| { | |
| "best_metric": 1.1988952159881592, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l58-l/checkpoint-3500", | |
| "epoch": 0.37329351535836175, | |
| "eval_steps": 500, | |
| "global_step": 3500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05332764505119454, | |
| "grad_norm": 217.40109252929688, | |
| "learning_rate": 4.911120591581342e-08, | |
| "loss": 0.4667, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05332764505119454, | |
| "eval_loss": 1.4427576065063477, | |
| "eval_runtime": 60.328, | |
| "eval_samples_per_second": 16.361, | |
| "eval_steps_per_second": 2.055, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.10665529010238908, | |
| "grad_norm": 70.38941955566406, | |
| "learning_rate": 4.822241183162685e-08, | |
| "loss": 0.4534, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10665529010238908, | |
| "eval_loss": 1.3823094367980957, | |
| "eval_runtime": 61.4884, | |
| "eval_samples_per_second": 16.052, | |
| "eval_steps_per_second": 2.017, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1599829351535836, | |
| "grad_norm": 389.9967956542969, | |
| "learning_rate": 4.733361774744027e-08, | |
| "loss": 0.3753, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1599829351535836, | |
| "eval_loss": 1.3328827619552612, | |
| "eval_runtime": 63.0378, | |
| "eval_samples_per_second": 15.657, | |
| "eval_steps_per_second": 1.967, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21331058020477817, | |
| "grad_norm": 13.427445411682129, | |
| "learning_rate": 4.6444823663253694e-08, | |
| "loss": 0.3361, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21331058020477817, | |
| "eval_loss": 1.2922736406326294, | |
| "eval_runtime": 63.1958, | |
| "eval_samples_per_second": 15.618, | |
| "eval_steps_per_second": 1.962, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2666382252559727, | |
| "grad_norm": 320.7197265625, | |
| "learning_rate": 4.555602957906712e-08, | |
| "loss": 0.3597, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2666382252559727, | |
| "eval_loss": 1.257211685180664, | |
| "eval_runtime": 63.3241, | |
| "eval_samples_per_second": 15.586, | |
| "eval_steps_per_second": 1.958, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.3199658703071672, | |
| "grad_norm": 0.0019184721168130636, | |
| "learning_rate": 4.4667235494880546e-08, | |
| "loss": 0.3042, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3199658703071672, | |
| "eval_loss": 1.2240594625473022, | |
| "eval_runtime": 63.5118, | |
| "eval_samples_per_second": 15.54, | |
| "eval_steps_per_second": 1.952, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.37329351535836175, | |
| "grad_norm": 11.738512992858887, | |
| "learning_rate": 4.3778441410693965e-08, | |
| "loss": 0.3252, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.37329351535836175, | |
| "eval_loss": 1.1988952159881592, | |
| "eval_runtime": 63.5384, | |
| "eval_samples_per_second": 15.534, | |
| "eval_steps_per_second": 1.952, | |
| "step": 3500 | |
| } | |
| ], | |
| "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": 1259873746112520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |