| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 248, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 4.933078765869141, |
| "learning_rate": 1.7580645161290325e-05, |
| "loss": 0.4086, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.783539089652777, |
| "eval_loss": 0.16160552203655243, |
| "eval_precision": 0.7601809954730898, |
| "eval_recall": 0.808378148879682, |
| "eval_runtime": 1.4708, |
| "eval_samples_per_second": 686.035, |
| "eval_steps_per_second": 5.439, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.215329170227051, |
| "learning_rate": 1.5080645161290324e-05, |
| "loss": 0.1213, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.8489169130173646, |
| "eval_loss": 0.11775331199169159, |
| "eval_precision": 0.823185323050191, |
| "eval_recall": 0.8763090857603275, |
| "eval_runtime": 1.3955, |
| "eval_samples_per_second": 723.05, |
| "eval_steps_per_second": 5.733, |
| "step": 62 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.6429105997085571, |
| "learning_rate": 1.2580645161290324e-05, |
| "loss": 0.0765, |
| "step": 93 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.8752420420264311, |
| "eval_loss": 0.11041084676980972, |
| "eval_precision": 0.8558290505792377, |
| "eval_recall": 0.8955561845431771, |
| "eval_runtime": 1.5773, |
| "eval_samples_per_second": 639.714, |
| "eval_steps_per_second": 5.072, |
| "step": 93 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.440000057220459, |
| "learning_rate": 1.0080645161290323e-05, |
| "loss": 0.0551, |
| "step": 124 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_f1": 0.8823774425760322, |
| "eval_loss": 0.10791593044996262, |
| "eval_precision": 0.8661395856028732, |
| "eval_recall": 0.8992357769575453, |
| "eval_runtime": 1.4615, |
| "eval_samples_per_second": 690.409, |
| "eval_steps_per_second": 5.474, |
| "step": 124 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.1584373712539673, |
| "learning_rate": 7.580645161290323e-06, |
| "loss": 0.042, |
| "step": 155 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_f1": 0.8873842702525155, |
| "eval_loss": 0.11261641979217529, |
| "eval_precision": 0.8669006479458238, |
| "eval_recall": 0.9088593263489702, |
| "eval_runtime": 1.5207, |
| "eval_samples_per_second": 663.502, |
| "eval_steps_per_second": 5.261, |
| "step": 155 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.7214231491088867, |
| "learning_rate": 5.080645161290323e-06, |
| "loss": 0.035, |
| "step": 186 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_f1": 0.8884892036331468, |
| "eval_loss": 0.11356285214424133, |
| "eval_precision": 0.8690121786174045, |
| "eval_recall": 0.9088593263489702, |
| "eval_runtime": 1.4456, |
| "eval_samples_per_second": 697.982, |
| "eval_steps_per_second": 5.534, |
| "step": 186 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 1.0617001056671143, |
| "learning_rate": 2.580645161290323e-06, |
| "loss": 0.0303, |
| "step": 217 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_f1": 0.8905534698226346, |
| "eval_loss": 0.11567464470863342, |
| "eval_precision": 0.8732317736646539, |
| "eval_recall": 0.9085762807786342, |
| "eval_runtime": 1.4347, |
| "eval_samples_per_second": 703.278, |
| "eval_steps_per_second": 5.576, |
| "step": 217 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.7687620520591736, |
| "learning_rate": 8.064516129032259e-08, |
| "loss": 0.028, |
| "step": 248 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_f1": 0.8886423469618369, |
| "eval_loss": 0.11542723327875137, |
| "eval_precision": 0.8711256117431454, |
| "eval_recall": 0.9068780073566179, |
| "eval_runtime": 1.5699, |
| "eval_samples_per_second": 642.7, |
| "eval_steps_per_second": 5.096, |
| "step": 248 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 248, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 8, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1813582770980094.0, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
