Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-base",
+  "_name_or_path": "deepset/deberta-v3-base-squad2",
   "architectures": [
     "DebertaV2ForQuestionAnswering"
   ],
@@ -9,10 +9,12 @@
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "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": 12,
   "num_hidden_layers": 12,
@@ -28,8 +30,12 @@
   "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": "4.38.1",
+  "transformers_version": "4.38.2",
   "type_vocab_size": 0,
   "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4e213e58e8eb029a2e5ddd629000d3039501126fad8cc2f7274c7a9c899aaf
+oid sha256:bcd35bf9e5c782fe58d3d76311262f6a84b00e7a470db5527e5b5f9d7690edee
 size 735356752

runs/Mar13_03-18-35_e0d8307554b3/events.out.tfevents.1710299916.e0d8307554b3.2373.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:160f82c6a08d1c37ad6b3bf6c0660ec86cc31a72afc4003b6df407b563579f43
+size 7308

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": 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
+  },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -27,7 +27,7 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -47,7 +47,7 @@
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 512,
   "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:d23e98028cd3145bcba23bd4d20ddde58a16e3fc86883f2cfdf5f95896e2c22b
+oid sha256:fa291a7dce4908efb5ed7e74ced642b06d65257ebab6644f5dc3be8ccb614dcf
 size 4920