| { | |
| "best_metric": 0.9714285714285714, | |
| "best_model_checkpoint": "delivery_truck_classification/checkpoint-120", | |
| "epoch": 60.0, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.12857142857142856, | |
| "eval_loss": 1.9401942491531372, | |
| "eval_runtime": 4.0508, | |
| "eval_samples_per_second": 17.281, | |
| "eval_steps_per_second": 0.741, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.24285714285714285, | |
| "eval_loss": 1.8379000425338745, | |
| "eval_runtime": 4.25, | |
| "eval_samples_per_second": 16.47, | |
| "eval_steps_per_second": 0.706, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.4, | |
| "eval_loss": 1.6960197687149048, | |
| "eval_runtime": 4.0325, | |
| "eval_samples_per_second": 17.359, | |
| "eval_steps_per_second": 0.744, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.7795, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5142857142857142, | |
| "eval_loss": 1.4422836303710938, | |
| "eval_runtime": 4.0892, | |
| "eval_samples_per_second": 17.118, | |
| "eval_steps_per_second": 0.734, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.6857142857142857, | |
| "eval_loss": 1.129531741142273, | |
| "eval_runtime": 4.0522, | |
| "eval_samples_per_second": 17.275, | |
| "eval_steps_per_second": 0.74, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.7285714285714285, | |
| "eval_loss": 0.8280124068260193, | |
| "eval_runtime": 4.1393, | |
| "eval_samples_per_second": 16.911, | |
| "eval_steps_per_second": 0.725, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8428571428571429, | |
| "eval_loss": 0.5571854710578918, | |
| "eval_runtime": 4.1115, | |
| "eval_samples_per_second": 17.026, | |
| "eval_steps_per_second": 0.73, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.0588, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.38549211621284485, | |
| "eval_runtime": 4.081, | |
| "eval_samples_per_second": 17.153, | |
| "eval_steps_per_second": 0.735, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.3106531500816345, | |
| "eval_runtime": 4.0992, | |
| "eval_samples_per_second": 17.076, | |
| "eval_steps_per_second": 0.732, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.25636935234069824, | |
| "eval_runtime": 4.1866, | |
| "eval_samples_per_second": 16.72, | |
| "eval_steps_per_second": 0.717, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.20498664677143097, | |
| "eval_runtime": 4.0728, | |
| "eval_samples_per_second": 17.187, | |
| "eval_steps_per_second": 0.737, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.591, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.19002115726470947, | |
| "eval_runtime": 4.0628, | |
| "eval_samples_per_second": 17.23, | |
| "eval_steps_per_second": 0.738, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.17195703089237213, | |
| "eval_runtime": 4.0868, | |
| "eval_samples_per_second": 17.128, | |
| "eval_steps_per_second": 0.734, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.188080832362175, | |
| "eval_runtime": 4.0578, | |
| "eval_samples_per_second": 17.251, | |
| "eval_steps_per_second": 0.739, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.1788831204175949, | |
| "eval_runtime": 4.1273, | |
| "eval_samples_per_second": 16.96, | |
| "eval_steps_per_second": 0.727, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.4609, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9142857142857143, | |
| "eval_loss": 0.199941948056221, | |
| "eval_runtime": 4.0992, | |
| "eval_samples_per_second": 17.076, | |
| "eval_steps_per_second": 0.732, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.1491808146238327, | |
| "eval_runtime": 4.1379, | |
| "eval_samples_per_second": 16.917, | |
| "eval_steps_per_second": 0.725, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.1648150235414505, | |
| "eval_runtime": 4.0523, | |
| "eval_samples_per_second": 17.274, | |
| "eval_steps_per_second": 0.74, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.11947301775217056, | |
| "eval_runtime": 4.0582, | |
| "eval_samples_per_second": 17.249, | |
| "eval_steps_per_second": 0.739, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3941, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.13950331509113312, | |
| "eval_runtime": 4.1018, | |
| "eval_samples_per_second": 17.066, | |
| "eval_steps_per_second": 0.731, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.9285714285714286, | |
| "eval_loss": 0.14757172763347626, | |
| "eval_runtime": 4.0132, | |
| "eval_samples_per_second": 17.443, | |
| "eval_steps_per_second": 0.748, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1113029271364212, | |
| "eval_runtime": 4.0076, | |
| "eval_samples_per_second": 17.467, | |
| "eval_steps_per_second": 0.749, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.13283702731132507, | |
| "eval_runtime": 4.0346, | |
| "eval_samples_per_second": 17.35, | |
| "eval_steps_per_second": 0.744, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3475, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9714285714285714, | |
| "eval_loss": 0.11924324184656143, | |
| "eval_runtime": 4.026, | |
| "eval_samples_per_second": 17.387, | |
| "eval_steps_per_second": 0.745, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.11995943635702133, | |
| "eval_runtime": 4.1096, | |
| "eval_samples_per_second": 17.033, | |
| "eval_steps_per_second": 0.73, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.9714285714285714, | |
| "eval_loss": 0.1360194832086563, | |
| "eval_runtime": 4.1596, | |
| "eval_samples_per_second": 16.828, | |
| "eval_steps_per_second": 0.721, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.14246320724487305, | |
| "eval_runtime": 4.0478, | |
| "eval_samples_per_second": 17.293, | |
| "eval_steps_per_second": 0.741, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.3542, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.11028776317834854, | |
| "eval_runtime": 4.0318, | |
| "eval_samples_per_second": 17.362, | |
| "eval_steps_per_second": 0.744, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.12440218031406403, | |
| "eval_runtime": 4.038, | |
| "eval_samples_per_second": 17.335, | |
| "eval_steps_per_second": 0.743, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.11757094413042068, | |
| "eval_runtime": 4.0522, | |
| "eval_samples_per_second": 17.275, | |
