|
{ |
|
"best_metric": 0.96875, |
|
"best_model_checkpoint": "delivery_truck_classification/checkpoint-52", |
|
"epoch": 59.888888888888886, |
|
"global_step": 240, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.89, |
|
"eval_accuracy": 0.15625, |
|
"eval_loss": 2.007406234741211, |
|
"eval_runtime": 4.1284, |
|
"eval_samples_per_second": 15.502, |
|
"eval_steps_per_second": 0.484, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"eval_accuracy": 0.25, |
|
"eval_loss": 1.8895925283432007, |
|
"eval_runtime": 4.9483, |
|
"eval_samples_per_second": 12.934, |
|
"eval_steps_per_second": 0.404, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 2.89, |
|
"eval_accuracy": 0.40625, |
|
"eval_loss": 1.7421282529830933, |
|
"eval_runtime": 4.1039, |
|
"eval_samples_per_second": 15.595, |
|
"eval_steps_per_second": 0.487, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 3.89, |
|
"eval_accuracy": 0.4375, |
|
"eval_loss": 1.5891958475112915, |
|
"eval_runtime": 4.5489, |
|
"eval_samples_per_second": 14.069, |
|
"eval_steps_per_second": 0.44, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"learning_rate": 4.166666666666667e-05, |
|
"loss": 1.973, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 4.89, |
|
"eval_accuracy": 0.609375, |
|
"eval_loss": 1.362261176109314, |
|
"eval_runtime": 4.1743, |
|
"eval_samples_per_second": 15.332, |
|
"eval_steps_per_second": 0.479, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 5.89, |
|
"eval_accuracy": 0.609375, |
|
"eval_loss": 1.1093113422393799, |
|
"eval_runtime": 4.4702, |
|
"eval_samples_per_second": 14.317, |
|
"eval_steps_per_second": 0.447, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 6.89, |
|
"eval_accuracy": 0.78125, |
|
"eval_loss": 0.7900974154472351, |
|
"eval_runtime": 4.1973, |
|
"eval_samples_per_second": 15.248, |
|
"eval_steps_per_second": 0.476, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 7.89, |
|
"eval_accuracy": 0.84375, |
|
"eval_loss": 0.5773038268089294, |
|
"eval_runtime": 4.6009, |
|
"eval_samples_per_second": 13.91, |
|
"eval_steps_per_second": 0.435, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 8.89, |
|
"eval_accuracy": 0.890625, |
|
"eval_loss": 0.38568082451820374, |
|
"eval_runtime": 4.1614, |
|
"eval_samples_per_second": 15.379, |
|
"eval_steps_per_second": 0.481, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 9.89, |
|
"learning_rate": 4.62962962962963e-05, |
|
"loss": 1.0433, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 9.89, |
|
"eval_accuracy": 0.90625, |
|
"eval_loss": 0.32543647289276123, |
|
"eval_runtime": 4.5756, |
|
"eval_samples_per_second": 13.987, |
|
"eval_steps_per_second": 0.437, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 10.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.2461281269788742, |
|
"eval_runtime": 4.2012, |
|
"eval_samples_per_second": 15.234, |
|
"eval_steps_per_second": 0.476, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 11.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.2339743673801422, |
|
"eval_runtime": 4.5321, |
|
"eval_samples_per_second": 14.121, |
|
"eval_steps_per_second": 0.441, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 12.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.18353550136089325, |
|
"eval_runtime": 4.3055, |
|
"eval_samples_per_second": 14.865, |
|
"eval_steps_per_second": 0.465, |
|
"step": 52 |
|
}, |
|
{ |
|
"epoch": 13.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.17793762683868408, |
|
"eval_runtime": 4.4643, |
|
"eval_samples_per_second": 14.336, |
|
"eval_steps_per_second": 0.448, |
|
"step": 56 |
|
}, |
|
{ |
|
"epoch": 14.89, |
|
"learning_rate": 4.166666666666667e-05, |
|
"loss": 0.5842, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 14.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.15445110201835632, |
|
"eval_runtime": 4.1434, |
|
"eval_samples_per_second": 15.446, |
|
"eval_steps_per_second": 0.483, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 15.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.14869830012321472, |
|
"eval_runtime": 4.5456, |
|
"eval_samples_per_second": 14.08, |
|
"eval_steps_per_second": 0.44, |
|
"step": 64 |
|
}, |
|
{ |
|
"epoch": 16.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.19956862926483154, |
|
"eval_runtime": 4.0021, |
|
"eval_samples_per_second": 15.992, |
|
"eval_steps_per_second": 0.5, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 17.89, |
|
"eval_accuracy": 0.90625, |
|
"eval_loss": 0.1619431972503662, |
|
"eval_runtime": 4.478, |
|
"eval_samples_per_second": 14.292, |
|
"eval_steps_per_second": 0.447, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 18.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.13495692610740662, |
|
"eval_runtime": 4.1244, |
|
"eval_samples_per_second": 15.517, |
|
"eval_steps_per_second": 0.485, |
|
"step": 76 |
|
}, |
|
{ |
|
"epoch": 19.89, |
|
"learning_rate": 3.7037037037037037e-05, |
|
"loss": 0.4616, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 19.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.17057114839553833, |
|
"eval_runtime": 4.5586, |
|
"eval_samples_per_second": 14.039, |
|
"eval_steps_per_second": 0.439, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 20.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.15793055295944214, |
|
"eval_runtime": 4.126, |
|
"eval_samples_per_second": 15.511, |
|
"eval_steps_per_second": 0.485, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 21.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.16296246647834778, |
|
"eval_runtime": 4.5173, |
|
"eval_samples_per_second": 14.168, |
|
"eval_steps_per_second": 0.443, |
|
"step": 88 |
|
}, |
|
{ |
|
"epoch": 22.89, |
|
"eval_accuracy": 0.90625, |
|
"eval_loss": 0.20802505314350128, |
|
"eval_runtime": 4.0833, |
|
"eval_samples_per_second": 15.674, |
|
"eval_steps_per_second": 0.49, |
|
"step": 92 |
|
}, |
|
{ |
|
"epoch": 23.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.14634451270103455, |
|
"eval_runtime": 4.6059, |
|
"eval_samples_per_second": 13.895, |
|
"eval_steps_per_second": 0.434, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 24.89, |
|
"learning_rate": 3.240740740740741e-05, |
|
"loss": 0.3898, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 24.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.11846979707479477, |
|
"eval_runtime": 4.1451, |
|
"eval_samples_per_second": 15.44, |
|
"eval_steps_per_second": 0.483, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 25.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.14448919892311096, |
|
"eval_runtime": 4.4782, |
|
"eval_samples_per_second": 14.291, |
|
"eval_steps_per_second": 0.447, |
|
"step": 104 |
|
}, |
|
{ |
|
"epoch": 26.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.20514565706253052, |
|
"eval_runtime": 4.0807, |
|
"eval_samples_per_second": 15.683, |
|
"eval_steps_per_second": 0.49, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 27.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.19281229376792908, |
|
"eval_runtime": 4.457, |
|
"eval_samples_per_second": 14.36, |
|
"eval_steps_per_second": 0.449, |
|
"step": 112 |
|
}, |
|
{ |
|
"epoch": 28.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.13649864494800568, |
|
"eval_runtime": 4.038, |
|
"eval_samples_per_second": 15.849, |
|
"eval_steps_per_second": 0.495, |
|
"step": 116 |
|
}, |
|
{ |
|
"epoch": 29.89, |
|
"learning_rate": 2.777777777777778e-05, |
|
"loss": 0.3511, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 29.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.10572843253612518, |
|
"eval_runtime": 4.5443, |
|
"eval_samples_per_second": 14.084, |
|
"eval_steps_per_second": 0.44, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 30.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.10910199582576752, |
