| { | |
| "best_metric": 2.3164420127868652, | |
| "best_model_checkpoint": "house-plant-image-detection/checkpoint-9500", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 9500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8556344977304124, | |
| "eval_loss": 2.8916101455688477, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 432.8446, | |
| "eval_samples_per_second": 23.413, | |
| "eval_steps_per_second": 2.927, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 1.0526315789473684, | |
| "grad_norm": 1.8381797075271606, | |
| "learning_rate": 6.666666666666666e-07, | |
| "loss": 2.8708, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8576080521018354, | |
| "eval_loss": 2.826198101043701, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 428.5537, | |
| "eval_samples_per_second": 23.647, | |
| "eval_steps_per_second": 2.956, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1052631578947367, | |
| "grad_norm": 1.7179186344146729, | |
| "learning_rate": 6.296296296296295e-07, | |
| "loss": 2.7975, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8616538385632524, | |
| "eval_loss": 2.7662417888641357, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 433.9241, | |
| "eval_samples_per_second": 23.354, | |
| "eval_steps_per_second": 2.92, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 3.1578947368421053, | |
| "grad_norm": 1.8532851934432983, | |
| "learning_rate": 5.925925925925926e-07, | |
| "loss": 2.7278, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8657983027432405, | |
| "eval_loss": 2.709693193435669, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 425.7007, | |
| "eval_samples_per_second": 23.805, | |
| "eval_steps_per_second": 2.976, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 4.2105263157894735, | |
| "grad_norm": 2.0495333671569824, | |
| "learning_rate": 5.555555555555555e-07, | |
| "loss": 2.6669, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8683639234260904, | |
| "eval_loss": 2.658360481262207, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 429.652, | |
| "eval_samples_per_second": 23.587, | |
| "eval_steps_per_second": 2.949, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 5.2631578947368425, | |
| "grad_norm": 2.159403085708618, | |
| "learning_rate": 5.185185185185185e-07, | |
| "loss": 2.6089, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8711268995460825, | |
| "eval_loss": 2.611485004425049, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 431.1924, | |
| "eval_samples_per_second": 23.502, | |
| "eval_steps_per_second": 2.938, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 6.315789473684211, | |
| "grad_norm": 1.8190717697143555, | |
| "learning_rate": 4.814814814814814e-07, | |
| "loss": 2.5599, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8738898756660746, | |
| "eval_loss": 2.568486213684082, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 424.9082, | |
| "eval_samples_per_second": 23.85, | |
| "eval_steps_per_second": 2.982, | |
| "step": 3325 | |
| }, | |
| { | |
| "epoch": 7.368421052631579, | |
| "grad_norm": 1.934565544128418, | |
| "learning_rate": 4.444444444444444e-07, | |
| "loss": 2.5097, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8752713637260706, | |
| "eval_loss": 2.528704881668091, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 425.6933, | |
| "eval_samples_per_second": 23.806, | |
| "eval_steps_per_second": 2.976, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 8.421052631578947, | |
| "grad_norm": 1.9486241340637207, | |
| "learning_rate": 4.0740740740740737e-07, | |
| "loss": 2.4702, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8776396289717782, | |
| "eval_loss": 2.4933688640594482, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 424.8372, | |
| "eval_samples_per_second": 23.854, | |
| "eval_steps_per_second": 2.982, | |
| "step": 4275 | |
| }, | |
| { | |
| "epoch": 9.473684210526315, | |
| "grad_norm": 1.9259217977523804, | |
| "learning_rate": 3.703703703703703e-07, | |
| "loss": 2.4287, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8796131833432012, | |
| "eval_loss": 2.462188243865967, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 438.9669, | |
| "eval_samples_per_second": 23.086, | |
| "eval_steps_per_second": 2.886, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 10.526315789473685, | |