| "eval_steps_per_second": 0.74, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.10275254398584366, | |
| "eval_runtime": 4.073, | |
| "eval_samples_per_second": 17.186, | |
| "eval_steps_per_second": 0.737, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.317, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1084454134106636, | |
| "eval_runtime": 4.0241, | |
| "eval_samples_per_second": 17.395, | |
| "eval_steps_per_second": 0.746, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.12689971923828125, | |
| "eval_runtime": 4.0167, | |
| "eval_samples_per_second": 17.427, | |
| "eval_steps_per_second": 0.747, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.12951645255088806, | |
| "eval_runtime": 4.1051, | |
| "eval_samples_per_second": 17.052, | |
| "eval_steps_per_second": 0.731, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1245197132229805, | |
| "eval_runtime": 4.0579, | |
| "eval_samples_per_second": 17.251, | |
| "eval_steps_per_second": 0.739, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.2947, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.13154344260692596, | |
| "eval_runtime": 4.0212, | |
| "eval_samples_per_second": 17.408, | |
| "eval_steps_per_second": 0.746, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.13128569722175598, | |
| "eval_runtime": 4.0731, | |
| "eval_samples_per_second": 17.186, | |
| "eval_steps_per_second": 0.737, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.14208073914051056, | |
| "eval_runtime": 4.0445, | |
| "eval_samples_per_second": 17.307, | |
| "eval_steps_per_second": 0.742, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1440354883670807, | |
| "eval_runtime": 4.02, | |
| "eval_samples_per_second": 17.413, | |
| "eval_steps_per_second": 0.746, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3124, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.13390059769153595, | |
| "eval_runtime": 4.0153, | |
| "eval_samples_per_second": 17.433, | |
| "eval_steps_per_second": 0.747, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.15533578395843506, | |
| "eval_runtime": 4.0821, | |
| "eval_samples_per_second": 17.148, | |
| "eval_steps_per_second": 0.735, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.1547066867351532, | |
| "eval_runtime": 4.0957, | |
| "eval_samples_per_second": 17.091, | |
| "eval_steps_per_second": 0.732, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.13160941004753113, | |
| "eval_runtime": 4.1174, | |
| "eval_samples_per_second": 17.001, | |
| "eval_steps_per_second": 0.729, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.2843, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.12867721915245056, | |
| "eval_runtime": 4.1356, | |
| "eval_samples_per_second": 16.926, | |
| "eval_steps_per_second": 0.725, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.13077586889266968, | |
| "eval_runtime": 4.164, | |
| "eval_samples_per_second": 16.811, | |
| "eval_steps_per_second": 0.72, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1401166319847107, | |
| "eval_runtime": 4.0319, | |
| "eval_samples_per_second": 17.362, | |
| "eval_steps_per_second": 0.744, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.11855422705411911, | |
| "eval_runtime": 4.0342, | |
| "eval_samples_per_second": 17.351, | |
| "eval_steps_per_second": 0.744, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.2655, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.10567642003297806, | |
| "eval_runtime": 4.0324, | |
| "eval_samples_per_second": 17.359, | |
| "eval_steps_per_second": 0.744, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.12025075405836105, | |
| "eval_runtime": 4.0512, | |
| "eval_samples_per_second": 17.279, | |
| "eval_steps_per_second": 0.741, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1373574286699295, | |
| "eval_runtime": 4.0455, | |
| "eval_samples_per_second": 17.303, | |
| "eval_steps_per_second": 0.742, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1361333578824997, | |
| "eval_runtime": 4.0102, | |
| "eval_samples_per_second": 17.455, | |
| "eval_steps_per_second": 0.748, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.26, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.11978749185800552, | |
| "eval_runtime": 4.1202, | |
| "eval_samples_per_second": 16.989, | |
| "eval_steps_per_second": 0.728, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.11752226948738098, | |
| "eval_runtime": 4.0691, | |
| "eval_samples_per_second": 17.203, | |
| "eval_steps_per_second": 0.737, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.13132056593894958, | |
| "eval_runtime": 4.068, | |
| "eval_samples_per_second": 17.207, | |
| "eval_steps_per_second": 0.737, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.9428571428571428, | |
| "eval_loss": 0.13983343541622162, | |
| "eval_runtime": 4.0628, | |
| "eval_samples_per_second": 17.229, | |
| "eval_steps_per_second": 0.738, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.2601, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.13535180687904358, | |
| "eval_runtime": 4.003, | |
| "eval_samples_per_second": 17.487, | |
| "eval_steps_per_second": 0.749, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.1271456480026245, | |
| "eval_runtime": 4.0903, | |
| "eval_samples_per_second": 17.113, | |
| "eval_steps_per_second": 0.733, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.12419404834508896, | |
| "eval_runtime": 3.995, | |
| "eval_samples_per_second": 17.522, | |
| "eval_steps_per_second": 0.751, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.12333472073078156, | |
| "eval_runtime": 4.144, | |
| "eval_samples_per_second": 16.892, | |
| "eval_steps_per_second": 0.724, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2562, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.9571428571428572, | |
| "eval_loss": 0.12345683574676514, | |
| "eval_runtime": 4.0756, | |
| "eval_samples_per_second": 17.176, | |
| "eval_steps_per_second": 0.736, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "step": 300, | |
| "total_flos": 9.381960833056358e+17, | |
| "train_loss": 0.48240819613138836, | |
| "train_runtime": 5472.4354, | |
| "train_samples_per_second": 6.896, | |
| "train_steps_per_second": 0.055 | |
| } | |
| ], | |
| "max_steps": 300, | |
| "num_train_epochs": 60, | |
| "total_flos": 9.381960833056358e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |