| { | |
| "best_metric": 2.078455924987793, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e2l57-l/checkpoint-500", | |
| "epoch": 0.18422991893883567, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09211495946941783, | |
| "grad_norm": 0.00766215892508626, | |
| "learning_rate": 4.769712601326456e-05, | |
| "loss": 0.7207, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09211495946941783, | |
| "eval_loss": 2.078455924987793, | |
| "eval_runtime": 73.0449, | |
| "eval_samples_per_second": 16.524, | |
| "eval_steps_per_second": 2.067, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "grad_norm": 0.016227997839450836, | |
| "learning_rate": 4.539425202652911e-05, | |
| "loss": 0.702, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "eval_loss": 2.0786073207855225, | |
| "eval_runtime": 73.7466, | |
| "eval_samples_per_second": 16.367, | |
| "eval_steps_per_second": 2.048, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 10856, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 360477867962520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |