Training in progress, epoch 0

config.json

@@ -3,44 +3,43 @@
     "VisionEncoderDecoderModel"
   ],
   "decoder": {
-    "_name_or_path": "cnmoro/tiny-image-captioning",
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
     "add_cross_attention": true,
-    "attention_probs_dropout_prob": 0.1,
-    "classifier_dropout": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.1,
-    "hidden_size": 128,
-    "initializer_range": 0.02,
-    "intermediate_size": 512,
+    "attention_dropout": 0.0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": 384,
+    "d_model": 256,
+    "decoder_attention_heads": 8,
+    "decoder_ffn_dim": 1024,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "dropout": 0.1,
+    "init_std": 0.02,
     "is_decoder": true,
-    "layer_norm_eps": 1e-12,
+    "layernorm_embedding": true,
     "max_position_embeddings": 512,
-    "model_type": "bert",
-    "num_attention_heads": 2,
-    "num_hidden_layers": 2,
-    "position_embedding_type": "absolute",
+    "model_type": "trocr",
+    "scale_embedding": true,
+    "tie_word_embeddings": false,
     "torch_dtype": "float32",
-    "type_vocab_size": 2,
-    "use_cache": true,
-    "vocab_size": 30522
+    "use_cache": false,
+    "use_learned_position_embeddings": true,
+    "vocab_size": 64044
   },
-  "decoder_start_token_id": 101,
+  "decoder_start_token_id": 0,
   "early_stopping": null,
   "encoder": {
-    "_name_or_path": "cnmoro/tiny-image-captioning",
-    "architectures": [
-      "ViTForImageClassification"
-    ],
     "attention_probs_dropout_prob": 0.0,
     "encoder_stride": 16,
     "hidden_act": "gelu",
     "hidden_dropout_prob": 0.0,
     "hidden_size": 384,
-    "image_size": 224,
+    "image_size": 384,
     "initializer_range": 0.02,
     "intermediate_size": 1536,
     "layer_norm_eps": 1e-12,
-    "model_type": "vit",
+    "model_type": "deit",
     "num_attention_heads": 6,
     "num_channels": 3,
     "num_hidden_layers": 12,
@@ -50,16 +49,16 @@
     "qkv_bias": true,
     "torch_dtype": "float32"
   },
-  "eos_token_id": 102,
+  "eos_token_id": 2,
   "is_encoder_decoder": true,
   "length_penalty": null,
   "max_length": null,
   "model_type": "vision-encoder-decoder",
   "no_repeat_ngram_size": null,
   "num_beams": null,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.53.3",
-  "vocab_size": 30522
+  "vocab_size": 64044
 }

generation_config.json

@@ -1,11 +1,14 @@
 {
-  "decoder_start_token_id": 101,
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
   "early_stopping": true,
+  "eos_token_id": 2,
   "length_penalty": 2.0,
   "max_length": 12,
-  "max_new_tokens": 25,
   "no_repeat_ngram_size": 3,
   "num_beams": 2,
-  "pad_token_id": 0,
-  "transformers_version": "4.53.3"
+  "pad_token_id": 1,
+  "transformers_version": "4.53.3",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12fe404167036107b8ee2e3717ca8e604640c4dece5b9d2117005c36c8bbc5b
-size 105680032
+oid sha256:5feebaf5284c9d5c0a13162424b29191fafcc1c9c64c0adc6ac36f36fe167fc0
+size 246430696