Training in progress, step 500

config.json

@@ -1,12 +1,13 @@
 {
-  "_name_or_path": "ai-forever/ruT5-large",
+  "_name_or_path": "ai-forever/ruT5-base",
+  "_num_labels": 2,
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 4096,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +19,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3d5e7834d7996de758c558eaadf3fe2819a1922995c909eb87341e69c45eff
-size 2950734544
+oid sha256:446164606c39fc09af24f82a109631490155370250200b1c9098d7cfa39ab505
+size 891644712

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f48706df486799b49bf77f49791c17aa5ee995d67fdbd3fae26c49c26d68671f
+oid sha256:51f8749500f16414b2d00bcab037c4a6c0ffe0f40865ee1d2b241aa8ae8a0918
 size 5112