| { |
| "best_metric": 0.848531684698609, |
| "best_model_checkpoint": "deit-base-patch16-224-FV-finetuned-memes/checkpoint-400", |
| "epoch": 19.987654320987655, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.49, |
| "learning_rate": 3e-05, |
| "loss": 1.5611, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 6e-05, |
| "loss": 1.2733, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.99, |
| "eval_accuracy": 0.5811437403400309, |
| "eval_f1": 0.5292880795121996, |
| "eval_loss": 1.0893372297286987, |
| "eval_precision": 0.5790375140189687, |
| "eval_recall": 0.5811437403400309, |
| "eval_runtime": 14.3471, |
| "eval_samples_per_second": 90.193, |
| "eval_steps_per_second": 1.464, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 9e-05, |
| "loss": 0.9586, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.00012, |
| "loss": 0.7284, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.99, |
| "eval_accuracy": 0.7210200927357032, |
| "eval_f1": 0.7270557661305002, |
| "eval_loss": 0.7350967526435852, |
| "eval_precision": 0.7642254611707266, |
| "eval_recall": 0.7210200927357032, |
| "eval_runtime": 12.1717, |
| "eval_samples_per_second": 106.312, |
| "eval_steps_per_second": 1.725, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 0.00011666666666666667, |
| "loss": 0.4906, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 0.00011333333333333333, |
| "loss": 0.4267, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.99, |
| "eval_accuracy": 0.7990726429675425, |
| "eval_f1": 0.8033064919218132, |
| "eval_loss": 0.5202070474624634, |
| "eval_precision": 0.8104410130277757, |
| "eval_recall": 0.7990726429675425, |
| "eval_runtime": 11.9509, |
| "eval_samples_per_second": 108.276, |
| "eval_steps_per_second": 1.757, |
| "step": 60 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 0.00011, |
| "loss": 0.2421, |
| "step": 70 |
| }, |
| { |
| "epoch": 3.99, |
| "learning_rate": 0.00010666666666666667, |
| "loss": 0.2181, |
| "step": 80 |
| }, |
| { |
| "epoch": 3.99, |
| "eval_accuracy": 0.8346213292117465, |
| "eval_f1": 0.8333748900624175, |
| "eval_loss": 0.4604855477809906, |
| "eval_precision": 0.8350729859390106, |
| "eval_recall": 0.8346213292117465, |
| "eval_runtime": 12.1854, |
| "eval_samples_per_second": 106.193, |
| "eval_steps_per_second": 1.723, |
| "step": 80 |
| }, |
| { |
| "epoch": 4.49, |
| "learning_rate": 0.00010333333333333334, |
| "loss": 0.1358, |
| "step": 90 |
| }, |
| { |
| "epoch": 4.99, |
| "learning_rate": 0.0001, |
| "loss": 0.1504, |
| "step": 100 |
| }, |
| { |
| "epoch": 4.99, |
| "eval_accuracy": 0.8253477588871716, |
| "eval_f1": 0.8265696468740246, |
| "eval_loss": 0.5281366109848022, |
| "eval_precision": 0.828062631171004, |
| "eval_recall": 0.8253477588871716, |
| "eval_runtime": 12.1945, |
| "eval_samples_per_second": 106.113, |
| "eval_steps_per_second": 1.722, |
| "step": 100 |
| }, |
| { |
| "epoch": 5.49, |
| "learning_rate": 9.666666666666667e-05, |
| "loss": 0.0916, |
| "step": 110 |
| }, |
| { |
| "epoch": 5.99, |
| "learning_rate": 9.333333333333334e-05, |
| "loss": 0.1001, |
| "step": 120 |
| }, |
| { |
| "epoch": 5.99, |
| "eval_accuracy": 0.8369397217928902, |
| "eval_f1": 0.8347021830575708, |
| "eval_loss": 0.49452078342437744, |
| "eval_precision": 0.8335589987471665, |
| "eval_recall": 0.8369397217928902, |
| "eval_runtime": 13.7132, |
| "eval_samples_per_second": 94.362, |
| "eval_steps_per_second": 1.531, |
| "step": 120 |
| }, |
| { |
| "epoch": 6.49, |
| "learning_rate": 9e-05, |
| "loss": 0.0693, |
| "step": 130 |
| }, |
| { |
| "epoch": 6.99, |
| "learning_rate": 8.666666666666667e-05, |
| "loss": 0.0874, |
| "step": 140 |
| }, |
| { |
| "epoch": 6.99, |
| "eval_accuracy": 0.8338485316846986, |
| "eval_f1": 0.8347731418598773, |
| "eval_loss": 0.5901951789855957, |
| "eval_precision": 0.8369841836772862, |
| "eval_recall": 0.8338485316846986, |
| "eval_runtime": 12.1626, |
| "eval_samples_per_second": 106.392, |
| "eval_steps_per_second": 1.727, |
| "step": 140 |
| }, |
| { |
| "epoch": 7.49, |
| "learning_rate": 8.333333333333333e-05, |
| "loss": 0.0698, |
| "step": 150 |
| }, |
| { |
| "epoch": 7.99, |
| "learning_rate": 7.999999999999999e-05, |
| "loss": 0.0634, |
| "step": 160 |
| }, |
| { |
| "epoch": 7.99, |
| "eval_accuracy": 0.8253477588871716, |
| "eval_f1": 0.8234470253240962, |
| "eval_loss": 0.6087659597396851, |
| "eval_precision": 0.8221220381584785, |
| "eval_recall": 0.8253477588871716, |
| "eval_runtime": 12.1235, |
| "eval_samples_per_second": 106.735, |
| "eval_steps_per_second": 1.732, |
| "step": 160 |
| }, |
| { |
| "epoch": 8.49, |
| "learning_rate": 7.666666666666667e-05, |
| "loss": 0.065, |
| "step": 170 |
| }, |
| { |
| "epoch": 8.99, |
| "learning_rate": 7.333333333333334e-05, |
| "loss": 0.0699, |
| "step": 180 |
| }, |
| { |
| "epoch": 8.99, |
| "eval_accuracy": 0.8207109737248841, |
| "eval_f1": 0.8185767382509123, |
| "eval_loss": 0.6210456490516663, |
| "eval_precision": 0.8201740897388502, |
| "eval_recall": 0.8207109737248841, |
| "eval_runtime": 12.2668, |
| "eval_samples_per_second": 105.488, |
| "eval_steps_per_second": 1.712, |
| "step": 180 |
| }, |
| { |
| "epoch": 9.49, |
| "learning_rate": 7.000000000000001e-05, |
| "loss": 0.0548, |
| "step": 190 |
| }, |
| { |
| "epoch": 9.99, |
| "learning_rate": 6.666666666666667e-05, |
| "loss": 0.0661, |
| "step": 200 |
| }, |
| { |
| "epoch": 9.99, |
| "eval_accuracy": 0.8384853168469861, |
| "eval_f1": 0.8392602772109944, |
| "eval_loss": 0.567503809928894, |
| "eval_precision": 0.8416984089400088, |
| "eval_recall": 0.8384853168469861, |
| "eval_runtime": 13.1333, |
| "eval_samples_per_second": 98.528, |
| "eval_steps_per_second": 1.599, |
| "step": 200 |
| }, |
| { |
| "epoch": 10.49, |
| "learning_rate": 6.333333333333333e-05, |
| "loss": 0.0584, |
| "step": 210 |
| }, |
| { |
| "epoch": 10.99, |
| "learning_rate": 6e-05, |
| "loss": 0.0592, |
| "step": 220 |
| }, |
| { |
| "epoch": 10.99, |
| "eval_accuracy": 0.8253477588871716, |
| "eval_f1": 0.8275102000168703, |
| "eval_loss": 0.6549890041351318, |
| "eval_precision": 0.8324336806598226, |
| "eval_recall": 0.8253477588871716, |
| "eval_runtime": 12.4308, |
| "eval_samples_per_second": 104.096, |
| "eval_steps_per_second": 1.689, |
| "step": 220 |
| }, |
| { |
| "epoch": 11.49, |
| "learning_rate": 5.6666666666666664e-05, |
| "loss": 0.0547, |
| "step": 230 |
| }, |
| { |
| "epoch": 11.99, |
| "learning_rate": 5.333333333333333e-05, |
| "loss": 0.0559, |
| "step": 240 |
| }, |
| { |
| "epoch": 11.99, |
| "eval_accuracy": 0.8415765069551777, |
| "eval_f1": 0.8386771501165272, |
| "eval_loss": 0.6400041580200195, |
| "eval_precision": 0.8369803259815121, |
| "eval_recall": 0.8415765069551777, |
| "eval_runtime": 12.0827, |
| "eval_samples_per_second": 107.095, |
| "eval_steps_per_second": 1.738, |
| "step": 240 |
| }, |
| { |
| "epoch": 12.49, |
| "learning_rate": 5e-05, |
| "loss": 0.0544, |
| "step": 250 |
| }, |
| { |
| "epoch": 12.99, |
| "learning_rate": 4.666666666666667e-05, |
| "loss": 0.0501, |
| "step": 260 |
| }, |
| { |
| "epoch": 12.99, |
| "eval_accuracy": 0.839258114374034, |
| "eval_f1": 0.8349827197339503, |
| "eval_loss": 0.6725842952728271, |
| "eval_precision": 0.8352807610136271, |
| "eval_recall": 0.839258114374034, |
| "eval_runtime": 12.235, |
| "eval_samples_per_second": 105.762, |
| "eval_steps_per_second": 1.716, |
| "step": 260 |
| }, |
| { |
| "epoch": 13.49, |
| "learning_rate": 4.3333333333333334e-05, |
| "loss": 0.0504, |
| "step": 270 |
| }, |
| { |
| "epoch": 13.99, |
| "learning_rate": 3.9999999999999996e-05, |
| "loss": 0.0529, |
| "step": 280 |
| }, |
| { |
| "epoch": 13.99, |
| "eval_accuracy": 0.8408037094281299, |
| "eval_f1": 0.8401045386097177, |
| "eval_loss": 0.6284657120704651, |
| "eval_precision": 0.8399002499413157, |
| "eval_recall": 0.8408037094281299, |
| "eval_runtime": 12.1571, |
| "eval_samples_per_second": 106.44, |
| "eval_steps_per_second": 1.727, |
| "step": 280 |
| }, |
| { |
| "epoch": 14.49, |
| "learning_rate": 3.666666666666667e-05, |
| "loss": 0.0483, |
| "step": 290 |
| }, |
| { |
| "epoch": 14.99, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0478, |
| "step": 300 |
| }, |
| { |
| "epoch": 14.99, |
| "eval_accuracy": 0.8400309119010819, |
| "eval_f1": 0.8384325271224449, |
| "eval_loss": 0.6423028707504272, |
| "eval_precision": 0.8380083960258947, |
| "eval_recall": 0.8400309119010819, |
| "eval_runtime": 13.5896, |
| "eval_samples_per_second": 95.22, |
| "eval_steps_per_second": 1.545, |
| "step": 300 |
| }, |
| { |
| "epoch": 15.49, |
| "learning_rate": 3e-05, |
| "loss": 0.0511, |
| "step": 310 |
| }, |
| { |
| "epoch": 15.99, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 0.0458, |
| "step": 320 |
| }, |
| { |
| "epoch": 15.99, |
| "eval_accuracy": 0.8369397217928902, |
| "eval_f1": 0.8347511755501414, |
| "eval_loss": 0.6632058620452881, |
| "eval_precision": 0.8336581851460658, |
| "eval_recall": 0.8369397217928902, |
| "eval_runtime": 12.2903, |
| "eval_samples_per_second": 105.286, |
| "eval_steps_per_second": 1.709, |
| "step": 320 |
| }, |
| { |
| "epoch": 16.49, |
| "learning_rate": 2.3333333333333336e-05, |
| "loss": 0.044, |
| "step": 330 |
| }, |
| { |
| "epoch": 16.99, |
| "learning_rate": 1.9999999999999998e-05, |
| "loss": 0.048, |
| "step": 340 |
| }, |
| { |
| "epoch": 16.99, |
| "eval_accuracy": 0.8423493044822257, |
| "eval_f1": 0.8403953031110398, |
| "eval_loss": 0.6718657612800598, |
| "eval_precision": 0.8400986650043714, |
| "eval_recall": 0.8423493044822257, |
| "eval_runtime": 12.1549, |
| "eval_samples_per_second": 106.459, |
| "eval_steps_per_second": 1.728, |
| "step": 340 |
| }, |
| { |
| "epoch": 17.49, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0531, |
| "step": 350 |
| }, |
| { |
| "epoch": 17.99, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 0.0417, |
| "step": 360 |
| }, |
| { |
| "epoch": 17.99, |
| "eval_accuracy": 0.8423493044822257, |
| "eval_f1": 0.8408137285370694, |
| "eval_loss": 0.6807297468185425, |
| "eval_precision": 0.8414734958978292, |
| "eval_recall": 0.8423493044822257, |
| "eval_runtime": 12.1578, |
| "eval_samples_per_second": 106.434, |
| "eval_steps_per_second": 1.727, |
| "step": 360 |
| }, |
| { |
| "epoch": 18.49, |
| "learning_rate": 9.999999999999999e-06, |
| "loss": 0.0463, |
| "step": 370 |
| }, |
| { |
| "epoch": 18.99, |
| "learning_rate": 6.666666666666667e-06, |
| "loss": 0.0461, |
| "step": 380 |
| }, |
| { |
| "epoch": 18.99, |
| "eval_accuracy": 0.8454404945904173, |
| "eval_f1": 0.8437536089910989, |
| "eval_loss": 0.6732441782951355, |
| "eval_precision": 0.8439655958777214, |
| "eval_recall": 0.8454404945904173, |
| "eval_runtime": 12.2922, |
| "eval_samples_per_second": 105.27, |
| "eval_steps_per_second": 1.708, |
| "step": 380 |
| }, |
| { |
| "epoch": 19.49, |
| "learning_rate": 3.3333333333333333e-06, |
| "loss": 0.0467, |
| "step": 390 |
| }, |
| { |
| "epoch": 19.99, |
| "learning_rate": 0.0, |
| "loss": 0.044, |
| "step": 400 |
| }, |
| { |
| "epoch": 19.99, |
| "eval_accuracy": 0.848531684698609, |
| "eval_f1": 0.8463625265241504, |
| "eval_loss": 0.6769371628761292, |
| "eval_precision": 0.8458069264500935, |
| "eval_recall": 0.848531684698609, |
| "eval_runtime": 13.4679, |
| "eval_samples_per_second": 96.08, |
| "eval_steps_per_second": 1.559, |
| "step": 400 |
| }, |
| { |
| "epoch": 19.99, |
| "step": 400, |
| "total_flos": 8.014902017179374e+18, |
| "train_loss": 0.19803269907832147, |
| "train_runtime": 1524.6859, |
| "train_samples_per_second": 67.87, |
| "train_steps_per_second": 0.262 |
| } |
| ], |
| "max_steps": 400, |
| "num_train_epochs": 20, |
| "total_flos": 8.014902017179374e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
