Training in progress, step 500

config.json

@@ -27,7 +27,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.1",
   "use_cache": true,
   "vocab_size": 32128
 }

tokenizer.json

@@ -964,8 +964,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "prepend_scheme": "always",
+    "split": true
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -1024,8 +1024,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true,
-    "prepend_scheme": "always"
+    "prepend_scheme": "always",
+    "split": true
   },
   "model": {
     "type": "Unigram",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:085f29bb41341461a5f6ea932afc63c0113cf166247994fc7695b9b688abb095
-size 5048
+oid sha256:59ac6162a3a883df8b9dd14451369f34366e8d5a475b5d1368409d7b024a7634
+size 5112