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_23-06-50_n136-082-130/events.out.tfevents.1717081743.n136-082-130.3690638.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aea99220c8a710722c4294b567cfe309019cb95eb5b533d2c9e6966fabdd32f8
-size 13363
+oid sha256:da85794157e225b954f87b803cd3114b355bbc52e1ebedf601617c4f9a90c631
+size 20959

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 sha256:22e6e8fd2db42b5bcee0f6513108dbd03df91bb18e83b0bf1c0a9a1f8f523058
-size 6264
+oid sha256:64b9ce726680b0e48b6ed9b9cf02bd9886d9c4dc43b9488efca75e67b2fe6cd7
+size 6520