Training in progress, step 100

README.md

@@ -0,0 +1,139 @@
+---
+library_name: transformers
+license: cc-by-4.0
+base_model: facebook/nougat-small
+tags:
+- generated_from_trainer
+model-index:
+- name: dhivehi-nougat-small-dv01-01
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# dhivehi-nougat-small-dv01-01
+
+This model is a fine-tuned version of [facebook/nougat-small](https://huggingface.co/facebook/nougat-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0300
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 3
+- eval_batch_size: 3
+- seed: 42
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 18
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 7.1462        | 0.0567 | 100  | 1.1326          |
+| 6.5572        | 0.1135 | 200  | 1.0543          |
+| 6.1831        | 0.1702 | 300  | 0.9868          |
+| 6.0022        | 0.2269 | 400  | 0.9323          |
+| 5.6527        | 0.2837 | 500  | 0.8896          |
+| 5.5004        | 0.3404 | 600  | 0.8478          |
+| 5.2741        | 0.3971 | 700  | 0.8168          |
+| 4.9927        | 0.4539 | 800  | 0.7466          |
+| 4.3776        | 0.5106 | 900  | 0.6724          |
+| 2.816         | 0.5673 | 1000 | 0.4038          |
+| 1.8526        | 0.6241 | 1100 | 0.2720          |
+| 1.5099        | 0.6808 | 1200 | 0.2064          |
+| 1.3084        | 0.7375 | 1300 | 0.1696          |
+| 1.1449        | 0.7943 | 1400 | 0.1516          |
+| 0.8819        | 0.8510 | 1500 | 0.1331          |
+| 0.7947        | 0.9077 | 1600 | 0.1194          |
+| 0.9857        | 0.9644 | 1700 | 0.1091          |
+| 0.7097        | 1.0210 | 1800 | 0.1023          |
+| 0.5212        | 1.0777 | 1900 | 0.0953          |
+| 0.6396        | 1.1345 | 2000 | 0.0882          |
+| 0.6073        | 1.1912 | 2100 | 0.0863          |
+| 0.5683        | 1.2479 | 2200 | 0.0815          |
+| 0.5399        | 1.3047 | 2300 | 0.0770          |
+| 0.5433        | 1.3614 | 2400 | 0.0740          |
+| 0.5824        | 1.4181 | 2500 | 0.0688          |
+| 0.447         | 1.4748 | 2600 | 0.0665          |
+| 0.4875        | 1.5316 | 2700 | 0.0633          |
+| 0.4694        | 1.5883 | 2800 | 0.0616          |
+| 0.4001        | 1.6450 | 2900 | 0.0580          |
+| 0.3971        | 1.7018 | 3000 | 0.0585          |
+| 0.3889        | 1.7585 | 3100 | 0.0556          |
+| 0.3088        | 1.8152 | 3200 | 0.0546          |
+| 0.3476        | 1.8720 | 3300 | 0.0522          |
+| 0.4569        | 1.9287 | 3400 | 0.0513          |
+| 0.3979        | 1.9854 | 3500 | 0.0502          |
+| 0.2847        | 2.0420 | 3600 | 0.0486          |
+| 0.4332        | 2.0987 | 3700 | 0.0465          |
+| 0.3647        | 2.1554 | 3800 | 0.0469          |
+| 0.3791        | 2.2122 | 3900 | 0.0459          |
+| 0.2982        | 2.2689 | 4000 | 0.0450          |
+| 0.3294        | 2.3256 | 4100 | 0.0447          |
+| 0.2839        | 2.3824 | 4200 | 0.0434          |
+| 0.3094        | 2.4391 | 4300 | 0.0433          |
+| 0.3062        | 2.4958 | 4400 | 0.0422          |
+| 0.2723        | 2.5526 | 4500 | 0.0412          |
+| 0.2348        | 2.6093 | 4600 | 0.0406          |
+| 0.2125        | 2.6660 | 4700 | 0.0403          |
+| 0.3172        | 2.7228 | 4800 | 0.0385          |
+| 0.2315        | 2.7795 | 4900 | 0.0382          |
+| 0.2707        | 2.8362 | 5000 | 0.0385          |
+| 0.2391        | 2.8930 | 5100 | 0.0373          |
+| 0.2979        | 2.9497 | 5200 | 0.0372          |
+| 0.2933        | 3.0062 | 5300 | 0.0362          |
+| 0.2388        | 3.0630 | 5400 | 0.0357          |
+| 0.2525        | 3.1197 | 5500 | 0.0364          |
+| 0.2563        | 3.1764 | 5600 | 0.0359          |
+| 0.2534        | 3.2332 | 5700 | 0.0354          |
+| 0.2401        | 3.2899 | 5800 | 0.0344          |
+| 0.2116        | 3.3466 | 5900 | 0.0340          |
+| 0.2713        | 3.4034 | 6000 | 0.0340          |
+| 0.2351        | 3.4601 | 6100 | 0.0333          |
+| 0.1471        | 3.5168 | 6200 | 0.0335          |
+| 0.2209        | 3.5736 | 6300 | 0.0326          |
+| 0.2206        | 3.6303 | 6400 | 0.0324          |
+| 0.2208        | 3.6870 | 6500 | 0.0316          |
+| 0.2329        | 3.7438 | 6600 | 0.0316          |
+| 0.1439        | 3.8005 | 6700 | 0.0312          |
+| 0.2335        | 3.8572 | 6800 | 0.0315          |
+| 0.1582        | 3.9140 | 6900 | 0.0312          |
+| 0.2298        | 3.9707 | 7000 | 0.0305          |
+| 0.1649        | 4.0272 | 7100 | 0.0309          |
+| 0.1489        | 4.0840 | 7200 | 0.0304          |
+| 0.1729        | 4.1407 | 7300 | 0.0304          |
+| 0.1907        | 4.1974 | 7400 | 0.0297          |
+| 0.2           | 4.2542 | 7500 | 0.0298          |
+| 0.1776        | 4.3109 | 7600 | 0.0296          |
+| 0.1955        | 4.3676 | 7700 | 0.0292          |
+| 0.1838        | 4.4244 | 7800 | 0.0295          |
+| 0.1685        | 4.4811 | 7900 | 0.0292          |
+| 0.161         | 4.5378 | 8000 | 0.0300          |
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,193 @@
+{
+  "_name_or_path": "facebook/nougat-base",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_attn_implementation_autoset": false,
+    "_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": 10,
+    "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": 4096,
+    "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": false,
+    "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": 50000
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_attn_implementation_autoset": false,
+    "_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": [
+      896,
+      672
+    ],
+    "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,
+    "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": 7
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0"
+}

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": "4.47.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3849a2405bfbb42310c026c2bbd98c02f4ff6da4ee06ccd72cbfd418d18c6ab
+size 697843112

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "do_align_long_axis": false,
+  "do_crop_margin": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_thumbnail": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "NougatImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "processor_class": "NougatProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 896,
+    "width": 672
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55d96f2b7de51106c8daeac9e4f76567fa44336c14db287d5015285eb420b78
+size 5624