| { | |
| "best_metric": 0.02781366929411888, | |
| "best_model_checkpoint": "./teapotllm/checkpoint-372", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 372, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "em_boolean": 0.4, | |
| "em_extraction": 0.5, | |
| "em_qa": 0.0, | |
| "em_summarization": 0.0, | |
| "em_unanswerable": 0.0, | |
| "epoch": 1.0, | |
| "mean_em": 0.13636363636363635, | |
| "mean_similarity": 0.7151702378848286, | |
| "mean_word_count_diff": 4.0606060606060606, | |
| "similarity_boolean": 0.6859854146838188, | |
| "similarity_extraction": 0.6776353690773249, | |
| "similarity_qa": 0.7660255491733551, | |
| "similarity_summarization": 0.7428409457206726, | |
| "similarity_unanswerable": 0.7166690183803439, | |
| "word_count_diff_boolean": 1.9, | |
| "word_count_diff_extraction": 3.1, | |
| "word_count_diff_qa": 4.7, | |
| "word_count_diff_summarization": 19.25, | |
| "word_count_diff_unanswerable": 2.9375 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.1633770614862442, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.0597, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.02993270382285118, | |
| "eval_runtime": 4.3173, | |
| "eval_samples_per_second": 15.287, | |
| "eval_steps_per_second": 2.085, | |
| "step": 186 | |
| }, | |
| { | |
| "em_boolean": 0.4, | |
| "em_extraction": 0.4, | |
| "em_qa": 0.2, | |
| "em_summarization": 0.0, | |
| "em_unanswerable": 0.03125, | |
| "epoch": 2.0, | |
| "mean_em": 0.16666666666666666, | |
| "mean_similarity": 0.6823387349193747, | |
| "mean_word_count_diff": 4.393939393939394, | |
| "similarity_boolean": 0.6429030410945415, | |
| "similarity_extraction": 0.5662426881492137, | |
| "similarity_qa": 0.8177247762680053, | |
| "similarity_summarization": 0.6609117537736893, | |
| "similarity_unanswerable": 0.6913126385770738, | |
| "word_count_diff_boolean": 2.0, | |
| "word_count_diff_extraction": 4.5, | |
| "word_count_diff_qa": 4.4, | |
| "word_count_diff_summarization": 18.25, | |
| "word_count_diff_unanswerable": 3.375 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.11337712407112122, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.0236, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.02781366929411888, | |
| "eval_runtime": 4.3427, | |
| "eval_samples_per_second": 15.198, | |
| "eval_steps_per_second": 2.072, | |
| "step": 372 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5580, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "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": 1714747355430912.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |