| { | |
| "best_metric": 0.6357071995735168, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-6000", | |
| "epoch": 1.105379513633014, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09211495946941783, | |
| "grad_norm": 2.6780805587768555, | |
| "learning_rate": 4.84647506755097e-07, | |
| "loss": 0.2705, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.09211495946941783, | |
| "eval_loss": 1.0680681467056274, | |
| "eval_runtime": 74.5723, | |
| "eval_samples_per_second": 16.186, | |
| "eval_steps_per_second": 2.025, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "grad_norm": 8.301130294799805, | |
| "learning_rate": 4.69295013510194e-07, | |
| "loss": 0.2545, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.18422991893883567, | |
| "eval_loss": 0.9443553686141968, | |
| "eval_runtime": 74.9643, | |
| "eval_samples_per_second": 16.101, | |
| "eval_steps_per_second": 2.014, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2763448784082535, | |
| "grad_norm": 0.018898434937000275, | |
| "learning_rate": 4.5394252026529107e-07, | |
| "loss": 0.234, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2763448784082535, | |
| "eval_loss": 0.876915693283081, | |
| "eval_runtime": 75.6401, | |
| "eval_samples_per_second": 15.957, | |
| "eval_steps_per_second": 1.996, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.36845983787767134, | |
| "grad_norm": 0.00010984255641233176, | |
| "learning_rate": 4.385900270203881e-07, | |
| "loss": 0.1539, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.36845983787767134, | |
| "eval_loss": 0.8415330648422241, | |
| "eval_runtime": 76.9959, | |
| "eval_samples_per_second": 15.676, | |
| "eval_steps_per_second": 1.961, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.46057479734708917, | |
| "grad_norm": 395.890625, | |
| "learning_rate": 4.232375337754851e-07, | |
| "loss": 0.1766, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.46057479734708917, | |
| "eval_loss": 0.7660450339317322, | |
| "eval_runtime": 76.733, | |
| "eval_samples_per_second": 15.73, | |
| "eval_steps_per_second": 1.968, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.552689756816507, | |
| "grad_norm": 363.6924743652344, | |
| "learning_rate": 4.0788504053058217e-07, | |
| "loss": 0.1679, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.552689756816507, | |
| "eval_loss": 0.7269155383110046, | |
| "eval_runtime": 76.7928, | |
| "eval_samples_per_second": 15.718, | |
| "eval_steps_per_second": 1.966, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6448047162859248, | |
| "grad_norm": 28.914026260375977, | |
| "learning_rate": 3.925325472856792e-07, | |
| "loss": 0.1104, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.6448047162859248, | |
| "eval_loss": 0.7097663283348083, | |
| "eval_runtime": 76.6897, | |
| "eval_samples_per_second": 15.739, | |
| "eval_steps_per_second": 1.969, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7369196757553427, | |
| "grad_norm": 116.85651397705078, | |
| "learning_rate": 3.771800540407762e-07, | |
| "loss": 0.1367, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7369196757553427, | |
| "eval_loss": 0.6968969106674194, | |
| "eval_runtime": 77.1872, | |
| "eval_samples_per_second": 15.637, | |
| "eval_steps_per_second": 1.956, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.8290346352247605, | |
| "grad_norm": 391.0343322753906, | |
| "learning_rate": 3.618275607958732e-07, | |
| "loss": 0.1129, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8290346352247605, | |
| "eval_loss": 0.6776800751686096, | |
| "eval_runtime": 75.0351, | |
| "eval_samples_per_second": 16.086, | |
| "eval_steps_per_second": 2.012, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.9211495946941783, | |
| "grad_norm": 2.0514346033451147e-05, | |
| "learning_rate": 3.464750675509703e-07, | |
| "loss": 0.1125, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.9211495946941783, | |
| "eval_loss": 0.6658498048782349, | |
| "eval_runtime": 77.111, | |
| "eval_samples_per_second": 15.653, | |
| "eval_steps_per_second": 1.958, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.013264554163596, | |
| "grad_norm": 0.000568103976547718, | |
| "learning_rate": 3.311225743060673e-07, | |
| "loss": 0.1071, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.013264554163596, | |
| "eval_loss": 0.6465296149253845, | |
| "eval_runtime": 75.2951, | |
| "eval_samples_per_second": 16.03, | |
| "eval_steps_per_second": 2.005, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.105379513633014, | |
| "grad_norm": 0.02698369137942791, | |
| "learning_rate": 3.157700810611643e-07, | |
| "loss": 0.0553, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.105379513633014, | |
| "eval_loss": 0.6357071995735168, | |
| "eval_runtime": 76.6726, | |
| "eval_samples_per_second": 15.742, | |
| "eval_steps_per_second": 1.969, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 16284, | |
| "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": 2159269624262520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |