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 +1,72 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: xlm_r_base-finetuned_after_mrp-v2-lilac-water-12
+  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. -->
+
+# xlm_r_base-finetuned_after_mrp-v2-lilac-water-12
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4879
+- Precision 0: 0.8632
+- Precision 1: 0.8038
+- Recall 0: 0.8667
+- Recall 1: 0.7990
+- F1 0: 0.8649
+- F1 1: 0.8014
+- Precision Weighted: 0.8391
+- Recall Weighted: 0.8392
+- F1 Weighted: 0.8391
+- F1 Macro: 0.8332
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision 0 | Precision 1 | Recall 0 | Recall 1 | F1 0   | F1 1   | Precision Weighted | Recall Weighted | F1 Weighted | F1 Macro |
+|:-------------:|:-----:|:----:|:---------------:|:-----------:|:-----------:|:--------:|:--------:|:------:|:------:|:------------------:|:---------------:|:-----------:|:--------:|
+| 0.5884        | 1.0   | 469  | 0.4450          | 0.8408      | 0.7812      | 0.8539   | 0.7635   | 0.8473 | 0.7723 | 0.8167             | 0.8172          | 0.8169      | 0.8098   |
+| 0.3866        | 2.0   | 938  | 0.4053          | 0.8801      | 0.7518      | 0.8108   | 0.8384   | 0.8440 | 0.7927 | 0.8280             | 0.822           | 0.8232      | 0.8184   |
+| 0.3641        | 3.0   | 1407 | 0.3683          | 0.8583      | 0.8091      | 0.8727   | 0.7892   | 0.8654 | 0.7990 | 0.8383             | 0.8388          | 0.8385      | 0.8322   |
+| 0.282         | 4.0   | 1876 | 0.3963          | 0.8551      | 0.8096      | 0.8741   | 0.7833   | 0.8645 | 0.7962 | 0.8366             | 0.8372          | 0.8367      | 0.8303   |
+| 0.2128        | 5.0   | 2345 | 0.4879          | 0.8632      | 0.8038      | 0.8667   | 0.7990   | 0.8649 | 0.8014 | 0.8391             | 0.8392          | 0.8391      | 0.8332   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "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": "NOT",
+    "1": "OFF"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "NOT": 0,
+    "OFF": 1
+  },
+  "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": "4.41.2",
+  "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:c0c6dfe05d6c3637e4156a7bfe6c822761dbcb62acae8fb2f94bb5bb90bc1a7a
+size 1112205008

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 sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

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 sha256:9ab1e48c6acc100f3688d9ee261c73b7060129f913edae4e9235cd3fc6bea655
+size 5176