Training in progress, epoch 1

config.json

@@ -0,0 +1,83 @@
+{
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "image_text_hidden_size": 256,
+  "image_token_index": 50265,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "_attn_implementation_autoset": true,
+    "attention_probs_dropout_prob": 0.1,
+    "classifier_dropout": null,
+    "cross_attention_frequency": 2,
+    "encoder_hidden_size": 1408,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "blip_2_qformer",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "position_embedding_type": "absolute",
+    "torch_dtype": "float32",
+    "use_qformer_text_input": false,
+    "vocab_size": 30522
+  },
+  "text_config": {
+    "_name_or_path": "facebook/opt-2.7b",
+    "_remove_final_layer_norm": false,
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "architectures": [
+      "OPTForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "do_layer_norm_before": true,
+    "dropout": 0.1,
+    "enable_bias": true,
+    "eos_token_id": 50118,
+    "ffn_dim": 10240,
+    "hidden_size": 2560,
+    "init_std": 0.02,
+    "layer_norm_elementwise_affine": true,
+    "layerdrop": 0.0,
+    "max_position_embeddings": 2048,
+    "model_type": "opt",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "prefix": "</s>",
+    "torch_dtype": "float32",
+    "use_cache": true,
+    "vocab_size": 50304,
+    "word_embed_proj_dim": 2560
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 1e-10,
+    "intermediate_size": 6144,
+    "layer_norm_eps": 1e-06,
+    "model_type": "blip_2_vision_model",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 39,
+    "patch_size": 14,
+    "projection_dim": 512,
+    "qkv_bias": true,
+    "torch_dtype": "float32"
+  }
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09bf6ed71dd4037c8881ee5f0473696bb27c771c447e57c9c763a105fb8de258
+size 4987223832

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7643768d3c9b528f6ea6ea1f1909d96be6e3ef022ac645db086a2461b1cd16
+size 4982878872

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3726dc92e6118601e268ff3ea577e132f805a02b036d63619e1048a32b6d0f82
+size 4904215096

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3e459c12e42997e2b3944961d0cabfa6bf8003122a1dd7558ff101349b00db
+size 104888856

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c1f59f9e6461b9e09de4a4349068a4a001a1dc9f2809d2ad341c9fcb1c4c9c
+size 5496