| { | |
| "best_metric": 0.6946045049764275, | |
| "best_model_checkpoint": "/content/dissertation/scripts/ner/output/checkpoint-1088", | |
| "epoch": 9.967845659163988, | |
| "eval_steps": 500, | |
| "global_step": 1550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9967845659163987, | |
| "eval_accuracy": 0.9435978055118868, | |
| "eval_f1": 0.593056643174106, | |
| "eval_loss": 0.14849668741226196, | |
| "eval_precision": 0.5668662674650699, | |
| "eval_recall": 0.6217843459222769, | |
| "eval_runtime": 5.8633, | |
| "eval_samples_per_second": 429.618, | |
| "eval_steps_per_second": 53.724, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9408546953704001, | |
| "eval_f1": 0.6299060919817, | |
| "eval_loss": 0.16094118356704712, | |
| "eval_precision": 0.5623387790197765, | |
| "eval_recall": 0.715927750410509, | |
| "eval_runtime": 5.9155, | |
| "eval_samples_per_second": 425.831, | |
| "eval_steps_per_second": 53.25, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 2.996784565916399, | |
| "eval_accuracy": 0.9486669447207161, | |
| "eval_f1": 0.6676790685902303, | |
| "eval_loss": 0.1634686440229416, | |
| "eval_precision": 0.6209981167608286, | |
| "eval_recall": 0.7219485495347564, | |
| "eval_runtime": 5.9009, | |
| "eval_samples_per_second": 426.884, | |
| "eval_steps_per_second": 53.382, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 3.215434083601286, | |
| "grad_norm": 0.9288749098777771, | |
| "learning_rate": 3.387096774193548e-05, | |
| "loss": 0.1246, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9492604831723828, | |
| "eval_f1": 0.6711919630735812, | |
| "eval_loss": 0.20466655492782593, | |
| "eval_precision": 0.665948275862069, | |
| "eval_recall": 0.6765188834154351, | |
| "eval_runtime": 5.9155, | |
| "eval_samples_per_second": 425.831, | |
| "eval_steps_per_second": 53.25, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 4.996784565916399, | |
| "eval_accuracy": 0.9479771567904007, | |
| "eval_f1": 0.6827731092436975, | |
| "eval_loss": 0.2133806049823761, | |
| "eval_precision": 0.6562342251388188, | |
| "eval_recall": 0.7115489874110563, | |
| "eval_runtime": 5.8759, | |
| "eval_samples_per_second": 428.701, | |
| "eval_steps_per_second": 53.609, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.949388815810581, | |
| "eval_f1": 0.6795913020696882, | |
| "eval_loss": 0.2258971482515335, | |
| "eval_precision": 0.6517587939698493, | |
| "eval_recall": 0.7099069512862616, | |
| "eval_runtime": 5.9106, | |
| "eval_samples_per_second": 426.187, | |
| "eval_steps_per_second": 53.294, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 6.430868167202572, | |
| "grad_norm": 0.18494442105293274, | |
| "learning_rate": 1.774193548387097e-05, | |
| "loss": 0.0242, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.996784565916399, | |
| "eval_accuracy": 0.9496615226667522, | |
| "eval_f1": 0.6946045049764275, | |
| "eval_loss": 0.24502409994602203, | |
| "eval_precision": 0.6659969864389754, | |
| "eval_recall": 0.7257799671592775, | |
| "eval_runtime": 5.8918, | |
| "eval_samples_per_second": 427.542, | |
| "eval_steps_per_second": 53.464, | |
| "step": 1088 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9490679842150855, | |
| "eval_f1": 0.6841015018125324, | |
| "eval_loss": 0.26501980423927307, | |
| "eval_precision": 0.6491400491400492, | |
| "eval_recall": 0.7230432402846196, | |
| "eval_runtime": 5.9184, | |
| "eval_samples_per_second": 425.624, | |
| "eval_steps_per_second": 53.224, | |
| "step": 1244 | |
| }, | |
| { | |
| "epoch": 8.996784565916398, | |
| "eval_accuracy": 0.9497577721454009, | |
| "eval_f1": 0.687797147385103, | |
| "eval_loss": 0.27453720569610596, | |
| "eval_precision": 0.664624808575804, | |
| "eval_recall": 0.7126436781609196, | |
| "eval_runtime": 5.9283, | |
| "eval_samples_per_second": 424.913, | |
| "eval_steps_per_second": 53.135, | |
| "step": 1399 | |
| }, | |
| { | |
| "epoch": 9.646302250803858, | |
| "grad_norm": 0.35425594449043274, | |
| "learning_rate": 1.6129032258064516e-06, | |
| "loss": 0.0083, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.967845659163988, | |
| "eval_accuracy": 0.950255061118419, | |
| "eval_f1": 0.6896008403361344, | |
| "eval_loss": 0.27744925022125244, | |
| "eval_precision": 0.662796567390207, | |
| "eval_recall": 0.7186644772851669, | |
| "eval_runtime": 6.1493, | |
| "eval_samples_per_second": 409.643, | |
| "eval_steps_per_second": 51.226, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 9.967845659163988, | |
| "step": 1550, | |
| "total_flos": 4644619911314910.0, | |
| "train_loss": 0.050868147861573, | |
| "train_runtime": 855.1929, | |
| "train_samples_per_second": 116.102, | |
| "train_steps_per_second": 1.812 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1550, | |
| "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": 4644619911314910.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |