Training in progress, step 5000

config.json

@@ -12,7 +12,7 @@
   "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
   "decoder_layers": 12,
-  "decoder_start_token_id": 2,
+  "decoder_start_token_id": 0,
   "dropout": 0.1,
   "dtype": "float32",
   "encoder_attention_heads": 16,
@@ -30,7 +30,7 @@
   "pad_token_id": 1,
   "scale_embedding": false,
   "tokenizer_class": "BartphoTokenizer",
-  "transformers_version": "4.57.6",
+  "transformers_version": "4.57.3",
   "use_cache": true,
   "vocab_size": 40030
 }

generation_config.json

@@ -4,7 +4,8 @@
   "eos_token_id": [
     2
   ],
+  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.57.6"
+  "transformers_version": "4.57.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9d267a511971693ef71d020d5b10ca915c5a4bbd2e424a8962a6cbdded7ca8
+oid sha256:e3da1766635ecbb55ecbb0b6c1a376da0ab0fec1c8d50d9b6742a2836aa11c62
 size 1583480280

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:850c93f6a583b4561034505e991d9ce6dea898e97bead9b92788bf5c5178a901
-size 6033
+oid sha256:fe86080add0f9155969504f919fc53c878a84179784f0f9146a46b7afc04914e
+size 5969