cstorm125 commited on
Commit
6bc2da7
1 Parent(s): 95882a6

first commit

Browse files
README.md ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Run with:
2
+ ```
3
+ export WANDB_PROJECT=wangchanberta-qa
4
+ export MODEL_NAME=airesearchth/wangchanberta-base-wiki-20210520-spm
5
+ CUDA_LAUNCH_BLOCKING=1 python train_question_answering_lm_finetuning.py \
6
+ --model_name $MODEL_NAME \
7
+ --revision main@ckp-25000 \
8
+ --dataset_name iapp_thaiqa \
9
+ --output_dir $MODEL_NAME-finetune-iapp_thaiqa-model \
10
+ --log_dir $MODEL_NAME-finetune-iapp_thaiqa-log \
11
+ --model_max_length 400 \
12
+ --pad_on_right \
13
+ --fp16
14
+ ```
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "airesearchth/wangchanberta-base-wiki-20210520-spm-finetune-iapp_thaiqa-model/checkpoint-3058",
3
+ "architectures": [
4
+ "CamembertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "camembert",
18
+ "num_attention_head": 12,
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "transformers_version": "4.4.0",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 24005
27
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244e2f7ff245f1a72e8c667616424eb49b1b51d19a80097a9fb370f3a806ac67
3
+ size 415639223
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2059a7452cb4f0254070b2d4f810daf1027dda9329c3f8bbadfa2bcc55a8282e
3
+ size 872531
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
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 ADDED
@@ -0,0 +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"}, "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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9a63be556d58823da5a62221f362c8c833d80d5cd22e68cd48ac9fbd32933b
3
+ size 2415