| { | |
| "best_metric": 1.0416266918182373, | |
| "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-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": 247.07174682617188, | |
| "learning_rate": 9.822241183162683e-08, | |
| "loss": 0.4515, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05332764505119454, | |
| "eval_loss": 1.38526451587677, | |
| "eval_runtime": 63.6956, | |
| "eval_samples_per_second": 15.496, | |
| "eval_steps_per_second": 1.947, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.10665529010238908, | |
| "grad_norm": 72.11767578125, | |
| "learning_rate": 9.64448236632537e-08, | |
| "loss": 0.414, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10665529010238908, | |
| "eval_loss": 1.284197211265564, | |
| "eval_runtime": 62.7418, | |
| "eval_samples_per_second": 15.731, | |
| "eval_steps_per_second": 1.976, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1599829351535836, | |
| "grad_norm": 812.2269287109375, | |
| "learning_rate": 9.466723549488054e-08, | |
| "loss": 0.3279, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1599829351535836, | |
| "eval_loss": 1.2100127935409546, | |
| "eval_runtime": 62.6215, | |
| "eval_samples_per_second": 15.761, | |
| "eval_steps_per_second": 1.98, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.21331058020477817, | |
| "grad_norm": 4.459943771362305, | |
| "learning_rate": 9.288964732650739e-08, | |
| "loss": 0.2912, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.21331058020477817, | |
| "eval_loss": 1.1584910154342651, | |
| "eval_runtime": 64.0453, | |
| "eval_samples_per_second": 15.411, | |
| "eval_steps_per_second": 1.936, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2666382252559727, | |
| "grad_norm": 328.06475830078125, | |
| "learning_rate": 9.111205915813424e-08, | |
| "loss": 0.3056, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2666382252559727, | |
| "eval_loss": 1.1090214252471924, | |
| "eval_runtime": 63.2171, | |
| "eval_samples_per_second": 15.613, | |
| "eval_steps_per_second": 1.961, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.3199658703071672, | |
| "grad_norm": 0.00026008329587057233, | |
| "learning_rate": 8.933447098976109e-08, | |
| "loss": 0.2453, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3199658703071672, | |
| "eval_loss": 1.0675184726715088, | |
| "eval_runtime": 63.9757, | |
| "eval_samples_per_second": 15.428, | |
| "eval_steps_per_second": 1.938, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.37329351535836175, | |
| "grad_norm": 7.824947834014893, | |
| "learning_rate": 8.755688282138793e-08, | |
| "loss": 0.2721, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.37329351535836175, | |
| "eval_loss": 1.0416266918182373, | |
| "eval_runtime": 63.8858, | |
| "eval_samples_per_second": 15.449, | |
| "eval_steps_per_second": 1.941, | |
| "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 | |
| } | |