| { |
| "best_global_step": 1500, |
| "best_metric": 0.9490445859872612, |
| "best_model_checkpoint": "/workspace/AI/Trend_Primus-FineWeb_Filtering-pipeline/securebert_finetuned/defensive_vs_rest/checkpoint-1500", |
| "epoch": 2.7272727272727275, |
| "eval_steps": 300, |
| "global_step": 1500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 1.2393633127212524, |
| "learning_rate": 5.6571428571428576e-06, |
| "loss": 0.1439, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 1.2253516912460327, |
| "learning_rate": 1.1371428571428573e-05, |
| "loss": 0.0855, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 0.6038007140159607, |
| "learning_rate": 1.708571428571429e-05, |
| "loss": 0.0369, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "eval_f1": 0.8451570393147375, |
| "eval_f2": 0.9234018045690152, |
| "eval_loss": 0.022321535274386406, |
| "eval_precision": 0.7405696689761355, |
| "eval_recall": 0.9841432225063939, |
| "eval_runtime": 10.9053, |
| "eval_samples_per_second": 717.082, |
| "eval_steps_per_second": 11.279, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.47052955627441406, |
| "learning_rate": 1.924615384615385e-05, |
| "loss": 0.0203, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 2.0642011165618896, |
| "learning_rate": 1.770769230769231e-05, |
| "loss": 0.0176, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0909090909090908, |
| "grad_norm": 0.28900912404060364, |
| "learning_rate": 1.6169230769230772e-05, |
| "loss": 0.0116, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0909090909090908, |
| "eval_f1": 0.9583852479441815, |
| "eval_f2": 0.9733751771613687, |
| "eval_loss": 0.013802087865769863, |
| "eval_precision": 0.934402332361516, |
| "eval_recall": 0.9836317135549872, |
| "eval_runtime": 11.4515, |
| "eval_samples_per_second": 682.883, |
| "eval_steps_per_second": 10.741, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.2727272727272727, |
| "grad_norm": 0.4510941803455353, |
| "learning_rate": 1.4630769230769233e-05, |
| "loss": 0.0083, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.4545454545454546, |
| "grad_norm": 0.546210765838623, |
| "learning_rate": 1.3092307692307693e-05, |
| "loss": 0.0074, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.6363636363636362, |
| "grad_norm": 2.2349956035614014, |
| "learning_rate": 1.1553846153846156e-05, |
| "loss": 0.0084, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.6363636363636362, |
| "eval_f1": 0.9500734214390602, |
| "eval_f2": 0.9752788664455834, |
| "eval_loss": 0.009357056580483913, |
| "eval_precision": 0.9108399812294697, |
| "eval_recall": 0.992838874680307, |
| "eval_runtime": 11.0303, |
| "eval_samples_per_second": 708.955, |
| "eval_steps_per_second": 11.151, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 0.4002629518508911, |
| "learning_rate": 1.0015384615384615e-05, |
| "loss": 0.0076, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.0686814934015274, |
| "learning_rate": 8.476923076923078e-06, |
| "loss": 0.0063, |
| "step": 1100 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 0.40794429183006287, |
| "learning_rate": 6.9384615384615395e-06, |
| "loss": 0.0032, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "eval_f1": 0.9634601043997018, |
| "eval_f2": 0.9799757281553398, |
| "eval_loss": 0.009985245764255524, |
| "eval_precision": 0.937137330754352, |
| "eval_recall": 0.991304347826087, |
| "eval_runtime": 10.5643, |
| "eval_samples_per_second": 740.231, |
| "eval_steps_per_second": 11.643, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 0.26694178581237793, |
| "learning_rate": 5.400000000000001e-06, |
| "loss": 0.0031, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 0.1839500516653061, |
| "learning_rate": 3.861538461538462e-06, |
| "loss": 0.0028, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 0.3117663264274597, |
| "learning_rate": 2.3230769230769234e-06, |
| "loss": 0.0021, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "eval_f1": 0.9694694694694694, |
| "eval_f2": 0.9821519115708346, |
| "eval_loss": 0.010657339356839657, |
| "eval_precision": 0.9490445859872612, |
| "eval_recall": 0.9907928388746803, |
| "eval_runtime": 10.7067, |
| "eval_samples_per_second": 730.384, |
| "eval_steps_per_second": 11.488, |
| "step": 1500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 1650, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 300, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 2, |
| "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": 5.05067981869056e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
