| { |
| "best_metric": 2.1580135822296143, |
| "best_model_checkpoint": "hBERTv1_data_aug_stsb/checkpoint-2518", |
| "epoch": 7.0, |
| "global_step": 8813, |
| "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": 0.5955, |
| "step": 1259 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_combined_score": 0.47484120749505343, |
| "eval_loss": 2.1996302604675293, |
| "eval_pearson": 0.4856864748436668, |
| "eval_runtime": 1.9364, |
| "eval_samples_per_second": 774.643, |
| "eval_spearmanr": 0.46399594014644, |
| "eval_steps_per_second": 3.099, |
| "step": 1259 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 4.800317712470215e-05, |
| "loss": 0.1017, |
| "step": 2518 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_combined_score": 0.4382596970133626, |
| "eval_loss": 2.1580135822296143, |
| "eval_pearson": 0.44709778469878486, |
| "eval_runtime": 1.9287, |
| "eval_samples_per_second": 777.734, |
| "eval_spearmanr": 0.4294216093279403, |
| "eval_steps_per_second": 3.111, |
| "step": 2518 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.700317712470215e-05, |
| "loss": 0.06, |
| "step": 3777 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_combined_score": 0.38922631391071794, |
| "eval_loss": 2.548009157180786, |
| "eval_pearson": 0.4051839261133397, |
| "eval_runtime": 1.9268, |
| "eval_samples_per_second": 778.48, |
| "eval_spearmanr": 0.3732687017080961, |
| "eval_steps_per_second": 3.114, |
| "step": 3777 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.6003177124702146e-05, |
| "loss": 0.0454, |
| "step": 5036 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_combined_score": 0.4346505731105881, |
| "eval_loss": 2.159414768218994, |
| "eval_pearson": 0.4500421063451717, |
| "eval_runtime": 1.9297, |
| "eval_samples_per_second": 777.303, |
| "eval_spearmanr": 0.4192590398760045, |
| "eval_steps_per_second": 3.109, |
| "step": 5036 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 4.500317712470214e-05, |
| "loss": 0.038, |
| "step": 6295 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_combined_score": 0.3864515733139051, |
| "eval_loss": 2.6866118907928467, |
| "eval_pearson": 0.4070549773094471, |
| "eval_runtime": 1.9309, |
| "eval_samples_per_second": 776.835, |
| "eval_spearmanr": 0.36584816931836317, |
| "eval_steps_per_second": 3.107, |
| "step": 6295 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 4.4003177124702145e-05, |
| "loss": 0.0318, |
| "step": 7554 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_combined_score": 0.3663189236788687, |
| "eval_loss": 2.8519299030303955, |
| "eval_pearson": 0.38914717784652014, |
| "eval_runtime": 1.9281, |
| "eval_samples_per_second": 777.965, |
| "eval_spearmanr": 0.34349066951121726, |
| "eval_steps_per_second": 3.112, |
| "step": 7554 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 4.300397140587769e-05, |
| "loss": 0.0283, |
| "step": 8813 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_combined_score": 0.3650262138633089, |
| "eval_loss": 2.6783053874969482, |
| "eval_pearson": 0.38364980458648423, |
| "eval_runtime": 1.9499, |
| "eval_samples_per_second": 769.257, |
| "eval_spearmanr": 0.34640262314013365, |
| "eval_steps_per_second": 3.077, |
| "step": 8813 |
| }, |
| { |
| "epoch": 7.0, |
| "step": 8813, |
| "total_flos": 2.8492079890746573e+17, |
| "train_loss": 0.12866550420884254, |
| "train_runtime": 8318.4396, |
| "train_samples_per_second": 1936.944, |
| "train_steps_per_second": 7.568 |
| } |
| ], |
| "max_steps": 62950, |
| "num_train_epochs": 50, |
| "total_flos": 2.8492079890746573e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
