Training in progress, epoch 1

config.json

@@ -85,6 +85,7 @@
     "vocab_size": 30522
   },
   "decoder_start_token_id": 0,
+  "early_stopping": true,
   "encoder": {
     "_name_or_path": "dura-garage/nepberta",
     "add_cross_attention": false,
@@ -166,11 +167,17 @@
     "use_cache": true,
     "vocab_size": 30522
   },
+  "eos_token_id": 2,
   "from_tf": true,
   "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 512,
+  "min_length": 1,
   "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 5,
   "pad_token_id": 1,
   "torch_dtype": "float32",
-  "transformers_version": "4.37.0",
+  "transformers_version": "4.35.2",
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10883f7ebcf6358a44ad14c93e0f711fe7af2b64867bdca56fb7dd9f3cec8778
+oid sha256:9a0db68e7ac333cb8e1e4995871852934885db1ccf187f62999e27d994125eb2
 size 989518784

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676d2c925844c37d5c65cf896cb53c24613c95a125d0acd6176db2dbe191ef0c
-size 4792
+oid sha256:b86b52412cf3e336d443fb9c8a7d4e1f2e2e28ead334d595f0962f5b0456fa65
+size 4664