| { | |
| "best_metric": 0.5428571428571428, | |
| "best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-75", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 11.617264747619629, | |
| "learning_rate": 4.850746268656717e-05, | |
| "loss": 2.377, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 10.894355773925781, | |
| "learning_rate": 4.104477611940299e-05, | |
| "loss": 2.2211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 8.908524513244629, | |
| "learning_rate": 3.358208955223881e-05, | |
| "loss": 2.1478, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 9.142258644104004, | |
| "learning_rate": 2.6119402985074626e-05, | |
| "loss": 2.109, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 11.492398262023926, | |
| "learning_rate": 1.865671641791045e-05, | |
| "loss": 2.077, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 9.018352508544922, | |
| "learning_rate": 1.119402985074627e-05, | |
| "loss": 1.8977, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 14.4193115234375, | |
| "learning_rate": 3.7313432835820893e-06, | |
| "loss": 1.9343, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5428571428571428, | |
| "eval_loss": 1.724652886390686, | |
| "eval_runtime": 13.0426, | |
| "eval_samples_per_second": 5.367, | |
| "eval_steps_per_second": 1.38, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 75, | |
| "total_flos": 3.73846047031296e+17, | |
| "train_loss": 2.0760047658284506, | |
| "train_runtime": 147.1173, | |
| "train_samples_per_second": 2.039, | |
| "train_steps_per_second": 0.51 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2838709677419355, | |
| "eval_loss": 1.9679653644561768, | |
| "eval_runtime": 28.6695, | |
| "eval_samples_per_second": 5.406, | |
| "eval_steps_per_second": 1.36, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2838709677419355, | |
| "eval_loss": 1.9679656028747559, | |
| "eval_runtime": 26.6207, | |
| "eval_samples_per_second": 5.823, | |
| "eval_steps_per_second": 1.465, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 3.73846047031296e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |