| { |
| "best_global_step": 1376, |
| "best_metric": 0.012005209922790527, |
| "best_model_checkpoint": "projects/PetHarbor/data/augment/arrow_v5/model/checkpoint-1376", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 2752, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0, |
| "eval_f1": 0.011655798995725575, |
| "eval_loss": 2.4493634700775146, |
| "eval_precision": 0.09168997185092281, |
| "eval_recall": 0.05262704226436905, |
| "eval_runtime": 12.3437, |
| "eval_samples_per_second": 134.238, |
| "eval_steps_per_second": 4.213, |
| "step": 0 |
| }, |
| { |
| "epoch": 0.7267441860465116, |
| "grad_norm": 0.2848288416862488, |
| "learning_rate": 4.996373546511628e-05, |
| "loss": 0.0484, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.8927075594912149, |
| "eval_loss": 0.013240625150501728, |
| "eval_precision": 0.8758418145856814, |
| "eval_recall": 0.9170635030650058, |
| "eval_runtime": 12.5123, |
| "eval_samples_per_second": 132.429, |
| "eval_steps_per_second": 4.156, |
| "step": 688 |
| }, |
| { |
| "epoch": 1.4534883720930232, |
| "grad_norm": 0.19568854570388794, |
| "learning_rate": 4.992739825581396e-05, |
| "loss": 0.0071, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.9068541971529176, |
| "eval_loss": 0.012005209922790527, |
| "eval_precision": 0.9104600842733132, |
| "eval_recall": 0.9040660692132211, |
| "eval_runtime": 12.5166, |
| "eval_samples_per_second": 132.384, |
| "eval_steps_per_second": 4.154, |
| "step": 1376 |
| }, |
| { |
| "epoch": 2.1802325581395348, |
| "grad_norm": 0.035110026597976685, |
| "learning_rate": 4.989106104651163e-05, |
| "loss": 0.0038, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.9069767441860463, |
| "grad_norm": 0.008144177496433258, |
| "learning_rate": 4.985472383720931e-05, |
| "loss": 0.0025, |
| "step": 2000 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.9162870645176323, |
| "eval_loss": 0.01785987988114357, |
| "eval_precision": 0.9166192713919116, |
| "eval_recall": 0.9175617135937298, |
| "eval_runtime": 12.5589, |
| "eval_samples_per_second": 131.939, |
| "eval_steps_per_second": 4.14, |
| "step": 2064 |
| }, |
| { |
| "epoch": 3.633720930232558, |
| "grad_norm": 0.44367948174476624, |
| "learning_rate": 4.981838662790698e-05, |
| "loss": 0.0021, |
| "step": 2500 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.9225461672714073, |
| "eval_loss": 0.016809402033686638, |
| "eval_precision": 0.920670658749496, |
| "eval_recall": 0.9248274530000097, |
| "eval_runtime": 12.5585, |
| "eval_samples_per_second": 131.942, |
| "eval_steps_per_second": 4.141, |
| "step": 2752 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 688000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1000, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "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": 2.2993895044079616e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
