| { | |
| "best_metric": 0.6829268292682927, | |
| "best_model_checkpoint": "MAE-CT-CPC-Dicotomized-v4-early-stop/checkpoint-81", | |
| "epoch": 3.05625, | |
| "eval_steps": 500, | |
| "global_step": 324, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6.944444444444446e-07, | |
| "loss": 0.6989, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.3888888888888892e-06, | |
| "loss": 0.6577, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.0833333333333334e-06, | |
| "loss": 0.6586, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 0.5975, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.4722222222222224e-06, | |
| "loss": 0.6342, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.166666666666667e-06, | |
| "loss": 0.685, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 4.861111111111111e-06, | |
| "loss": 0.5336, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 5.555555555555557e-06, | |
| "loss": 0.5496, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "eval_accuracy": 0.6829268292682927, | |
| "eval_loss": 0.6272094249725342, | |
| "eval_runtime": 8.9631, | |
| "eval_samples_per_second": 4.574, | |
| "eval_steps_per_second": 1.227, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.25e-06, | |
| "loss": 0.4225, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.8021, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 7.638888888888888e-06, | |
| "loss": 0.5772, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.667, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 9.027777777777779e-06, | |
| "loss": 0.7481, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.5948, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.953703703703704e-06, | |
| "loss": 0.6092, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 9.876543209876543e-06, | |
| "loss": 0.6089, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "eval_accuracy": 0.6829268292682927, | |
| "eval_loss": 0.596904993057251, | |
| "eval_runtime": 8.0298, | |
| "eval_samples_per_second": 5.106, | |
| "eval_steps_per_second": 1.37, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.799382716049384e-06, | |
| "loss": 0.5514, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 9.722222222222223e-06, | |
| "loss": 0.5377, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "learning_rate": 9.645061728395062e-06, | |
| "loss": 0.5121, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.567901234567902e-06, | |
| "loss": 0.8356, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.03, | |
| "learning_rate": 9.490740740740741e-06, | |
| "loss": 0.591, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 9.413580246913581e-06, | |
| "loss": 0.4467, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.33641975308642e-06, | |
| "loss": 0.5282, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 9.25925925925926e-06, | |
| "loss": 0.715, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "eval_accuracy": 0.6585365853658537, | |
| "eval_loss": 0.6061528921127319, | |
| "eval_runtime": 7.8186, | |
| "eval_samples_per_second": 5.244, | |
| "eval_steps_per_second": 1.407, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 9.1820987654321e-06, | |
| "loss": 0.6485, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "learning_rate": 9.10493827160494e-06, | |
| "loss": 0.7628, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 9.027777777777779e-06, | |
| "loss": 0.5779, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 8.950617283950618e-06, | |
| "loss": 0.5771, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 8.873456790123458e-06, | |
| "loss": 0.7393, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 8.796296296296297e-06, | |
| "loss": 0.6242, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 8.719135802469136e-06, | |
| "loss": 0.5647, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 8.641975308641975e-06, | |
| "loss": 0.474, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_accuracy": 0.6829268292682927, | |
| "eval_loss": 0.6187382936477661, | |
| "eval_runtime": 7.9589, | |
| "eval_samples_per_second": 5.151, | |
| "eval_steps_per_second": 1.382, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "step": 324, | |
| "total_flos": 5.655641894102237e+18, | |
| "train_loss": 0.6119254886368175, | |
| "train_runtime": 569.9574, | |
| "train_samples_per_second": 10.106, | |
| "train_steps_per_second": 2.527 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_accuracy": 0.6829268292682927, | |
| "eval_loss": 0.6236140727996826, | |
| "eval_runtime": 8.7888, | |
| "eval_samples_per_second": 4.665, | |
| "eval_steps_per_second": 1.252, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "eval_accuracy": 0.6829268292682927, | |
| "eval_loss": 0.6236140727996826, | |
| "eval_runtime": 8.1467, | |
| "eval_samples_per_second": 5.033, | |
| "eval_steps_per_second": 1.35, | |
| "step": 324 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1440, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 5.655641894102237e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |