| { | |
| "best_metric": 0.869766114702863, | |
| "best_model_checkpoint": "/home/sh0416/checkpoints/20211030_182857/checkpoint-1500", | |
| "epoch": 2.9029261495587555, | |
| "global_step": 6250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12, | |
| "eval_stsb_spearman": 0.8586775587747187, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.6922124167827844e-05, | |
| "loss": 0.8323, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_stsb_spearman": 0.8588352299545762, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_stsb_spearman": 0.8580685212417721, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.38256696082985e-05, | |
| "loss": 0.5448, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_stsb_spearman": 0.8655406738313124, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_stsb_spearman": 0.8626629415411806, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.072921504876916e-05, | |
| "loss": 0.4935, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_stsb_spearman": 0.869766114702863, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_stsb_spearman": 0.8661819449759747, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.763276048923982e-05, | |
| "loss": 0.4665, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_stsb_spearman": 0.8688986052089305, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_stsb_spearman": 0.8614421115182633, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.4536305929710486e-05, | |
| "loss": 0.3944, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_stsb_spearman": 0.8667786347692652, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_stsb_spearman": 0.8587597761659841, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.1439851370181147e-05, | |
| "loss": 0.3514, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_stsb_spearman": 0.86505437379439, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_stsb_spearman": 0.8630015797975009, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.8343396810651805e-05, | |
| "loss": 0.3495, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_stsb_spearman": 0.8624447448946402, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_stsb_spearman": 0.8647011236719792, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.5246942251122465e-05, | |
| "loss": 0.3396, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_stsb_spearman": 0.8652945750275577, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_stsb_spearman": 0.8660931281888605, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.2150487691593128e-05, | |
| "loss": 0.3021, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_stsb_spearman": 0.8696657089398002, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_stsb_spearman": 0.8663003347371815, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.054033132063787e-06, | |
| "loss": 0.2647, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_stsb_spearman": 0.8647154190554845, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_stsb_spearman": 0.8667254115422314, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.957578572534448e-06, | |
| "loss": 0.2656, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_stsb_spearman": 0.8672662268611117, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_stsb_spearman": 0.8684060372542215, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.8611240130051095e-06, | |
| "loss": 0.2623, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_stsb_spearman": 0.8671780719961613, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_stsb_spearman": 0.8671768780451615, | |
| "step": 6250 | |
| } | |
| ], | |
| "max_steps": 6459, | |
| "num_train_epochs": 3, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |