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 +1,88 @@
+---
+library_name: transformers
+license: mit
+base_model: nielsr/lilt-xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: test
+  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. -->
+
+# test
+
+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: 1.6605
+- Precision: 0.7460
+- Recall: 0.7692
+- F1: 0.7575
+- Accuracy: 0.7526
+
+## 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
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.3333  | 100  | 1.0907          | 0.4971    | 0.6210 | 0.5522 | 0.5889   |
+| No log        | 2.6667  | 200  | 0.7374          | 0.6135    | 0.6857 | 0.6476 | 0.7475   |
+| No log        | 4.0     | 300  | 0.8119          | 0.6292    | 0.7193 | 0.6713 | 0.7490   |
+| No log        | 5.3333  | 400  | 0.8152          | 0.6930    | 0.7555 | 0.7229 | 0.7616   |
+| 0.6197        | 6.6667  | 500  | 0.9915          | 0.6824    | 0.7682 | 0.7227 | 0.7458   |
+| 0.6197        | 8.0     | 600  | 1.0589          | 0.6952    | 0.7809 | 0.7356 | 0.7680   |
+| 0.6197        | 9.3333  | 700  | 1.1514          | 0.7072    | 0.7285 | 0.7177 | 0.7456   |
+| 0.6197        | 10.6667 | 800  | 1.1828          | 0.7190    | 0.7652 | 0.7414 | 0.7625   |
+| 0.6197        | 12.0    | 900  | 1.2011          | 0.7301    | 0.7606 | 0.7450 | 0.7679   |
+| 0.0998        | 13.3333 | 1000 | 1.2323          | 0.7347    | 0.7662 | 0.7501 | 0.7622   |
+| 0.0998        | 14.6667 | 1100 | 1.3060          | 0.7413    | 0.7881 | 0.7640 | 0.7688   |
+| 0.0998        | 16.0    | 1200 | 1.3649          | 0.7337    | 0.7636 | 0.7484 | 0.7647   |
+| 0.0998        | 17.3333 | 1300 | 1.3661          | 0.7319    | 0.7789 | 0.7547 | 0.7685   |
+| 0.0998        | 18.6667 | 1400 | 1.4831          | 0.7386    | 0.7672 | 0.7526 | 0.7635   |
+| 0.0226        | 20.0    | 1500 | 1.4216          | 0.7299    | 0.7682 | 0.7486 | 0.7654   |
+| 0.0226        | 21.3333 | 1600 | 1.5146          | 0.7295    | 0.7733 | 0.7507 | 0.7539   |
+| 0.0226        | 22.6667 | 1700 | 1.6595          | 0.7398    | 0.7748 | 0.7569 | 0.7476   |
+| 0.0226        | 24.0    | 1800 | 1.5785          | 0.7609    | 0.7702 | 0.7656 | 0.7677   |
+| 0.0226        | 25.3333 | 1900 | 1.5824          | 0.7544    | 0.7886 | 0.7711 | 0.7587   |
+| 0.0057        | 26.6667 | 2000 | 1.6605          | 0.7460    | 0.7692 | 0.7575 | 0.7526   |
+| 0.0057        | 28.0    | 2100 | 1.6459          | 0.7396    | 0.7697 | 0.7544 | 0.7520   |
+| 0.0057        | 29.3333 | 2200 | 1.6605          | 0.7467    | 0.7748 | 0.7605 | 0.7541   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cpu
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,39 @@
+{
+  "_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,
+  "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:f22612f8f49d344402867f9bcb19b994117e9f521c4ae93efcdd59ba119bd6e7
+size 1134319924

runs/Sep25_12-53-03_SLKDFW01M5035/events.out.tfevents.1727286787.SLKDFW01M5035.51176.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a718a0c0e30856a702af2f788abb8308bcb4cf9aa8ac57251320d41353910756
+size 16729

runs/Sep25_12-53-03_SLKDFW01M5035/events.out.tfevents.1727296507.SLKDFW01M5035.51176.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:574c4934975a2de43631a48307694409eb9e8b1e72506a2186a2d3e3a4a1c90f
+size 560

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 sha256:1783df0a80fa458ffc8fe9ffdf5c3eb0b6cf05694340d613987b70b311105c4f
+size 5176