| { | |
| "best_metric": 1.0984020233154297, | |
| "best_model_checkpoint": "add_BERT_no_pretrain_mnli/checkpoint-9204", | |
| "epoch": 8.0, | |
| "global_step": 24544, | |
| "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": 1.1024, | |
| "step": 3068 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.31818644931227713, | |
| "eval_loss": 1.0987340211868286, | |
| "eval_runtime": 18.3205, | |
| "eval_samples_per_second": 535.74, | |
| "eval_steps_per_second": 4.203, | |
| "step": 3068 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 1.0997, | |
| "step": 6136 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.0985723733901978, | |
| "eval_runtime": 18.3326, | |
| "eval_samples_per_second": 535.385, | |
| "eval_steps_per_second": 4.2, | |
| "step": 6136 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 1.0988, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0984020233154297, | |
| "eval_runtime": 18.3176, | |
| "eval_samples_per_second": 535.823, | |
| "eval_steps_per_second": 4.204, | |
| "step": 9204 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 1.0987, | |
| "step": 12272 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0986018180847168, | |
| "eval_runtime": 18.4288, | |
| "eval_samples_per_second": 532.589, | |
| "eval_steps_per_second": 4.178, | |
| "step": 12272 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 1.0986, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.3544574630667346, | |
| "eval_loss": 1.0985984802246094, | |
| "eval_runtime": 18.4293, | |
| "eval_samples_per_second": 532.575, | |
| "eval_steps_per_second": 4.178, | |
| "step": 15340 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 1.0987, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.098618745803833, | |
| "eval_runtime": 18.4765, | |
| "eval_samples_per_second": 531.214, | |
| "eval_steps_per_second": 4.167, | |
| "step": 18408 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 1.0986, | |
| "step": 21476 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.098617434501648, | |
| "eval_runtime": 18.4088, | |
| "eval_samples_per_second": 533.17, | |
| "eval_steps_per_second": 4.183, | |
| "step": 21476 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 1.0986, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.3273560876209883, | |
| "eval_loss": 1.0986160039901733, | |
| "eval_runtime": 18.373, | |
| "eval_samples_per_second": 534.207, | |
| "eval_steps_per_second": 4.191, | |
| "step": 24544 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 24544, | |
| "total_flos": 4.487017617634099e+17, | |
| "train_loss": 1.0992557968278907, | |
| "train_runtime": 17750.054, | |
| "train_samples_per_second": 1106.199, | |
| "train_steps_per_second": 8.642 | |
| } | |
| ], | |
| "max_steps": 153400, | |
| "num_train_epochs": 50, | |
| "total_flos": 4.487017617634099e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |