| { | |
| "best_metric": 0.6310679611650486, | |
| "best_model_checkpoint": "videomae-large-finetuned-right-hand-conflab-v3/checkpoint-531", | |
| "epoch": 10.034188034188034, | |
| "eval_steps": 500, | |
| "global_step": 618, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01221001221001221, | |
| "grad_norm": 10.883779525756836, | |
| "learning_rate": 6.0975609756097564e-06, | |
| "loss": 2.1132, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02442002442002442, | |
| "grad_norm": 9.386421203613281, | |
| "learning_rate": 1.2195121951219513e-05, | |
| "loss": 2.0109, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03663003663003663, | |
| "grad_norm": 9.540677070617676, | |
| "learning_rate": 1.8292682926829268e-05, | |
| "loss": 1.9597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04884004884004884, | |
| "grad_norm": 8.591822624206543, | |
| "learning_rate": 2.4390243902439026e-05, | |
| "loss": 1.9359, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06105006105006105, | |
| "grad_norm": 8.493247985839844, | |
| "learning_rate": 3.048780487804878e-05, | |
| "loss": 1.9038, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07203907203907203, | |
| "eval_accuracy": 0.24757281553398058, | |
| "eval_loss": 2.092643976211548, | |
| "eval_runtime": 20.1931, | |
| "eval_samples_per_second": 10.201, | |
| "eval_steps_per_second": 0.644, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.0012210012210012, | |
| "grad_norm": 9.048627853393555, | |
| "learning_rate": 3.6585365853658535e-05, | |
| "loss": 2.0497, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0134310134310134, | |
| "grad_norm": 5.44881010055542, | |
| "learning_rate": 4.26829268292683e-05, | |
| "loss": 2.0479, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 6.384305477142334, | |
| "learning_rate": 4.878048780487805e-05, | |
| "loss": 2.09, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.037851037851038, | |
| "grad_norm": 4.374388694763184, | |
| "learning_rate": 4.94572591587517e-05, | |
| "loss": 2.0209, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.05006105006105, | |
| "grad_norm": 4.627490043640137, | |
| "learning_rate": 4.877883310719132e-05, | |
| "loss": 2.0525, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0622710622710623, | |
| "grad_norm": 5.586881160736084, | |
| "learning_rate": 4.810040705563094e-05, | |
| "loss": 1.8963, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.072039072039072, | |
| "eval_accuracy": 0.24271844660194175, | |
| "eval_loss": 1.9697831869125366, | |
| "eval_runtime": 21.1947, | |
| "eval_samples_per_second": 9.719, | |
| "eval_steps_per_second": 0.613, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.0024420024420024, | |
| "grad_norm": 5.62977409362793, | |
| "learning_rate": 4.742198100407056e-05, | |
| "loss": 1.9983, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0146520146520146, | |
| "grad_norm": 4.484747886657715, | |
| "learning_rate": 4.674355495251018e-05, | |
| "loss": 1.9586, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0268620268620268, | |
| "grad_norm": 4.371191501617432, | |
| "learning_rate": 4.60651289009498e-05, | |
| "loss": 1.8729, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.039072039072039, | |
| "grad_norm": 4.68417501449585, | |
| "learning_rate": 4.5386702849389416e-05, | |
| "loss": 2.0021, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 12.167759895324707, | |
| "learning_rate": 4.470827679782904e-05, | |
| "loss": 1.7877, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0634920634920633, | |
| "grad_norm": 3.787353515625, | |
| "learning_rate": 4.402985074626866e-05, | |
| "loss": 1.9154, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.0720390720390722, | |
| "eval_accuracy": 0.36893203883495146, | |
| "eval_loss": 1.7126853466033936, | |
| "eval_runtime": 18.7207, | |
| "eval_samples_per_second": 11.004, | |
| "eval_steps_per_second": 0.694, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 3.0036630036630036, | |
| "grad_norm": 5.718711853027344, | |
| "learning_rate": 4.335142469470828e-05, | |
| "loss": 1.7051, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.015873015873016, | |
| "grad_norm": 6.827328681945801, | |
| "learning_rate": 4.26729986431479e-05, | |
| "loss": 1.7233, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.028083028083028, | |
| "grad_norm": 6.945235252380371, | |
| "learning_rate": 4.199457259158752e-05, | |
| "loss": 1.5634, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.04029304029304, | |
| "grad_norm": 7.2410197257995605, | |
| "learning_rate": 4.131614654002714e-05, | |
| "loss": 1.5571, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0525030525030523, | |
| "grad_norm": 5.356701374053955, | |
| "learning_rate": 4.063772048846676e-05, | |
| "loss": 1.6352, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.064713064713065, | |
| "grad_norm": 6.82385778427124, | |
| "learning_rate": 3.995929443690638e-05, | |
| "loss": 1.4173, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.0720390720390722, | |
| "eval_accuracy": 0.5242718446601942, | |
| "eval_loss": 1.4571937322616577, | |
| "eval_runtime": 25.9349, | |
| "eval_samples_per_second": 7.943, | |
| "eval_steps_per_second": 0.501, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 4.004884004884005, | |
| "grad_norm": 5.349239349365234, | |
| "learning_rate": 3.9280868385345995e-05, | |
| "loss": 1.5368, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.017094017094017, | |
| "grad_norm": 7.013088703155518, | |
| "learning_rate": 3.860244233378562e-05, | |
| "loss": 1.3767, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.029304029304029, | |
| "grad_norm": 8.280290603637695, | |
| "learning_rate": 3.792401628222524e-05, | |
| "loss": 1.4361, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.041514041514041, | |
| "grad_norm": 8.19866943359375, | |
| "learning_rate": 3.724559023066486e-05, | |
| "loss": 1.193, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.0537240537240535, | |
| "grad_norm": 7.372025012969971, | |
| "learning_rate": 3.656716417910448e-05, | |
| "loss": 1.3667, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.065934065934066, | |
| "grad_norm": 5.639531135559082, | |
| "learning_rate": 3.58887381275441e-05, | |
| "loss": 1.3246, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.072039072039072, | |
| "eval_accuracy": 0.5679611650485437, | |
| "eval_loss": 1.223657488822937, | |
| "eval_runtime": 20.7954, | |
| "eval_samples_per_second": 9.906, | |
| "eval_steps_per_second": 0.625, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 5.006105006105006, | |
| "grad_norm": 7.878034591674805, | |
| "learning_rate": 3.521031207598372e-05, | |
| "loss": 1.1881, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.018315018315018, | |
| "grad_norm": 7.679462909698486, | |
| "learning_rate": 3.453188602442334e-05, | |
| "loss": 1.1117, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 5.03052503052503, | |
| "grad_norm": 10.07403564453125, | |
| "learning_rate": 3.385345997286296e-05, | |
| "loss": 1.0766, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.042735042735043, | |
| "grad_norm": 7.193727970123291, | |
| "learning_rate": 3.3175033921302575e-05, | |
| "loss": 1.006, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.054945054945055, | |
| "grad_norm": 5.925375461578369, | |
| "learning_rate": 3.24966078697422e-05, | |
| "loss": 0.9709, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.067155067155067, | |
| "grad_norm": 13.94832706451416, | |
| "learning_rate": 3.181818181818182e-05, | |
| "loss": 1.077, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.072039072039072, | |
| "eval_accuracy": 0.49514563106796117, | |
| "eval_loss": 1.4524530172348022, | |
| "eval_runtime": 22.2248, | |
| "eval_samples_per_second": 9.269, | |
| "eval_steps_per_second": 0.585, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 6.007326007326007, | |
| "grad_norm": 8.016749382019043, | |
| "learning_rate": 3.113975576662144e-05, | |
| "loss": 0.9269, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.0195360195360195, | |
| "grad_norm": 5.849711894989014, | |
| "learning_rate": 3.046132971506106e-05, | |
| "loss": 0.8371, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.031746031746032, | |
| "grad_norm": 7.203096389770508, | |
| "learning_rate": 2.9782903663500678e-05, | |
| "loss": 0.7639, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.043956043956044, | |
| "grad_norm": 7.49542236328125, | |
| "learning_rate": 2.91044776119403e-05, | |
| "loss": 0.8475, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.056166056166056, | |
| "grad_norm": 9.251474380493164, | |
| "learning_rate": 2.842605156037992e-05, | |
| "loss": 0.8942, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.068376068376068, | |
| "grad_norm": 8.035192489624023, | |
| "learning_rate": 2.7747625508819542e-05, | |
| "loss": 0.923, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.072039072039072, | |
| "eval_accuracy": 0.587378640776699, | |
| "eval_loss": 1.3191975355148315, | |
| "eval_runtime": 21.2599, | |
| "eval_samples_per_second": 9.69, | |
| "eval_steps_per_second": 0.611, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 7.0085470085470085, | |
| "grad_norm": 9.951005935668945, | |
| "learning_rate": 2.7069199457259158e-05, | |
| "loss": 0.6643, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.020757020757021, | |
| "grad_norm": 10.067875862121582, | |
| "learning_rate": 2.639077340569878e-05, | |
| "loss": 0.6866, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 7.032967032967033, | |
| "grad_norm": 11.081637382507324, | |
| "learning_rate": 2.57123473541384e-05, | |
| "loss": 0.5887, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.045177045177045, | |
| "grad_norm": 7.662527084350586, | |
| "learning_rate": 2.5033921302578023e-05, | |
| "loss": 0.6175, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.057387057387057, | |
| "grad_norm": 6.395303726196289, | |
| "learning_rate": 2.4355495251017642e-05, | |
| "loss": 0.6575, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.069597069597069, | |
| "grad_norm": 12.816076278686523, | |
| "learning_rate": 2.367706919945726e-05, | |
| "loss": 0.651, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.072039072039072, | |
| "eval_accuracy": 0.5728155339805825, | |
| "eval_loss": 1.3817497491836548, | |
| "eval_runtime": 22.418, | |
| "eval_samples_per_second": 9.189, | |
| "eval_steps_per_second": 0.58, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 8.00976800976801, | |
| "grad_norm": 6.377563953399658, | |
| "learning_rate": 2.299864314789688e-05, | |
| "loss": 0.4579, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.021978021978022, | |
| "grad_norm": 9.152300834655762, | |
| "learning_rate": 2.2320217096336503e-05, | |
| "loss": 0.4142, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.034188034188034, | |
| "grad_norm": 6.605992317199707, | |
| "learning_rate": 2.164179104477612e-05, | |
| "loss": 0.4407, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.046398046398046, | |
| "grad_norm": 14.947940826416016, | |
| "learning_rate": 2.0963364993215738e-05, | |
| "loss": 0.3638, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.058608058608058, | |
| "grad_norm": 9.7440824508667, | |
| "learning_rate": 2.028493894165536e-05, | |
| "loss": 0.5602, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.07081807081807, | |
| "grad_norm": 8.176590919494629, | |
| "learning_rate": 1.960651289009498e-05, | |
| "loss": 0.5092, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.072039072039072, | |
| "eval_accuracy": 0.6310679611650486, | |
| "eval_loss": 1.3680421113967896, | |
| "eval_runtime": 18.341, | |
| "eval_samples_per_second": 11.232, | |
| "eval_steps_per_second": 0.709, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 9.010989010989011, | |
| "grad_norm": 6.507408142089844, | |
| "learning_rate": 1.89280868385346e-05, | |
| "loss": 0.3515, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.023199023199023, | |
| "grad_norm": 10.037909507751465, | |
| "learning_rate": 1.824966078697422e-05, | |
| "loss": 0.38, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 9.035409035409035, | |
| "grad_norm": 8.945121765136719, | |
| "learning_rate": 1.757123473541384e-05, | |
| "loss": 0.2686, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.047619047619047, | |
| "grad_norm": 7.725048542022705, | |
| "learning_rate": 1.689280868385346e-05, | |
| "loss": 0.318, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.05982905982906, | |
| "grad_norm": 8.256610870361328, | |
| "learning_rate": 1.6214382632293083e-05, | |
| "loss": 0.3725, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.072039072039072, | |
| "grad_norm": 11.454293251037598, | |
| "learning_rate": 1.55359565807327e-05, | |
| "loss": 0.2484, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.072039072039072, | |
| "eval_accuracy": 0.6262135922330098, | |
| "eval_loss": 1.4326366186141968, | |
| "eval_runtime": 19.1344, | |
| "eval_samples_per_second": 10.766, | |
| "eval_steps_per_second": 0.679, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 10.012210012210012, | |
| "grad_norm": 16.326658248901367, | |
| "learning_rate": 1.485753052917232e-05, | |
| "loss": 0.2977, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 10.024420024420024, | |
| "grad_norm": 6.485968112945557, | |
| "learning_rate": 1.417910447761194e-05, | |
| "loss": 0.2218, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 10.034188034188034, | |
| "eval_accuracy": 0.5804878048780487, | |
| "eval_loss": 1.7306667566299438, | |
| "eval_runtime": 28.969, | |
| "eval_samples_per_second": 7.077, | |
| "eval_steps_per_second": 0.449, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 10.034188034188034, | |
| "eval_accuracy": 0.5804878048780487, | |
| "eval_loss": 1.7345412969589233, | |
| "eval_runtime": 19.4619, | |
| "eval_samples_per_second": 10.533, | |
| "eval_steps_per_second": 0.668, | |
| "step": 618 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 819, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.276946192165241e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |