LiLT-RE-FR

.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: 0.3126
+- Recall: 0.6777
+- F1: 0.4278
+- Loss: 0.5651
+
+## 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 |
+|:-------------:|:------:|:-----:|:------:|:---------------:|:---------:|:------:|
+| 0.2058        | 19.23  | 500   | 0      | 0.2763          | 0         | 0      |
+| 0.145         | 38.46  | 1000  | 0.0623 | 0.2325          | 0.2889    | 0.0349 |
+| 0.1441        | 57.69  | 1500  | 0.1232 | 0.2306          | 0.2616    | 0.0806 |
+| 0.0902        | 76.92  | 2000  | 0.2645 | 0.2439          | 0.2526    | 0.2775 |
+| 0.0768        | 96.15  | 2500  | 0.3176 | 0.3033          | 0.2440    | 0.4548 |
+| 0.0707        | 115.38 | 3000  | 0.3472 | 0.3333          | 0.2778    | 0.4628 |
+| 0.0649        | 134.62 | 3500  | 0.3509 | 0.3677          | 0.2629    | 0.5273 |
+| 0.0257        | 153.85 | 4000  | 0.3705 | 0.4219          | 0.2810    | 0.5434 |
+| 0.054         | 173.08 | 4500  | 0.3699 | 0.4440          | 0.2729    | 0.5739 |
+| 0.0368        | 192.31 | 5000  | 0.3942 | 0.4843          | 0.3005    | 0.5730 |
+| 0.0326        | 211.54 | 5500  | 0.3968 | 0.4651          | 0.2952    | 0.6052 |
+| 0.0412        | 230.77 | 6000  | 0.4100 | 0.5386          | 0.3018    | 0.6392 |
+| 0.0603        | 250.0  | 6500  | 0.4189 | 0.4957          | 0.3068    | 0.6598 |
+| 0.0215        | 269.23 | 7000  | 0.4127 | 0.4768          | 0.2999    | 0.6616 |
+| 0.0233        | 288.46 | 7500  | 0.4284 | 0.5245          | 0.3183    | 0.6553 |
+| 0.0212        | 307.69 | 8000  | 0.4259 | 0.5424          | 0.3091    | 0.6849 |
+| 0.0152        | 326.92 | 8500  | 0.4206 | 0.5655          | 0.3073    | 0.6661 |
+| 0.0147        | 346.15 | 9000  | 0.4260 | 0.5630          | 0.3123    | 0.6697 |
+| 0.0205        | 365.38 | 9500  | 0.4321 | 0.5389          | 0.3174    | 0.6768 |
+| 0.0115        | 384.62 | 10000 | 0.4278 | 0.5651          | 0.3126    | 0.6777 |
+
+
+### 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 sha256:31a3a9ac99871d99092dc633ae2f7fda1c9129740342b5210fa958349e74dc6c
+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 sha256:494d5ddc97e490ab3c18df419c52a3940ea05c85eb3be7db4f294d011e531a90
+size 4984