| { | |
| "best_metric": 0.9956499952041198, | |
| "best_model_checkpoint": "C:\\Users\\tm011\\PycharmProjects\\Custom_baseline\\sangsang_re\\checkpoint-5625", | |
| "epoch": 1.0, | |
| "global_step": 5625, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 1.9822222222222226e-05, | |
| "loss": 0.0627, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 1.9644444444444447e-05, | |
| "loss": 0.0274, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 1.9466666666666668e-05, | |
| "loss": 0.032, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.928888888888889e-05, | |
| "loss": 0.0335, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 1.9111111111111113e-05, | |
| "loss": 0.0276, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8933333333333334e-05, | |
| "loss": 0.034, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 1.8755555555555558e-05, | |
| "loss": 0.0292, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.857777777777778e-05, | |
| "loss": 0.0203, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 1.8400000000000003e-05, | |
| "loss": 0.0303, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 1.8222222222222224e-05, | |
| "loss": 0.0251, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.8044444444444445e-05, | |
| "loss": 0.0192, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 1.7866666666666666e-05, | |
| "loss": 0.02, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 1.768888888888889e-05, | |
| "loss": 0.0278, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 1.751111111111111e-05, | |
| "loss": 0.0217, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.7333333333333336e-05, | |
| "loss": 0.0125, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.7155555555555557e-05, | |
| "loss": 0.0288, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 1.697777777777778e-05, | |
| "loss": 0.0193, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 1.6800000000000002e-05, | |
| "loss": 0.0208, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.6622222222222223e-05, | |
| "loss": 0.0183, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 1.6444444444444444e-05, | |
| "loss": 0.0171, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.6266666666666668e-05, | |
| "loss": 0.0179, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 1.608888888888889e-05, | |
| "loss": 0.0196, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.5911111111111113e-05, | |
| "loss": 0.0215, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 1.5733333333333334e-05, | |
| "loss": 0.0249, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.555555555555556e-05, | |
| "loss": 0.0193, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 1.537777777777778e-05, | |
| "loss": 0.0259, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.5200000000000002e-05, | |
| "loss": 0.0237, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 1.5022222222222223e-05, | |
| "loss": 0.0272, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 1.4844444444444445e-05, | |
| "loss": 0.013, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 1.4666666666666666e-05, | |
| "loss": 0.0257, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 1.448888888888889e-05, | |
| "loss": 0.0219, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 1.4311111111111111e-05, | |
| "loss": 0.0139, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 1.4133333333333334e-05, | |
| "loss": 0.019, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 1.3955555555555558e-05, | |
| "loss": 0.0181, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 1.377777777777778e-05, | |
| "loss": 0.0078, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.3600000000000002e-05, | |
| "loss": 0.0233, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "learning_rate": 1.3422222222222223e-05, | |
| "loss": 0.021, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.3244444444444447e-05, | |
| "loss": 0.0201, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 1.3066666666666668e-05, | |
| "loss": 0.0222, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.288888888888889e-05, | |
| "loss": 0.0216, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.2711111111111112e-05, | |
| "loss": 0.0206, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.2533333333333336e-05, | |
| "loss": 0.0113, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.2355555555555557e-05, | |
| "loss": 0.0161, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.217777777777778e-05, | |
| "loss": 0.025, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.0097, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.1822222222222225e-05, | |
| "loss": 0.0219, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 1.1644444444444446e-05, | |
| "loss": 0.0294, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.1466666666666668e-05, | |
| "loss": 0.017, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 1.1288888888888889e-05, | |
| "loss": 0.0198, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1.1111111111111113e-05, | |
| "loss": 0.0189, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 1.0933333333333334e-05, | |
| "loss": 0.0161, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.0755555555555557e-05, | |
| "loss": 0.0167, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.0577777777777778e-05, | |
| "loss": 0.0236, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.04e-05, | |
| "loss": 0.0147, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 1.0222222222222223e-05, | |
| "loss": 0.0324, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.0044444444444446e-05, | |
| "loss": 0.0209, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_f1": 0.9956499952041198, | |
| "eval_loss": 0.016555603593587875, | |
| "eval_runtime": 53.6078, | |
| "eval_samples_per_second": 373.08, | |
| "eval_steps_per_second": 11.659, | |
| "step": 5625 | |
| } | |
| ], | |
| "max_steps": 11250, | |
| "num_train_epochs": 2, | |
| "total_flos": 4.193691134976e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |