| { | |
| "best_metric": 0.9644754528999329, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-1000", | |
| "epoch": 0.10665529010238908, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05332764505119454, | |
| "grad_norm": 401.61187744140625, | |
| "learning_rate": 4.911120591581342e-07, | |
| "loss": 0.3808, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05332764505119454, | |
| "eval_loss": 1.1107642650604248, | |
| "eval_runtime": 62.4169, | |
| "eval_samples_per_second": 15.813, | |
| "eval_steps_per_second": 1.987, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.10665529010238908, | |
| "grad_norm": 42.57551193237305, | |
| "learning_rate": 4.822241183162685e-07, | |
| "loss": 0.2666, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10665529010238908, | |
| "eval_loss": 0.9644754528999329, | |
| "eval_runtime": 63.4304, | |
| "eval_samples_per_second": 15.56, | |
| "eval_steps_per_second": 1.955, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 28128, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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 | |
| } | |