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-large
+tags:
+- generated_from_trainer
+model-index:
+- name: xlm_r_large-baseline_model-v2-fallen-oath-3
+  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_large-baseline_model-v2-fallen-oath-3
+
+This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5036
+- Precision 0: 0.8766
+- Precision 1: 0.7911
+- Recall 0: 0.8512
+- Recall 1: 0.8246
+- F1 0: 0.8637
+- F1 1: 0.8075
+- Precision Weighted: 0.8419
+- Recall Weighted: 0.8404
+- F1 Weighted: 0.8409
+- F1 Macro: 0.8356
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-----------:|:-----------:|:--------:|:--------:|:------:|:------:|:------------------:|:---------------:|:-----------:|:--------:|
+| 0.4937        | 1.0   | 469  | 0.4268          | 0.8346      | 0.7933      | 0.8667   | 0.7488   | 0.8503 | 0.7704 | 0.8179             | 0.8188          | 0.8179      | 0.8104   |
+| 0.3945        | 2.0   | 938  | 0.3987          | 0.9083      | 0.7168      | 0.7603   | 0.8877   | 0.8277 | 0.7931 | 0.8305             | 0.812           | 0.8137      | 0.8104   |
+| 0.3721        | 3.0   | 1407 | 0.3612          | 0.8654      | 0.7992      | 0.8620   | 0.8039   | 0.8637 | 0.8016 | 0.8386             | 0.8384          | 0.8385      | 0.8326   |
+| 0.2721        | 4.0   | 1876 | 0.4191          | 0.8514      | 0.8246      | 0.8875   | 0.7734   | 0.8691 | 0.7982 | 0.8405             | 0.8412          | 0.8403      | 0.8336   |
+| 0.2144        | 5.0   | 2345 | 0.5036          | 0.8766      | 0.7911      | 0.8512   | 0.8246   | 0.8637 | 0.8075 | 0.8419             | 0.8404          | 0.8409      | 0.8356   |
+
+
+### 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-large",
+  "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": 1024,
+  "id2label": {
+    "0": "NOT",
+    "1": "OFF"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "NOT": 0,
+    "OFF": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "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 sha256:45a9aebb527d9d20eb1e1f09d9e3c0a7d223924cf68a10037ee998b37e7981ef
+size 2239618672

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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

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 sha256:78ae725a3170c4f8a0f473b14ab74e60d9183a36b4975d509e1b638f2f16dddf
+size 5176