| { |
| "best_global_step": 148, |
| "best_metric": 0.9142857142857143, |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-148", |
| "epoch": 3.22972972972973, |
| "eval_steps": 500, |
| "global_step": 148, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06756756756756757, |
| "grad_norm": 7.40066385269165, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 2.283, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.13513513513513514, |
| "grad_norm": 7.144842147827148, |
| "learning_rate": 4.81203007518797e-05, |
| "loss": 2.2444, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.20270270270270271, |
| "grad_norm": 6.828388214111328, |
| "learning_rate": 4.43609022556391e-05, |
| "loss": 2.0763, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.25675675675675674, |
| "eval_accuracy": 0.5857142857142857, |
| "eval_loss": 1.6526830196380615, |
| "eval_runtime": 18.1085, |
| "eval_samples_per_second": 3.866, |
| "eval_steps_per_second": 0.497, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.0135135135135136, |
| "grad_norm": 9.339892387390137, |
| "learning_rate": 4.0601503759398494e-05, |
| "loss": 1.8731, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.0810810810810811, |
| "grad_norm": 11.664366722106934, |
| "learning_rate": 3.6842105263157895e-05, |
| "loss": 1.3972, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.1486486486486487, |
| "grad_norm": 16.482961654663086, |
| "learning_rate": 3.3082706766917295e-05, |
| "loss": 1.0329, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.2162162162162162, |
| "grad_norm": 5.483195781707764, |
| "learning_rate": 2.9323308270676693e-05, |
| "loss": 0.6845, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.2567567567567568, |
| "eval_accuracy": 0.8, |
| "eval_loss": 0.6961432695388794, |
| "eval_runtime": 18.1176, |
| "eval_samples_per_second": 3.864, |
| "eval_steps_per_second": 0.497, |
| "step": 76 |
| }, |
| { |
| "epoch": 2.027027027027027, |
| "grad_norm": 6.847842693328857, |
| "learning_rate": 2.556390977443609e-05, |
| "loss": 0.7041, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.0945945945945947, |
| "grad_norm": 4.047189235687256, |
| "learning_rate": 2.1804511278195487e-05, |
| "loss": 0.5721, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.1621621621621623, |
| "grad_norm": 9.763541221618652, |
| "learning_rate": 1.8045112781954888e-05, |
| "loss": 0.5223, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.22972972972973, |
| "grad_norm": 7.095814228057861, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 0.5159, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.2567567567567566, |
| "eval_accuracy": 0.8285714285714286, |
| "eval_loss": 0.45256105065345764, |
| "eval_runtime": 18.9877, |
| "eval_samples_per_second": 3.687, |
| "eval_steps_per_second": 0.474, |
| "step": 114 |
| }, |
| { |
| "epoch": 3.0405405405405403, |
| "grad_norm": 2.604196786880493, |
| "learning_rate": 1.0526315789473684e-05, |
| "loss": 0.3598, |
| "step": 120 |
| }, |
| { |
| "epoch": 3.108108108108108, |
| "grad_norm": 2.877445936203003, |
| "learning_rate": 6.766917293233083e-06, |
| "loss": 0.2583, |
| "step": 130 |
| }, |
| { |
| "epoch": 3.175675675675676, |
| "grad_norm": 7.803931713104248, |
| "learning_rate": 3.007518796992481e-06, |
| "loss": 0.2407, |
| "step": 140 |
| }, |
| { |
| "epoch": 3.22972972972973, |
| "eval_accuracy": 0.9142857142857143, |
| "eval_loss": 0.37618494033813477, |
| "eval_runtime": 16.478, |
| "eval_samples_per_second": 4.248, |
| "eval_steps_per_second": 0.546, |
| "step": 148 |
| }, |
| { |
| "epoch": 3.22972972972973, |
| "step": 148, |
| "total_flos": 1.460491890402263e+18, |
| "train_loss": 1.0104753785842173, |
| "train_runtime": 782.0727, |
| "train_samples_per_second": 1.514, |
| "train_steps_per_second": 0.189 |
| }, |
| { |
| "epoch": 3.22972972972973, |
| "eval_accuracy": 0.8193548387096774, |
| "eval_loss": 0.4802559018135071, |
| "eval_runtime": 37.4049, |
| "eval_samples_per_second": 4.144, |
| "eval_steps_per_second": 0.535, |
| "step": 148 |
| }, |
| { |
| "epoch": 3.22972972972973, |
| "eval_accuracy": 0.8193548387096774, |
| "eval_loss": 0.4802559018135071, |
| "eval_runtime": 37.3836, |
| "eval_samples_per_second": 4.146, |
| "eval_steps_per_second": 0.535, |
| "step": 148 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 148, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.460491890402263e+18, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
