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/May29_01-45-07_n136-082-130/events.out.tfevents.1716918651.n136-082-130.2665532.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f5682a13d704dcd5092b545846699fea2986d469adc5c5cc4079f7dc558a5c
-size 20885
+oid sha256:3ddf24f553333828786988c3971d9d1022e8757f1230b262d1d8425c990e02ee
+size 28505

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 sha256:9c6ef97f0ae5fdc0c432ac82567593d35a0af306147fdde011f9f421bccdc5eb
-size 6264
+oid sha256:533300aff07f4f7ab51e724374f988f2b2aa6030a0ee25060f9738d24e503159
+size 6520