| { | |
| "best_metric": 0.8723729492374466, | |
| "best_model_checkpoint": "/home/sh0416/checkpoints/20211030_190839/checkpoint-1000", | |
| "epoch": 2.7881040892193307, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.23, | |
| "eval_stsb_spearman": 0.8659646120861637, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.381660470879802e-05, | |
| "loss": 0.7797, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_stsb_spearman": 0.8706623644301015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_stsb_spearman": 0.8702169032693835, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.7620817843866174e-05, | |
| "loss": 0.5768, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_stsb_spearman": 0.8723729492374466, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_stsb_spearman": 0.8685705737267285, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.142503097893433e-05, | |
| "loss": 0.466, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_stsb_spearman": 0.8659661298808028, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_stsb_spearman": 0.8698201734589346, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.522924411400248e-05, | |
| "loss": 0.4376, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_stsb_spearman": 0.8717249238803574, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_stsb_spearman": 0.8710413913813898, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.033457249070633e-06, | |
| "loss": 0.374, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_stsb_spearman": 0.8684187080814486, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_stsb_spearman": 0.8716808135297102, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.837670384138786e-06, | |
| "loss": 0.3582, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_stsb_spearman": 0.8707616723276398, | |
| "step": 3000 | |
| } | |
| ], | |
| "max_steps": 3228, | |
| "num_train_epochs": 3, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |