Training in progress epoch 0

.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 +1,58 @@
+---
+license: mit
+base_model: vnktrmnb/xlm-roberta-base-FT-TyDiQA_AUQC
+tags:
+- generated_from_keras_callback
+model-index:
+- name: vnktrmnb/xlm-roberta-base-FT-TyDiQA_AUQC-FT-TyDiQA_AUQC
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# vnktrmnb/xlm-roberta-base-FT-TyDiQA_AUQC-FT-TyDiQA_AUQC
+
+This model is a fine-tuned version of [vnktrmnb/xlm-roberta-base-FT-TyDiQA_AUQC](https://huggingface.co/vnktrmnb/xlm-roberta-base-FT-TyDiQA_AUQC) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 0.7982
+- Train End Logits Accuracy: 0.7889
+- Train Start Logits Accuracy: 0.8252
+- Validation Loss: 0.4654
+- Validation End Logits Accuracy: 0.8587
+- Validation Start Logits Accuracy: 0.9119
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 9744, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
+- training_precision: float32
+
+### Training results
+
+| Train Loss | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
+|:----------:|:-------------------------:|:---------------------------:|:---------------:|:------------------------------:|:--------------------------------:|:-----:|
+| 0.7982     | 0.7889                    | 0.8252                      | 0.4654          | 0.8587                         | 0.9119                           | 0     |
+
+
+### Framework versions
+
+- Transformers 4.32.0
+- TensorFlow 2.12.0
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "vnktrmnb/xlm-roberta-base-FT-TyDiQA_AUQC",
+  "architectures": [
+    "XLMRobertaForQuestionAnswering"
+  ],
+  "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",
+  "transformers_version": "4.32.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

logs/train/events.out.tfevents.1692771749.7d0470c98178.316.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f35e2f771c8fa33677e3300f5244f01cf21281f57e9bb2606b4741ccb0dc7c1
+size 2753713

logs/validation/events.out.tfevents.1692772740.7d0470c98178.316.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce6eb213d1be2faa6c7abff759791fcb938fa7ac302ae5019ae2b6c8f706834e
+size 604

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>"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b445ada40cf51461016b32407c01c0e852845a17827f469422b8e2466ed67e98
+size 1110105320

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87df8b5822e8de40a826123aac6fcd969f604772ff7754eb334529840f8501bc
+size 17082925

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_length": 384,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 128,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "<unk>"
+}