| { | |
| "best_metric": 0.8625848570907281, | |
| "best_model_checkpoint": "/home/sh0416/checkpoints/20211030_161612/checkpoint-2000", | |
| "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": 0.849104410089273, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.6922124167827844e-05, | |
| "loss": 0.6558, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_stsb_spearman": 0.8549645102083819, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "eval_stsb_spearman": 0.8493755409241399, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 3.38256696082985e-05, | |
| "loss": 0.5061, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "eval_stsb_spearman": 0.8558743382367817, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_stsb_spearman": 0.8579781749671418, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.072921504876916e-05, | |
| "loss": 0.4618, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_stsb_spearman": 0.8551950210432068, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "eval_stsb_spearman": 0.8575288731834817, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 2.763276048923982e-05, | |
| "loss": 0.4405, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_stsb_spearman": 0.8625848570907281, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_stsb_spearman": 0.8528228965029796, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "learning_rate": 2.4536305929710486e-05, | |
| "loss": 0.3455, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.16, | |
| "eval_stsb_spearman": 0.8583216121633138, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "eval_stsb_spearman": 0.8586320312896799, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 2.1439851370181147e-05, | |
| "loss": 0.3004, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_stsb_spearman": 0.857754063729947, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "eval_stsb_spearman": 0.8550335796509426, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 1.8343396810651805e-05, | |
| "loss": 0.3009, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_stsb_spearman": 0.8562914790933086, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "eval_stsb_spearman": 0.857049471480084, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.5246942251122465e-05, | |
| "loss": 0.2926, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "eval_stsb_spearman": 0.8569922144510925, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_stsb_spearman": 0.8574082752357015, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.2150487691593128e-05, | |
| "loss": 0.2544, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "eval_stsb_spearman": 0.8589184399762652, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_stsb_spearman": 0.8591238608101542, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "learning_rate": 9.054033132063787e-06, | |
| "loss": 0.2103, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "eval_stsb_spearman": 0.8571706494995457, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.44, | |
| "eval_stsb_spearman": 0.8598802982895895, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 5.957578572534448e-06, | |
| "loss": 0.2138, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_stsb_spearman": 0.8581741085030632, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_stsb_spearman": 0.8579268770161598, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 2.8611240130051095e-06, | |
| "loss": 0.2134, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_stsb_spearman": 0.8573359421904918, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "eval_stsb_spearman": 0.857414208386273, | |
| "step": 6250 | |
| } | |
| ], | |
| "max_steps": 6459, | |
| "num_train_epochs": 3, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |