| { |
| "best_metric": 0.43153366446495056, |
| "best_model_checkpoint": "./plant-classification/checkpoint-280", |
| "epoch": 3.5, |
| "global_step": 280, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.00019375000000000002, |
| "loss": 2.4618, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.0001875, |
| "loss": 2.0277, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00018125000000000001, |
| "loss": 1.6392, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.000175, |
| "loss": 1.3747, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_accuracy": 0.7626168224299066, |
| "eval_loss": 1.1831709146499634, |
| "eval_runtime": 384.9557, |
| "eval_samples_per_second": 1.39, |
| "eval_steps_per_second": 0.174, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.00016875, |
| "loss": 1.2425, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.00016250000000000002, |
| "loss": 1.1063, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.00015625, |
| "loss": 0.9224, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00015000000000000001, |
| "loss": 0.7905, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8130841121495327, |
| "eval_loss": 0.7577788233757019, |
| "eval_runtime": 381.7049, |
| "eval_samples_per_second": 1.402, |
| "eval_steps_per_second": 0.176, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00014375, |
| "loss": 0.6613, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.0001375, |
| "loss": 0.6946, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.00013125000000000002, |
| "loss": 0.5187, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.000125, |
| "loss": 0.5223, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.5, |
| "eval_accuracy": 0.8186915887850468, |
| "eval_loss": 0.6094576120376587, |
| "eval_runtime": 389.3932, |
| "eval_samples_per_second": 1.374, |
| "eval_steps_per_second": 0.172, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00011875, |
| "loss": 0.5048, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 0.00011250000000000001, |
| "loss": 0.5559, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.00010625000000000001, |
| "loss": 0.4757, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.0001, |
| "loss": 0.3683, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8542056074766355, |
| "eval_loss": 0.5075709819793701, |
| "eval_runtime": 384.1646, |
| "eval_samples_per_second": 1.393, |
| "eval_steps_per_second": 0.174, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 9.375e-05, |
| "loss": 0.3126, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 8.75e-05, |
| "loss": 0.3093, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 8.125000000000001e-05, |
| "loss": 0.3063, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 7.500000000000001e-05, |
| "loss": 0.2401, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_accuracy": 0.8467289719626169, |
| "eval_loss": 0.4515593349933624, |
| "eval_runtime": 374.8793, |
| "eval_samples_per_second": 1.427, |
| "eval_steps_per_second": 0.179, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 6.875e-05, |
| "loss": 0.3209, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 6.25e-05, |
| "loss": 0.2538, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 5.6250000000000005e-05, |
| "loss": 0.2671, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 5e-05, |
| "loss": 0.2688, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8598130841121495, |
| "eval_loss": 0.4518713057041168, |
| "eval_runtime": 371.598, |
| "eval_samples_per_second": 1.44, |
| "eval_steps_per_second": 0.18, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.12, |
| "learning_rate": 4.375e-05, |
| "loss": 0.1702, |
| "step": 250 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 3.7500000000000003e-05, |
| "loss": 0.1993, |
| "step": 260 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 3.125e-05, |
| "loss": 0.218, |
| "step": 270 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 2.5e-05, |
| "loss": 0.1583, |
| "step": 280 |
| }, |
| { |
| "epoch": 3.5, |
| "eval_accuracy": 0.874766355140187, |
| "eval_loss": 0.43153366446495056, |
| "eval_runtime": 380.0584, |
| "eval_samples_per_second": 1.408, |
| "eval_steps_per_second": 0.176, |
| "step": 280 |
| } |
| ], |
| "max_steps": 320, |
| "num_train_epochs": 4, |
| "total_flos": 3.467364497947607e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
