Training in progress, epoch 1

config.json

@@ -0,0 +1,142 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "add_final_layer_norm": true,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "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,
+    "dropout": 0.1,
+    "dtype": "float32",
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 1536,
+    "model_type": "mbart",
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "return_dict": true,
+    "scale_embedding": true,
+    "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,
+    "use_cache": true,
+    "vocab_size": 57600
+  },
+  "decoder_start_token_id": 57525,
+  "dtype": "float32",
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "drop_path_rate": 0.1,
+    "dtype": "float32",
+    "embed_dim": 128,
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": [
+      2560,
+      1920
+    ],
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "return_dict": true,
+    "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_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,
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": false
+}

generation_config.json

@@ -0,0 +1,30 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 2,
+  "forced_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": 1,
+  "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": "5.0.0.dev0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a784de21b0d039180afee4a42100172e401be820bef50e222c3d7424c4ad64ad
+size 809377944

runs/Jan23_20-56-32_5edf36cc8f19/events.out.tfevents.1769201792.5edf36cc8f19.3794.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e9bd831ca3d6ae582e33196f3124b73e346f078352034915a30f78b748fa49
+size 4184

runs/Jan23_20-57-33_5edf36cc8f19/events.out.tfevents.1769201853.5edf36cc8f19.7525.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef24f2d1ab05fb428c6fbf4797206ed271b29d2db5fa64d1602bbac330360fff
+size 20359

runs/Jan23_21-10-49_5edf36cc8f19/events.out.tfevents.1769202649.5edf36cc8f19.10436.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea14957ce7806ba81e4075ca116dc128f3fb0add0701633eb2a9b6502369406d
+size 20145

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d2ca7077efaf710d03be37a335cd44c87dc965c0b7fd9f6a62dd4de6ddcf8c
+size 5329