| { |
| "best_global_step": 69, |
| "best_metric": 2.4306833744049072, |
| "best_model_checkpoint": "bert_base_rand_100_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": 5.4255146980285645, |
| "learning_rate": 4.9e-05, |
| "loss": 2.8477, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.0840225394397058, |
| "eval_loss": 2.5025646686553955, |
| "eval_pearson": 0.08808286019741556, |
| "eval_runtime": 0.9797, |
| "eval_samples_per_second": 1531.146, |
| "eval_spearmanr": 0.07996221868199607, |
| "eval_steps_per_second": 6.125, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 7.359004497528076, |
| "learning_rate": 4.8e-05, |
| "loss": 1.9428, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.14166004417568906, |
| "eval_loss": 2.4720664024353027, |
| "eval_pearson": 0.14748358720946364, |
| "eval_runtime": 0.9917, |
| "eval_samples_per_second": 1512.613, |
| "eval_spearmanr": 0.1358365011419145, |
| "eval_steps_per_second": 6.05, |
| "step": 46 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 6.980101585388184, |
| "learning_rate": 4.7e-05, |
| "loss": 1.6984, |
| "step": 69 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.2211151865926963, |
| "eval_loss": 2.4306833744049072, |
| "eval_pearson": 0.2244225133951147, |
| "eval_runtime": 1.0084, |
| "eval_samples_per_second": 1487.573, |
| "eval_spearmanr": 0.21780785979027786, |
| "eval_steps_per_second": 5.95, |
| "step": 69 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 11.058927536010742, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 1.3566, |
| "step": 92 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.24161991754584333, |
| "eval_loss": 2.509110689163208, |
| "eval_pearson": 0.24258512771609939, |
| "eval_runtime": 0.9629, |
| "eval_samples_per_second": 1557.809, |
| "eval_spearmanr": 0.24065470737558728, |
| "eval_steps_per_second": 6.231, |
| "step": 92 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 7.6623101234436035, |
| "learning_rate": 4.5e-05, |
| "loss": 1.0597, |
| "step": 115 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.2455312141979038, |
| "eval_loss": 2.56744384765625, |
| "eval_pearson": 0.24862260186601912, |
| "eval_runtime": 0.9956, |
| "eval_samples_per_second": 1506.578, |
| "eval_spearmanr": 0.2424398265297885, |
| "eval_steps_per_second": 6.026, |
| "step": 115 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 10.41344165802002, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.8102, |
| "step": 138 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.26896620086023215, |
| "eval_loss": 2.6909260749816895, |
| "eval_pearson": 0.27129893094532953, |
| "eval_runtime": 0.9643, |
| "eval_samples_per_second": 1555.598, |
| "eval_spearmanr": 0.2666334707751347, |
| "eval_steps_per_second": 6.222, |
| "step": 138 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 9.79807186126709, |
| "learning_rate": 4.3e-05, |
| "loss": 0.6127, |
| "step": 161 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_combined_score": 0.26158713009122414, |
| "eval_loss": 2.752532482147217, |
| "eval_pearson": 0.2639329043714456, |
| "eval_runtime": 0.9621, |
| "eval_samples_per_second": 1559.123, |
| "eval_spearmanr": 0.25924135581100266, |
| "eval_steps_per_second": 6.236, |
| "step": 161 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 7.937746524810791, |
| "learning_rate": 4.2e-05, |
| "loss": 0.4965, |
| "step": 184 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_combined_score": 0.25855071258906015, |
| "eval_loss": 2.8617939949035645, |
| "eval_pearson": 0.26063827406606793, |
| "eval_runtime": 1.0019, |
| "eval_samples_per_second": 1497.225, |
| "eval_spearmanr": 0.2564631511120524, |
| "eval_steps_per_second": 5.989, |
| "step": 184 |
| }, |
| { |
| "epoch": 8.0, |
| "step": 184, |
| "total_flos": 6050447504044032.0, |
| "train_loss": 1.3530696837798408, |
| "train_runtime": 100.1363, |
| "train_samples_per_second": 2870.586, |
| "train_steps_per_second": 11.484 |
| } |
| ], |
| "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 |
| } |
|
|
