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

.gitignore

@@ -1,3 +1,3 @@
-*
-*.json
-!.gitignore
+# *
+# *.json
+# !.gitignore

README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+base_model: xlm-roberta-large
+tags:
+- generated_from_trainer
+model-index:
+- name: fine_tuned_XLMROBERTA_cs_wikann
+  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. -->
+
+# fine_tuned_XLMROBERTA_cs_wikann
+
+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: 0.1238
+- Overall Precision: 0.8962
+- Overall Recall: 0.9193
+- Overall F1: 0.9076
+- Overall Accuracy: 0.9684
+
+## 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
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.3625        | 0.4   | 500  | 0.1809          | 0.7915            | 0.8509         | 0.8201     | 0.9486           |
+| 0.1807        | 0.8   | 1000 | 0.1373          | 0.8363            | 0.8785         | 0.8568     | 0.9583           |
+| 0.1384        | 1.2   | 1500 | 0.1371          | 0.8758            | 0.9085         | 0.8918     | 0.9651           |
+| 0.1079        | 1.6   | 2000 | 0.1467          | 0.8924            | 0.9168         | 0.9044     | 0.9659           |
+| 0.0997        | 2.0   | 2500 | 0.1170          | 0.9018            | 0.9264         | 0.9139     | 0.9700           |
+| 0.0644        | 2.4   | 3000 | 0.1344          | 0.9123            | 0.9285         | 0.9203     | 0.9706           |
+| 0.0594        | 2.8   | 3500 | 0.1269          | 0.9138            | 0.9345         | 0.9240     | 0.9718           |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-LOC": 5,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "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:dd09fa201110d056da479b14b1129f7282c8edb220bcc420dc589e675504f988
+size 2235440556

runs/Dec13_02-41-07_n26/events.out.tfevents.1702431672.n26.81031.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1129ce5f9877fa60b7ab89844cf258785a36a84c7441d141d0c6589959f76f02
+size 9583

runs/Dec13_02-52-24_n26/events.out.tfevents.1702432347.n26.81031.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1726fa5ce7e0efcd1fd4e610962ce2832de720eaae83daee2be597e96cce076f
+size 5932

runs/Dec13_02-55-54_n26/events.out.tfevents.1702432556.n26.81674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b810b69f975eb710278b80c77bdde91084d22940b9994097f309bc1fcbf59fb6
+size 9591

runs/Dec13_02-55-54_n26/events.out.tfevents.1702433096.n26.81674.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe102b19696534326c5884e8e9d41b939a2a67a7ac788cdab988b8ae812c4bd
+size 544

runs/Dec26_19-04-22_n32/events.out.tfevents.1703613867.n32.1384543.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2b4fbb715c834474af544036c6cadd459cbcc09e7dd89b0f61ccce8522b936
+size 9593

runs/Dec26_19-04-22_n32/events.out.tfevents.1703615214.n32.1384543.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c088b1a2bc1c41d7c2be35b4092898e831c100ce5081819be27abe3c0c8ee8d
+size 1048

runs/Jan16_01-53-22_n25/events.out.tfevents.1705366426.n25.620727.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b37afb07a85605d16d5dcc029cf7c5404f572ae72c602f077cafd69c0772e6
+size 9630

runs/Jan16_01-53-22_n25/events.out.tfevents.1705367769.n25.620727.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff0c1083c10bd180fbb396238aceafce51f072d8b826c3c3b2bce16f14c8638
+size 1552

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:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

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 sha256:8a30c003ed329cd968cc7b555311e89954f12c145a30513142693b6cde2e58a5
+size 4728