| { |
| "best_metric": 0.133230060338974, |
| "best_model_checkpoint": "./beans_outputs/checkpoint-260", |
| "epoch": 5.0, |
| "global_step": 325, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15, |
| "learning_rate": 1.9384615384615386e-05, |
| "loss": 1.0096, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 1.876923076923077e-05, |
| "loss": 0.8998, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 1.8153846153846155e-05, |
| "loss": 0.7782, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 1.753846153846154e-05, |
| "loss": 0.6903, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 1.6923076923076924e-05, |
| "loss": 0.589, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 1.630769230769231e-05, |
| "loss": 0.4885, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9548872180451128, |
| "eval_loss": 0.3982284665107727, |
| "eval_runtime": 1.8876, |
| "eval_samples_per_second": 70.46, |
| "eval_steps_per_second": 4.768, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 1.5692307692307693e-05, |
| "loss": 0.4291, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 1.5076923076923078e-05, |
| "loss": 0.3622, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 1.4461538461538462e-05, |
| "loss": 0.3564, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 1.3846153846153847e-05, |
| "loss": 0.2736, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 1.3230769230769231e-05, |
| "loss": 0.2401, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 1.2615384615384616e-05, |
| "loss": 0.2522, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 1.2e-05, |
| "loss": 0.271, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.18636491894721985, |
| "eval_runtime": 1.9478, |
| "eval_samples_per_second": 68.283, |
| "eval_steps_per_second": 4.621, |
| "step": 130 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 1.1384615384615385e-05, |
| "loss": 0.2319, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 1.076923076923077e-05, |
| "loss": 0.2097, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 1.0153846153846154e-05, |
| "loss": 0.1922, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 9.53846153846154e-06, |
| "loss": 0.1735, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 8.923076923076925e-06, |
| "loss": 0.1778, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.92, |
| "learning_rate": 8.307692307692309e-06, |
| "loss": 0.1419, |
| "step": 190 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9774436090225563, |
| "eval_loss": 0.1587418019771576, |
| "eval_runtime": 1.8455, |
| "eval_samples_per_second": 72.066, |
| "eval_steps_per_second": 4.877, |
| "step": 195 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 7.692307692307694e-06, |
| "loss": 0.1654, |
| "step": 200 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 7.076923076923078e-06, |
| "loss": 0.1738, |
| "step": 210 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 6.461538461538463e-06, |
| "loss": 0.1743, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.54, |
| "learning_rate": 5.846153846153847e-06, |
| "loss": 0.168, |
| "step": 230 |
| }, |
| { |
| "epoch": 3.69, |
| "learning_rate": 5.230769230769232e-06, |
| "loss": 0.1521, |
| "step": 240 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 4.615384615384616e-06, |
| "loss": 0.182, |
| "step": 250 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.1658, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.133230060338974, |
| "eval_runtime": 1.846, |
| "eval_samples_per_second": 72.047, |
| "eval_steps_per_second": 4.875, |
| "step": 260 |
| }, |
| { |
| "epoch": 4.15, |
| "learning_rate": 3.384615384615385e-06, |
| "loss": 0.1186, |
| "step": 270 |
| }, |
| { |
| "epoch": 4.31, |
| "learning_rate": 2.7692307692307697e-06, |
| "loss": 0.1364, |
| "step": 280 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 2.153846153846154e-06, |
| "loss": 0.1747, |
| "step": 290 |
| }, |
| { |
| "epoch": 4.62, |
| "learning_rate": 1.5384615384615387e-06, |
| "loss": 0.122, |
| "step": 300 |
| }, |
| { |
| "epoch": 4.77, |
| "learning_rate": 9.230769230769232e-07, |
| "loss": 0.1588, |
| "step": 310 |
| }, |
| { |
| "epoch": 4.92, |
| "learning_rate": 3.0769230769230774e-07, |
| "loss": 0.1767, |
| "step": 320 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9699248120300752, |
| "eval_loss": 0.1348881870508194, |
| "eval_runtime": 1.8455, |
| "eval_samples_per_second": 72.065, |
| "eval_steps_per_second": 4.877, |
| "step": 325 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 325, |
| "total_flos": 4.006371770595533e+17, |
| "train_loss": 0.0, |
| "train_runtime": 0.1083, |
| "train_samples_per_second": 47737.884, |
| "train_steps_per_second": 3000.931 |
| } |
| ], |
| "max_steps": 325, |
| "num_train_epochs": 5, |
| "total_flos": 4.006371770595533e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
