OSainz/mdt-ie-re-entity-pair

.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 +1,72 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: tmp
+  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. -->
+
+# tmp
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3272
+- Precision: 0.5560
+- Recall: 0.3209
+- F1: 0.4069
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
+| 0.7083        | 0.35  | 500  | 0.4423          | 0.2785    | 0.0529 | 0.0889 |
+| 0.4849        | 0.7   | 1000 | 0.4009          | 0.3623    | 0.1803 | 0.2408 |
+| 0.4021        | 1.04  | 1500 | 0.3621          | 0.5027    | 0.2212 | 0.3072 |
+| 0.3276        | 1.39  | 2000 | 0.3606          | 0.4006    | 0.3077 | 0.3481 |
+| 0.2857        | 1.74  | 2500 | 0.3432          | 0.5073    | 0.25   | 0.3349 |
+| 0.251         | 2.09  | 3000 | 0.3481          | 0.4431    | 0.3413 | 0.3856 |
+| 0.2184        | 2.43  | 3500 | 0.3309          | 0.5274    | 0.3353 | 0.4100 |
+| 0.2162        | 2.78  | 4000 | 0.3411          | 0.4167    | 0.3726 | 0.3934 |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "[/E1]": 250003,
+  "[/E2]": 250005,
+  "[E1]": 250002,
+  "[E2]": 250004
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForEntityPairClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "head_token": "[E1]",
+  "head_token_id": 250002,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "arg",
+    "1": "causes",
+    "2": "domain",
+    "3": "entails",
+    "4": "has-part",
+    "5": "has-property",
+    "6": "in-context",
+    "7": "in-place",
+    "8": "in-time",
+    "9": "is-a",
+    "10": "no_relation",
+    "11": "part-of",
+    "12": "subject",
+    "13": "target"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "arg": 0,
+    "causes": 1,
+    "domain": 2,
+    "entails": 3,
+    "has-part": 4,
+    "has-property": 5,
+    "in-context": 6,
+    "in-place": 7,
+    "in-time": 8,
+    "is-a": 9,
+    "no_relation": 10,
+    "part-of": 11,
+    "subject": 12,
+    "target": 13
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tail_token": "[E2]",
+  "tail_token_id": 250004,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250006
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a852a3340739af1e500f60b21e57d0aa58e90eb35d255d32d0746e367cb3d16e
+size 1114613472

runs/Feb19_09-10-13_a4027b53f756/events.out.tfevents.1708333814.a4027b53f756.3931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f8d9e5a9e786c9e47de2cff110f59f4cbee6a90828df7528f28eea822d29ba
+size 5036

runs/Feb19_09-11-16_a4027b53f756/events.out.tfevents.1708333884.a4027b53f756.3931.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcf3d82aac54ebbfe69164e0064e9509cc09b8a18240bef755137661626b498
+size 10006

runs/Feb19_09-11-16_a4027b53f756/events.out.tfevents.1708335102.a4027b53f756.3931.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41b552e0182add38d0099dfb5f8984cd1301bd702ca0eed1529deadcb5d511c
+size 508

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c64f894a9888ec9d193474397c28acc9154e070264bae25477f0385b12f2b8d
+size 17083580

tokenizer_config.json

@@ -0,0 +1,87 @@
+{
+  "add_prefix_space": true,
+  "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
+    },
+    "250002": {
+      "content": "[E1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250003": {
+      "content": "[/E1]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250004": {
+      "content": "[E2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "250005": {
+      "content": "[/E2]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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:b17f4f14c924f1c5d53637b7e698d2fdf1795498423b9fefffba0f32c605aa85
+size 4664