| { |
| "best_global_step": 500, |
| "best_metric": 0.8781195327560386, |
| "best_model_checkpoint": "models/norbert4-v6-stage2-group-b-v3/checkpoint-500", |
| "epoch": 0.1968503937007874, |
| "eval_steps": 500, |
| "global_step": 500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03937007874015748, |
| "grad_norm": 5.167735576629639, |
| "learning_rate": 4.981281544380601e-06, |
| "loss": 0.3873, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07874015748031496, |
| "grad_norm": 3.158674955368042, |
| "learning_rate": 4.924654926599624e-06, |
| "loss": 0.311, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.11811023622047244, |
| "grad_norm": 2.273364782333374, |
| "learning_rate": 4.830983399960023e-06, |
| "loss": 0.2868, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.15748031496062992, |
| "grad_norm": 2.8687314987182617, |
| "learning_rate": 4.701698117872101e-06, |
| "loss": 0.262, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1968503937007874, |
| "grad_norm": 5.26961088180542, |
| "learning_rate": 4.538774355843794e-06, |
| "loss": 0.2655, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1968503937007874, |
| "eval_group_b_retrieval_cosine_accuracy@1": 0.8330661322645291, |
| "eval_group_b_retrieval_cosine_accuracy@10": 0.9219438877755511, |
| "eval_group_b_retrieval_cosine_accuracy@3": 0.8883767535070141, |
| "eval_group_b_retrieval_cosine_accuracy@5": 0.904308617234469, |
| "eval_group_b_retrieval_cosine_map@100": 0.8658417432001136, |
| "eval_group_b_retrieval_cosine_mrr@10": 0.8640294080223927, |
| "eval_group_b_retrieval_cosine_ndcg@10": 0.8781195327560386, |
| "eval_group_b_retrieval_cosine_precision@1": 0.8330661322645291, |
| "eval_group_b_retrieval_cosine_precision@10": 0.0921943887775551, |
| "eval_group_b_retrieval_cosine_precision@3": 0.296125584502338, |
| "eval_group_b_retrieval_cosine_precision@5": 0.18086172344689377, |
| "eval_group_b_retrieval_cosine_recall@1": 0.8330661322645291, |
| "eval_group_b_retrieval_cosine_recall@10": 0.9219438877755511, |
| "eval_group_b_retrieval_cosine_recall@3": 0.8883767535070141, |
| "eval_group_b_retrieval_cosine_recall@5": 0.904308617234469, |
| "eval_loss": 0.09108907729387283, |
| "eval_runtime": 145.4461, |
| "eval_samples_per_second": 68.616, |
| "eval_steps_per_second": 4.29, |
| "step": 500 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2540, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "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": 0.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
