| { |
| "best_metric": 0.34371807967313583, |
| "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/ViViT_wlasl_2000_20ep_coR/checkpoint-35720", |
| "epoch": 19.049867021276597, |
| "eval_steps": 500, |
| "global_step": 35720, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "grad_norm": 24.059249877929688, |
| "learning_rate": 2.4958006718924974e-05, |
| "loss": 30.7198, |
| "step": 1786 |
| }, |
| { |
| "epoch": 0.05, |
| "eval_accuracy": 0.0022982635342185904, |
| "eval_loss": 7.576542854309082, |
| "eval_runtime": 219.084, |
| "eval_samples_per_second": 17.874, |
| "eval_steps_per_second": 8.937, |
| "step": 1786 |
| }, |
| { |
| "epoch": 1.0499930011198209, |
| "grad_norm": 40.50696563720703, |
| "learning_rate": 4.994400895856663e-05, |
| "loss": 29.0292, |
| "step": 3572 |
| }, |
| { |
| "epoch": 1.0499930011198209, |
| "eval_accuracy": 0.02553626149131767, |
| "eval_loss": 6.733867645263672, |
| "eval_runtime": 215.9108, |
| "eval_samples_per_second": 18.137, |
| "eval_steps_per_second": 9.069, |
| "step": 3572 |
| }, |
| { |
| "epoch": 2.0499860022396414, |
| "grad_norm": 45.38137435913086, |
| "learning_rate": 4.722999875575464e-05, |
| "loss": 24.0941, |
| "step": 5358 |
| }, |
| { |
| "epoch": 2.0499860022396414, |
| "eval_accuracy": 0.0888661899897855, |
| "eval_loss": 5.7015604972839355, |
| "eval_runtime": 222.6277, |
| "eval_samples_per_second": 17.59, |
| "eval_steps_per_second": 8.795, |
| "step": 5358 |
| }, |
| { |
| "epoch": 3.0500069988801792, |
| "grad_norm": 51.2833366394043, |
| "learning_rate": 4.445222097797686e-05, |
| "loss": 18.973, |
| "step": 7145 |
| }, |
| { |
| "epoch": 3.0500069988801792, |
| "eval_accuracy": 0.16036772216547499, |
| "eval_loss": 4.895291328430176, |
| "eval_runtime": 219.6583, |
| "eval_samples_per_second": 17.828, |
| "eval_steps_per_second": 8.914, |
| "step": 7145 |
| }, |
| { |
| "epoch": 4.05, |
| "grad_norm": 52.295650482177734, |
| "learning_rate": 4.167599850690556e-05, |
| "loss": 14.3207, |
| "step": 8931 |
| }, |
| { |
| "epoch": 4.05, |
| "eval_accuracy": 0.21884576098059244, |
| "eval_loss": 4.277897357940674, |
| "eval_runtime": 218.8078, |
| "eval_samples_per_second": 17.897, |
| "eval_steps_per_second": 8.948, |
| "step": 8931 |
| }, |
| { |
| "epoch": 5.04999300111982, |
| "grad_norm": 50.395076751708984, |
| "learning_rate": 3.889977603583427e-05, |
| "loss": 10.2288, |
| "step": 10717 |
| }, |
| { |
| "epoch": 5.04999300111982, |
| "eval_accuracy": 0.2561287027579162, |
| "eval_loss": 3.8242266178131104, |
| "eval_runtime": 225.204, |
| "eval_samples_per_second": 17.389, |
| "eval_steps_per_second": 8.694, |
| "step": 10717 |
| }, |
| { |
| "epoch": 6.049986002239642, |
| "grad_norm": 55.203548431396484, |
| "learning_rate": 3.612355356476298e-05, |
| "loss": 6.8987, |
| "step": 12503 |
| }, |
| { |
| "epoch": 6.049986002239642, |
| "eval_accuracy": 0.29902962206332995, |
| "eval_loss": 3.4815824031829834, |
| "eval_runtime": 220.8825, |
| "eval_samples_per_second": 17.729, |
| "eval_steps_per_second": 8.864, |
| "step": 12503 |
| }, |
| { |
| "epoch": 7.050006998880179, |
| "grad_norm": 55.21098709106445, |
| "learning_rate": 3.3345775786985196e-05, |
| "loss": 4.4195, |
| "step": 14290 |
| }, |
| { |
| "epoch": 7.050006998880179, |
| "eval_accuracy": 0.3105209397344229, |
| "eval_loss": 3.3353631496429443, |
| "eval_runtime": 223.744, |
| "eval_samples_per_second": 17.502, |
| "eval_steps_per_second": 8.751, |
| "step": 14290 |
| }, |
| { |
| "epoch": 8.05, |
| "grad_norm": 32.616092681884766, |
| "learning_rate": 3.0567998009207415e-05, |
| "loss": 2.8005, |
| "step": 16076 |
| }, |
| { |
| "epoch": 8.05, |
| "eval_accuracy": 0.3212461695607763, |
| "eval_loss": 3.2289328575134277, |
| "eval_runtime": 219.0256, |
| "eval_samples_per_second": 17.879, |
| "eval_steps_per_second": 8.94, |
| "step": 16076 |
| }, |
| { |
| "epoch": 9.049993001119821, |
| "grad_norm": 13.484119415283203, |
| "learning_rate": 2.7791775538136124e-05, |
| "loss": 1.8191, |
| "step": 17862 |
| }, |
| { |
| "epoch": 9.049993001119821, |
| "eval_accuracy": 0.31996935648621044, |
| "eval_loss": 3.1794984340667725, |
| "eval_runtime": 220.8087, |
| "eval_samples_per_second": 17.735, |
| "eval_steps_per_second": 8.867, |
| "step": 17862 |
| }, |
| { |
| "epoch": 10.049986002239642, |
| "grad_norm": 42.50637435913086, |
| "learning_rate": 2.501555306706483e-05, |
| "loss": 1.2778, |
| "step": 19648 |
| }, |
| { |
| "epoch": 10.049986002239642, |
| "eval_accuracy": 0.32916241062308477, |
| "eval_loss": 3.1636714935302734, |
| "eval_runtime": 221.9506, |
| "eval_samples_per_second": 17.644, |
| "eval_steps_per_second": 8.822, |
| "step": 19648 |
| }, |
| { |
| "epoch": 11.050006998880178, |
| "grad_norm": 37.23781967163086, |
| "learning_rate": 2.2237775289287048e-05, |
| "loss": 1.0009, |
| "step": 21435 |
| }, |
| { |
| "epoch": 11.050006998880178, |
| "eval_accuracy": 0.3299284984678243, |
| "eval_loss": 3.1523447036743164, |
| "eval_runtime": 218.4658, |
| "eval_samples_per_second": 17.925, |
| "eval_steps_per_second": 8.963, |
| "step": 21435 |
| }, |
| { |
| "epoch": 12.05, |
| "grad_norm": 40.751251220703125, |
| "learning_rate": 1.9461552818215754e-05, |
| "loss": 0.8082, |
| "step": 23221 |
| }, |
| { |
| "epoch": 12.05, |
| "eval_accuracy": 0.32916241062308477, |
| "eval_loss": 3.1507740020751953, |
| "eval_runtime": 224.3639, |
| "eval_samples_per_second": 17.454, |
| "eval_steps_per_second": 8.727, |
| "step": 23221 |
| }, |
| { |
| "epoch": 13.049993001119821, |
| "grad_norm": 4.265609264373779, |
| "learning_rate": 1.6685330347144456e-05, |
| "loss": 0.7047, |
| "step": 25007 |
| }, |
| { |
| "epoch": 13.049993001119821, |
| "eval_accuracy": 0.3276302349336057, |
| "eval_loss": 3.1626386642456055, |
| "eval_runtime": 219.2788, |
| "eval_samples_per_second": 17.859, |
| "eval_steps_per_second": 8.929, |
| "step": 25007 |
| }, |
| { |
| "epoch": 14.049986002239642, |
| "grad_norm": 3.2967989444732666, |
| "learning_rate": 1.3909107876073163e-05, |
| "loss": 0.6152, |
| "step": 26793 |
| }, |
| { |
| "epoch": 14.049986002239642, |
| "eval_accuracy": 0.33273748723186924, |
| "eval_loss": 3.1711015701293945, |
| "eval_runtime": 226.0547, |
| "eval_samples_per_second": 17.323, |
| "eval_steps_per_second": 8.662, |
| "step": 26793 |
| }, |
| { |
| "epoch": 15.050006998880178, |
| "grad_norm": 19.58565902709961, |
| "learning_rate": 1.1131330098295383e-05, |
| "loss": 0.545, |
| "step": 28580 |
| }, |
| { |
| "epoch": 15.050006998880178, |
| "eval_accuracy": 0.33937691521961183, |
| "eval_loss": 3.2040486335754395, |
| "eval_runtime": 223.5485, |
| "eval_samples_per_second": 17.517, |
| "eval_steps_per_second": 8.759, |
| "step": 28580 |
| }, |
| { |
| "epoch": 16.05, |
| "grad_norm": 0.6755233407020569, |
| "learning_rate": 8.353552320517606e-06, |
| "loss": 0.4952, |
| "step": 30366 |
| }, |
| { |
| "epoch": 16.05, |
| "eval_accuracy": 0.34244126659857, |
| "eval_loss": 3.193638563156128, |
| "eval_runtime": 223.395, |
| "eval_samples_per_second": 17.529, |
| "eval_steps_per_second": 8.765, |
| "step": 30366 |
| }, |
| { |
| "epoch": 17.04999300111982, |
| "grad_norm": 0.49139681458473206, |
| "learning_rate": 5.577329849446311e-06, |
| "loss": 0.4463, |
| "step": 32152 |
| }, |
| { |
| "epoch": 17.04999300111982, |
| "eval_accuracy": 0.3434627170582227, |
| "eval_loss": 3.2132766246795654, |
| "eval_runtime": 224.3803, |
| "eval_samples_per_second": 17.453, |
| "eval_steps_per_second": 8.726, |
| "step": 32152 |
| }, |
| { |
| "epoch": 18.049986002239642, |
| "grad_norm": 18.495391845703125, |
| "learning_rate": 2.801107378375016e-06, |
| "loss": 0.403, |
| "step": 33938 |
| }, |
| { |
| "epoch": 18.049986002239642, |
| "eval_accuracy": 0.3432073544433095, |
| "eval_loss": 3.223970413208008, |
| "eval_runtime": 223.2828, |
| "eval_samples_per_second": 17.538, |
| "eval_steps_per_second": 8.769, |
| "step": 33938 |
| }, |
| { |
| "epoch": 19.049867021276597, |
| "grad_norm": 35.13886260986328, |
| "learning_rate": 3.110613412965037e-08, |
| "loss": 0.3506, |
| "step": 35720 |
| }, |
| { |
| "epoch": 19.049867021276597, |
| "eval_accuracy": 0.34371807967313583, |
| "eval_loss": 3.2256083488464355, |
| "eval_runtime": 220.3806, |
| "eval_samples_per_second": 17.769, |
| "eval_steps_per_second": 8.885, |
| "step": 35720 |
| }, |
| { |
| "epoch": 19.049867021276597, |
| "step": 35720, |
| "total_flos": 7.447705591753212e+20, |
| "train_loss": 7.498166088347739, |
| "train_runtime": 38616.1542, |
| "train_samples_per_second": 7.4, |
| "train_steps_per_second": 0.925 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 35720, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.447705591753212e+20, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
