| { |
| "best_metric": 0.40960419178009033, |
| "best_model_checkpoint": "autotrain-roblox-10/checkpoint-300", |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02, |
| "grad_norm": 8.799605369567871, |
| "learning_rate": 2.777777777777778e-06, |
| "loss": 0.8052, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.04, |
| "grad_norm": 11.565935134887695, |
| "learning_rate": 6.111111111111111e-06, |
| "loss": 0.8027, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.06, |
| "grad_norm": 7.1787590980529785, |
| "learning_rate": 9.444444444444445e-06, |
| "loss": 0.796, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 2.775609254837036, |
| "learning_rate": 1.2777777777777777e-05, |
| "loss": 0.7706, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 4.121618747711182, |
| "learning_rate": 1.6111111111111115e-05, |
| "loss": 0.7175, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.12, |
| "grad_norm": 1.8891937732696533, |
| "learning_rate": 1.9444444444444445e-05, |
| "loss": 0.697, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.14, |
| "grad_norm": 2.095088243484497, |
| "learning_rate": 2.277777777777778e-05, |
| "loss": 0.6848, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 3.5387184619903564, |
| "learning_rate": 2.6111111111111114e-05, |
| "loss": 0.7146, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.18, |
| "grad_norm": 4.3815131187438965, |
| "learning_rate": 2.9444444444444448e-05, |
| "loss": 0.6832, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 6.097675800323486, |
| "learning_rate": 3.277777777777778e-05, |
| "loss": 0.7085, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.22, |
| "grad_norm": 3.172816276550293, |
| "learning_rate": 3.611111111111111e-05, |
| "loss": 0.6388, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 2.8284499645233154, |
| "learning_rate": 3.944444444444445e-05, |
| "loss": 0.727, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.26, |
| "grad_norm": 4.939257621765137, |
| "learning_rate": 4.277777777777778e-05, |
| "loss": 0.653, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.28, |
| "grad_norm": 5.6476521492004395, |
| "learning_rate": 4.6111111111111115e-05, |
| "loss": 0.6342, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 8.957379341125488, |
| "learning_rate": 4.9444444444444446e-05, |
| "loss": 0.5829, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 10.431815147399902, |
| "learning_rate": 4.969135802469136e-05, |
| "loss": 0.629, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.34, |
| "grad_norm": 7.197211742401123, |
| "learning_rate": 4.938271604938271e-05, |
| "loss": 0.6038, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.36, |
| "grad_norm": 18.572933197021484, |
| "learning_rate": 4.901234567901235e-05, |
| "loss": 0.5653, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.38, |
| "grad_norm": 3.8738515377044678, |
| "learning_rate": 4.864197530864198e-05, |
| "loss": 0.5197, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 13.589826583862305, |
| "learning_rate": 4.827160493827161e-05, |
| "loss": 0.5653, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.42, |
| "grad_norm": 7.053980350494385, |
| "learning_rate": 4.7901234567901237e-05, |
| "loss": 0.6216, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.44, |
| "grad_norm": 5.756833076477051, |
| "learning_rate": 4.7530864197530866e-05, |
| "loss": 0.6131, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.46, |
| "grad_norm": 4.334901809692383, |
| "learning_rate": 4.7160493827160495e-05, |
| "loss": 0.5738, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 5.856199264526367, |
| "learning_rate": 4.6790123456790124e-05, |
| "loss": 0.5103, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 5.805249214172363, |
| "learning_rate": 4.641975308641975e-05, |
| "loss": 0.4794, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.52, |
| "grad_norm": 6.147461414337158, |
| "learning_rate": 4.604938271604938e-05, |
| "loss": 0.4606, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.54, |
| "grad_norm": 10.369290351867676, |
| "learning_rate": 4.567901234567901e-05, |
| "loss": 0.4953, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 12.811848640441895, |
| "learning_rate": 4.530864197530865e-05, |
| "loss": 0.3625, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.58, |
| "grad_norm": 11.082608222961426, |
| "learning_rate": 4.493827160493828e-05, |
| "loss": 0.5738, |
| "step": 174 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 2.9676032066345215, |
| "learning_rate": 4.4567901234567906e-05, |
| "loss": 0.374, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.62, |
| "grad_norm": 19.597843170166016, |
| "learning_rate": 4.4197530864197535e-05, |
| "loss": 0.4335, |
| "step": 186 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 6.006842613220215, |
| "learning_rate": 4.3827160493827164e-05, |
| "loss": 0.5708, |
| "step": 192 |
| }, |
| { |
| "epoch": 0.66, |
| "grad_norm": 6.002368450164795, |
| "learning_rate": 4.345679012345679e-05, |
| "loss": 0.4244, |
| "step": 198 |
| }, |
| { |
| "epoch": 0.68, |
| "grad_norm": 4.788684368133545, |
| "learning_rate": 4.308641975308642e-05, |
| "loss": 0.4441, |
| "step": 204 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 6.1746954917907715, |
| "learning_rate": 4.271604938271605e-05, |
| "loss": 0.5917, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 4.382603645324707, |
| "learning_rate": 4.234567901234568e-05, |
| "loss": 0.5596, |
| "step": 216 |
| }, |
| { |
| "epoch": 0.74, |
| "grad_norm": 30.41250228881836, |
| "learning_rate": 4.197530864197531e-05, |
| "loss": 0.521, |
| "step": 222 |
| }, |
| { |
| "epoch": 0.76, |
| "grad_norm": 4.90874719619751, |
| "learning_rate": 4.1604938271604946e-05, |
| "loss": 0.4642, |
| "step": 228 |
| }, |
| { |
| "epoch": 0.78, |
| "grad_norm": 7.5287675857543945, |
| "learning_rate": 4.1234567901234575e-05, |
| "loss": 0.4263, |
| "step": 234 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 10.244704246520996, |
| "learning_rate": 4.0864197530864204e-05, |
| "loss": 0.5723, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.82, |
| "grad_norm": 4.225964069366455, |
| "learning_rate": 4.049382716049383e-05, |
| "loss": 0.4529, |
| "step": 246 |
| }, |
| { |
| "epoch": 0.84, |
| "grad_norm": 4.297839641571045, |
| "learning_rate": 4.012345679012346e-05, |
| "loss": 0.4485, |
| "step": 252 |
| }, |
| { |
| "epoch": 0.86, |
| "grad_norm": 8.949761390686035, |
| "learning_rate": 3.975308641975309e-05, |
| "loss": 0.463, |
| "step": 258 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 5.039264678955078, |
| "learning_rate": 3.938271604938272e-05, |
| "loss": 0.446, |
| "step": 264 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 5.201369762420654, |
| "learning_rate": 3.901234567901234e-05, |
| "loss": 0.4966, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.92, |
| "grad_norm": 7.023820400238037, |
| "learning_rate": 3.864197530864197e-05, |
| "loss": 0.5405, |
| "step": 276 |
| }, |
| { |
| "epoch": 0.94, |
| "grad_norm": 5.257862091064453, |
| "learning_rate": 3.82716049382716e-05, |
| "loss": 0.4393, |
| "step": 282 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 9.458020210266113, |
| "learning_rate": 3.790123456790123e-05, |
| "loss": 0.3889, |
| "step": 288 |
| }, |
| { |
| "epoch": 0.98, |
| "grad_norm": 6.277890205383301, |
| "learning_rate": 3.7530864197530867e-05, |
| "loss": 0.4674, |
| "step": 294 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.080256462097168, |
| "learning_rate": 3.7160493827160496e-05, |
| "loss": 0.4566, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8067542213883677, |
| "eval_auc": 0.8871317829457365, |
| "eval_f1": 0.8074766355140187, |
| "eval_loss": 0.40960419178009033, |
| "eval_precision": 0.779783393501805, |
| "eval_recall": 0.8372093023255814, |
| "eval_runtime": 0.9868, |
| "eval_samples_per_second": 540.12, |
| "eval_steps_per_second": 17.227, |
| "step": 300 |
| } |
| ], |
| "logging_steps": 6, |
| "max_steps": 900, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.01 |
| }, |
| "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": 315272822085120.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
