ptx0
30000 steps (approx 4 epochs) with terminal SNR on 22k Midjourney 5.1 images plus 7200 real photographs as balance data with complete BLIP captions on all data. BS=4, LR=4e-7 to 1e-8
02b28ff | { | |
| "_name_or_path": "/notebooks/datasets/models/checkpoint-30000/text_encoder", | |
| "architectures": [ | |
| "CLIPTextModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "dropout": 0.0, | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_size": 1024, | |
| "initializer_factor": 1.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 77, | |
| "model_type": "clip_text_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 23, | |
| "pad_token_id": 1, | |
| "projection_dim": 512, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.28.1", | |
| "vocab_size": 49408 | |
| } | |