|
"eval_runtime": 4.2535, |
|
"eval_samples_per_second": 15.046, |
|
"eval_steps_per_second": 0.47, |
|
"step": 124 |
|
}, |
|
{ |
|
"epoch": 31.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.1893911063671112, |
|
"eval_runtime": 4.6955, |
|
"eval_samples_per_second": 13.63, |
|
"eval_steps_per_second": 0.426, |
|
"step": 128 |
|
}, |
|
{ |
|
"epoch": 32.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.12075338512659073, |
|
"eval_runtime": 4.1214, |
|
"eval_samples_per_second": 15.529, |
|
"eval_steps_per_second": 0.485, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 33.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.11010686308145523, |
|
"eval_runtime": 4.5267, |
|
"eval_samples_per_second": 14.138, |
|
"eval_steps_per_second": 0.442, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 34.89, |
|
"learning_rate": 2.314814814814815e-05, |
|
"loss": 0.3286, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 34.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.14093339443206787, |
|
"eval_runtime": 4.119, |
|
"eval_samples_per_second": 15.538, |
|
"eval_steps_per_second": 0.486, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 35.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.18304279446601868, |
|
"eval_runtime": 4.4932, |
|
"eval_samples_per_second": 14.244, |
|
"eval_steps_per_second": 0.445, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 36.89, |
|
"eval_accuracy": 0.921875, |
|
"eval_loss": 0.1518746018409729, |
|
"eval_runtime": 4.1186, |
|
"eval_samples_per_second": 15.539, |
|
"eval_steps_per_second": 0.486, |
|
"step": 148 |
|
}, |
|
{ |
|
"epoch": 37.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.10309180617332458, |
|
"eval_runtime": 4.5179, |
|
"eval_samples_per_second": 14.166, |
|
"eval_steps_per_second": 0.443, |
|
"step": 152 |
|
}, |
|
{ |
|
"epoch": 38.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.09621511399745941, |
|
"eval_runtime": 4.2076, |
|
"eval_samples_per_second": 15.211, |
|
"eval_steps_per_second": 0.475, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 39.89, |
|
"learning_rate": 1.8518518518518518e-05, |
|
"loss": 0.3095, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 39.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.09031268954277039, |
|
"eval_runtime": 4.5982, |
|
"eval_samples_per_second": 13.919, |
|
"eval_steps_per_second": 0.435, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 40.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.08859497308731079, |
|
"eval_runtime": 4.1937, |
|
"eval_samples_per_second": 15.261, |
|
"eval_steps_per_second": 0.477, |
|
"step": 164 |
|
}, |
|
{ |
|
"epoch": 41.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.10331027209758759, |
|
"eval_runtime": 4.5829, |
|
"eval_samples_per_second": 13.965, |
|
"eval_steps_per_second": 0.436, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 42.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.11172451823949814, |
|
"eval_runtime": 4.2291, |
|
"eval_samples_per_second": 15.133, |
|
"eval_steps_per_second": 0.473, |
|
"step": 172 |
|
}, |
|
{ |
|
"epoch": 43.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.11921519041061401, |
|
"eval_runtime": 4.595, |
|
"eval_samples_per_second": 13.928, |
|
"eval_steps_per_second": 0.435, |
|
"step": 176 |
|
}, |
|
{ |
|
"epoch": 44.89, |
|
"learning_rate": 1.388888888888889e-05, |
|
"loss": 0.3056, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 44.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.09840899705886841, |
|
"eval_runtime": 4.2775, |
|
"eval_samples_per_second": 14.962, |
|
"eval_steps_per_second": 0.468, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 45.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.08203314244747162, |
|
"eval_runtime": 4.5543, |
|
"eval_samples_per_second": 14.053, |
|
"eval_steps_per_second": 0.439, |
|
"step": 184 |
|
}, |
|
{ |
|
"epoch": 46.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.08574767410755157, |
|
"eval_runtime": 4.1553, |
|
"eval_samples_per_second": 15.402, |
|
"eval_steps_per_second": 0.481, |
|
"step": 188 |
|
}, |
|
{ |
|
"epoch": 47.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.10580457001924515, |
|
"eval_runtime": 4.6204, |
|
"eval_samples_per_second": 13.852, |
|
"eval_steps_per_second": 0.433, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 48.89, |
|
"eval_accuracy": 0.9375, |
|
"eval_loss": 0.11630271375179291, |
|
"eval_runtime": 4.1519, |
|
"eval_samples_per_second": 15.415, |
|
"eval_steps_per_second": 0.482, |
|
"step": 196 |
|
}, |
|
{ |
|
"epoch": 49.89, |
|
"learning_rate": 9.259259259259259e-06, |
|
"loss": 0.255, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 49.89, |
|
"eval_accuracy": 0.953125, |
|
"eval_loss": 0.11214150488376617, |
|
"eval_runtime": 4.4888, |
|
"eval_samples_per_second": 14.258, |
|
"eval_steps_per_second": 0.446, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 50.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.10038581490516663, |
|
"eval_runtime": 4.1624, |
|
"eval_samples_per_second": 15.376, |
|
"eval_steps_per_second": 0.48, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 51.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.09537401050329208, |
|
"eval_runtime": 4.5154, |
|
"eval_samples_per_second": 14.174, |
|
"eval_steps_per_second": 0.443, |
|
"step": 208 |
|
}, |
|
{ |
|
"epoch": 52.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.0925481989979744, |
|
"eval_runtime": 4.141, |
|
"eval_samples_per_second": 15.455, |
|
"eval_steps_per_second": 0.483, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 53.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.08920943737030029, |
|
"eval_runtime": 4.5736, |
|
"eval_samples_per_second": 13.993, |
|
"eval_steps_per_second": 0.437, |
|
"step": 216 |
|
}, |
|
{ |
|
"epoch": 54.89, |
|
"learning_rate": 4.6296296296296296e-06, |
|
"loss": 0.2494, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 54.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.08926128596067429, |
|
"eval_runtime": 4.0979, |
|
"eval_samples_per_second": 15.618, |
|
"eval_steps_per_second": 0.488, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 55.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.0900685042142868, |
|
"eval_runtime": 4.5713, |
|
"eval_samples_per_second": 14.001, |
|
"eval_steps_per_second": 0.438, |
|
"step": 224 |
|
}, |
|
{ |
|
"epoch": 56.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.08957040309906006, |
|
"eval_runtime": 4.2031, |
|
"eval_samples_per_second": 15.227, |
|
"eval_steps_per_second": 0.476, |
|
"step": 228 |
|
}, |
|
{ |
|
"epoch": 57.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.09029233455657959, |
|
"eval_runtime": 4.5507, |
|
"eval_samples_per_second": 14.064, |
|
"eval_steps_per_second": 0.439, |
|
"step": 232 |
|
}, |
|
{ |
|
"epoch": 58.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.09133943915367126, |
|
"eval_runtime": 4.5211, |
|
"eval_samples_per_second": 14.156, |
|
"eval_steps_per_second": 0.442, |
|
"step": 236 |
|
}, |
|
{ |
|
"epoch": 59.89, |
|
"learning_rate": 0.0, |
|
"loss": 0.2588, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 59.89, |
|
"eval_accuracy": 0.96875, |
|
"eval_loss": 0.09184324741363525, |
|
"eval_runtime": 4.5891, |
|
"eval_samples_per_second": 13.946, |
|
"eval_steps_per_second": 0.436, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 59.89, |
|
"step": 240, |
|
"total_flos": 8.516851567051162e+17, |
|
"train_loss": 0.5424989521503448, |
|
"train_runtime": 4233.7913, |
|
"train_samples_per_second": 8.106, |
|
"train_steps_per_second": 0.057 |
|
} |
|
], |
|
"max_steps": 240, |
|
"num_train_epochs": 60, |
|
"total_flos": 8.516851567051162e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|