| { | |
| "best_metric": 0.6930924654006958, | |
| "best_model_checkpoint": "hBERTv1_no_pretrain_qnli/checkpoint-8736", | |
| "epoch": 13.0, | |
| "global_step": 14196, | |
| "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": 0.7059, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.7003825306892395, | |
| "eval_runtime": 25.3252, | |
| "eval_samples_per_second": 215.714, | |
| "eval_steps_per_second": 2.251, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 0.6948, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.693818986415863, | |
| "eval_runtime": 25.5889, | |
| "eval_samples_per_second": 213.491, | |
| "eval_steps_per_second": 2.228, | |
| "step": 2184 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 0.6939, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6931672692298889, | |
| "eval_runtime": 25.592, | |
| "eval_samples_per_second": 213.465, | |
| "eval_steps_per_second": 2.227, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 0.6936, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.693107545375824, | |
| "eval_runtime": 25.5969, | |
| "eval_samples_per_second": 213.424, | |
| "eval_steps_per_second": 2.227, | |
| "step": 4368 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.6934, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6930991411209106, | |
| "eval_runtime": 25.4035, | |
| "eval_samples_per_second": 215.05, | |
| "eval_steps_per_second": 2.244, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 0.6936, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6931207180023193, | |
| "eval_runtime": 25.4067, | |
| "eval_samples_per_second": 215.022, | |
| "eval_steps_per_second": 2.244, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 0.6933, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.693096935749054, | |
| "eval_runtime": 25.4153, | |
| "eval_samples_per_second": 214.949, | |
| "eval_steps_per_second": 2.243, | |
| "step": 7644 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 0.6933, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6930924654006958, | |
| "eval_runtime": 25.5577, | |
| "eval_samples_per_second": 213.751, | |
| "eval_steps_per_second": 2.23, | |
| "step": 8736 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.28e-05, | |
| "loss": 0.6934, | |
| "step": 9828 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6934182047843933, | |
| "eval_runtime": 25.5166, | |
| "eval_samples_per_second": 214.096, | |
| "eval_steps_per_second": 2.234, | |
| "step": 9828 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.6933, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6930983662605286, | |
| "eval_runtime": 25.3329, | |
| "eval_samples_per_second": 215.649, | |
| "eval_steps_per_second": 2.25, | |
| "step": 10920 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.1200000000000006e-05, | |
| "loss": 0.6932, | |
| "step": 12012 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6932870149612427, | |
| "eval_runtime": 25.3051, | |
| "eval_samples_per_second": 215.885, | |
| "eval_steps_per_second": 2.253, | |
| "step": 12012 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.0400000000000004e-05, | |
| "loss": 0.6932, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6931389570236206, | |
| "eval_runtime": 25.2541, | |
| "eval_samples_per_second": 216.322, | |
| "eval_steps_per_second": 2.257, | |
| "step": 13104 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 2.96e-05, | |
| "loss": 0.6933, | |
| "step": 14196 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6931240558624268, | |
| "eval_runtime": 25.2965, | |
| "eval_samples_per_second": 215.959, | |
| "eval_steps_per_second": 2.253, | |
| "step": 14196 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 14196, | |
| "total_flos": 2.0165730126056653e+17, | |
| "train_loss": 0.6944669291952289, | |
| "train_runtime": 19598.9141, | |
| "train_samples_per_second": 267.216, | |
| "train_steps_per_second": 2.786 | |
| } | |
| ], | |
| "max_steps": 54600, | |
| "num_train_epochs": 50, | |
| "total_flos": 2.0165730126056653e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |