Training in progress, step 500

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "VisionPixtralEncoderDecoder"
+  ],
+  "bos_token_id": 0,
+  "decoder": {
+    "activation_dropout": 0.0,
+    "activation_function": "relu",
+    "add_cross_attention": true,
+    "attention_dropout": 0.0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": 768,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 0,
+    "dropout": 0.1,
+    "init_std": 0.02,
+    "is_decoder": true,
+    "layernorm_embedding": false,
+    "max_position_embeddings": 1024,
+    "model_type": "trocr",
+    "scale_embedding": true,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32",
+    "use_cache": false,
+    "use_learned_position_embeddings": false,
+    "vocab_size": 50265
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_attn_implementation_autoset": true,
+    "_name_or_path": "pixtral_encoder_decoder",
+    "architectures": [
+      "PixtralVisionModelBatch"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+      "AutoConfig": "configuration.PixtralVisionModelBatchConfig",
+      "AutoModel": "modeling.PixtralVisionModelBatch"
+    },
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_composition": true,
+    "model_type": "pixtral_batch",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 16,
+    "rope_theta": 10000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float32"
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "model_type": "vision_pixtral_encoder_decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3854bcc3919c60111ce733271d965fed8b11caa1f1a1a92bce0fde76291a3098
+size 2810021492

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "PixtralImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "patch_size": {
+    "height": 16,
+    "width": 16
+  },
+  "processor_class": "TrOCRProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 1024
+  }
+}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "processor_class": "TrOCRProcessor",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c96ae398b95491149cc1e5ffaebdfe94e5300dd1b2c2e5914afc3d2396bad5
+size 5763