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 +1,85 @@
+---
+license: mit
+base_model: nielsr/lilt-xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: LiLT-SER-EN
+  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. -->
+
+# LiLT-SER-EN
+
+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: 2.3960
+- Precision: 0.7248
+- Recall: 0.7458
+- F1: 0.7351
+- Accuracy: 0.7438
+
+## 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: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0832        | 6.67   | 500   | 1.0009          | 0.6741    | 0.6923 | 0.6831 | 0.7292   |
+| 0.052         | 13.33  | 1000  | 1.4186          | 0.7225    | 0.7320 | 0.7272 | 0.7441   |
+| 0.0027        | 20.0   | 1500  | 1.5508          | 0.7218    | 0.7376 | 0.7297 | 0.7464   |
+| 0.0034        | 26.67  | 2000  | 1.7198          | 0.7051    | 0.7382 | 0.7213 | 0.7422   |
+| 0.002         | 33.33  | 2500  | 1.8116          | 0.7106    | 0.7392 | 0.7246 | 0.7424   |
+| 0.0002        | 40.0   | 3000  | 1.8843          | 0.6769    | 0.7514 | 0.7122 | 0.7435   |
+| 0.0009        | 46.67  | 3500  | 1.9528          | 0.7401    | 0.7514 | 0.7457 | 0.7518   |
+| 0.0224        | 53.33  | 4000  | 2.0602          | 0.7178    | 0.7529 | 0.7350 | 0.7476   |
+| 0.0002        | 60.0   | 4500  | 2.2901          | 0.7283    | 0.7509 | 0.7394 | 0.7287   |
+| 0.0001        | 66.67  | 5000  | 2.1746          | 0.7198    | 0.7433 | 0.7313 | 0.7371   |
+| 0.0001        | 73.33  | 5500  | 1.9452          | 0.7214    | 0.7387 | 0.7299 | 0.7641   |
+| 0.0           | 80.0   | 6000  | 2.0976          | 0.7350    | 0.7560 | 0.7454 | 0.7442   |
+| 0.0021        | 86.67  | 6500  | 2.3034          | 0.7200    | 0.7387 | 0.7292 | 0.7365   |
+| 0.0           | 93.33  | 7000  | 2.2409          | 0.7348    | 0.7636 | 0.7489 | 0.7499   |
+| 0.0           | 100.0  | 7500  | 2.2742          | 0.7362    | 0.7193 | 0.7276 | 0.7472   |
+| 0.0           | 106.67 | 8000  | 2.4953          | 0.7312    | 0.7509 | 0.7409 | 0.7363   |
+| 0.0           | 113.33 | 8500  | 2.4936          | 0.7340    | 0.7438 | 0.7389 | 0.7396   |
+| 0.0           | 120.0  | 9000  | 2.3976          | 0.7239    | 0.7453 | 0.7344 | 0.7440   |
+| 0.0001        | 126.67 | 9500  | 2.3723          | 0.7282    | 0.7478 | 0.7379 | 0.7441   |
+| 0.0           | 133.33 | 10000 | 2.3960          | 0.7248    | 0.7458 | 0.7351 | 0.7438   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1

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": "O",
+    "1": "B-HEADER",
+    "2": "I-HEADER",
+    "3": "B-QUESTION",
+    "4": "I-QUESTION",
+    "5": "B-ANSWER",
+    "6": "I-ANSWER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANSWER": 5,
+    "B-HEADER": 1,
+    "B-QUESTION": 3,
+    "I-ANSWER": 6,
+    "I-HEADER": 2,
+    "I-QUESTION": 4,
+    "O": 0
+  },
+  "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": "4.35.2",
+  "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 sha256:3e94082fef7b04f3ebc28411b79fb66da630178f912e938463f2f961614e3db3
+size 1134319924

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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>",
+  "max_length": 512,
+  "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 sha256:7cc3668a3cc85ae03767121cd2b67e5b17140d6f67cc269e712e3cbf026f5c78
+size 4728