| { | |
| "best_metric": 0.07841455936431885, | |
| "best_model_checkpoint": "./vit-base-beans/checkpoint-280", | |
| "epoch": 0.7608695652173914, | |
| "global_step": 280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00019322033898305085, | |
| "loss": 0.6554, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.0001864406779661017, | |
| "loss": 0.306, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00017966101694915257, | |
| "loss": 0.267, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00017288135593220342, | |
| "loss": 0.2825, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "eval_accuracy": 0.9318801089918256, | |
| "eval_loss": 0.2294050008058548, | |
| "eval_runtime": 16.8062, | |
| "eval_samples_per_second": 43.674, | |
| "eval_steps_per_second": 5.474, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00016610169491525423, | |
| "loss": 0.3097, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00015932203389830508, | |
| "loss": 0.2772, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00015254237288135592, | |
| "loss": 0.1711, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00014576271186440677, | |
| "loss": 0.1483, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "eval_accuracy": 0.944141689373297, | |
| "eval_loss": 0.16020944714546204, | |
| "eval_runtime": 17.3798, | |
| "eval_samples_per_second": 42.233, | |
| "eval_steps_per_second": 5.294, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00013898305084745764, | |
| "loss": 0.2356, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00013220338983050849, | |
| "loss": 0.1144, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00012542372881355933, | |
| "loss": 0.2216, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.00011864406779661017, | |
| "loss": 0.2209, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_accuracy": 0.829700272479564, | |
| "eval_loss": 0.29767370223999023, | |
| "eval_runtime": 17.13, | |
| "eval_samples_per_second": 42.849, | |
| "eval_steps_per_second": 5.371, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.00011186440677966102, | |
| "loss": 0.2153, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00010508474576271188, | |
| "loss": 0.1693, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 9.830508474576272e-05, | |
| "loss": 0.1625, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 9.152542372881357e-05, | |
| "loss": 0.1384, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_accuracy": 0.9645776566757494, | |
| "eval_loss": 0.10578873753547668, | |
| "eval_runtime": 16.6083, | |
| "eval_samples_per_second": 44.195, | |
| "eval_steps_per_second": 5.539, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 8.474576271186441e-05, | |
| "loss": 0.1371, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 7.796610169491526e-05, | |
| "loss": 0.1355, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.11864406779661e-05, | |
| "loss": 0.1557, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 6.440677966101695e-05, | |
| "loss": 0.1551, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.9114441416893733, | |
| "eval_loss": 0.1725204885005951, | |
| "eval_runtime": 17.0671, | |
| "eval_samples_per_second": 43.007, | |
| "eval_steps_per_second": 5.39, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 5.76271186440678e-05, | |
| "loss": 0.2091, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 5.0847457627118643e-05, | |
| "loss": 0.1313, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 4.4067796610169495e-05, | |
| "loss": 0.1056, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 3.728813559322034e-05, | |
| "loss": 0.1608, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.9673024523160763, | |
| "eval_loss": 0.09211871027946472, | |
| "eval_runtime": 16.6063, | |
| "eval_samples_per_second": 44.2, | |
| "eval_steps_per_second": 5.54, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.050847457627119e-05, | |
| "loss": 0.0761, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 2.3728813559322036e-05, | |
| "loss": 0.1044, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 1.694915254237288e-05, | |
| "loss": 0.1141, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.016949152542373e-05, | |
| "loss": 0.12, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "eval_accuracy": 0.9754768392370572, | |
| "eval_loss": 0.07841455936431885, | |
| "eval_runtime": 16.7459, | |
| "eval_samples_per_second": 43.832, | |
| "eval_steps_per_second": 5.494, | |
| "step": 280 | |
| } | |
| ], | |
| "max_steps": 295, | |
| "num_train_epochs": 1, | |
| "total_flos": 3.471672249955123e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |