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": "4.41.1",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/May30_11-16-51_n136-082-130/events.out.tfevents.1717039153.n136-082-130.3319876.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d489dec93b24f9c9d5f20182dd1b19790674eabd50a6876aad94d7454ba14b1a
-size 13358
+oid sha256:6e815938764c0a9d4d25352518aa856aede3a4dbe98e92dc0cda8a8bde548c5a
+size 20954

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:b3f943ec10c03c0b36e6f7cf63a55e819cb580b98a2a33846c2e1059e1f696c2
-size 6328
+oid sha256:3101c501cb9463cb757d57fc1ba9afd767800873490708bfba47496b8c2a73c9
+size 6520