| { |
| "best_global_step": 69, |
| "best_metric": 2.177503824234009, |
| "best_model_checkpoint": "bert_base_rand_50_v2_stsb/checkpoint-69", |
| "epoch": 8.0, |
| "eval_steps": 500, |
| "global_step": 184, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 7.015968322753906, |
| "learning_rate": 4.9e-05, |
| "loss": 2.7742, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.1141745824587814, |
| "eval_loss": 2.6997809410095215, |
| "eval_pearson": 0.12423493512401264, |
| "eval_runtime": 0.9816, |
| "eval_samples_per_second": 1528.104, |
| "eval_spearmanr": 0.10411422979355016, |
| "eval_steps_per_second": 6.112, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 12.438505172729492, |
| "learning_rate": 4.8e-05, |
| "loss": 1.9014, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.22189278127564338, |
| "eval_loss": 2.20047664642334, |
| "eval_pearson": 0.23168831697869519, |
| "eval_runtime": 0.9873, |
| "eval_samples_per_second": 1519.28, |
| "eval_spearmanr": 0.21209724557259158, |
| "eval_steps_per_second": 6.077, |
| "step": 46 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 9.028873443603516, |
| "learning_rate": 4.7e-05, |
| "loss": 1.647, |
| "step": 69 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.2988210826571779, |
| "eval_loss": 2.177503824234009, |
| "eval_pearson": 0.3055323486414381, |
| "eval_runtime": 1.0236, |
| "eval_samples_per_second": 1465.45, |
| "eval_spearmanr": 0.2921098166729177, |
| "eval_steps_per_second": 5.862, |
| "step": 69 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 19.29217529296875, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 1.2684, |
| "step": 92 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.3049377990658696, |
| "eval_loss": 2.243820905685425, |
| "eval_pearson": 0.3100292144418018, |
| "eval_runtime": 0.9744, |
| "eval_samples_per_second": 1539.359, |
| "eval_spearmanr": 0.2998463836899374, |
| "eval_steps_per_second": 6.157, |
| "step": 92 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 19.03211212158203, |
| "learning_rate": 4.5e-05, |
| "loss": 0.9726, |
| "step": 115 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.2954603417746404, |
| "eval_loss": 2.6894407272338867, |
| "eval_pearson": 0.2977501099753369, |
| "eval_runtime": 0.9691, |
| "eval_samples_per_second": 1547.85, |
| "eval_spearmanr": 0.29317057357394394, |
| "eval_steps_per_second": 6.191, |
| "step": 115 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 8.887028694152832, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.7533, |
| "step": 138 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.3101275987953827, |
| "eval_loss": 2.5985212326049805, |
| "eval_pearson": 0.31027679401627467, |
| "eval_runtime": 0.9753, |
| "eval_samples_per_second": 1538.005, |
| "eval_spearmanr": 0.30997840357449075, |
| "eval_steps_per_second": 6.152, |
| "step": 138 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 9.385457038879395, |
| "learning_rate": 4.3e-05, |
| "loss": 0.5559, |
| "step": 161 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_combined_score": 0.3401279746718968, |
| "eval_loss": 2.514089584350586, |
| "eval_pearson": 0.33971260003015225, |
| "eval_runtime": 0.956, |
| "eval_samples_per_second": 1569.002, |
| "eval_spearmanr": 0.3405433493136414, |
| "eval_steps_per_second": 6.276, |
| "step": 161 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 5.784945011138916, |
| "learning_rate": 4.2e-05, |
| "loss": 0.4489, |
| "step": 184 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_combined_score": 0.32879470610338724, |
| "eval_loss": 2.703766345977783, |
| "eval_pearson": 0.328013228548718, |
| "eval_runtime": 1.0213, |
| "eval_samples_per_second": 1468.787, |
| "eval_spearmanr": 0.3295761836580564, |
| "eval_steps_per_second": 5.875, |
| "step": 184 |
| }, |
| { |
| "epoch": 8.0, |
| "step": 184, |
| "total_flos": 6050447504044032.0, |
| "train_loss": 1.290205955505371, |
| "train_runtime": 101.6643, |
| "train_samples_per_second": 2827.444, |
| "train_steps_per_second": 11.312 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1150, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 50, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 5 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6050447504044032.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
