| { |
| "best_metric": 0.04531409963965416, |
| "best_model_checkpoint": "results_bert-base-spanish-wwm-cased/epoch20_bs64/checkpoint-48", |
| "epoch": 11.0, |
| "eval_steps": 500, |
| "global_step": 176, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.9667894840240479, |
| "learning_rate": 4.75e-05, |
| "loss": 0.3262, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accurracy": { |
| "accuracy": 0.9767987486965589 |
| }, |
| "eval_f1": [ |
| 0.9801708132194579, |
| 0.8147120055517002, |
| 1.0 |
| ], |
| "eval_loss": 0.06416129320859909, |
| "eval_precision": [ |
| 0.9833109819699002, |
| 0.7911051212938005, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9770506366597572, |
| 0.8397711015736766, |
| 1.0 |
| ], |
| "eval_runtime": 3.1156, |
| "eval_samples_per_second": 43.972, |
| "eval_steps_per_second": 0.963, |
| "step": 16 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.47570934891700745, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0561, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accurracy": { |
| "accuracy": 0.9820994091067083 |
| }, |
| "eval_f1": [ |
| 0.9846999405822935, |
| 0.8571428571428571, |
| 1.0 |
| ], |
| "eval_loss": 0.04880336672067642, |
| "eval_precision": [ |
| 0.9879284649776453, |
| 0.8317631224764468, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.981492448919159, |
| 0.8841201716738197, |
| 1.0 |
| ], |
| "eval_runtime": 3.673, |
| "eval_samples_per_second": 37.299, |
| "eval_steps_per_second": 0.817, |
| "step": 32 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.4510585069656372, |
| "learning_rate": 4.25e-05, |
| "loss": 0.041, |
| "step": 48 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accurracy": { |
| "accuracy": 0.9831421619742787 |
| }, |
| "eval_f1": [ |
| 0.9856040368061739, |
| 0.8643356643356643, |
| 1.0 |
| ], |
| "eval_loss": 0.04531409963965416, |
| "eval_precision": [ |
| 0.9879500148765249, |
| 0.8454172366621067, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9832691738229198, |
| 0.8841201716738197, |
| 1.0 |
| ], |
| "eval_runtime": 3.2836, |
| "eval_samples_per_second": 41.722, |
| "eval_steps_per_second": 0.914, |
| "step": 48 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.5891135334968567, |
| "learning_rate": 4e-05, |
| "loss": 0.0305, |
| "step": 64 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accurracy": { |
| "accuracy": 0.9830552659019812 |
| }, |
| "eval_f1": [ |
| 0.9855544855174457, |
| 0.8614072494669509, |
| 1.0 |
| ], |
| "eval_loss": 0.04799243062734604, |
| "eval_precision": [ |
| 0.9862120088954781, |
| 0.8559322033898306, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9848978383180338, |
| 0.8669527896995708, |
| 1.0 |
| ], |
| "eval_runtime": 3.6636, |
| "eval_samples_per_second": 37.395, |
| "eval_steps_per_second": 0.819, |
| "step": 64 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.9005504250526428, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.023, |
| "step": 80 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accurracy": { |
| "accuracy": 0.982186305179006 |
| }, |
| "eval_f1": [ |
| 0.9847843835819787, |
| 0.8569434752267969, |
| 1.0 |
| ], |
| "eval_loss": 0.055779680609703064, |
| "eval_precision": [ |
| 0.9873493079327281, |
| 0.8365122615803815, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9822327509623927, |
| 0.8783977110157367, |
| 1.0 |
| ], |
| "eval_runtime": 3.8421, |
| "eval_samples_per_second": 35.657, |
| "eval_steps_per_second": 0.781, |
| "step": 80 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.5966660976409912, |
| "learning_rate": 3.5e-05, |
| "loss": 0.0181, |
| "step": 96 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accurracy": { |
| "accuracy": 0.982186305179006 |
| }, |
| "eval_f1": [ |
| 0.9847776045147397, |
| 0.857539958304378, |
| 1.0 |
| ], |
| "eval_loss": 0.055696263909339905, |
