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 +1,106 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: xlm-roberta-base-finetuned
+  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-roberta-base-finetuned
+
+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: 0.2266
+- Accuracy: 0.9541
+- F1: 0.9542
+
+## 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
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|
+| No log        | 0.2327 | 200  | 0.2630          | 0.8904   | 0.8872 |
+| No log        | 0.4654 | 400  | 0.2128          | 0.9117   | 0.9129 |
+| No log        | 0.6981 | 600  | 0.1844          | 0.9308   | 0.9311 |
+| No log        | 0.9308 | 800  | 0.1673          | 0.9346   | 0.9346 |
+| No log        | 1.1635 | 1000 | 0.1735          | 0.9346   | 0.9338 |
+| No log        | 1.3962 | 1200 | 0.1440          | 0.9433   | 0.9429 |
+| No log        | 1.6289 | 1400 | 0.1443          | 0.9467   | 0.9469 |
+| No log        | 1.8615 | 1600 | 0.1357          | 0.9504   | 0.9507 |
+| 0.2197        | 2.0942 | 1800 | 0.1532          | 0.9469   | 0.9473 |
+| 0.2197        | 2.3269 | 2000 | 0.1478          | 0.9496   | 0.9500 |
+| 0.2197        | 2.5596 | 2200 | 0.1379          | 0.9501   | 0.9504 |
+| 0.2197        | 2.7923 | 2400 | 0.1381          | 0.9511   | 0.9514 |
+| 0.2197        | 3.0250 | 2600 | 0.1627          | 0.9493   | 0.9496 |
+| 0.2197        | 3.2577 | 2800 | 0.1596          | 0.9546   | 0.9546 |
+| 0.2197        | 3.4904 | 3000 | 0.1421          | 0.9526   | 0.9527 |
+| 0.2197        | 3.7231 | 3200 | 0.1459          | 0.9539   | 0.9539 |
+| 0.2197        | 3.9558 | 3400 | 0.1348          | 0.9495   | 0.9499 |
+| 0.1176        | 4.1885 | 3600 | 0.1519          | 0.9501   | 0.9507 |
+| 0.1176        | 4.4212 | 3800 | 0.1570          | 0.9525   | 0.9529 |
+| 0.1176        | 4.6539 | 4000 | 0.1367          | 0.9511   | 0.9514 |
+| 0.1176        | 4.8866 | 4200 | 0.1409          | 0.954    | 0.9541 |
+| 0.1176        | 5.1193 | 4400 | 0.1690          | 0.9539   | 0.9541 |
+| 0.1176        | 5.3519 | 4600 | 0.1757          | 0.9544   | 0.9545 |
+| 0.1176        | 5.5846 | 4800 | 0.1508          | 0.9513   | 0.9518 |
+| 0.1176        | 5.8173 | 5000 | 0.1537          | 0.9545   | 0.9546 |
+| 0.0849        | 6.0500 | 5200 | 0.1814          | 0.954    | 0.9540 |
+| 0.0849        | 6.2827 | 5400 | 0.1674          | 0.9543   | 0.9546 |
+| 0.0849        | 6.5154 | 5600 | 0.1923          | 0.9538   | 0.9539 |
+| 0.0849        | 6.7481 | 5800 | 0.1750          | 0.9543   | 0.9545 |
+| 0.0849        | 6.9808 | 6000 | 0.1890          | 0.9527   | 0.9529 |
+| 0.0849        | 7.2135 | 6200 | 0.1999          | 0.9547   | 0.9548 |
+| 0.0849        | 7.4462 | 6400 | 0.1722          | 0.9547   | 0.9549 |
+| 0.0849        | 7.6789 | 6600 | 0.1693          | 0.9524   | 0.9528 |
+| 0.0849        | 7.9116 | 6800 | 0.1848          | 0.9548   | 0.9549 |
+| 0.0614        | 8.1443 | 7000 | 0.2067          | 0.9554   | 0.9554 |
+| 0.0614        | 8.3770 | 7200 | 0.2073          | 0.9544   | 0.9546 |
+| 0.0614        | 8.6097 | 7400 | 0.1929          | 0.9547   | 0.9548 |
+| 0.0614        | 8.8424 | 7600 | 0.2081          | 0.9544   | 0.9545 |
+| 0.0614        | 9.0750 | 7800 | 0.2031          | 0.9541   | 0.9542 |
+| 0.0614        | 9.3077 | 8000 | 0.2232          | 0.9549   | 0.9552 |
+| 0.0614        | 9.5404 | 8200 | 0.2238          | 0.9544   | 0.9545 |
+| 0.0614        | 9.7731 | 8400 | 0.2266          | 0.9541   | 0.9542 |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,29 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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:bafc29e289cc0cee37d40154a12a765637a28d5ca550cbf455a57a2fc1555377
+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 sha256:883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
+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:f3df08d836c43b32f09ed99b729ec0e57f3b784b94ccf1ecddb8912137af8393
+size 5048