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 @@
+---
+library_name: transformers
+license: mit
+base_model: FacebookAI/xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+model-index:
+- name: scandi-fine-web-cleaner
+  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. -->
+
+# scandi-fine-web-cleaner
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on the data-is-better-together/fineweb-c dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1816
+- Precision: 0.9524
+- Recall: 0.7018
+- F1: 0.8081
+- Auc Roc: 0.9648
+- Balanced Accuracy: 0.8480
+- Average Precision: 0.8906
+
+## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Auc Roc | Balanced Accuracy | Average Precision |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:-------:|:-----------------:|:-----------------:|
+| 0.3165        | 1.0   | 100  | 0.2333          | 0.95      | 0.6667 | 0.7835 | 0.8099  | 0.8304            | 0.7721            |
+| 0.1929        | 2.0   | 200  | 0.1359          | 0.9130    | 0.7368 | 0.8155 | 0.9778  | 0.8626            | 0.9105            |
+| 0.1775        | 3.0   | 300  | 0.2245          | 0.9268    | 0.6667 | 0.7755 | 0.9481  | 0.8290            | 0.8721            |
+| 0.1553        | 4.0   | 400  | 0.1816          | 0.9524    | 0.7018 | 0.8081 | 0.9648  | 0.8480            | 0.8906            |
+
+
+### Framework versions
+
+- Transformers 4.48.0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,37 @@
+{
+  "_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": "not_problematic",
+    "1": "problematic"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "false": 0,
+    "true": 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": "4.48.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fab6d66dae3bb936e449fc5d732439efda048b96ce368cc0022795edf93f162
+size 1112250158

runs/Jan10_14-24-47_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736515488.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.893.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6ba9a270da977d90c2251d9db32e10986bebe0bae8fcbf6a28ae5f08766250
+size 8022

runs/Jan10_14-24-47_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736515553.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.893.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef52a0bd0b6ee86984e61b663c73e57f8cee517e133305493fefbdea8ee00c8f
+size 681

runs/Jan10_14-29-10_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736515751.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.893.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e5287f699c8d4c02059f9f8f9a4671cabc4d9cdf398832c792260b2fed8902
+size 8009

runs/Jan10_14-29-10_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736515817.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.893.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b0c16a1897300aee7e4bab460bc3573e6b957705623136482054c7070ae32a
+size 681

runs/Jan10_14-40-38_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736516439.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.1275.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f4769c5e010301e314abe8d9ec39dc7788696c069e826d112dca256d047e2d
+size 10435

runs/Jan10_14-40-38_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736516522.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.1275.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e844731df923fb5c9a15ac879cee4fa4422bf896eccadee419628bd527e8836f
+size 681

runs/Jan10_14-44-21_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736516663.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.1641.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a6fa1a524de7d33bcb1505f31173b9eacfb98f0c96be3205310d8977e499ba
+size 8827

runs/Jan10_14-44-21_r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w/events.out.tfevents.1736516701.r-davanstrien-jupyterlab-g2s19v44-96dc5-71v4w.1641.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76cab8db36b449d0836337cb25adca5a75c98e60dfa613ba096b2f2745cc5bd2
+size 1274

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 +1,55 @@
+{
+  "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": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "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 sha256:4d98cdb25a741469bd14f562b804e9cfad51e7c63e1f3adeab9f111c1ecaaf2a
+size 5368