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 +1,79 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: metadata-cls-no-gov-8k-vnnic-xml
+  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. -->
+
+# metadata-cls-no-gov-8k-vnnic-xml
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3308
+- Accuracy: 0.9345
+- F1: 0.7072
+
+## 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: 2e-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: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.5703 | 150  | 0.2151          | 0.9411   | 0.4945 |
+| 0.5567        | 1.1407 | 300  | 0.2789          | 0.9121   | 0.4579 |
+| 0.5567        | 1.7110 | 450  | 0.2676          | 0.9130   | 0.6930 |
+| 0.2703        | 2.2814 | 600  | 0.1926          | 0.9345   | 0.7071 |
+| 0.2703        | 2.8517 | 750  | 0.1984          | 0.9411   | 0.7390 |
+| 0.2055        | 3.4221 | 900  | 0.2503          | 0.9205   | 0.6689 |
+| 0.1573        | 3.9924 | 1050 | 0.1895          | 0.9476   | 0.7332 |
+| 0.1573        | 4.5627 | 1200 | 0.3001          | 0.9130   | 0.6974 |
+| 0.1287        | 5.1331 | 1350 | 0.1834          | 0.9495   | 0.7302 |
+| 0.1287        | 5.7034 | 1500 | 0.2586          | 0.9429   | 0.7345 |
+| 0.1022        | 6.2738 | 1650 | 0.3486          | 0.9261   | 0.7055 |
+| 0.1022        | 6.8441 | 1800 | 0.3064          | 0.9317   | 0.7053 |
+| 0.085         | 7.4144 | 1950 | 0.3445          | 0.9308   | 0.7086 |
+| 0.0689        | 7.9848 | 2100 | 0.3342          | 0.9336   | 0.7130 |
+| 0.0689        | 8.5551 | 2250 | 0.3272          | 0.9345   | 0.7074 |
+| 0.0525        | 9.1255 | 2400 | 0.3391          | 0.9345   | 0.7030 |
+| 0.0525        | 9.6958 | 2550 | 0.3308          | 0.9345   | 0.7072 |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "FacebookAI/xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "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",
+  "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:de3fac99a1daa2f0f750008c0319919b5db4eff15817fa76d1f09520d4c09dd7
+size 1112214236

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 sha256:252c24077824973279b663c6de6704d54e0ef405be31a583c1b304059a6bdbde
+size 17082987

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:abc6cbf16b6920dcaeac548a949995b8e929a8d93b91d5f495bd41ed3b67988f
+size 5176