| { |
| "best_global_step": 1760, |
| "best_metric": 0.004073738120496273, |
| "best_model_checkpoint": "/content/drive/MyDrive/evo_ablation_DirectEvolution_CodeT5base_FullFT/checkpoint-1760", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 1760, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.0355877876281738, |
| "learning_rate": 4.991027181875014e-05, |
| "loss": 1.8348119562322442, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.03580193594098091, |
| "eval_runtime": 3.039, |
| "eval_samples_per_second": 72.392, |
| "eval_steps_per_second": 18.098, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.07191833108663559, |
| "learning_rate": 4.925493631367695e-05, |
| "loss": 0.08348724191839045, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.019032808020710945, |
| "eval_runtime": 3.0215, |
| "eval_samples_per_second": 72.811, |
| "eval_steps_per_second": 18.203, |
| "step": 440 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.5394785404205322, |
| "learning_rate": 4.79727833666922e-05, |
| "loss": 0.04584090492942117, |
| "step": 660 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.012234838679432869, |
| "eval_runtime": 3.0514, |
| "eval_samples_per_second": 72.098, |
| "eval_steps_per_second": 18.024, |
| "step": 660 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.1377420276403427, |
| "learning_rate": 4.610819813755038e-05, |
| "loss": 0.025517858158458362, |
| "step": 880 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.00837874785065651, |
| "eval_runtime": 3.0383, |
| "eval_samples_per_second": 72.409, |
| "eval_steps_per_second": 18.102, |
| "step": 880 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.66103595495224, |
| "learning_rate": 4.3692257202498335e-05, |
| "loss": 0.017070700905539773, |
| "step": 1100 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.006502046715468168, |
| "eval_runtime": 3.2267, |
| "eval_samples_per_second": 68.182, |
| "eval_steps_per_second": 17.045, |
| "step": 1100 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.002123212441802025, |
| "learning_rate": 4.079444088124431e-05, |
| "loss": 0.012019785967740145, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.00527948047965765, |
| "eval_runtime": 3.1399, |
| "eval_samples_per_second": 70.066, |
| "eval_steps_per_second": 17.516, |
| "step": 1320 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.03506750613451004, |
| "learning_rate": 3.7489453172552035e-05, |
| "loss": 0.008358093283393167, |
| "step": 1540 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.004877733998000622, |
| "eval_runtime": 3.0578, |
| "eval_samples_per_second": 71.948, |
| "eval_steps_per_second": 17.987, |
| "step": 1540 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.0033804229460656643, |
| "learning_rate": 3.386249471384405e-05, |
| "loss": 0.007093059474771673, |
| "step": 1760 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.004073738120496273, |
| "eval_runtime": 3.0231, |
| "eval_samples_per_second": 72.772, |
| "eval_steps_per_second": 18.193, |
| "step": 1760 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 4400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 20, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.001 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 2 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3188462920519680.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
