deberta and replace linear with conv depth wise

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "checkpoints/deberta-vie-small-3",
+  "architectures": [
+    "DebertaV2ForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "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-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": null,
+  "position_biased_input": true,
+  "relative_attention": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.1",
+  "type_vocab_size": 0,
+  "vocab_size": 40030
+}

deberta_train.log

@@ -0,0 +1,7 @@
+    DATASET: corpus_v1_10000000 | Model: deberta-vie-small
+>>> Train Epochs: 1 | Losses: 2.423206581025543 | lr: 0.00013761917313292747
+>>> Eval Epochs:  1 | Losses: 1.8951771660055028 | Perplexity: 6.673118307905794
+>>> Train Epochs: 2 | Losses: 1.8172417448716809 | lr: 6.880958656646373e-05
+>>> Eval Epochs:  2 | Losses: 1.6318174320577783 | Perplexity: 5.106666322469493
+>>> Train Epochs: 3 | Losses: 1.6091945579320812 | lr: 0.0
+>>> Eval Epochs:  3 | Losses: 1.487273468930144 | Perplexity: 4.307366906292279

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49c32945d0e7ae1871a591cba2ae36a7a0b32d3ee9a23ad4ec2495d8f95b560
+size 297229737

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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "name_or_path": "checkpoints/deberta-vie-small-3",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartphoTokenizer",
+  "unk_token": "<unk>"
+}