| { | |
| "best_metric": 0.12063875794410706, | |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-160", | |
| "epoch": 0.43478260869565216, | |
| "global_step": 160, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0001891304347826087, | |
| "loss": 0.6558, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001782608695652174, | |
| "loss": 0.3045, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0001673913043478261, | |
| "loss": 0.2567, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001565217391304348, | |
| "loss": 0.2319, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.8637602179836512, | |
| "eval_loss": 0.2531130313873291, | |
| "eval_runtime": 17.2839, | |
| "eval_samples_per_second": 42.467, | |
| "eval_steps_per_second": 5.323, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001456521739130435, | |
| "loss": 0.2499, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.0001347826086956522, | |
| "loss": 0.2874, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00012391304347826086, | |
| "loss": 0.1609, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00011304347826086956, | |
| "loss": 0.1306, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.9564032697547684, | |
| "eval_loss": 0.1377830058336258, | |
| "eval_runtime": 17.1335, | |
| "eval_samples_per_second": 42.84, | |
| "eval_steps_per_second": 5.37, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00010217391304347828, | |
| "loss": 0.228, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 9.130434782608696e-05, | |
| "loss": 0.1187, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 8.043478260869566e-05, | |
| "loss": 0.1811, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 6.956521739130436e-05, | |
| "loss": 0.2075, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.8419618528610354, | |
| "eval_loss": 0.3006892800331116, | |
| "eval_runtime": 17.1056, | |
| "eval_samples_per_second": 42.91, | |
| "eval_steps_per_second": 5.378, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 5.869565217391305e-05, | |
| "loss": 0.2099, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 4.782608695652174e-05, | |
| "loss": 0.1518, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 3.695652173913043e-05, | |
| "loss": 0.1559, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 2.608695652173913e-05, | |
| "loss": 0.1573, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.9618528610354223, | |
| "eval_loss": 0.12063875794410706, | |
| "eval_runtime": 16.7256, | |
| "eval_samples_per_second": 43.885, | |
| "eval_steps_per_second": 5.501, | |
| "step": 160 | |
| } | |
| ], | |
| "max_steps": 184, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.9838127142600704e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |