Training in progress, step 10000

config.json

@@ -1,12 +1,13 @@
 {
-  "_name_or_path": "microsoft/deberta-base",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "DebertaForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -20,7 +21,6 @@
     "9": "LABEL_9"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -33,24 +33,17 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 768,
-  "pos_att_type": [
-    "c2p",
-    "p2c"
-  ],
-  "position_biased_input": false,
-  "relative_attention": true,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.34.1",
-  "type_vocab_size": 0,
-  "vocab_size": 50265
+  "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a7a400d3851ebfe1fcda2e17cdfb096b8154ddb0b71e37702434b0b259049d
-size 556868717
+oid sha256:6f56299ea490796f81115ae99aea9aef40abb6bb550a15080b225cc7d8a91df5
+size 267880554

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "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": true,
-    "normalized": true,
-    "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": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",
@@ -10,50 +8,48 @@
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "[CLS]",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "[SEP]",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "[UNK]",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "103": {
       "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "errors": "replace",
+  "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "tokenizer_class": "DebertaTokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "gpt2"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf560eb43e0151d17446600f539e99cb0849420224e32c73a72270c0086396a8
-size 4091
+oid sha256:77eebddd87ae3f8abb109d5c333b5311774ffbe951f6414a02ef1cbba30752d6
+size 4536