Training in progress, epoch 1

config.json

@@ -1,18 +1,14 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "google/electra-base-generator",
   "architectures": [
-    "AlbertForSequenceClassification"
+    "ElectraForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
-  "hidden_size": 768,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -31,13 +27,10 @@
     "14": "LABEL_14",
     "15": "LABEL_15",
     "16": "LABEL_16",
-    "17": "LABEL_17",
-    "18": "LABEL_18",
-    "19": "LABEL_19"
+    "17": "LABEL_17"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
+  "intermediate_size": 1024,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -49,8 +42,6 @@
     "LABEL_15": 15,
     "LABEL_16": 16,
     "LABEL_17": 17,
-    "LABEL_18": 18,
-    "LABEL_19": 19,
     "LABEL_2": 2,
     "LABEL_3": 3,
     "LABEL_4": 4,
@@ -62,17 +53,19 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
-  "num_attention_heads": 12,
-  "num_hidden_groups": 1,
+  "model_type": "electra",
+  "num_attention_heads": 4,
   "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 2,
-  "vocab_size": 30000
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:687ef3ef83c28e61211a98a14ecd93b203ed0a48e92eded3587d2d401251c886
-size 46799280
+oid sha256:7ba4b1793edc9743e0ba81e8fcd92c7fa37b73ec75654601470608acdc7e029f
+size 134350640

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "unk_token": "<unk>"
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<unk>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,26 +32,24 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
-      "lstrip": 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": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "remove_space": true,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "tokenizer_class": "AlbertTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0ebe009c461da0f636d84a9267633d9913cde54097adad8acf87e98c57044ef
+oid sha256:5a22a3ff5eb41358377d8a6d2791fc82c92b5cccdf792f3499d3de48a64c0eb4
 size 4856