LiLT-RE-ES

.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 +1,86 @@
+---
+license: mit
+base_model: nielsr/lilt-xlm-roberta-base
+tags:
+- generated_from_trainer
+datasets:
+- xfun
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: checkpoints
+  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. -->
+
+# checkpoints
+
+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:
+- Precision: 0.3111
+- Recall: 0.5225
+- F1: 0.3900
+- Loss: 0.1579
+
+## 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: 1e-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
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch  | Step  | F1     | Validation Loss | Precision | Recall |
+|:-------------:|:------:|:-----:|:------:|:---------------:|:---------:|:------:|
+| 0.2077        | 16.13  | 500   | 0      | 0.2127          | 0         | 0      |
+| 0.1792        | 32.26  | 1000  | 0.2520 | 0.1668          | 0.2345    | 0.2723 |
+| 0.1063        | 48.39  | 1500  | 0.2491 | 0.1439          | 0.5851    | 0.1582 |
+| 0.1147        | 64.52  | 2000  | 0.3900 | 0.1579          | 0.3111    | 0.5225 |
+| 0.0718        | 80.65  | 2500  | 0.4216 | 0.2598          | 0.3328    | 0.5753 |
+| 0.0503        | 96.77  | 3000  | 0.4471 | 0.1888          | 0.3563    | 0.6002 |
+| 0.0823        | 112.9  | 3500  | 0.4302 | 0.2690          | 0.3157    | 0.6750 |
+| 0.0586        | 129.03 | 4000  | 0.4360 | 0.2429          | 0.3211    | 0.6788 |
+| 0.0604        | 145.16 | 4500  | 0.4578 | 0.2745          | 0.3503    | 0.6606 |
+| 0.0603        | 161.29 | 5000  | 0.4630 | 0.2694          | 0.3483    | 0.6903 |
+| 0.0434        | 177.42 | 5500  | 0.4575 | 0.3200          | 0.3417    | 0.6922 |
+| 0.0367        | 193.55 | 6000  | 0.4523 | 0.2991          | 0.3321    | 0.7085 |
+| 0.0402        | 209.68 | 6500  | 0.4664 | 0.2628          | 0.3507    | 0.6961 |
+| 0.027         | 225.81 | 7000  | 0.4671 | 0.3375          | 0.3495    | 0.7037 |
+| 0.0363        | 241.94 | 7500  | 0.3445 | 0.7018          | 0.4621    | 0.3380 |
+| 0.0411        | 258.06 | 8000  | 0.3641 | 0.6769          | 0.4735    | 0.2984 |
+| 0.0348        | 274.19 | 8500  | 0.3530 | 0.6951          | 0.4682    | 0.3455 |
+| 0.0031        | 290.32 | 9000  | 0.3510 | 0.6999          | 0.4675    | 0.3841 |
+| 0.0259        | 306.45 | 9500  | 0.3532 | 0.6989          | 0.4693    | 0.3586 |
+| 0.0129        | 322.58 | 10000 | 0.3513 | 0.7009          | 0.4680    | 0.3604 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "nielsr/lilt-xlm-roberta-base",
+  "architectures": [
+    "LiLTRobertaLikeForRelationExtraction"
+  ],
+  "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,
+  "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": "4.38.2",
+  "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:dbb9fe2b6cc17ec9dad47315bbb55229d37e647982dad4d7dc55e87be4182e48
+size 1147300280

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 +1,54 @@
+{
+  "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 sha256:625f93eadca6edddbac6ec39f1d99f7e7c7ae10016489b131d1d06a30386a405
+size 5048