| { |
| "best_metric": 2.135712146759033, |
| "best_model_checkpoint": "hBERTv2_data_aug_stsb/checkpoint-1259", |
| "epoch": 6.0, |
| "global_step": 7554, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 4.900317712470215e-05, |
| "loss": 0.6302, |
| "step": 1259 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.5155992873552944, |
| "eval_loss": 2.135712146759033, |
| "eval_pearson": 0.5180732083614772, |
| "eval_runtime": 1.7839, |
| "eval_samples_per_second": 840.872, |
| "eval_spearmanr": 0.5131253663491117, |
| "eval_steps_per_second": 3.363, |
| "step": 1259 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.800317712470215e-05, |
| "loss": 0.0973, |
| "step": 2518 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.4388959634942341, |
| "eval_loss": 2.4677507877349854, |
| "eval_pearson": 0.44945880353679196, |
| "eval_runtime": 1.7897, |
| "eval_samples_per_second": 838.143, |
| "eval_spearmanr": 0.4283331234516762, |
| "eval_steps_per_second": 3.353, |
| "step": 2518 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.700317712470215e-05, |
| "loss": 0.0514, |
| "step": 3777 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.40110936321253565, |
| "eval_loss": 2.3102009296417236, |
| "eval_pearson": 0.4100592328009352, |
| "eval_runtime": 1.8032, |
| "eval_samples_per_second": 831.867, |
| "eval_spearmanr": 0.39215949362413616, |
| "eval_steps_per_second": 3.327, |
| "step": 3777 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.6003177124702146e-05, |
| "loss": 0.0384, |
| "step": 5036 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.4411314393998532, |
| "eval_loss": 2.5410399436950684, |
| "eval_pearson": 0.44464954748981084, |
| "eval_runtime": 1.8348, |
| "eval_samples_per_second": 817.514, |
| "eval_spearmanr": 0.43761333130989566, |
| "eval_steps_per_second": 3.27, |
| "step": 5036 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.500317712470214e-05, |
| "loss": 0.031, |
| "step": 6295 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.40039690758107405, |
| "eval_loss": 2.4586338996887207, |
| "eval_pearson": 0.4091069786387324, |
| "eval_runtime": 1.8247, |
| "eval_samples_per_second": 822.056, |
| "eval_spearmanr": 0.3916868365234156, |
| "eval_steps_per_second": 3.288, |
| "step": 6295 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4003177124702145e-05, |
| "loss": 0.0255, |
| "step": 7554 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.39364433082151107, |
| "eval_loss": 2.5980560779571533, |
| "eval_pearson": 0.39984420561965867, |
| "eval_runtime": 1.817, |
| "eval_samples_per_second": 825.557, |
| "eval_spearmanr": 0.3874444560233634, |
| "eval_steps_per_second": 3.302, |
| "step": 7554 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 7554, |
| "total_flos": 2.4081953784122573e+17, |
| "train_loss": 0.14565795876217924, |
| "train_runtime": 6838.9097, |
| "train_samples_per_second": 2355.982, |
| "train_steps_per_second": 9.205 |
| } |
| ], |
| "max_steps": 62950, |
| "num_train_epochs": 50, |
| "total_flos": 2.4081953784122573e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
