Training in progress, step 300

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/May31_01-13-18_n136-082-130/events.out.tfevents.1717089327.n136-082-130.3730659.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209ab34ce2cb711cae741e3358725467dd6227f12220971a556f998d42ddd7ad
-size 20959
+oid sha256:a615e1890f482937e0071599f0ffc9c51798e79a0ce8a2f8ca23e8b4e559918f
+size 28579

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 sha256:25686a2a94e778bd06e64992e121362fb8e396ce160a2ce4cb0004cc6efb88ff
-size 6264
+oid sha256:4cfcdc187e96bc5f72f21240b097691d6a8cdf8d0fcc5ad2fe20f43a43287471
+size 6520