| { | |
| "best_metric": 0.8250355618776671, | |
| "best_model_checkpoint": "MRR_image_classification_dit_29_jan-finetuned-eurosat/checkpoint-525", | |
| "epoch": 2.987197724039829, | |
| "eval_steps": 500, | |
| "global_step": 525, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 9.433962264150944e-06, | |
| "loss": 2.0011, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 1.8867924528301888e-05, | |
| "loss": 1.411, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 2.830188679245283e-05, | |
| "loss": 1.2419, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 3.7735849056603776e-05, | |
| "loss": 1.24, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.716981132075472e-05, | |
| "loss": 1.1031, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.925847457627119e-05, | |
| "loss": 1.0103, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.819915254237288e-05, | |
| "loss": 1.1038, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 4.7139830508474584e-05, | |
| "loss": 1.1555, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 4.608050847457627e-05, | |
| "loss": 1.0994, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.502118644067797e-05, | |
| "loss": 1.1303, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.396186440677966e-05, | |
| "loss": 1.0542, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.290254237288136e-05, | |
| "loss": 1.0717, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 4.1843220338983054e-05, | |
| "loss": 1.0289, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.078389830508475e-05, | |
| "loss": 0.9717, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.9724576271186445e-05, | |
| "loss": 0.9926, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.866525423728814e-05, | |
| "loss": 0.9859, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.7605932203389835e-05, | |
| "loss": 1.0588, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6621621621621622, | |
| "eval_loss": 0.8930806517601013, | |
| "eval_runtime": 59.7101, | |
| "eval_samples_per_second": 23.547, | |
| "eval_steps_per_second": 2.948, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.654661016949153e-05, | |
| "loss": 0.9578, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 3.548728813559322e-05, | |
| "loss": 0.9455, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 3.442796610169492e-05, | |
| "loss": 0.9959, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 3.336864406779661e-05, | |
| "loss": 0.9689, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.230932203389831e-05, | |
| "loss": 0.9743, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.125e-05, | |
| "loss": 0.8971, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 3.0190677966101693e-05, | |
| "loss": 0.8917, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 2.913135593220339e-05, | |
| "loss": 0.7242, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.48, | |
| "learning_rate": 2.8072033898305083e-05, | |
| "loss": 0.9562, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.54, | |
| "learning_rate": 2.7012711864406782e-05, | |
| "loss": 0.8342, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.59, | |
| "learning_rate": 2.5953389830508474e-05, | |
| "loss": 0.8166, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "learning_rate": 2.489406779661017e-05, | |
| "loss": 0.829, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 2.3834745762711865e-05, | |
| "loss": 0.7821, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.277542372881356e-05, | |
| "loss": 0.8847, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.82, | |
| "learning_rate": 2.1716101694915255e-05, | |
| "loss": 0.7451, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "learning_rate": 2.065677966101695e-05, | |
| "loss": 0.7431, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.9597457627118646e-05, | |
| "loss": 0.7861, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.99, | |
| "learning_rate": 1.853813559322034e-05, | |
| "loss": 0.7206, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7773826458036984, | |
| "eval_loss": 0.6266400218009949, | |
| "eval_runtime": 57.5992, | |
| "eval_samples_per_second": 24.41, | |
| "eval_steps_per_second": 3.056, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 1.7478813559322037e-05, | |
| "loss": 0.6948, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 1.641949152542373e-05, | |
| "loss": 0.7623, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 1.5360169491525424e-05, | |
| "loss": 0.6679, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 1.430084745762712e-05, | |
| "loss": 0.623, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 1.3241525423728815e-05, | |
| "loss": 0.7125, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.33, | |
| "learning_rate": 1.2182203389830509e-05, | |
| "loss": 0.8716, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1122881355932204e-05, | |
| "loss": 0.7073, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 1.0063559322033898e-05, | |
| "loss": 0.722, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 9.004237288135593e-06, | |
| "loss": 0.733, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 7.944915254237288e-06, | |
| "loss": 0.6861, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 6.885593220338983e-06, | |
| "loss": 0.6785, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 5.826271186440678e-06, | |
| "loss": 0.71, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 4.766949152542373e-06, | |
| "loss": 0.6091, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 3.707627118644068e-06, | |
| "loss": 0.754, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 2.648305084745763e-06, | |
| "loss": 0.6406, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.9, | |
| "learning_rate": 1.5889830508474576e-06, | |
| "loss": 0.6826, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 5.296610169491525e-07, | |
| "loss": 0.6833, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8250355618776671, | |
| "eval_loss": 0.4995260536670685, | |
| "eval_runtime": 58.3941, | |
| "eval_samples_per_second": 24.078, | |
| "eval_steps_per_second": 3.014, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "step": 525, | |
| "total_flos": 4.6009321944033853e+18, | |
| "train_loss": 0.9024475538162958, | |
| "train_runtime": 1330.277, | |
| "train_samples_per_second": 12.676, | |
| "train_steps_per_second": 0.395 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 525, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 4.6009321944033853e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |