| { | |
| "best_metric": 1.0, | |
| "best_model_checkpoint": "st_vit_trained-8epoch-ucf101-subset/checkpoint-76", | |
| "epoch": 7.101351351351352, | |
| "eval_steps": 500, | |
| "global_step": 296, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 2.1556, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.6436, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6314, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_accuracy": 0.9333333333333333, | |
| "eval_loss": 0.12640628218650818, | |
| "eval_runtime": 107.3422, | |
| "eval_samples_per_second": 0.279, | |
| "eval_steps_per_second": 0.037, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 4.81203007518797e-05, | |
| "loss": 0.2368, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 4.62406015037594e-05, | |
| "loss": 0.2077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 4.43609022556391e-05, | |
| "loss": 0.4179, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 4.24812030075188e-05, | |
| "loss": 0.3547, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.007708676625043154, | |
| "eval_runtime": 109.7958, | |
| "eval_samples_per_second": 0.273, | |
| "eval_steps_per_second": 0.036, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 4.0601503759398494e-05, | |
| "loss": 0.2593, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 3.87218045112782e-05, | |
| "loss": 0.1361, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.6842105263157895e-05, | |
| "loss": 0.079, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 3.49624060150376e-05, | |
| "loss": 0.0189, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.13, | |
| "eval_accuracy": 0.9333333333333333, | |
| "eval_loss": 0.510276734828949, | |
| "eval_runtime": 110.2619, | |
| "eval_samples_per_second": 0.272, | |
| "eval_steps_per_second": 0.036, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.3082706766917295e-05, | |
| "loss": 0.0021, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.05, | |
| "learning_rate": 3.120300751879699e-05, | |
| "loss": 0.0596, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.09, | |
| "learning_rate": 2.9323308270676693e-05, | |
| "loss": 0.0554, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "learning_rate": 2.7443609022556393e-05, | |
| "loss": 0.0611, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "eval_accuracy": 0.9333333333333333, | |
| "eval_loss": 0.15075534582138062, | |
| "eval_runtime": 110.9545, | |
| "eval_samples_per_second": 0.27, | |
| "eval_steps_per_second": 0.036, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 2.556390977443609e-05, | |
| "loss": 0.219, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.06, | |
| "learning_rate": 2.368421052631579e-05, | |
| "loss": 0.1464, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.09, | |
| "learning_rate": 2.1804511278195487e-05, | |
| "loss": 0.0131, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "learning_rate": 1.9924812030075188e-05, | |
| "loss": 0.0027, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "eval_accuracy": 1.0, | |
| "eval_loss": 0.0017944329883903265, | |
| "eval_runtime": 111.261, | |
| "eval_samples_per_second": 0.27, | |
| "eval_steps_per_second": 0.036, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 1.8045112781954888e-05, | |
| "loss": 0.0291, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 1.6165413533834585e-05, | |
| "loss": 0.0183, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 0.0812, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.13, | |
| "eval_accuracy": 0.9333333333333333, | |
| "eval_loss": 0.0942629873752594, | |
| "eval_runtime": 110.723, | |
| "eval_samples_per_second": 0.271, | |
| "eval_steps_per_second": 0.036, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "learning_rate": 1.2406015037593984e-05, | |
| "loss": 0.0072, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 1.0526315789473684e-05, | |
| "loss": 0.1462, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 8.646616541353383e-06, | |
| "loss": 0.1258, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.11, | |
| "learning_rate": 6.766917293233083e-06, | |
| "loss": 0.0005, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.13, | |
| "eval_accuracy": 0.9666666666666667, | |
| "eval_loss": 0.06345120072364807, | |
| "eval_runtime": 111.1102, | |
| "eval_samples_per_second": 0.27, | |
| "eval_steps_per_second": 0.036, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.887218045112782e-06, | |
| "loss": 0.0017, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.05, | |
| "learning_rate": 3.007518796992481e-06, | |
| "loss": 0.0004, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.08, | |
| "learning_rate": 1.1278195488721805e-06, | |
| "loss": 0.3035, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.9666666666666667, | |
| "eval_loss": 0.05302112549543381, | |
| "eval_runtime": 111.2744, | |
| "eval_samples_per_second": 0.27, | |
| "eval_steps_per_second": 0.036, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "step": 296, | |
| "total_flos": 0.0, | |
| "train_loss": 0.21684430856918413, | |
| "train_runtime": 10490.4185, | |
| "train_samples_per_second": 0.226, | |
| "train_steps_per_second": 0.028 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.9733333333333334, | |
| "eval_loss": 0.06482689082622528, | |
| "eval_runtime": 274.5585, | |
| "eval_samples_per_second": 0.273, | |
| "eval_steps_per_second": 0.036, | |
| "step": 296 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 296, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |