Training in progress, step 500

config.json

@@ -1,19 +1,18 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-base",
+  "_name_or_path": "microsoft/deberta-base",
   "architectures": [
-    "DebertaV2ForSequenceClassification"
+    "DebertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.5,
+  "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",
-  "norm_rel_ebd": "layer_norm",
+  "model_type": "deberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
@@ -21,15 +20,13 @@
   "pooler_hidden_act": "gelu",
   "pooler_hidden_size": 768,
   "pos_att_type": [
-    "p2c",
-    "c2p"
+    "c2p",
+    "p2c"
   ],
   "position_biased_input": false,
-  "position_buckets": 256,
   "relative_attention": true,
-  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "type_vocab_size": 0,
-  "vocab_size": 128100
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9358a218e195688b2f72a65b7087541ded007e795104da5273f27e2748be45e9
-size 737719272
+oid sha256:81a811373d71a471d22d7cea034ae8a19a8cc507303316508cc4fb6e20ffd981
+size 556799560

runs/Sep23_16-29-48_a16eb3d641a3/events.out.tfevents.1727109707.a16eb3d641a3.49815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ee0a5ee52783aa105939e2537c2fb817a9a7e9ebef2284f0ccdd9e891cf46e
+size 5260

special_tokens_map.json

@@ -1,14 +1,50 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",
@@ -27,15 +29,15 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128000": {
+    "50264": {
       "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
+      "lstrip": true,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -46,13 +48,12 @@
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "eos_token": "[SEP]",
+  "errors": "replace",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
+  "tokenizer_class": "DebertaTokenizer",
   "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "vocab_type": "gpt2"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72f4139238133a80cbfc330dc2e31535e9986ad52757cd7e6f7dd5de9ebb23ce
+oid sha256:7afbf407859500c10b4d161baf41f91a3339cb014b4acbd00d16bfc01339e1c3
 size 5240