End of training

config.json

@@ -1,28 +1,34 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "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,
+  "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,
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
   "num_attention_heads": 12,
+  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.32.0.dev0",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "type_vocab_size": 2,
+  "vocab_size": 30000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db30f8c710f4f13634edfb76e245e55bb514af4cd49a2475ed825d5f05e85b2
-size 498657649
+oid sha256:e3c052cc90fc69e9cf5e77aa5a4a72fb15d7cd8a1b13d6d12adf22121e53f22a
+size 46749762