Training in progress, step 500

config.json

@@ -1,35 +1,28 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-large",
+  "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-large-uncased-abstract",
   "architectures": [
-    "DebertaV2ForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 1024,
   "initializer_range": 0.02,
   "intermediate_size": 4096,
-  "layer_norm_eps": 1e-07,
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
+  "model_type": "bert",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
+  "output_past": true,
   "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1024,
-  "pos_att_type": [
-    "p2c",
-    "c2p"
-  ],
-  "position_biased_input": false,
-  "position_buckets": 256,
-  "relative_attention": true,
-  "share_att_key": true,
+  "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.26.0",
-  "type_vocab_size": 0,
-  "vocab_size": 128100
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cea72aad0037c513cd906e1cf46f9e634a9f99a76a67581a9e8a7b16893e3110
-size 1736194351
+oid sha256:b248ce617ef5e6e35acaf865a71fb764a418f05b40bdbe66865bff05976c5490
+size 1336507185

runs/Mar20_01-57-58_g002/1679273885.6293068/events.out.tfevents.1679273885.g002.189082.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afba8cf8b0a042e379f8cfe4a2a1f32dda2b4d599de79131d83767a45f105cc3
+size 5680

runs/Mar20_01-57-58_g002/events.out.tfevents.1679273885.g002.189082.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9717bc9a7556f366833995b1925b80eb52e75f805c888506a5daa85b01c499
+size 4050

special_tokens_map.json

@@ -1,7 +1,5 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

tokenizer_config.json

@@ -1,17 +1,16 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "microsoft/deberta-v3-large",
+  "name_or_path": "microsoft/BiomedNLP-PubMedBERT-large-uncased-abstract",
+  "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
   "special_tokens_map_file": null,
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f007bd5dd6b29c8b5637328b28dbbc23563841601a5be9e125a7c1862307c361
+oid sha256:b40f1673bab2022942080c2e359df4f8de328fe43ec253f4d45cae38e4d76254
 size 3503