| "grad_norm": 1.8153620958328247, | |
| "learning_rate": 3.333333333333333e-07, | |
| "loss": 2.3971, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8814880599960528, | |
| "eval_loss": 2.4335598945617676, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 431.8448, | |
| "eval_samples_per_second": 23.467, | |
| "eval_steps_per_second": 2.934, | |
| "step": 5225 | |
| }, | |
| { | |
| "epoch": 11.578947368421053, | |
| "grad_norm": 1.7595205307006836, | |
| "learning_rate": 2.962962962962963e-07, | |
| "loss": 2.3613, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8818827708703375, | |
| "eval_loss": 2.4088268280029297, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 431.0231, | |
| "eval_samples_per_second": 23.512, | |
| "eval_steps_per_second": 2.94, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 12.631578947368421, | |
| "grad_norm": 2.0843069553375244, | |
| "learning_rate": 2.5925925925925923e-07, | |
| "loss": 2.3362, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8838563252417604, | |
| "eval_loss": 2.386713981628418, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 430.8876, | |
| "eval_samples_per_second": 23.519, | |
| "eval_steps_per_second": 2.94, | |
| "step": 6175 | |
| }, | |
| { | |
| "epoch": 13.68421052631579, | |
| "grad_norm": 2.014787197113037, | |
| "learning_rate": 2.222222222222222e-07, | |
| "loss": 2.3164, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8847444247089007, | |
| "eval_loss": 2.3680498600006104, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 427.872, | |
| "eval_samples_per_second": 23.685, | |
| "eval_steps_per_second": 2.961, | |
| "step": 6650 | |
| }, | |
| { | |
| "epoch": 14.736842105263158, | |
| "grad_norm": 1.8344244956970215, | |
| "learning_rate": 1.8518518518518516e-07, | |
| "loss": 2.2957, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8851391355831854, | |
| "eval_loss": 2.3520989418029785, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 431.2, | |
| "eval_samples_per_second": 23.502, | |
| "eval_steps_per_second": 2.938, | |
| "step": 7125 | |
| }, | |
| { | |
| "epoch": 15.789473684210526, | |
| "grad_norm": 2.0472302436828613, | |
| "learning_rate": 1.4814814814814815e-07, | |
| "loss": 2.2776, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8857312018946122, | |
| "eval_loss": 2.33898663520813, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 442.8262, | |
| "eval_samples_per_second": 22.885, | |
| "eval_steps_per_second": 2.861, | |
| "step": 7600 | |
| }, | |
| { | |
| "epoch": 16.842105263157894, | |
| "grad_norm": 2.0044050216674805, | |
| "learning_rate": 1.111111111111111e-07, | |
| "loss": 2.2646, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8862245904874679, | |
| "eval_loss": 2.3293344974517822, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 429.8545, | |
| "eval_samples_per_second": 23.575, | |
| "eval_steps_per_second": 2.948, | |
| "step": 8075 | |
| }, | |
| { | |
| "epoch": 17.894736842105264, | |
| "grad_norm": 1.9763357639312744, | |
| "learning_rate": 7.407407407407407e-08, | |
| "loss": 2.2562, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8864219459246102, | |
| "eval_loss": 2.3220701217651367, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 428.7293, | |
| "eval_samples_per_second": 23.637, | |
| "eval_steps_per_second": 2.955, | |
| "step": 8550 | |
| }, | |
| { | |
| "epoch": 18.94736842105263, | |
| "grad_norm": 2.227926254272461, | |
| "learning_rate": 3.7037037037037036e-08, | |
| "loss": 2.251, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8868166567988948, | |
| "eval_loss": 2.3178884983062744, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 435.7094, | |
| "eval_samples_per_second": 23.259, | |
| "eval_steps_per_second": 2.908, | |
| "step": 9025 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 1.9126635789871216, | |
| "learning_rate": 0.0, | |
| "loss": 2.2443, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8867179790803237, | |
| "eval_loss": 2.3164420127868652, | |
| "eval_model_preparation_time": 0.0054, | |
| "eval_runtime": 431.3925, | |
| "eval_samples_per_second": 23.491, | |
| "eval_steps_per_second": 2.937, | |
| "step": 9500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3565515633067655e+19, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |