Training in progress, step 200

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/May28_04-27-47_n136-112-146/events.out.tfevents.1716842585.n136-112-146.359517.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee5f69bd7ba859a19e83a25a2ac0d1546612dc14e9bf186c81f52f8ce8743ad
-size 13131
+oid sha256:878c1f073e315676a4e78eb7838dc75893b576622a91b845b59c95c038dcb107
+size 20727

tokenizer.json

@@ -152,6 +152,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b64dfab1ce040e27997d2752ad0f6bcc64c589d63538334728b2c1dabfd13511
-size 6264
+oid sha256:aab4573f211e1825da610c91d86ed7a8bc0cfa8f8bba8dbb6800dc69b7080723
+size 6328