Training in progress, step 5

config.json

@@ -1,12 +1,10 @@
 {
-  "_name_or_path": "allenai/biomed_roberta_base",
+  "_name_or_path": "KISTI-AI/Scideberta-full",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
+  "attention_head_size": 64,
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -18,17 +16,28 @@
   "label2id": {
     "LABEL_0": 0
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "problem_type": "regression",
+  "pad_token_id": 0,
+  "padding_idx": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.42.3",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03adab69754c548e09bd4a8c50a413e4934ba8ed697beec631fdbb7b2844a71
-size 498609748
+oid sha256:6a33be2d91be8389d4e73ceb50fce4e2e00409e2f14b61fa833f56a58d7085fc
+size 737716196

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65336245f3b1d34b203e487327f728ab73991107d39ab49416974729ba1a07e7
+oid sha256:3b47617641608005be9f517273e98ede48e4a6f000a71e65f6d1bfa1aaacf08a
 size 5176