| { | |
| "best_metric": 1.0985817909240723, | |
| "best_model_checkpoint": "add_BERT_48_mnli/checkpoint-18408", | |
| "epoch": 11.0, | |
| "global_step": 33748, | |
| "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": 1.1006, | |
| "step": 3068 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.33010697911360165, | |
| "eval_loss": 1.0990883111953735, | |
| "eval_runtime": 18.8354, | |
| "eval_samples_per_second": 521.094, | |
| "eval_steps_per_second": 4.088, | |
| "step": 3068 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 1.0989, | |
| "step": 6136 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.31818644931227713, | |
| "eval_loss": 1.0987157821655273, | |
| "eval_runtime": 18.8101, | |
| "eval_samples_per_second": 521.794, | |
| "eval_steps_per_second": 4.094, | |
| "step": 6136 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 1.0988, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.098842978477478, | |
| "eval_runtime": 18.8979, | |
| "eval_samples_per_second": 519.37, | |
| "eval_steps_per_second": 4.075, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 1.0986, | |
| "step": 12272 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0985958576202393, | |
| "eval_runtime": 18.9455, | |
| "eval_samples_per_second": 518.064, | |
| "eval_steps_per_second": 4.064, | |
| "step": 12272 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.0987, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.31818644931227713, | |
| "eval_loss": 1.0986104011535645, | |
| "eval_runtime": 18.85, | |
| "eval_samples_per_second": 520.689, | |
| "eval_steps_per_second": 4.085, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 1.0994, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.0985817909240723, | |
| "eval_runtime": 18.8392, | |
| "eval_samples_per_second": 520.989, | |
| "eval_steps_per_second": 4.087, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 1.0986, | |
| "step": 21476 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.0985937118530273, | |
| "eval_runtime": 18.8521, | |
| "eval_samples_per_second": 520.632, | |
| "eval_steps_per_second": 4.084, | |
| "step": 21476 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 1.0986, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.31818644931227713, | |
| "eval_loss": 1.098621129989624, | |
| "eval_runtime": 18.8177, | |
| "eval_samples_per_second": 521.584, | |
| "eval_steps_per_second": 4.092, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.28e-05, | |
| "loss": 1.0986, | |
| "step": 27612 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0986088514328003, | |
| "eval_runtime": 18.8232, | |
| "eval_samples_per_second": 521.43, | |
| "eval_steps_per_second": 4.091, | |
| "step": 27612 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 1.0986, | |
| "step": 30680 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0986006259918213, | |
| "eval_runtime": 18.8354, | |
| "eval_samples_per_second": 521.094, | |
| "eval_steps_per_second": 4.088, | |
| "step": 30680 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.1200000000000006e-05, | |
| "loss": 1.0986, | |
| "step": 33748 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.31818644931227713, | |
| "eval_loss": 1.0986229181289673, | |
| "eval_runtime": 18.817, | |
| "eval_samples_per_second": 521.602, | |
| "eval_steps_per_second": 4.092, | |
| "step": 33748 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "step": 33748, | |
| "total_flos": 6.169649224246886e+17, | |
| "train_loss": 1.0989104475867089, | |
| "train_runtime": 25503.8517, | |
| "train_samples_per_second": 769.888, | |
| "train_steps_per_second": 6.015 | |
| } | |
| ], | |
| "max_steps": 153400, | |
| "num_train_epochs": 50, | |
| "total_flos": 6.169649224246886e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |