| { | |
| "best_metric": 0.6930883526802063, | |
| "best_model_checkpoint": "hBERTv2_new_pretrain_48_emb_com_qnli/checkpoint-6552", | |
| "epoch": 13.0, | |
| "global_step": 10647, | |
| "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": 0.7033, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.7265331149101257, | |
| "eval_runtime": 23.8269, | |
| "eval_samples_per_second": 229.278, | |
| "eval_steps_per_second": 1.805, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.8400000000000005e-05, | |
| "loss": 0.6988, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.693661093711853, | |
| "eval_runtime": 23.8046, | |
| "eval_samples_per_second": 229.494, | |
| "eval_steps_per_second": 1.806, | |
| "step": 1638 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3.76e-05, | |
| "loss": 0.6969, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6934164762496948, | |
| "eval_runtime": 23.8982, | |
| "eval_samples_per_second": 228.595, | |
| "eval_steps_per_second": 1.799, | |
| "step": 2457 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.680000000000001e-05, | |
| "loss": 0.6951, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6945135593414307, | |
| "eval_runtime": 23.9809, | |
| "eval_samples_per_second": 227.807, | |
| "eval_steps_per_second": 1.793, | |
| "step": 3276 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3.6e-05, | |
| "loss": 0.6944, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6963419914245605, | |
| "eval_runtime": 23.9706, | |
| "eval_samples_per_second": 227.904, | |
| "eval_steps_per_second": 1.794, | |
| "step": 4095 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3.52e-05, | |
| "loss": 0.6944, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6945961117744446, | |
| "eval_runtime": 23.9924, | |
| "eval_samples_per_second": 227.697, | |
| "eval_steps_per_second": 1.792, | |
| "step": 4914 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3.44e-05, | |
| "loss": 0.6945, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6958634853363037, | |
| "eval_runtime": 23.9459, | |
| "eval_samples_per_second": 228.139, | |
| "eval_steps_per_second": 1.796, | |
| "step": 5733 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3.3600000000000004e-05, | |
| "loss": 0.6943, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6930883526802063, | |
| "eval_runtime": 23.8611, | |
| "eval_samples_per_second": 228.95, | |
| "eval_steps_per_second": 1.802, | |
| "step": 6552 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3.28e-05, | |
| "loss": 0.6938, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5053999633900788, | |
| "eval_loss": 0.6936526894569397, | |
| "eval_runtime": 23.9423, | |
| "eval_samples_per_second": 228.173, | |
| "eval_steps_per_second": 1.796, | |
| "step": 7371 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.6939, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6943687796592712, | |
| "eval_runtime": 23.9435, | |
| "eval_samples_per_second": 228.162, | |
| "eval_steps_per_second": 1.796, | |
| "step": 8190 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "learning_rate": 3.1200000000000006e-05, | |
| "loss": 0.6936, | |
| "step": 9009 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6939591765403748, | |
| "eval_runtime": 23.9154, | |
| "eval_samples_per_second": 228.43, | |
| "eval_steps_per_second": 1.798, | |
| "step": 9009 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.0400000000000004e-05, | |
| "loss": 0.6937, | |
| "step": 9828 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6932513117790222, | |
| "eval_runtime": 23.9462, | |
| "eval_samples_per_second": 228.136, | |
| "eval_steps_per_second": 1.796, | |
| "step": 9828 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "learning_rate": 2.96e-05, | |
| "loss": 0.6937, | |
| "step": 10647 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.4946000366099213, | |
| "eval_loss": 0.6986988186836243, | |
| "eval_runtime": 23.9628, | |
| "eval_samples_per_second": 227.978, | |
| "eval_steps_per_second": 1.794, | |
| "step": 10647 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "step": 10647, | |
| "total_flos": 1.9946858592652493e+17, | |
| "train_loss": 0.6954118920859456, | |
| "train_runtime": 18702.192, | |
| "train_samples_per_second": 280.029, | |
| "train_steps_per_second": 2.19 | |
| } | |
| ], | |
| "max_steps": 40950, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.9946858592652493e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |