| { | |
| "best_metric": 2.0889017581939697, | |
| "best_model_checkpoint": "hBERTv2_new_pretrain_48_emb_com_stsb/checkpoint-270", | |
| "epoch": 11.0, | |
| "global_step": 495, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 2.398, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_combined_score": 0.09895010694148698, | |
| "eval_loss": 3.0621144771575928, | |
| "eval_pearson": 0.09716147087454774, | |
| "eval_runtime": 6.6464, | |
| "eval_samples_per_second": 225.687, | |
| "eval_spearmanr": 0.10073874300842621, | |
| "eval_steps_per_second": 1.805, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 2.0392, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_combined_score": 0.1034324527519338, | |
| "eval_loss": 2.3673651218414307, | |
| "eval_pearson": 0.10576369783248928, | |
| "eval_runtime": 6.649, | |
| "eval_samples_per_second": 225.599, | |
| "eval_spearmanr": 0.10110120767137833, | |
| "eval_steps_per_second": 1.805, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 1.967, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_combined_score": 0.14406165227233136, | |
| "eval_loss": 2.2296175956726074, | |
| "eval_pearson": 0.1449013667377033, | |
| "eval_runtime": 6.6544, | |
| "eval_samples_per_second": 225.413, | |
| "eval_spearmanr": 0.1432219378069594, | |
| "eval_steps_per_second": 1.803, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 1.8176, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_combined_score": 0.21118121154784042, | |
| "eval_loss": 2.6036436557769775, | |
| "eval_pearson": 0.20548311347538742, | |
| "eval_runtime": 6.6575, | |
| "eval_samples_per_second": 225.31, | |
| "eval_spearmanr": 0.21687930962029345, | |
| "eval_steps_per_second": 1.802, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.6744, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_combined_score": 0.2525005191829983, | |
| "eval_loss": 2.211899518966675, | |
| "eval_pearson": 0.2516120663465377, | |
| "eval_runtime": 6.6423, | |
| "eval_samples_per_second": 225.825, | |
| "eval_spearmanr": 0.2533889720194589, | |
| "eval_steps_per_second": 1.807, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 1.4727, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_combined_score": 0.3097995530447314, | |
| "eval_loss": 2.0889017581939697, | |
| "eval_pearson": 0.3123035846861543, | |
| "eval_runtime": 6.6602, | |
| "eval_samples_per_second": 225.22, | |
| "eval_spearmanr": 0.30729552140330846, | |
| "eval_steps_per_second": 1.802, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 1.1852, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_combined_score": 0.3576145342345672, | |
| "eval_loss": 2.6371889114379883, | |
| "eval_pearson": 0.3609188491818449, | |
| "eval_runtime": 6.6672, | |
| "eval_samples_per_second": 224.98, | |
| "eval_spearmanr": 0.35431021928728945, | |
| "eval_steps_per_second": 1.8, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 0.9895, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_combined_score": 0.3317055254815958, | |
| "eval_loss": 2.588080644607544, | |
| "eval_pearson": 0.33116489670500054, | |
| "eval_runtime": 6.6536, | |
| "eval_samples_per_second": 225.443, | |
| "eval_spearmanr": 0.33224615425819115, | |
| "eval_steps_per_second": 1.804, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.28e-05, | |
| "loss": 0.8254, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_combined_score": 0.3982595186047335, | |
| "eval_loss": 2.1745543479919434, | |
| "eval_pearson": 0.3991394074548835, | |
| "eval_runtime": 6.6724, | |
| "eval_samples_per_second": 224.808, | |
| "eval_spearmanr": 0.39737962975458346, | |
| "eval_steps_per_second": 1.798, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.6759, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_combined_score": 0.3678032139062265, | |
| "eval_loss": 2.7670793533325195, | |
| "eval_pearson": 0.36931051876970317, | |
| "eval_runtime": 6.6727, | |
| "eval_samples_per_second": 224.798, | |
| "eval_spearmanr": 0.3662959090427499, | |
| "eval_steps_per_second": 1.798, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.1200000000000006e-05, | |
| "loss": 0.558, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_combined_score": 0.39545239437613955, | |
| "eval_loss": 2.595386266708374, | |
| "eval_pearson": 0.39674723773087794, | |
| "eval_runtime": 6.6598, | |
| "eval_samples_per_second": 225.233, | |
| "eval_spearmanr": 0.3941575510214012, | |
| "eval_steps_per_second": 1.802, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "step": 495, | |
| "total_flos": 9263767447666688.0, | |
| "train_loss": 1.418446342391197, | |
| "train_runtime": 1051.0193, | |
| "train_samples_per_second": 273.496, | |
| "train_steps_per_second": 2.141 | |
| } | |
| ], | |
| "max_steps": 2250, | |
| "num_train_epochs": 50, | |
| "total_flos": 9263767447666688.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |