| { | |
| "best_metric": 0.9090909090909091, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset-nimeshbuddhika/checkpoint-1350", | |
| "epoch": 9.1, | |
| "global_step": 1500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 2.4285, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.20320855614973263, | |
| "eval_loss": 2.118558406829834, | |
| "eval_runtime": 43.6317, | |
| "eval_samples_per_second": 4.286, | |
| "eval_steps_per_second": 2.154, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 4.814814814814815e-05, | |
| "loss": 1.6775, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.9154, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_accuracy": 0.6042780748663101, | |
| "eval_loss": 1.1913264989852905, | |
| "eval_runtime": 43.6901, | |
| "eval_samples_per_second": 4.28, | |
| "eval_steps_per_second": 2.152, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 4.074074074074074e-05, | |
| "loss": 0.4498, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.1, | |
| "eval_accuracy": 0.8823529411764706, | |
| "eval_loss": 0.37695419788360596, | |
| "eval_runtime": 43.5293, | |
| "eval_samples_per_second": 4.296, | |
| "eval_steps_per_second": 2.159, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.3165, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.3012, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.1, | |
| "eval_accuracy": 0.8663101604278075, | |
| "eval_loss": 0.39042213559150696, | |
| "eval_runtime": 33.9376, | |
| "eval_samples_per_second": 5.51, | |
| "eval_steps_per_second": 2.77, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.07, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.1458, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "eval_accuracy": 0.7967914438502673, | |
| "eval_loss": 0.8938174843788147, | |
| "eval_runtime": 39.5211, | |
| "eval_samples_per_second": 4.732, | |
| "eval_steps_per_second": 2.378, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.03, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 0.0895, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0464, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.1, | |
| "eval_accuracy": 0.8556149732620321, | |
| "eval_loss": 0.6180762052536011, | |
| "eval_runtime": 43.0074, | |
| "eval_samples_per_second": 4.348, | |
| "eval_steps_per_second": 2.186, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.07, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0274, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "eval_accuracy": 0.8074866310160428, | |
| "eval_loss": 0.7182068228721619, | |
| "eval_runtime": 42.9074, | |
| "eval_samples_per_second": 4.358, | |
| "eval_steps_per_second": 2.191, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 7.03, | |
| "learning_rate": 1.4814814814814815e-05, | |
| "loss": 0.0189, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0022, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 7.1, | |
| "eval_accuracy": 0.8716577540106952, | |
| "eval_loss": 0.45252320170402527, | |
| "eval_runtime": 43.1934, | |
| "eval_samples_per_second": 4.329, | |
| "eval_steps_per_second": 2.176, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 0.0302, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 8.1, | |
| "eval_accuracy": 0.9090909090909091, | |
| "eval_loss": 0.31720033288002014, | |
| "eval_runtime": 43.0746, | |
| "eval_samples_per_second": 4.341, | |
| "eval_steps_per_second": 2.182, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 0.003, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 0.0, | |
| "loss": 0.0166, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_accuracy": 0.8983957219251337, | |
| "eval_loss": 0.28981590270996094, | |
| "eval_runtime": 43.1833, | |
| "eval_samples_per_second": 4.33, | |
| "eval_steps_per_second": 2.177, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "step": 1500, | |
| "total_flos": 3.738527145787392e+18, | |
| "train_loss": 0.4312617871661981, | |
| "train_runtime": 1888.5613, | |
| "train_samples_per_second": 1.589, | |
| "train_steps_per_second": 0.794 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_accuracy": 0.9730941704035875, | |
| "eval_loss": 0.10973779112100601, | |
| "eval_runtime": 51.205, | |
| "eval_samples_per_second": 4.355, | |
| "eval_steps_per_second": 2.187, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "eval_accuracy": 0.9730941704035875, | |
| "eval_loss": 0.10973779112100601, | |
| "eval_runtime": 50.2397, | |
| "eval_samples_per_second": 4.439, | |
| "eval_steps_per_second": 2.229, | |
| "step": 1500 | |
| } | |
| ], | |
| "max_steps": 1500, | |
| "num_train_epochs": 9223372036854775807, | |
| "total_flos": 3.738527145787392e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |