Training in progress, step 500

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 sha256:426de063a365bb078acf462d4e0a44b8ec6a2f5614cc8fe816dee8b965c9b9c3
-size 498657649
+oid sha256:0668a72bba713afb37516ae79e935f0a86c4ea5ba8fec64e2722a1fce9087f06
+size 46749762