Training completed!

.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 +1,84 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-large
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: xlm-roberta-large-en-15
+  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-large-en-15
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8635
+- F1: 0.0986
+
+## 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: 5e-05
+- train_batch_size: 10
+- eval_batch_size: 10
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 25
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.6633        | 1.0   | 2000  | 0.4470          | 0.6619 |
+| 0.4004        | 2.0   | 4000  | 0.4114          | 0.7385 |
+| 0.3302        | 3.0   | 6000  | 0.3452          | 0.7693 |
+| 0.6865        | 4.0   | 8000  | 1.4687          | 0.1242 |
+| 1.5637        | 5.0   | 10000 | 1.7529          | 0.0    |
+| 1.5523        | 6.0   | 12000 | 1.8619          | 0.0986 |
+| 1.5439        | 7.0   | 14000 | 1.7808          | 0.0986 |
+| 1.5551        | 8.0   | 16000 | 1.7549          | 0.0986 |
+| 1.5403        | 9.0   | 18000 | 1.8007          | 0.0986 |
+| 1.5366        | 10.0  | 20000 | 1.8351          | 0.0986 |
+| 1.5324        | 11.0  | 22000 | 1.8882          | 0.0986 |
+| 1.5291        | 12.0  | 24000 | 1.8566          | 0.0986 |
+| 1.5285        | 13.0  | 26000 | 1.8071          | 0.0986 |
+| 1.5273        | 14.0  | 28000 | 1.8546          | 0.0986 |
+| 1.5518        | 15.0  | 30000 | 1.6967          | 0.0    |
+| 1.5424        | 16.0  | 32000 | 1.8714          | 0.0965 |
+| 1.5356        | 17.0  | 34000 | 1.8270          | 0.0986 |
+| 1.5324        | 18.0  | 36000 | 1.8352          | 0.0986 |
+| 1.5286        | 19.0  | 38000 | 1.8234          | 0.0986 |
+| 1.5318        | 20.0  | 40000 | 1.8017          | 0.0986 |
+| 1.5285        | 21.0  | 42000 | 1.9042          | 0.0986 |
+| 1.528         | 22.0  | 44000 | 1.8549          | 0.0986 |
+| 1.5269        | 23.0  | 46000 | 1.8606          | 0.0986 |
+| 1.525         | 24.0  | 48000 | 1.8404          | 0.0986 |
+| 1.5243        | 25.0  | 50000 | 1.8635          | 0.0986 |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "FacebookAI/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": "4.40.1",
+  "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 sha256:3178672564cc47e6b2df07e982431a044815a7e338deb837a7c7a590ce903951
+size 2235440556

runs/May04_17-20-46_fd286b2d7a08/events.out.tfevents.1714843266.fd286b2d7a08.1917.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ee240b1774e7322791e1ff0b2da25b7182d8c73dec84e6c2a65774dc9aa4a40
+size 18744

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:eb0c1da01d43b7b150a2edea3f6c352c987d49b78b173926d74039583a0e91c5
+size 4984