f1": 0.10037453183520599, | |
| "eval_loss": 3.259751319885254, | |
| "eval_precision": 0.1268939393939394, | |
| "eval_recall": 0.08302354399008674, | |
| "eval_runtime": 0.4015, | |
| "eval_samples_per_second": 724.86, | |
| "eval_steps_per_second": 92.164, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4903903903903904, | |
| "eval_f1": 0.2385254788579689, | |
| "eval_loss": 2.3082196712493896, | |
| "eval_precision": 0.2862098872506505, | |
| "eval_recall": 0.20446096654275092, | |
| "eval_runtime": 0.3924, | |
| "eval_samples_per_second": 741.662, | |
| "eval_steps_per_second": 94.301, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5990990990990991, | |
| "eval_f1": 0.3480905711388983, | |
| "eval_loss": 1.7047184705734253, | |
| "eval_precision": 0.3828996282527881, | |
| "eval_recall": 0.3190830235439901, | |
| "eval_runtime": 0.395, | |
| "eval_samples_per_second": 736.685, | |
| "eval_steps_per_second": 93.668, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6927927927927928, | |
| "eval_f1": 0.4707024927160893, | |
| "eval_loss": 1.2966375350952148, | |
| "eval_precision": 0.4928813559322034, | |
| "eval_recall": 0.45043370508054525, | |
| "eval_runtime": 0.3855, | |
| "eval_samples_per_second": 754.812, | |
| "eval_steps_per_second": 95.973, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.7678678678678679, | |
| "eval_f1": 0.5833596962986396, | |
| "eval_loss": 1.0009989738464355, | |
| "eval_precision": 0.5959922430510666, | |
| "eval_recall": 0.5712515489467163, | |
| "eval_runtime": 0.6988, | |
| "eval_samples_per_second": 416.416, | |
| "eval_steps_per_second": 52.946, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8144144144144144, | |
| "eval_f1": 0.6510903426791277, | |
| "eval_loss": 0.8084700107574463, | |
| "eval_precision": 0.6547619047619048, | |
| "eval_recall": 0.6474597273853779, | |
| "eval_runtime": 0.3918, | |
| "eval_samples_per_second": 742.642, | |
| "eval_steps_per_second": 94.425, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8366366366366367, | |
| "eval_f1": 0.6894850447116867, | |
| "eval_loss": 0.7090229988098145, | |
| "eval_precision": 0.6863106200122775, | |
| "eval_recall": 0.6926889714993805, | |
| "eval_runtime": 0.4014, | |
| "eval_samples_per_second": 724.894, | |
| "eval_steps_per_second": 92.169, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8426426426426427, | |
| "eval_f1": 0.7053378586855908, | |
| "eval_loss": 0.6727187037467957, | |
| "eval_precision": 0.702519975414874, | |
| "eval_recall": 0.70817843866171, | |
| "eval_runtime": 0.3949, | |
| "eval_samples_per_second": 736.903, | |
| "eval_steps_per_second": 93.696, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8552552552552553, | |
| "eval_f1": 0.7300613496932516, | |
| "eval_loss": 0.6368208527565002, | |
| "eval_precision": 0.7229647630619684, | |
| "eval_recall": 0.7372986369268897, | |
| "eval_runtime": 0.3928, | |
| "eval_samples_per_second": 740.915, | |
| "eval_steps_per_second": 94.206, | |
| "step": 473 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 559, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 13, | |
| "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": 0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": { | |
| "learning_rate": 3.979306441518639e-05, | |
| "num_train_epochs": 13, | |
| "per_device_train_batch_size": 32, | |
| "warmup_steps": 286, | |
| "weight_decay": 0.144636026358464 | |
| } | |
| } | |