| { | |
| "best_metric": 1.4132405519485474, | |
| "best_model_checkpoint": "facial_age_image_detection/checkpoint-6080", | |
| "epoch": 19.0, | |
| "eval_steps": 500, | |
| "global_step": 6080, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.52443315089914, | |
| "eval_loss": 1.4843693971633911, | |
| "eval_runtime": 53.5481, | |
| "eval_samples_per_second": 95.54, | |
| "eval_steps_per_second": 2.988, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 8.704541206359863, | |
| "learning_rate": 9.291338582677165e-07, | |
| "loss": 1.1351, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5242376856919468, | |
| "eval_loss": 1.4704760313034058, | |
| "eval_runtime": 53.4617, | |
| "eval_samples_per_second": 95.695, | |
| "eval_steps_per_second": 2.993, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.522869429241595, | |
| "eval_loss": 1.469245195388794, | |
| "eval_runtime": 53.691, | |
| "eval_samples_per_second": 95.286, | |
| "eval_steps_per_second": 2.98, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 8.570690155029297, | |
| "learning_rate": 8.503937007874016e-07, | |
| "loss": 1.1099, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.527756059421423, | |
| "eval_loss": 1.459570050239563, | |
| "eval_runtime": 53.2303, | |
| "eval_samples_per_second": 96.111, | |
| "eval_steps_per_second": 3.006, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 4.69, | |
| "grad_norm": 9.125391960144043, | |
| "learning_rate": 7.716535433070865e-07, | |
| "loss": 1.0965, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5275605942142298, | |
| "eval_loss": 1.4572798013687134, | |
| "eval_runtime": 53.1246, | |
| "eval_samples_per_second": 96.302, | |
| "eval_steps_per_second": 3.012, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5267787333854574, | |
| "eval_loss": 1.4519189596176147, | |
| "eval_runtime": 53.1208, | |
| "eval_samples_per_second": 96.309, | |
| "eval_steps_per_second": 3.012, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "grad_norm": 8.86064624786377, | |
| "learning_rate": 6.929133858267716e-07, | |
| "loss": 1.0762, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5287333854573886, | |
| "eval_loss": 1.4468164443969727, | |
| "eval_runtime": 53.0338, | |
| "eval_samples_per_second": 96.467, | |
| "eval_steps_per_second": 3.017, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 7.81, | |
| "grad_norm": 6.661502361297607, | |
| "learning_rate": 6.141732283464567e-07, | |
| "loss": 1.068, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5334245504300235, | |
| "eval_loss": 1.4398757219314575, | |
| "eval_runtime": 53.1182, | |
| "eval_samples_per_second": 96.314, | |
| "eval_steps_per_second": 3.012, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.5340109460516028, | |
| "eval_loss": 1.4362281560897827, | |
| "eval_runtime": 53.8211, | |
| "eval_samples_per_second": 95.056, | |
| "eval_steps_per_second": 2.973, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 9.38, | |
| "grad_norm": 7.235806941986084, | |
| "learning_rate": 5.354330708661418e-07, | |
| "loss": 1.0497, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.5349882720875684, | |
| "eval_loss": 1.4307777881622314, | |
| "eval_runtime": 53.0594, | |
| "eval_samples_per_second": 96.42, | |
| "eval_steps_per_second": 3.015, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 10.94, | |
| "grad_norm": 5.052951812744141, | |
| "learning_rate": 4.5669291338582676e-07, | |
| "loss": 1.0425, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.5367474589523065, | |
| "eval_loss": 1.4270881414413452, | |
| "eval_runtime": 53.3177, | |
| "eval_samples_per_second": 95.953, | |
| "eval_steps_per_second": 3.001, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5340109460516028, | |
| "eval_loss": 1.4276313781738281, | |
| "eval_runtime": 53.3844, | |
| "eval_samples_per_second": 95.833, | |
| "eval_steps_per_second": 2.997, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "grad_norm": 7.315602779388428, | |
| "learning_rate": 3.779527559055118e-07, | |
| "loss": 1.0301, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.534401876465989, | |
| "eval_loss": 1.4230455160140991, | |
| "eval_runtime": 53.3059, | |
| "eval_samples_per_second": 95.974, | |
| "eval_steps_per_second": 3.002, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.5359655981235341, | |
| "eval_loss": 1.4216346740722656, | |
| "eval_runtime": 52.9593, | |
| "eval_samples_per_second": 96.602, | |
| "eval_steps_per_second": 3.021, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 14.06, | |
| "grad_norm": 5.868752956390381, | |
| "learning_rate": 2.9921259842519687e-07, | |
| "loss": 1.0284, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.5369429241594996, | |
| "eval_loss": 1.4190484285354614, | |
| "eval_runtime": 53.6104, | |
| "eval_samples_per_second": 95.429, | |
| "eval_steps_per_second": 2.984, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 15.62, | |
| "grad_norm": 11.117311477661133, | |
| "learning_rate": 2.2047244094488187e-07, | |
| "loss": 1.0137, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.5383111806098514, | |
| "eval_loss": 1.4154096841812134, | |
| "eval_runtime": 53.1485, | |
| "eval_samples_per_second": 96.259, | |
| "eval_steps_per_second": 3.01, | |
| "step": 5120 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.5377247849882721, | |
| "eval_loss": 1.4145456552505493, | |
| "eval_runtime": 53.3337, | |
| "eval_samples_per_second": 95.924, | |
| "eval_steps_per_second": 3.0, | |
| "step": 5440 | |
| }, | |
| { | |
| "epoch": 17.19, | |
| "grad_norm": 7.341709136962891, | |
| "learning_rate": 1.4173228346456693e-07, | |
| "loss": 1.0175, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.5381157154026583, | |
| "eval_loss": 1.4157603979110718, | |
| "eval_runtime": 53.3037, | |
| "eval_samples_per_second": 95.978, | |
| "eval_steps_per_second": 3.002, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 18.75, | |
| "grad_norm": 9.26841926574707, | |
| "learning_rate": 6.299212598425197e-08, | |
| "loss": 1.0071, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.5381157154026583, | |
| "eval_loss": 1.4132405519485474, | |
| "eval_runtime": 53.3332, | |
| "eval_samples_per_second": 95.925, | |
| "eval_steps_per_second": 3.0, | |
| "step": 6080 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 6400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "total_flos": 3.0129905916761334e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |