Training in progress, step 2000

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "deepset/deberta-v3-large-squad2",
+  "_name_or_path": "microsoft/deberta-v3-large",
   "architectures": [
     "DebertaV2ForSequenceClassification"
   ],
@@ -9,12 +9,10 @@
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
-  "language": "english",
   "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
-  "name": "DebertaV2",
   "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
@@ -30,10 +28,6 @@
   "position_buckets": 256,
   "relative_attention": true,
   "share_att_key": true,
-  "summary_activation": "tanh",
-  "summary_last_dropout": 0,
-  "summary_type": "first",
-  "summary_use_proj": false,
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
   "type_vocab_size": 0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f75a1c9b271dbfd83fe3f3a45bc2c585c690931fed3681f6da77669afb5040e8
+oid sha256:373f64094b692ca24fcf50605369ca343831862db141b363f3e8a6887e480d6e
 size 1740304440

special_tokens_map.json

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

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -27,7 +27,7 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -47,7 +47,7 @@
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e302f2a8fa0d4816c3623585465970b8fde2fd8410e414aad33349f657df21
+oid sha256:8074a8a806c7c6249a493d4304126540fe12a86de8e386abedebe2d9d2c69912
 size 5368