| "eval_precision": [ |
| 0.9877848949798897, |
| 0.8337837837837838, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9817885697364525, |
| 0.882689556509299, |
| 1.0 |
| ], |
| "eval_runtime": 3.6299, |
| "eval_samples_per_second": 37.742, |
| "eval_steps_per_second": 0.826, |
| "step": 96 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.6903554797172546, |
| "learning_rate": 3.2500000000000004e-05, |
| "loss": 0.0142, |
| "step": 112 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accurracy": { |
| "accuracy": 0.9822732012513035 |
| }, |
| "eval_f1": [ |
| 0.984870958172649, |
| 0.8565400843881856, |
| 1.0 |
| ], |
| "eval_loss": 0.06568428128957748, |
| "eval_precision": [ |
| 0.986627043090639, |
| 0.8423236514522822, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.983121113414273, |
| 0.871244635193133, |
| 1.0 |
| ], |
| "eval_runtime": 3.4926, |
| "eval_samples_per_second": 39.226, |
| "eval_steps_per_second": 0.859, |
| "step": 112 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.4664444923400879, |
| "learning_rate": 3e-05, |
| "loss": 0.0096, |
| "step": 128 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accurracy": { |
| "accuracy": 0.9815780326729232 |
| }, |
| "eval_f1": [ |
| 0.9842613214550854, |
| 0.8523676880222841, |
| 1.0 |
| ], |
| "eval_loss": 0.07148059457540512, |
| "eval_precision": [ |
| 0.9870458606313282, |
| 0.830393487109905, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.981492448919159, |
| 0.8755364806866953, |
| 1.0 |
| ], |
| "eval_runtime": 3.6227, |
| "eval_samples_per_second": 37.817, |
| "eval_steps_per_second": 0.828, |
| "step": 128 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.12620803713798523, |
| "learning_rate": 2.7500000000000004e-05, |
| "loss": 0.0077, |
| "step": 144 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accurracy": { |
| "accuracy": 0.9833159541188738 |
| }, |
| "eval_f1": [ |
| 0.9858197932053175, |
| 0.8594436310395315, |
| 1.0 |
| ], |
| "eval_loss": 0.07231755554676056, |
| "eval_precision": [ |
| 0.9834954317712938, |
| 0.8800599700149925, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9881551673082618, |
| 0.8397711015736766, |
| 1.0 |
| ], |
| "eval_runtime": 3.2894, |
| "eval_samples_per_second": 41.649, |
| "eval_steps_per_second": 0.912, |
| "step": 144 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 0.5548684597015381, |
| "learning_rate": 2.5e-05, |
| "loss": 0.0062, |
| "step": 160 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accurracy": { |
| "accuracy": 0.9833159541188738 |
| }, |
| "eval_f1": [ |
| 0.9857798844615613, |
| 0.8632478632478633, |
| 1.0 |
| ], |
| "eval_loss": 0.07776156067848206, |
| "eval_precision": [ |
| 0.9862181387077653, |
| 0.8595744680851064, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9853420195439739, |
| 0.8669527896995708, |
| 1.0 |
| ], |
| "eval_runtime": 3.5848, |
| "eval_samples_per_second": 38.217, |
| "eval_steps_per_second": 0.837, |
| "step": 160 |
| }, |
| { |
| "epoch": 11.0, |
| "grad_norm": 0.6255295872688293, |
| "learning_rate": 2.25e-05, |
| "loss": 0.0049, |
| "step": 176 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_accurracy": { |
| "accuracy": 0.9835766423357665 |
| }, |
| "eval_f1": [ |
| 0.9859865055238378, |
| 0.8668076109936576, |
| 1.0 |
| ], |
| "eval_loss": 0.07731029391288757, |
| "eval_precision": [ |
| 0.9875241348581613, |
| 0.8541666666666666, |
| 1.0 |
| ], |
| "eval_recall": [ |
| 0.9844536570920935, |
| 0.8798283261802575, |
| 1.0 |
| ], |
| "eval_runtime": 3.8542, |
| "eval_samples_per_second": 35.545, |
| "eval_steps_per_second": 0.778, |
| "step": 176 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 320, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "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": 491604692303340.0, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
