trained with chimera_qa

README.md

@@ -5,19 +5,19 @@ widget:
 ---
 # xlm-roberta-base-finetune-qa
 
-Finetuning `xlm-roberta-base` with the training set of `iapp_wiki_qa_squad`, `thaiqa`, `xquad` (removed examples which have cosine similarity with validation and test examples over 0.8). Benchmarks shared on [wandb](https://wandb.ai/cstorm125/wangchanberta-qa) using validation and test sets of `iapp_wiki_qa_squad`.
-Trained with [thai2transformers](https://github.com/vistec-AI/thai2transformers/blob/dev/scripts/downstream/train_question_answering_lm_finetuning.py). Combined benchmark datasets downloadable at [vistec-ai/thai2transformers](https://github.com/vistec-AI/thai2transformers/releases/tag/qa-v0.2).
+Finetuning `xlm-roberta-base` with the training set of `iapp_wiki_qa_squad`, `thaiqa_squad`, and `nsc_qa` (removed examples which have cosine similarity with validation and test examples over 0.8; contexts of the latter two are trimmed to be around 300 `newmm` words). Benchmarks shared on [wandb](https://wandb.ai/cstorm125/wangchanberta-qa) using validation and test sets of `iapp_wiki_qa_squad`.
+Trained with [thai2transformers](https://github.com/vistec-AI/thai2transformers/blob/dev/scripts/downstream/train_question_answering_lm_finetuning.py).
 
-Run with:
+Train with:
 ```
 export WANDB_PROJECT=wangchanberta-qa
 
 export MODEL_NAME=xlm-roberta-base
-python train_question_answering_lm_finetuning.py \\
-  --model_name $MODEL_NAME \\
-  --dataset_name iapp_thaiqa_xquad \\
-  --output_dir $MODEL_NAME-finetune-iapp_thaiqa_xquad-model \\
-  --log_dir $MODEL_NAME-finetune-iapp_thaiqa_xquad-log \\
-  --pad_on_right \\
+python train_question_answering_lm_finetuning.py \
+  --model_name $MODEL_NAME \
+  --dataset_name chimera_qa \
+  --output_dir $MODEL_NAME-finetune-chimera_qa-model \
+  --log_dir $MODEL_NAME-finetune-chimera_qa-log \
+  --pad_on_right \
   --fp16
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "xlm-roberta-base-finetune-iapp_thaiqa-model/checkpoint-3350",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
     "XLMRobertaForQuestionAnswering"
   ],
@@ -20,7 +20,7 @@
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.4.0",
+  "transformers_version": "4.8.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 250002

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39206ca07e92f2abb020f9b0b7bc0d2b3b978b38a4568c6993a636d331364e3e
-size 1109908151
+oid sha256:faf558bd7a3dc268b2128c7d041f697825f4c27c5087de97b5d1dded0ed69132
+size 1109903089

tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 416, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base"}
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 416, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9764be17ae04c99819a5c5b2fc0b7ca9cf5d1ae62f4fe37c34b86521c9f552
-size 2351
+oid sha256:bd66a6c43756705178a5ff5b0af387c063b5043883bc3d7fb0f9aab8b717042c
+size 2671