| { | |
| "best_metric": 1.1162768602371216, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-l/checkpoint-3500", | |
| "epoch": 0.6448047162859248, | |
| "eval_steps": 500, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09211495946941783, | |
| "grad_norm": 20.28152847290039, | |
| "learning_rate": 4.8848563006632274e-08, | |
| "loss": 0.3758, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09211495946941783, | |
| "eval_loss": 1.418367862701416, | |
| "eval_runtime": 73.4439, | |
| "eval_samples_per_second": 16.434, | |
| "eval_steps_per_second": 2.056, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "grad_norm": 47.29538345336914, | |
| "learning_rate": 4.7697126013264556e-08, | |
| "loss": 0.4104, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "eval_loss": 1.3491536378860474, | |
| "eval_runtime": 74.3404, | |
| "eval_samples_per_second": 16.236, | |
| "eval_steps_per_second": 2.031, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2763448784082535, | |
| "grad_norm": 0.5450155138969421, | |
| "learning_rate": 4.6545689019896826e-08, | |
| "loss": 0.4325, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2763448784082535, | |
| "eval_loss": 1.2877168655395508, | |
| "eval_runtime": 75.3303, | |
| "eval_samples_per_second": 16.023, | |
| "eval_steps_per_second": 2.005, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.36845983787767134, | |
| "grad_norm": 0.11449883133172989, | |
| "learning_rate": 4.539425202652911e-08, | |
| "loss": 0.3423, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36845983787767134, | |
| "eval_loss": 1.2384389638900757, | |
| "eval_runtime": 76.113, | |
| "eval_samples_per_second": 15.858, | |
| "eval_steps_per_second": 1.984, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.46057479734708917, | |
| "grad_norm": 389.7380065917969, | |
| "learning_rate": 4.4242815033161385e-08, | |
| "loss": 0.3645, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46057479734708917, | |
| "eval_loss": 1.1896915435791016, | |
| "eval_runtime": 76.23, | |
| "eval_samples_per_second": 15.834, | |
| "eval_steps_per_second": 1.981, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.552689756816507, | |
| "grad_norm": 340.1103820800781, | |
| "learning_rate": 4.309137803979366e-08, | |
| "loss": 0.3171, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.552689756816507, | |
| "eval_loss": 1.149291753768921, | |
| "eval_runtime": 76.1662, | |
| "eval_samples_per_second": 15.847, | |
| "eval_steps_per_second": 1.983, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6448047162859248, | |
| "grad_norm": 196.7362518310547, | |
| "learning_rate": 4.193994104642594e-08, | |
| "loss": 0.275, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6448047162859248, | |
| "eval_loss": 1.1162768602371216, | |
| "eval_runtime": 74.6569, | |
| "eval_samples_per_second": 16.167, | |
| "eval_steps_per_second": 2.023, | |
| "step": 3500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 21712, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1259873746112520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |