| { | |
| "best_metric": 0.34285714285714286, | |
| "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": 9.491246223449707, | |
| "learning_rate": 4.850746268656717e-05, | |
| "loss": 2.2907, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 10.176407814025879, | |
| "learning_rate": 4.104477611940299e-05, | |
| "loss": 2.2125, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 10.320022583007812, | |
| "learning_rate": 3.358208955223881e-05, | |
| "loss": 2.157, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 9.819656372070312, | |
| "learning_rate": 2.6119402985074626e-05, | |
| "loss": 2.013, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 12.585600852966309, | |
| "learning_rate": 1.865671641791045e-05, | |
| "loss": 2.0902, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 9.586479187011719, | |
| "learning_rate": 1.119402985074627e-05, | |
| "loss": 1.8302, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 18.528013229370117, | |
| "learning_rate": 3.7313432835820893e-06, | |
| "loss": 1.9035, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.34285714285714286, | |
| "eval_loss": 1.724967360496521, | |
| "eval_runtime": 13.021, | |
| "eval_samples_per_second": 5.376, | |
| "eval_steps_per_second": 1.382, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 75, | |
| "total_flos": 3.73846047031296e+17, | |
| "train_loss": 2.0445140584309898, | |
| "train_runtime": 154.4764, | |
| "train_samples_per_second": 1.942, | |
| "train_steps_per_second": 0.486 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.38064516129032255, | |
| "eval_loss": 1.8708232641220093, | |
| "eval_runtime": 29.3555, | |
| "eval_samples_per_second": 5.28, | |
| "eval_steps_per_second": 1.329, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.38064516129032255, | |
| "eval_loss": 1.8708232641220093, | |
| "eval_runtime": 27.0879, | |
| "eval_samples_per_second": 5.722, | |
| "eval_steps_per_second": 1.44, | |
| "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 | |
| } | |