| { | |
| "best_metric": 0.8662938169391007, | |
| "best_model_checkpoint": "/home/sh0416/checkpoints/20211030_162237/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": 0.8524394451710808, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.382899628252789e-05, | |
| "loss": 0.7598, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_stsb_spearman": 0.8581363647048411, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_stsb_spearman": 0.857818787973787, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.7633209417596035e-05, | |
| "loss": 0.5895, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_stsb_spearman": 0.8662938169391007, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_stsb_spearman": 0.86093388442406, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.143742255266419e-05, | |
| "loss": 0.4598, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_stsb_spearman": 0.8611909628928307, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_stsb_spearman": 0.8620996137507876, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.5241635687732344e-05, | |
| "loss": 0.4302, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_stsb_spearman": 0.8628503615991803, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_stsb_spearman": 0.8615572798709574, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.045848822800495e-06, | |
| "loss": 0.3632, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_stsb_spearman": 0.8595222891463629, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "eval_stsb_spearman": 0.8615406222623156, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.8500619578686496e-06, | |
| "loss": 0.3447, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_stsb_spearman": 0.8601878437498801, | |
| "step": 3000 | |
| } | |
| ], | |
| "max_steps": 3228, | |
| "num_train_epochs": 3, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |