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 +1,109 @@
+---
+license: mit
+base_model: nielsr/lilt-xlm-roberta-base
+tags:
+- generated_from_trainer
+datasets:
+- xfun
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: LiLT-SER-ES
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: xfun
+      type: xfun
+      config: xfun.es
+      split: validation
+      args: xfun.es
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.6718889883616831
+    - name: Recall
+      type: recall
+      value: 0.6733961417676088
+    - name: F1
+      type: f1
+      value: 0.6726417208155948
+    - name: Accuracy
+      type: accuracy
+      value: 0.7462640815388152
+---
+
+<!-- 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-ES
+
+This model is a fine-tuned version of [nielsr/lilt-xlm-roberta-base](https://huggingface.co/nielsr/lilt-xlm-roberta-base) on the xfun dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5588
+- Precision: 0.6719
+- Recall: 0.6734
+- F1: 0.6726
+- Accuracy: 0.7463
+
+## 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  | Accuracy | F1     | Validation Loss | Precision | Recall |
+|:-------------:|:------:|:-----:|:--------:|:------:|:---------------:|:---------:|:------:|
+| 0.2279        | 8.2    | 500   | 0.6790   | 0.5205 | 1.2508          | 0.4589    | 0.6012 |
+| 0.032         | 16.39  | 1000  | 0.6936   | 0.5885 | 1.9637          | 0.6321    | 0.5505 |
+| 0.0073        | 24.59  | 1500  | 0.7351   | 0.6175 | 1.6711          | 0.5795    | 0.6608 |
+| 0.0479        | 32.79  | 2000  | 0.7405   | 0.6422 | 1.8259          | 0.6265    | 0.6586 |
+| 0.0666        | 40.98  | 2500  | 0.7424   | 0.6349 | 1.8343          | 0.5937    | 0.6824 |
+| 0.0006        | 49.18  | 3000  | 0.7475   | 0.6536 | 2.0575          | 0.6512    | 0.6559 |
+| 0.0084        | 57.38  | 3500  | 0.7138   | 0.6415 | 2.4488          | 0.6758    | 0.6106 |
+| 0.0002        | 65.57  | 4000  | 0.7571   | 0.6468 | 1.9641          | 0.6406    | 0.6532 |
+| 0.0005        | 73.77  | 4500  | 2.2976   | 0.6699 | 0.6429          | 0.6561    | 0.7413 |
+| 0.0003        | 81.97  | 5000  | 2.1562   | 0.6287 | 0.6653          | 0.6465    | 0.7468 |
+| 0.0007        | 90.16  | 5500  | 2.2806   | 0.6435 | 0.6689          | 0.6560    | 0.7435 |
+| 0.0002        | 98.36  | 6000  | 2.0508   | 0.6294 | 0.6734          | 0.6506    | 0.7538 |
+| 0.0           | 106.56 | 6500  | 2.2626   | 0.6602 | 0.6765          | 0.6683    | 0.7498 |
+| 0.0           | 114.75 | 7000  | 2.3467   | 0.6687 | 0.6492          | 0.6588    | 0.7409 |
+| 0.0           | 122.95 | 7500  | 2.4430   | 0.6773 | 0.6734          | 0.6754    | 0.7447 |
+| 0.0           | 131.15 | 8000  | 2.3653   | 0.6643 | 0.6765          | 0.6704    | 0.7476 |
+| 0.0           | 139.34 | 8500  | 2.2903   | 0.6567 | 0.6824          | 0.6693    | 0.7498 |
+| 0.0           | 147.54 | 9000  | 2.4458   | 0.6536 | 0.6824          | 0.6677    | 0.7440 |
+| 0.0           | 155.74 | 9500  | 2.5953   | 0.6703 | 0.6685          | 0.6694    | 0.7423 |
+| 0.0           | 163.93 | 10000 | 2.5588   | 0.6719 | 0.6734          | 0.6726    | 0.7463 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- 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-QUESTION",
+    "2": "B-ANSWER",
+    "3": "B-HEADER",
+    "4": "I-ANSWER",
+    "5": "I-QUESTION",
+    "6": "I-HEADER"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-ANSWER": 2,
+    "B-HEADER": 3,
+    "B-QUESTION": 1,
+    "I-ANSWER": 4,
+    "I-HEADER": 6,
+    "I-QUESTION": 5,
+    "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": "4.38.2",
+  "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 sha256:7b8647b510d4efff290b553fdf257a7edfb55604ac3329e4ab1dd0c6dcbfafc1
+size 1134319924

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:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

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:a11e02474d1073755953278865f1929bd468a249613a6c62af4d35e56e863107
+size 5048