lilt-xlm-roberta-1

.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 +1,87 @@
+---
+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: 1.6527
+- Precision: 0.7393
+- Recall: 0.7759
+- F1: 0.7571
+- Accuracy: 0.7614
+
+## 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  | 0.9776          | 0.4894    | 0.6113 | 0.5436 | 0.6166   |
+| No log        | 2.6667  | 200  | 0.8649          | 0.6249    | 0.6296 | 0.6273 | 0.7231   |
+| No log        | 4.0     | 300  | 0.8745          | 0.6449    | 0.7392 | 0.6888 | 0.7326   |
+| No log        | 5.3333  | 400  | 0.9419          | 0.6292    | 0.7168 | 0.6702 | 0.7367   |
+| 0.6362        | 6.6667  | 500  | 0.9902          | 0.7090    | 0.7458 | 0.7269 | 0.7700   |
+| 0.6362        | 8.0     | 600  | 1.0048          | 0.7050    | 0.7315 | 0.7180 | 0.7614   |
+| 0.6362        | 9.3333  | 700  | 1.1327          | 0.6918    | 0.7305 | 0.7106 | 0.7568   |
+| 0.6362        | 10.6667 | 800  | 1.3954          | 0.6952    | 0.7366 | 0.7153 | 0.7333   |
+| 0.6362        | 12.0    | 900  | 1.2721          | 0.7002    | 0.7509 | 0.7247 | 0.7491   |
+| 0.1105        | 13.3333 | 1000 | 1.3422          | 0.7166    | 0.7356 | 0.7260 | 0.7521   |
+| 0.1105        | 14.6667 | 1100 | 1.3957          | 0.72      | 0.7427 | 0.7312 | 0.7605   |
+| 0.1105        | 16.0    | 1200 | 1.4581          | 0.7250    | 0.7519 | 0.7382 | 0.7608   |
+| 0.1105        | 17.3333 | 1300 | 1.4598          | 0.7459    | 0.7371 | 0.7415 | 0.7577   |
+| 0.1105        | 18.6667 | 1400 | 1.5542          | 0.7182    | 0.7504 | 0.7339 | 0.7497   |
+| 0.0271        | 20.0    | 1500 | 1.5411          | 0.7176    | 0.7779 | 0.7465 | 0.7549   |
+| 0.0271        | 21.3333 | 1600 | 1.6468          | 0.7251    | 0.7539 | 0.7393 | 0.7452   |
+| 0.0271        | 22.6667 | 1700 | 1.6821          | 0.7311    | 0.7550 | 0.7429 | 0.7487   |
+| 0.0271        | 24.0    | 1800 | 1.6220          | 0.7364    | 0.7499 | 0.7431 | 0.7585   |
+| 0.0271        | 25.3333 | 1900 | 1.6220          | 0.7403    | 0.7667 | 0.7533 | 0.7599   |
+| 0.0055        | 26.6667 | 2000 | 1.6161          | 0.7370    | 0.7682 | 0.7523 | 0.7687   |
+| 0.0055        | 28.0    | 2100 | 1.6683          | 0.7396    | 0.7713 | 0.7551 | 0.7599   |
+| 0.0055        | 29.3333 | 2200 | 1.6527          | 0.7393    | 0.7759 | 0.7571 | 0.7614   |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- 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": "4.41.0",
+  "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 sha256:7161fd1865270b3a1b2dcf48b3cfb6f144ad9f414985aefaa89518d3121f501e
+size 1134319924

runs/May23_06-54-21_142600b4fecf/events.out.tfevents.1716447273.142600b4fecf.3462.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebbffe79183779cbce7199db05195de1c74c048e6a2d54108b74ca0276002ab2
+size 16630

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 sha256:49d408cbea66f4f4378b28ea2c4a270244367bc182e1bce2b998bf6f1bbe209e
+size 5048