Training in progress, step 500

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "AIRI-Institute/gena-lm-bert-base-t2t",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoModel": "AIRI-Institute/gena-lm-bert-base-t2t--modeling_bert.BertForMaskedLM"
+  },
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "last_layer_norm": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 3,
+  "position_embedding_type": "absolute",
+  "pre_layer_norm": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ae5485466d5c403f7567725cddf3a390c911774185891221038d45279bf2c0
+size 442676729

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f033523c57ed50ae8e029b7ce4dd932a4dc48765a4b30323202ca2cf2b3ced15
+size 4027