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 +1,66 @@
+---
+license: mit
+base_model: am-infoweb/QA_SYNTH_DATA_WITH_UNANSWERABLE_23_AUG_xlm_roberta-base
+tags:
+- generated_from_trainer
+model-index:
+- name: QA_SYNTH_DATA_WITH_UNANSWERABLE_23_AUG_xlm_FNETUNE_1.0
+  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. -->
+
+# QA_SYNTH_DATA_WITH_UNANSWERABLE_23_AUG_xlm_FNETUNE_1.0
+
+This model is a fine-tuned version of [am-infoweb/QA_SYNTH_DATA_WITH_UNANSWERABLE_23_AUG_xlm_roberta-base](https://huggingface.co/am-infoweb/QA_SYNTH_DATA_WITH_UNANSWERABLE_23_AUG_xlm_roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0000
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 188  | 0.0000          |
+| No log        | 2.0   | 376  | 0.0000          |
+| 0.2453        | 3.0   | 564  | 0.0000          |
+| 0.2453        | 4.0   | 752  | 0.0000          |
+| 0.2453        | 5.0   | 940  | 0.0000          |
+| 0.0002        | 6.0   | 1128 | 0.0000          |
+| 0.0002        | 7.0   | 1316 | 0.0000          |
+| 0.0           | 8.0   | 1504 | 0.0000          |
+| 0.0           | 9.0   | 1692 | 0.0000          |
+| 0.0           | 10.0  | 1880 | 0.0000          |
+
+
+### Framework versions
+
+- Transformers 4.32.0.dev0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "am-infoweb/QA_SYNTH_DATA_WITH_UNANSWERABLE_23_AUG_xlm_roberta-base",
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "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 sha256:5ff9c30402cbe205b57862fd0e423931917c271d094e34b38ab8241e5361280d
+size 1109886697

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:da0622cea7b6d2fd81dcd20fd6816f8d0ff407f2677819e942bb5889d026c9a3
+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": 510,
+  "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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35faa38d110e18b087440870335a10a5a6c6c1899518d45c4a082311813343d4
+size 4091