first commit

README.md

@@ -0,0 +1,14 @@
+Run with:
+```
+export WANDB_PROJECT=wangchanberta-qa
+export MODEL_NAME=airesearchth/wangchanberta-base-wiki-20210520-spm
+CUDA_LAUNCH_BLOCKING=1 python train_question_answering_lm_finetuning.py \
+  --model_name $MODEL_NAME \
+  --revision main@ckp-25000 \
+  --dataset_name iapp_thaiqa \
+  --output_dir $MODEL_NAME-finetune-iapp_thaiqa-model \
+  --log_dir $MODEL_NAME-finetune-iapp_thaiqa-log \
+  --model_max_length 400 \
+  --pad_on_right \
+  --fp16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "airesearchth/wangchanberta-base-wiki-20210520-spm-finetune-iapp_thaiqa-model/checkpoint-3058",
+  "architectures": [
+    "CamembertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_head": 12,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.4.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 24005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244e2f7ff245f1a72e8c667616424eb49b1b51d19a80097a9fb370f3a806ac67
+size 415639223

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2059a7452cb4f0254070b2d4f810daf1027dda9329c3f8bbadfa2bcc55a8282e
+size 872531

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED", "▁"]}

tokenizer_config.json

@@ -0,0 +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"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED", "▁"], "model_max_length": 400, "special_tokens_map_file": null, "name_or_path": "airesearchth/wangchanberta-base-wiki-20210520-spm"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f9a63be556d58823da5a62221f362c8c833d80d5cd22e68cd48ac9fbd32933b
+size 2415