Training in progress, epoch 1

added_tokens.json

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

config.json

@@ -1,35 +1,43 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "microsoft/deberta-v3-xsmall",
   "architectures": [
-    "BertForSequenceClassification"
+    "DebertaV2ForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 384,
   "id2label": {
     "0": "scientific",
     "1": "popscientific"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 1536,
   "label2id": {
     "popscientific": 1,
     "scientific": 0
   },
-  "layer_norm_eps": 1e-12,
+  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 6,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "problem_type": "single_label_classification",
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.36.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6046ac2c581539d81a1c267c0985e7cc42b51fa55b2b4e6ff4b8efe93da73401
-size 433270768
+oid sha256:e52c56abb145b2c847f10fee0bc405da0aa9cbc7971acb3ce5dfba1d9999fa96
+size 283347432

runs/Jan29_17-34-55_e90e3af65be2/events.out.tfevents.1706549698.e90e3af65be2.25.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f78607fd57b72a218328105236c932bfc76b2789394cfd1cde04ec589140b1
+size 5909

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": 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

@@ -8,31 +8,31 @@
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
+    "128000": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -41,15 +41,18 @@
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": false,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7f6a73d839138642e93ad907366539cdf64a042b5c0ce3c1cd73b59e2af22b
+oid sha256:6197284f2d118309f53654a7ee4733fde6cfb93560f24c9b3cf3d5bc89a8f928
 size 4283