| { | |
| "best_metric": 0.9277857484457198, | |
| "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-2172", | |
| "epoch": 9.98849252013809, | |
| "eval_steps": 500, | |
| "global_step": 4340, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.998849252013809, | |
| "eval_accuracy": 0.9982342248766554, | |
| "eval_f1": 0.8858669256920836, | |
| "eval_loss": 0.004620244260877371, | |
| "eval_precision": 0.8888888888888888, | |
| "eval_recall": 0.882865440464666, | |
| "eval_runtime": 17.4509, | |
| "eval_samples_per_second": 389.55, | |
| "eval_steps_per_second": 48.708, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 1.1507479861910241, | |
| "grad_norm": 0.23523670434951782, | |
| "learning_rate": 4.423963133640553e-05, | |
| "loss": 0.011, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9984679304076863, | |
| "eval_f1": 0.9142857142857144, | |
| "eval_loss": 0.003912799060344696, | |
| "eval_precision": 0.9147286821705426, | |
| "eval_recall": 0.9138431752178122, | |
| "eval_runtime": 17.405, | |
| "eval_samples_per_second": 390.577, | |
| "eval_steps_per_second": 48.836, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 2.3014959723820483, | |
| "grad_norm": 0.45862698554992676, | |
| "learning_rate": 3.847926267281106e-05, | |
| "loss": 0.0034, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.998849252013809, | |
| "eval_accuracy": 0.9984809140482992, | |
| "eval_f1": 0.9076464746772591, | |
| "eval_loss": 0.004498152993619442, | |
| "eval_precision": 0.9317023445463812, | |
| "eval_recall": 0.8848015488867377, | |
| "eval_runtime": 17.4254, | |
| "eval_samples_per_second": 390.121, | |
| "eval_steps_per_second": 48.779, | |
| "step": 1303 | |
| }, | |
| { | |
| "epoch": 3.4522439585730726, | |
| "grad_norm": 0.009071873500943184, | |
| "learning_rate": 3.271889400921659e-05, | |
| "loss": 0.0019, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9985588158919761, | |
| "eval_f1": 0.9217986314760508, | |
| "eval_loss": 0.005574463400989771, | |
| "eval_precision": 0.930898321816387, | |
| "eval_recall": 0.9128751210067764, | |
| "eval_runtime": 17.7524, | |
| "eval_samples_per_second": 382.935, | |
| "eval_steps_per_second": 47.881, | |
| "step": 1738 | |
| }, | |
| { | |
| "epoch": 4.602991944764097, | |
| "grad_norm": 0.004038061480969191, | |
| "learning_rate": 2.6958525345622122e-05, | |
| "loss": 0.0013, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 4.998849252013809, | |
| "eval_accuracy": 0.9986691768371851, | |
| "eval_f1": 0.9277857484457198, | |
| "eval_loss": 0.005119931884109974, | |
| "eval_precision": 0.9168241965973535, | |
| "eval_recall": 0.9390125847047435, | |
| "eval_runtime": 17.4161, | |
| "eval_samples_per_second": 390.329, | |
| "eval_steps_per_second": 48.805, | |
| "step": 2172 | |
| }, | |
| { | |
| "epoch": 5.7537399309551205, | |
| "grad_norm": 0.006356089375913143, | |
| "learning_rate": 2.1198156682027652e-05, | |
| "loss": 0.0008, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9985523240716697, | |
| "eval_f1": 0.9211170994610485, | |
| "eval_loss": 0.007121166214346886, | |
| "eval_precision": 0.9325396825396826, | |
| "eval_recall": 0.9099709583736689, | |
| "eval_runtime": 17.3919, | |
| "eval_samples_per_second": 390.872, | |
| "eval_steps_per_second": 48.873, | |
| "step": 2607 | |
| }, | |
| { | |
| "epoch": 6.904487917146145, | |
| "grad_norm": 0.162181556224823, | |
| "learning_rate": 1.543778801843318e-05, | |
| "loss": 0.0005, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 6.998849252013809, | |
| "eval_accuracy": 0.9986042586341211, | |
| "eval_f1": 0.9277750848279206, | |
| "eval_loss": 0.00681227957829833, | |
| "eval_precision": 0.929126213592233, | |
| "eval_recall": 0.9264278799612778, | |
| "eval_runtime": 17.3598, | |
| "eval_samples_per_second": 391.594, | |
| "eval_steps_per_second": 48.964, | |
| "step": 3041 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9985977668138146, | |
| "eval_f1": 0.9225556631171346, | |
| "eval_loss": 0.007519510108977556, | |
| "eval_precision": 0.9225556631171346, | |
| "eval_recall": 0.9225556631171346, | |
| "eval_runtime": 17.3761, | |
| "eval_samples_per_second": 391.228, | |
| "eval_steps_per_second": 48.918, | |
| "step": 3476 | |
| }, | |
| { | |
| "epoch": 8.055235903337168, | |
| "grad_norm": 0.0004161146644037217, | |
| "learning_rate": 9.67741935483871e-06, | |
| "loss": 0.0003, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.998849252013809, | |
| "eval_accuracy": 0.9986237340950402, | |
| "eval_f1": 0.9239653512993263, | |
| "eval_loss": 0.00804431363940239, | |
| "eval_precision": 0.9186602870813397, | |
| "eval_recall": 0.9293320425943853, | |
| "eval_runtime": 17.4994, | |
| "eval_samples_per_second": 388.47, | |
| "eval_steps_per_second": 48.573, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 9.205983889528193, | |
| "grad_norm": 0.004000700078904629, | |
| "learning_rate": 3.9170506912442395e-06, | |
| "loss": 0.0002, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.98849252013809, | |
| "eval_accuracy": 0.9986302259153467, | |
| "eval_f1": 0.9273255813953489, | |
| "eval_loss": 0.008330674842000008, | |
| "eval_precision": 0.9282250242483027, | |
| "eval_recall": 0.9264278799612778, | |
| "eval_runtime": 17.745, | |
| "eval_samples_per_second": 383.094, | |
| "eval_steps_per_second": 47.901, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 9.98849252013809, | |
| "step": 4340, | |
| "total_flos": 1.5097303758402288e+16, | |
| "train_loss": 0.00223495911781071, | |
| "train_runtime": 2333.8866, | |
| "train_samples_per_second": 119.097, | |
| "train_steps_per_second": 1.86 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4340, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5097303758402288e+16, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |