End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,92 @@
+---
+library_name: transformers
+license: mit
+base_model: nielsr/lilt-xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: output_LiLT_test_05
+  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. -->
+
+# output_LiLT_test_05
+
+This model is a fine-tuned version of [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1210
+- Precision: 0.8130
+- Recall: 0.8086
+- F1: 0.8108
+- Accuracy: 0.9647
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 300
+- num_epochs: 60
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 0.0808 | 100  | 0.6084          | 0.0053    | 0.0014 | 0.0023 | 0.8727   |
+| No log        | 0.1617 | 200  | 0.3137          | 0.2946    | 0.3010 | 0.2977 | 0.9036   |
+| No log        | 0.2425 | 300  | 0.2373          | 0.5717    | 0.6368 | 0.6025 | 0.9289   |
+| No log        | 0.3234 | 400  | 0.1952          | 0.7224    | 0.6518 | 0.6853 | 0.9473   |
+| 0.4203        | 0.4042 | 500  | 0.1695          | 0.7066    | 0.6936 | 0.7000 | 0.9491   |
+| 0.4203        | 0.4850 | 600  | 0.1826          | 0.6140    | 0.7420 | 0.6720 | 0.9371   |
+| 0.4203        | 0.5659 | 700  | 0.1806          | 0.6236    | 0.7818 | 0.6938 | 0.9407   |
+| 0.4203        | 0.6467 | 800  | 0.1706          | 0.6900    | 0.8201 | 0.7495 | 0.9511   |
+| 0.4203        | 0.7276 | 900  | 0.1551          | 0.7852    | 0.7567 | 0.7707 | 0.9588   |
+| 0.1009        | 0.8084 | 1000 | 0.1361          | 0.7655    | 0.7780 | 0.7717 | 0.9622   |
+| 0.1009        | 0.8892 | 1100 | 0.1439          | 0.7876    | 0.7697 | 0.7785 | 0.9601   |
+| 0.1009        | 0.9701 | 1200 | 0.1441          | 0.7775    | 0.7694 | 0.7734 | 0.9612   |
+| 0.1009        | 1.0509 | 1300 | 0.1282          | 0.7813    | 0.8158 | 0.7982 | 0.9643   |
+| 0.1009        | 1.1318 | 1400 | 0.1421          | 0.7794    | 0.8054 | 0.7922 | 0.9621   |
+| 0.0791        | 1.2126 | 1500 | 0.1557          | 0.7163    | 0.7780 | 0.7459 | 0.9528   |
+| 0.0791        | 1.2935 | 1600 | 0.1460          | 0.7489    | 0.7985 | 0.7729 | 0.9589   |
+| 0.0791        | 1.3743 | 1700 | 0.1343          | 0.7846    | 0.8031 | 0.7937 | 0.9621   |
+| 0.0791        | 1.4551 | 1800 | 0.1394          | 0.7944    | 0.7875 | 0.7910 | 0.9611   |
+| 0.0791        | 1.5360 | 1900 | 0.1504          | 0.7803    | 0.8066 | 0.7932 | 0.9631   |
+| 0.0652        | 1.6168 | 2000 | 0.1292          | 0.7615    | 0.8247 | 0.7919 | 0.9599   |
+| 0.0652        | 1.6977 | 2100 | 0.1298          | 0.7993    | 0.8115 | 0.8053 | 0.9644   |
+| 0.0652        | 1.7785 | 2200 | 0.1498          | 0.7394    | 0.8351 | 0.7844 | 0.9577   |
+| 0.0652        | 1.8593 | 2300 | 0.1319          | 0.7800    | 0.8086 | 0.7941 | 0.9618   |
+| 0.0652        | 1.9402 | 2400 | 0.1383          | 0.8145    | 0.7824 | 0.7981 | 0.9648   |
+| 0.0618        | 2.0210 | 2500 | 0.1210          | 0.8130    | 0.8086 | 0.8108 | 0.9647   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "nielsr/lilt-xlm-roberta-base",
+  "architectures": [
+    "LiltForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "channel_shrink_ratio": 4,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "suppVatId",
+    "1": "iban",
+    "2": "suppCompanyId",
+    "3": "O",
+    "4": "accountNumber",
+    "5": "bankCode",
+    "6": "constSymbol",
+    "7": "suppAddress",
+    "8": "suppName",
+    "9": "dueDate",
+    "10": "issueDate",
+    "11": "invoiceNumber",
+    "12": "taxPointDate",
+    "13": "specificSymbol",
+    "14": "totalPriceWithVat",
+    "15": "variableSymbol"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_2d_position_embeddings": 1024,
+  "max_position_embeddings": 514,
+  "model_type": "lilt",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe714a7be91fd5baf841b9716c35271e36448a60cdd0f10897cde56e51b83979
+size 1134347608

runs/Sep16_00-07-28_dcos10-neuron/events.out.tfevents.1726438059.dcos10-neuron.125857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c25d7c0668eee70493ca557def226e9a327cc4d635488703a0566610ab7d1934
+size 18631

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "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": false,
+    "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b414f109d7fbc439bdfab945954b9eda4902c453a48c40bc2656d647b87a47a3
+size 5176