bb42f39d03738ad65c86f4ce04257a663268a9104ef029601ef1cf7d33abeae1

.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 +1,90 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+datasets:
+- udpos28
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: 1a5e2b8e
+  results:
+  - task:
+      name: Token Classification
+      type: token-classification
+    dataset:
+      name: udpos28
+      type: udpos28
+      config: te
+      split: validation
+      args: te
+    metrics:
+    - name: Precision
+      type: precision
+      value: 0.894336015358501
+    - name: Recall
+      type: recall
+      value: 0.8576779328683283
+    - name: F1
+      type: f1
+      value: 0.8680916339670367
+    - name: Accuracy
+      type: accuracy
+      value: 0.947129909365559
+---
+
+<!-- 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. -->
+
+# 1a5e2b8e
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the udpos28 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3219
+- Precision: 0.8943
+- Recall: 0.8577
+- F1: 0.8681
+- Accuracy: 0.9471
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0423        | 7.58  | 1000 | 0.3219          | 0.8943    | 0.8577 | 0.8681 | 0.9471   |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 7.58,
+    "eval_accuracy": 0.947129909365559,
+    "eval_f1": 0.8680916339670367,
+    "eval_loss": 0.32186266779899597,
+    "eval_precision": 0.894336015358501,
+    "eval_recall": 0.8576779328683283,
+    "eval_runtime": 0.1421,
+    "eval_samples_per_second": 921.916,
+    "eval_steps_per_second": 119.638,
+    "train_loss": 0.2183959150314331,
+    "train_runtime": 129.8443,
+    "train_samples_per_second": 61.612,
+    "train_steps_per_second": 7.702
+}

config.json

@@ -0,0 +1,66 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "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": 768,
+  "id2label": {
+    "0": "ADJ",
+    "1": "ADP",
+    "2": "ADV",
+    "3": "AUX",
+    "4": "CCONJ",
+    "5": "DET",
+    "6": "INTJ",
+    "7": "NOUN",
+    "8": "NUM",
+    "9": "PART",
+    "10": "PRON",
+    "11": "PROPN",
+    "12": "PUNCT",
+    "13": "SCONJ",
+    "14": "SYM",
+    "15": "VERB",
+    "16": "X"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ADJ": 0,
+    "ADP": 1,
+    "ADV": 2,
+    "AUX": 3,
+    "CCONJ": 4,
+    "DET": 5,
+    "INTJ": 6,
+    "NOUN": 7,
+    "NUM": 8,
+    "PART": 9,
+    "PRON": 10,
+    "PROPN": 11,
+    "PUNCT": 12,
+    "SCONJ": 13,
+    "SYM": 14,
+    "VERB": 15,
+    "X": 16
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 7.58,
+    "eval_accuracy": 0.947129909365559,
+    "eval_f1": 0.8680916339670367,
+    "eval_loss": 0.32186266779899597,
+    "eval_precision": 0.894336015358501,
+    "eval_recall": 0.8576779328683283,
+    "eval_runtime": 0.1421,
+    "eval_samples_per_second": 921.916,
+    "eval_steps_per_second": 119.638
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d963c8d04f044c848671a93767bc76f4571d8c07bf227a4b041f13fbe9d588d1
+size 1109888564

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:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
+size 17082756

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_prefix_space": true,
+  "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>"
+}

train.args

@@ -0,0 +1 @@
+udpos --learning_rate=5e-5 --eval_steps=1000 --per_device_batch_size=10 --max_steps=1000 --multi --language_source te

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 7.58,
+    "train_loss": 0.2183959150314331,
+    "train_runtime": 129.8443,
+    "train_samples_per_second": 61.612,
+    "train_steps_per_second": 7.702
+}