| { |
| "best_metric": 0.16486743092536926, |
| "best_model_checkpoint": "G-SciEdBERT-definition_classification/checkpoint-2514", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 5028, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.39777247414478917, |
| "grad_norm": 2.676848888397217, |
| "learning_rate": 1.9204455051710422e-05, |
| "loss": 0.2996, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.7955449482895783, |
| "grad_norm": 3.230545997619629, |
| "learning_rate": 1.8408910103420846e-05, |
| "loss": 0.2716, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9563981042654028, |
| "eval_loss": 0.17062236368656158, |
| "eval_runtime": 16.2695, |
| "eval_samples_per_second": 129.691, |
| "eval_steps_per_second": 16.227, |
| "step": 1257 |
| }, |
| { |
| "epoch": 1.1933174224343674, |
| "grad_norm": 0.3801514804363251, |
| "learning_rate": 1.7613365155131266e-05, |
| "loss": 0.2206, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.5910898965791567, |
| "grad_norm": 0.17281392216682434, |
| "learning_rate": 1.681782020684169e-05, |
| "loss": 0.1996, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.988862370723946, |
| "grad_norm": 0.6494017839431763, |
| "learning_rate": 1.602227525855211e-05, |
| "loss": 0.213, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9597156398104265, |
| "eval_loss": 0.16486743092536926, |
| "eval_runtime": 14.5878, |
| "eval_samples_per_second": 144.641, |
| "eval_steps_per_second": 18.097, |
| "step": 2514 |
| }, |
| { |
| "epoch": 2.386634844868735, |
| "grad_norm": 0.14585678279399872, |
| "learning_rate": 1.5226730310262532e-05, |
| "loss": 0.1586, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.7844073190135243, |
| "grad_norm": 0.8012990355491638, |
| "learning_rate": 1.4431185361972953e-05, |
| "loss": 0.1683, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9502369668246445, |
| "eval_loss": 0.23463724553585052, |
| "eval_runtime": 14.6284, |
| "eval_samples_per_second": 144.24, |
| "eval_steps_per_second": 18.047, |
| "step": 3771 |
| }, |
| { |
| "epoch": 3.1821797931583133, |
| "grad_norm": 0.05950465425848961, |
| "learning_rate": 1.3635640413683375e-05, |
| "loss": 0.1582, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.579952267303103, |
| "grad_norm": 6.376718997955322, |
| "learning_rate": 1.2840095465393797e-05, |
| "loss": 0.1504, |
| "step": 4500 |
| }, |
| { |
| "epoch": 3.977724741447892, |
| "grad_norm": 2.2648589611053467, |
| "learning_rate": 1.2044550517104217e-05, |
| "loss": 0.1364, |
| "step": 5000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9597156398104265, |
| "eval_loss": 0.20282548666000366, |
| "eval_runtime": 14.4442, |
| "eval_samples_per_second": 146.08, |
| "eval_steps_per_second": 18.277, |
| "step": 5028 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 12570, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9166470557698800.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
