Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<s_iitcdip>": 57523,
+  "<s_synthdog>": 57524,
+  "<sep/>": 57522
+}

config.json

@@ -0,0 +1,192 @@
+{
+  "_name_or_path": "naver-clova-ix/donut-base",
+  "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,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "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,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": 2,
+    "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
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1536,
+    "min_length": 0,
+    "model_type": "mbart",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "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,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 57525
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_probs_dropout_prob": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "depths": [
+      2,
+      2,
+      14,
+      2
+    ],
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.1,
+    "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,
+    "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,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 4.0,
+    "model_type": "donut-swin",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_heads": [
+      4,
+      8,
+      16,
+      32
+    ],
+    "num_layers": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 4,
+    "path_norm": true,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "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,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "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": "4.42.3"
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af4e7c8b202101b839d4ac5c62b787a374ee1b469b6e8e509ab6ad4f42940ab2
+size 809070744

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14e4de8daa4ef9c6f5a427d7f11cfd205262174079e2f3b56cdc8c556f08b0f
+size 1615203711

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_align_long_axis": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "DonutImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "DonutProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 2560,
+    "width": 1920
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b40647fcacaec6a51e0fc1d064e72f6fad65c7c348f4c5f2b4069b63bb14ae37
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc94edf675b521b998e5558ae7d90017af7f292d0ea2e12850b821b0a864cf25
+size 1064

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
+size 1296245

special_tokens_map.json

@@ -0,0 +1,55 @@
+{
+  "additional_special_tokens": [
+    "<s_iitcdip>",
+    "<s_synthdog>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "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": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57521": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57522": {
+      "content": "<sep/>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57523": {
+      "content": "<s_iitcdip>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "57524": {
+      "content": "<s_synthdog>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<s_iitcdip>",
+    "<s_synthdog>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "DonutProcessor",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.32075471698113,
+  "eval_steps": 500,
+  "global_step": 32,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6037735849056604,
+      "eval_loss": 7.004851341247559,
+      "eval_runtime": 8.5772,
+      "eval_samples_per_second": 1.166,
+      "eval_steps_per_second": 1.166,
+      "step": 1
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "eval_loss": 3.771308183670044,
+      "eval_runtime": 8.4592,
+      "eval_samples_per_second": 1.182,
+      "eval_steps_per_second": 1.182,
+      "step": 3
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "eval_loss": 3.2317841053009033,
+      "eval_runtime": 8.5782,
+      "eval_samples_per_second": 1.166,
+      "eval_steps_per_second": 1.166,
+      "step": 4
+    },
+    {
+      "epoch": 3.6226415094339623,
+      "eval_loss": 2.7170462608337402,
+      "eval_runtime": 8.2554,
+      "eval_samples_per_second": 1.211,
+      "eval_steps_per_second": 1.211,
+      "step": 6
+    },
+    {
+      "epoch": 4.830188679245283,
+      "eval_loss": 2.4117250442504883,
+      "eval_runtime": 8.2693,
+      "eval_samples_per_second": 1.209,
+      "eval_steps_per_second": 1.209,
+      "step": 8
+    },
+    {
+      "epoch": 5.433962264150943,
+      "eval_loss": 2.3043994903564453,
+      "eval_runtime": 8.4472,
+      "eval_samples_per_second": 1.184,
+      "eval_steps_per_second": 1.184,
+      "step": 9
+    },
+    {
+      "epoch": 6.6415094339622645,
+      "eval_loss": 2.1263480186462402,
+      "eval_runtime": 8.3143,
+      "eval_samples_per_second": 1.203,
+      "eval_steps_per_second": 1.203,
+      "step": 11
+    },
+    {
+      "epoch": 7.849056603773585,
+      "eval_loss": 1.9751574993133545,
+      "eval_runtime": 9.6666,
+      "eval_samples_per_second": 1.034,
+      "eval_steps_per_second": 1.034,
+      "step": 13
+    },
+    {
+      "epoch": 8.452830188679245,
+      "eval_loss": 1.9131397008895874,
+      "eval_runtime": 9.3925,
+      "eval_samples_per_second": 1.065,
+      "eval_steps_per_second": 1.065,
+      "step": 14
+    },
+    {
+      "epoch": 9.660377358490566,
+      "eval_loss": 1.8003075122833252,
+      "eval_runtime": 8.2642,
+      "eval_samples_per_second": 1.21,
+      "eval_steps_per_second": 1.21,
+      "step": 16
+    },
+    {
+      "epoch": 10.867924528301886,
+      "eval_loss": 1.7071031332015991,
+      "eval_runtime": 8.3286,
+      "eval_samples_per_second": 1.201,
+      "eval_steps_per_second": 1.201,
+      "step": 18
+    },
+    {
+      "epoch": 11.471698113207546,
+      "eval_loss": 1.6670234203338623,
+      "eval_runtime": 8.538,
+      "eval_samples_per_second": 1.171,
+      "eval_steps_per_second": 1.171,
+      "step": 19
+    },
+    {
+      "epoch": 12.679245283018869,
+      "eval_loss": 1.5967587232589722,
+      "eval_runtime": 8.5178,
+      "eval_samples_per_second": 1.174,
+      "eval_steps_per_second": 1.174,
+      "step": 21
+    },
+    {
+      "epoch": 13.88679245283019,
+      "eval_loss": 1.531766653060913,
+      "eval_runtime": 8.3422,
+      "eval_samples_per_second": 1.199,
+      "eval_steps_per_second": 1.199,
+      "step": 23
+    },
+    {
+      "epoch": 14.49056603773585,
+      "eval_loss": 1.50529944896698,
+      "eval_runtime": 8.2464,
+      "eval_samples_per_second": 1.213,
+      "eval_steps_per_second": 1.213,
+      "step": 24
+    },
+    {
+      "epoch": 15.69811320754717,
+      "eval_loss": 1.4612596035003662,
+      "eval_runtime": 8.1581,
+      "eval_samples_per_second": 1.226,
+      "eval_steps_per_second": 1.226,
+      "step": 26
+    },
+    {
+      "epoch": 16.90566037735849,
+      "eval_loss": 1.4295562505722046,
+      "eval_runtime": 8.4036,
+      "eval_samples_per_second": 1.19,
+      "eval_steps_per_second": 1.19,
+      "step": 28
+    },
+    {
+      "epoch": 17.50943396226415,
+      "eval_loss": 1.4175879955291748,
+      "eval_runtime": 8.3644,
+      "eval_samples_per_second": 1.196,
+      "eval_steps_per_second": 1.196,
+      "step": 29
+    },
+    {
+      "epoch": 18.71698113207547,
+      "eval_loss": 1.4012755155563354,
+      "eval_runtime": 8.2943,
+      "eval_samples_per_second": 1.206,
+      "eval_steps_per_second": 1.206,
+      "step": 31
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 32,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 32,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2807830122581197e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f79418e4369c4148e90bfa1d9a185894e32f6a5d7db813132f53a3b59fc1acf
+size 5240