Update summary.jsonl

summary.jsonl

@@ -1,4 +1,4 @@
-{"train_file": "train.json", "validation_file": "valid.json", "test_file": "test.json", "num_examples": -1, "fea_encoder_name": "clip-vit-large-patch14", "scheduler_name": "stabilityai/stable-diffusion-2-1", "unet_model_name": null, "unet_model_config": "configs/diffusion_model_config_large_2048.json", "hf_model": null, "snr_gamma": 5.0, "freeze_text_encoder": true, "text_column": "captions", "image_column": "img", "audio_column": "audio_file", "video_column": "feature_file", "augment": false, "uncondition": false, "prefix": null, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 2, "learning_rate": 6e-05, "weight_decay": 1e-08, "num_train_epochs": 80, "max_train_steps": null, "gradient_accumulation_steps": 32, "lr_scheduler_type": "linear", "num_warmup_steps": 300, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_weight_decay": 0.01, "adam_epsilon": 1e-08, "output_dir": "saved/vta_ldm_clip4clip_large", "seed": null, "checkpointing_steps": "best", "save_every": 1, "resume_from_checkpoint": null, "vae_model": "audioldm-s-full", "with_tracking": false, "embedding_dim": 2048, "sample_rate": 16000, "report_to": "all", "task": "video2audio", "img_pretrained_model_path": "None"}
+{"train_file": "train.json", "validation_file": "valid.json", "test_file": "test.json", "num_examples": -1, "fea_encoder_name": "openai/clip-vit-large-patch14", "scheduler_name": "stabilityai/stable-diffusion-2-1", "unet_model_name": null, "unet_model_config": "configs/diffusion_model_config_large_2048.json", "hf_model": null, "snr_gamma": 5.0, "freeze_text_encoder": true, "text_column": "captions", "image_column": "img", "audio_column": "audio_file", "video_column": "feature_file", "augment": false, "uncondition": false, "prefix": null, "per_device_train_batch_size": 2, "per_device_eval_batch_size": 2, "learning_rate": 6e-05, "weight_decay": 1e-08, "num_train_epochs": 80, "max_train_steps": null, "gradient_accumulation_steps": 32, "lr_scheduler_type": "linear", "num_warmup_steps": 300, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_weight_decay": 0.01, "adam_epsilon": 1e-08, "output_dir": "saved/vta_ldm_clip4clip_large", "seed": null, "checkpointing_steps": "best", "save_every": 1, "resume_from_checkpoint": null, "vae_model": "ckpt/vta-ldm-clip4clip-v-large/audioldm-s-full.ckpt", "with_tracking": false, "embedding_dim": 2048, "sample_rate": 16000, "report_to": "all", "task": "video2audio", "img_pretrained_model_path": "None"}
 
 {"epoch": [1], "step": 372, "train_loss": 0.8671, "val_loss": 0.823}