| { | |
| "best_metric": 0.6899052858352661, | |
| "best_model_checkpoint": "add_BERT_no_pretrain_qnli/checkpoint-3276", | |
| "epoch": 9.0, | |
| "global_step": 7371, | |
| "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": 0.7079, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.7209677696228027, | |
| "eval_runtime": 10.2227, | |
| "eval_samples_per_second": 534.4, | |
| "eval_steps_per_second": 4.206, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 0.6952, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6911802291870117, | |
| "eval_runtime": 10.2371, | |
| "eval_samples_per_second": 533.649, | |
| "eval_steps_per_second": 4.2, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 0.6922, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.5279150649826103, | |
| "eval_loss": 0.6905035972595215, | |
| "eval_runtime": 10.231, | |
| "eval_samples_per_second": 533.964, | |
| "eval_steps_per_second": 4.203, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 0.6918, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.528830313014827, | |
| "eval_loss": 0.6899052858352661, | |
| "eval_runtime": 10.2564, | |
| "eval_samples_per_second": 532.644, | |
| "eval_steps_per_second": 4.193, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.6922, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5152846421380194, | |
| "eval_loss": 0.6922001838684082, | |
| "eval_runtime": 10.2507, | |
| "eval_samples_per_second": 532.941, | |
| "eval_steps_per_second": 4.195, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 0.6933, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5127219476478125, | |
| "eval_loss": 0.6926350593566895, | |
| "eval_runtime": 10.2253, | |
| "eval_samples_per_second": 534.263, | |
| "eval_steps_per_second": 4.205, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 0.6931, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6952403783798218, | |
| "eval_runtime": 10.2187, | |
| "eval_samples_per_second": 534.609, | |
| "eval_steps_per_second": 4.208, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 0.6933, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5112575507962658, | |
| "eval_loss": 0.6927889585494995, | |
| "eval_runtime": 10.2381, | |
| "eval_samples_per_second": 533.597, | |
| "eval_steps_per_second": 4.2, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.28e-05, | |
| "loss": 0.693, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5215083287570932, | |
| "eval_loss": 0.6921678781509399, | |
| "eval_runtime": 10.2872, | |
| "eval_samples_per_second": 531.048, | |
| "eval_steps_per_second": 4.18, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "step": 7371, | |
| "total_flos": 1.3463830193504256e+17, | |
| "train_loss": 0.6946712540991512, | |
| "train_runtime": 5581.0967, | |
| "train_samples_per_second": 938.373, | |
| "train_steps_per_second": 7.337 | |
| } | |
| ], | |
| "max_steps": 40950, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.3463830193504256e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |