| { | |
| "best_metric": 0.5617977528089888, | |
| "best_model_checkpoint": "videomae-base-finetuned-ElderReact-Happiness/checkpoint-308", | |
| "epoch": 4.189473684210526, | |
| "eval_steps": 500, | |
| "global_step": 380, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 4.016882419586182, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.7013, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 3.460171699523926, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.6796, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 4.785501480102539, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.74, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 4.875156879425049, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.7044, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 7.292051792144775, | |
| "learning_rate": 4.824561403508772e-05, | |
| "loss": 0.7057, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 7.376715660095215, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.7756, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 3.814006805419922, | |
| "learning_rate": 4.5321637426900585e-05, | |
| "loss": 0.6723, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_f1": 0.5549845837615622, | |
| "eval_loss": 0.7051836252212524, | |
| "eval_runtime": 1602.3534, | |
| "eval_samples_per_second": 0.497, | |
| "eval_steps_per_second": 0.062, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 3.5856733322143555, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.6769, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "grad_norm": 2.825258255004883, | |
| "learning_rate": 4.239766081871345e-05, | |
| "loss": 0.6709, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 2.5148415565490723, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.727, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "grad_norm": 2.4561989307403564, | |
| "learning_rate": 3.9473684210526316e-05, | |
| "loss": 0.6706, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "grad_norm": 2.8707118034362793, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.7212, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "grad_norm": 1.9631680250167847, | |
| "learning_rate": 3.654970760233918e-05, | |
| "loss": 0.7098, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "grad_norm": 9.788117408752441, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.7359, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 10.18767261505127, | |
| "learning_rate": 3.362573099415205e-05, | |
| "loss": 0.6748, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_f1": 0.006289308176100629, | |
| "eval_loss": 0.6582110524177551, | |
| "eval_runtime": 1572.4124, | |
| "eval_samples_per_second": 0.506, | |
| "eval_steps_per_second": 0.064, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 4.891780853271484, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.6535, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "grad_norm": 5.340829849243164, | |
| "learning_rate": 3.0701754385964913e-05, | |
| "loss": 0.6206, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "grad_norm": 2.49276065826416, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.7199, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "grad_norm": 4.326613903045654, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6836, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.12, | |
| "grad_norm": 3.0456364154815674, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.6351, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.15, | |
| "grad_norm": 3.2249398231506348, | |
| "learning_rate": 2.485380116959064e-05, | |
| "loss": 0.6387, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "grad_norm": 6.565281867980957, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.7079, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 3.1880271434783936, | |
| "learning_rate": 2.1929824561403507e-05, | |
| "loss": 0.7745, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "eval_f1": 0.5589403973509933, | |
| "eval_loss": 0.6776570677757263, | |
| "eval_runtime": 1484.5114, | |
| "eval_samples_per_second": 0.536, | |
| "eval_steps_per_second": 0.067, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "grad_norm": 1.8452378511428833, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.661, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "grad_norm": 3.8639652729034424, | |
| "learning_rate": 1.9005847953216373e-05, | |
| "loss": 0.6743, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.08, | |
| "grad_norm": 1.692387342453003, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.6429, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "grad_norm": 2.1387529373168945, | |
| "learning_rate": 1.608187134502924e-05, | |
| "loss": 0.6625, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "grad_norm": 4.23469352722168, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.7041, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.16, | |
| "grad_norm": 2.7067341804504395, | |
| "learning_rate": 1.3157894736842106e-05, | |
| "loss": 0.6662, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.18, | |
| "grad_norm": 5.802628040313721, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.6286, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "eval_f1": 0.5617977528089888, | |
| "eval_loss": 0.6901108026504517, | |
| "eval_runtime": 1598.6139, | |
| "eval_samples_per_second": 0.498, | |
| "eval_steps_per_second": 0.063, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "grad_norm": 6.488805294036865, | |
| "learning_rate": 1.023391812865497e-05, | |
| "loss": 0.5724, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "grad_norm": 5.795147895812988, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.6883, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "grad_norm": 2.8693175315856934, | |
| "learning_rate": 7.3099415204678366e-06, | |
| "loss": 0.6674, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 2.0438976287841797, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.6649, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.11, | |
| "grad_norm": 2.5664432048797607, | |
| "learning_rate": 4.3859649122807014e-06, | |
| "loss": 0.6188, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.14, | |
| "grad_norm": 6.117301940917969, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.6105, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "grad_norm": 5.357626914978027, | |
| "learning_rate": 1.4619883040935671e-06, | |
| "loss": 0.6511, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "grad_norm": 3.1075475215911865, | |
| "learning_rate": 0.0, | |
| "loss": 0.6018, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.552046783625731, | |
| "eval_loss": 0.6821714043617249, | |
| "eval_runtime": 1518.717, | |
| "eval_samples_per_second": 0.524, | |
| "eval_steps_per_second": 0.066, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "step": 380, | |
| "total_flos": 3.783052093636215e+18, | |
| "train_loss": 0.6766992167422646, | |
| "train_runtime": 18323.6613, | |
| "train_samples_per_second": 0.166, | |
| "train_steps_per_second": 0.021 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.48677248677248675, | |
| "eval_loss": 0.7341307997703552, | |
| "eval_runtime": 1329.5369, | |
| "eval_samples_per_second": 0.564, | |
| "eval_steps_per_second": 0.071, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.19, | |
| "eval_f1": 0.48677248677248675, | |
| "eval_loss": 0.7341306805610657, | |
| "eval_runtime": 1312.4548, | |
| "eval_samples_per_second": 0.571, | |
| "eval_steps_per_second": 0.072, | |
| "step": 380 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 3.783052093636215e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |