| { |
| "best_global_step": 23, |
| "best_metric": 2.2226240634918213, |
| "best_model_checkpoint": "distilbert_km_10_v1_stsb/checkpoint-23", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 138, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 5.956926345825195, |
| "learning_rate": 4.9e-05, |
| "loss": 2.9054, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.18042935626499793, |
| "eval_loss": 2.2226240634918213, |
| "eval_pearson": 0.1877864358275859, |
| "eval_runtime": 0.6223, |
| "eval_samples_per_second": 2410.424, |
| "eval_spearmanr": 0.17307227670240996, |
| "eval_steps_per_second": 9.642, |
| "step": 23 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 6.412149906158447, |
| "learning_rate": 4.8e-05, |
| "loss": 1.9443, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.21386067446126766, |
| "eval_loss": 2.364274501800537, |
| "eval_pearson": 0.22387351640138115, |
| "eval_runtime": 0.6809, |
| "eval_samples_per_second": 2202.939, |
| "eval_spearmanr": 0.2038478325211542, |
| "eval_steps_per_second": 8.812, |
| "step": 46 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 6.441744804382324, |
| "learning_rate": 4.7e-05, |
| "loss": 1.6962, |
| "step": 69 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.23367849137968633, |
| "eval_loss": 2.31948184967041, |
| "eval_pearson": 0.23733731027756047, |
| "eval_runtime": 0.6792, |
| "eval_samples_per_second": 2208.488, |
| "eval_spearmanr": 0.2300196724818122, |
| "eval_steps_per_second": 8.834, |
| "step": 69 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 15.10554027557373, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 1.3248, |
| "step": 92 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.27828612057195884, |
| "eval_loss": 2.291346788406372, |
| "eval_pearson": 0.277835713863869, |
| "eval_runtime": 0.6141, |
| "eval_samples_per_second": 2442.427, |
| "eval_spearmanr": 0.27873652728004866, |
| "eval_steps_per_second": 9.77, |
| "step": 92 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 11.395968437194824, |
| "learning_rate": 4.5e-05, |
| "loss": 0.9649, |
| "step": 115 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.2629117745376003, |
| "eval_loss": 2.628901481628418, |
| "eval_pearson": 0.2679049400535412, |
| "eval_runtime": 0.6927, |
| "eval_samples_per_second": 2165.501, |
| "eval_spearmanr": 0.25791860902165936, |
| "eval_steps_per_second": 8.662, |
| "step": 115 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 14.926880836486816, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.6945, |
| "step": 138 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.2792838187253882, |
| "eval_loss": 2.6541435718536377, |
| "eval_pearson": 0.28314629605204933, |
| "eval_runtime": 0.6254, |
| "eval_samples_per_second": 2398.282, |
| "eval_spearmanr": 0.27542134139872715, |
| "eval_steps_per_second": 9.593, |
| "step": 138 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 138, |
| "total_flos": 2284624480859136.0, |
| "train_loss": 1.5883519269418025, |
| "train_runtime": 43.9223, |
| "train_samples_per_second": 6544.505, |
| "train_steps_per_second": 26.183 |
| } |
| ], |
| "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": 2284624480859136.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
