| { | |
| "best_metric": 0.6554597020149231, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-6000", | |
| "epoch": 0.6399317406143344, | |
| "eval_steps": 500, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05332764505119454, | |
| "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 | |
| }, | |
| { | |
| "epoch": 0.1599829351535836, | |
| "grad_norm": 518.2286376953125, | |
| "learning_rate": 4.733361774744027e-07, | |
| "loss": 0.2085, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1599829351535836, | |
| "eval_loss": 0.9051361680030823, | |
| "eval_runtime": 63.9009, | |
| "eval_samples_per_second": 15.446, | |
| "eval_steps_per_second": 1.941, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21331058020477817, | |
| "grad_norm": 0.0223398394882679, | |
| "learning_rate": 4.6444823663253695e-07, | |
| "loss": 0.1867, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21331058020477817, | |
| "eval_loss": 0.8611643314361572, | |
| "eval_runtime": 63.9649, | |
| "eval_samples_per_second": 15.43, | |
| "eval_steps_per_second": 1.939, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2666382252559727, | |
| "grad_norm": 175.0380096435547, | |
| "learning_rate": 4.5556029579067116e-07, | |
| "loss": 0.2068, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2666382252559727, | |
| "eval_loss": 0.7947371006011963, | |
| "eval_runtime": 64.0455, | |
| "eval_samples_per_second": 15.411, | |
| "eval_steps_per_second": 1.936, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.3199658703071672, | |
| "grad_norm": 9.192651084788395e-09, | |
| "learning_rate": 4.4667235494880547e-07, | |
| "loss": 0.163, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3199658703071672, | |
| "eval_loss": 0.7677457332611084, | |
| "eval_runtime": 64.1593, | |
| "eval_samples_per_second": 15.384, | |
| "eval_steps_per_second": 1.933, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.37329351535836175, | |
| "grad_norm": 0.002516463166102767, | |
| "learning_rate": 4.377844141069397e-07, | |
| "loss": 0.1729, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.37329351535836175, | |
| "eval_loss": 0.7635349035263062, | |
| "eval_runtime": 62.8257, | |
| "eval_samples_per_second": 15.71, | |
| "eval_steps_per_second": 1.974, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.42662116040955633, | |
| "grad_norm": 7.581352710723877, | |
| "learning_rate": 4.2889647326507393e-07, | |
| "loss": 0.1149, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.42662116040955633, | |
| "eval_loss": 0.7458549737930298, | |
| "eval_runtime": 64.2184, | |
| "eval_samples_per_second": 15.369, | |
| "eval_steps_per_second": 1.931, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.47994880546075086, | |
| "grad_norm": 1.3885610103607178, | |
| "learning_rate": 4.2000853242320814e-07, | |
| "loss": 0.1264, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.47994880546075086, | |
| "eval_loss": 0.7185410261154175, | |
| "eval_runtime": 62.6998, | |
| "eval_samples_per_second": 15.742, | |
| "eval_steps_per_second": 1.978, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5332764505119454, | |
| "grad_norm": 4.22987541242037e-05, | |
| "learning_rate": 4.1112059158134245e-07, | |
| "loss": 0.1638, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.5332764505119454, | |
| "eval_loss": 0.7118513584136963, | |
| "eval_runtime": 63.9674, | |
| "eval_samples_per_second": 15.43, | |
| "eval_steps_per_second": 1.938, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.58660409556314, | |
| "grad_norm": 3.7000099837314337e-06, | |
| "learning_rate": 4.0223265073947665e-07, | |
| "loss": 0.1287, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.58660409556314, | |
| "eval_loss": 0.6782647967338562, | |
| "eval_runtime": 62.7899, | |
| "eval_samples_per_second": 15.719, | |
| "eval_steps_per_second": 1.975, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.6399317406143344, | |
| "grad_norm": 43.72269058227539, | |
| "learning_rate": 3.933447098976109e-07, | |
| "loss": 0.1324, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.6399317406143344, | |
| "eval_loss": 0.6554597020149231, | |
| "eval_runtime": 64.1964, | |
| "eval_samples_per_second": 15.375, | |
| "eval_steps_per_second": 1.932, | |
| "step": 6000 | |
| } | |
| ], | |
| "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": 2159269624262520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |