Training in progress, epoch 0

config.json

@@ -1,83 +1,85 @@
 {
-  "_commit_hash": "a959cf33c20e09215873e338299c900f57047c61",
-  "_name_or_path": "naver-clova-ix/donut-base",
+  "_commit_hash": "956e2761626d0c37672c7741204a105ecd389245",
+  "_name_or_path": "google/pix2struct-base",
   "architectures": [
-    "VisionEncoderDecoderModel"
+    "Pix2StructForConditionalGeneration"
   ],
-  "decoder": {
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "is_encoder_decoder": true,
+  "is_vqa": false,
+  "model_type": "pix2struct",
+  "pad_token_id": 0,
+  "text_config": {
     "_name_or_path": "",
-    "activation_dropout": 0.0,
-    "activation_function": "gelu",
-    "add_cross_attention": true,
-    "add_final_layer_norm": true,
+    "add_cross_attention": false,
     "architectures": null,
-    "attention_dropout": 0.0,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
-    "bos_token_id": 0,
+    "bos_token_id": null,
     "chunk_size_feed_forward": 0,
-    "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
-    "d_model": 1024,
-    "decoder_attention_heads": 16,
-    "decoder_ffn_dim": 4096,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 4,
-    "decoder_start_token_id": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.1,
+    "dropout_rate": 0.2,
     "early_stopping": false,
-    "encoder_attention_heads": 16,
-    "encoder_ffn_dim": 4096,
-    "encoder_layerdrop": 0.0,
-    "encoder_layers": 12,
+    "encoder_hidden_size": 768,
     "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
+    "eos_token_id": 1,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
-    "forced_eos_token_id": 2,
+    "forced_eos_token_id": null,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "init_std": 0.02,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "is_decoder": true,
     "is_encoder_decoder": false,
     "label2id": {
       "LABEL_0": 0,
       "LABEL_1": 1
     },
+    "layer_norm_epsilon": 1e-06,
     "length_penalty": 1.0,
-    "max_length": 768,
-    "max_position_embeddings": 1536,
+    "max_length": 20,
     "min_length": 0,
-    "model_type": "mbart",
+    "model_type": "pix2struct_text_model",
     "no_repeat_ngram_size": 0,
     "num_beam_groups": 1,
     "num_beams": 1,
-    "num_hidden_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
-    "pad_token_id": 1,
+    "pad_token_id": 0,
     "prefix": null,
     "problem_type": null,
     "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
-    "scale_embedding": true,
     "sep_token_id": null,
     "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
-    "tie_word_embeddings": true,
+    "tie_word_embeddings": false,
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
@@ -86,49 +88,43 @@
     "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
     "use_bfloat16": false,
-    "use_cache": true,
-    "vocab_size": 57544
+    "use_cache": false,
+    "vocab_size": 50362
   },
-  "decoder_start_token_id": 57543,
-  "encoder": {
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
     "_name_or_path": "",
     "add_cross_attention": false,
     "architectures": null,
-    "attention_probs_dropout_prob": 0.0,
+    "attention_dropout": 0.2,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": null,
     "chunk_size_feed_forward": 0,
     "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
     "decoder_start_token_id": null,
-    "depths": [
-      2,
-      2,
-      14,
-      2
-    ],
+    "dense_act_fn": "gelu_new",
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "drop_path_rate": 0.1,
+    "dropout_rate": 0.2,
     "early_stopping": false,
-    "embed_dim": 128,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": null,
     "exponential_decay_length_penalty": null,
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.0,
-    "hidden_size": 1024,
+    "hidden_dropout_prob": 0.2,
+    "hidden_size": 768,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
     },
-    "image_size": [
-      1920,
-      1280
-    ],
+    "initializer_factor": 1.0,
     "initializer_range": 0.02,
     "is_decoder": false,
     "is_encoder_decoder": false,
@@ -136,39 +132,37 @@
       "LABEL_0": 0,
       "LABEL_1": 1
     },
-    "layer_norm_eps": 1e-05,
+    "layer_norm_bias": false,
+    "layer_norm_eps": 1e-06,
     "length_penalty": 1.0,
     "max_length": 20,
     "min_length": 0,
-    "mlp_ratio": 4.0,
-    "model_type": "donut-swin",
+    "model_type": "pix2struct_vision_model",
     "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_channels": 3,
-    "num_heads": [
-      4,
-      8,
-      16,
-      32
-    ],
-    "num_layers": 4,
+    "num_hidden_layers": 12,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
     "output_scores": false,
     "pad_token_id": null,
-    "patch_size": 4,
-    "path_norm": true,
+    "patch_embed_hidden_size": 768,
+    "patch_size": 16,
     "prefix": null,
     "problem_type": null,
+    "projection_dim": 768,
     "pruned_heads": {},
-    "qkv_bias": true,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
     "remove_invalid_values": false,
     "repetition_penalty": 1.0,
     "return_dict": true,
     "return_dict_in_generate": false,
     "sep_token_id": null,
+    "seq_len": 4096,
     "suppress_tokens": null,
     "task_specific_params": null,
     "temperature": 1.0,
@@ -182,14 +176,6 @@
     "torchscript": false,
     "transformers_version": "4.31.0.dev0",
     "typical_p": 1.0,
-    "use_absolute_embeddings": false,
-    "use_bfloat16": false,
-    "window_size": 10
-  },
-  "is_encoder_decoder": true,
-  "model_type": "vision-encoder-decoder",
-  "pad_token_id": 1,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": null
+    "use_bfloat16": false
+  }
 }

generation_config.json

@@ -1,10 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "decoder_start_token_id": 57543,
-  "eos_token_id": 2,
-  "forced_eos_token_id": 2,
-  "max_length": 768,
-  "pad_token_id": 1,
-  "transformers_version": "4.31.0.dev0"
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": false
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a1ab266baa2e9888d655b955b32842a6184cb8fbd168d922e15f398d4c515d
-size 809256729
+oid sha256:8f1f4bd06e273460063a7aceb776a61db630fe051dcc8c64c41f19b0d028fdef
+size 1129967041