Training in progress, step 10

config.json

@@ -0,0 +1,90 @@
+{
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "label_smoothing": 0.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "add_cross_attention": false,
+    "attention_probs_dropout_prob": 0.0,
+    "bos_token_id": 30522,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dtype": "float32",
+    "encoder_hidden_size": 768,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "label_smoothing": 0.0,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "prefix": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "sep_token_id": 102,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30524
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.2.0",
+  "use_cache": false,
+  "vision_config": {
+    "add_cross_attention": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "image_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "layer_norm_eps": 1e-05,
+    "model_type": "blip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false
+  }
+}

generation_config.json

@@ -0,0 +1,29 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30522,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 2,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 0,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.2.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1596c094d57ca2ef4f06ce9181ab01c2cb9a5869c2d6364b667a7f1bbed8b9d0
+size 989839224

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1745c7300715f82e7b5649b73c55e4c74414af3c51d85ed995a7e3fdef12dee7
+size 4792