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_13-57-21_n136-082-130/events.out.tfevents.1717135169.n136-082-130.3960206.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d2364e987f84946ad7453e03d69b80196c33ed8bb47378b6fdc39073f28b68
-size 20961
+oid sha256:c130c91ef7113243470ee74fc5959570f20327dd05a92450e1012c82545df9b6
+size 28581

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:b464e038705b93d8cfb1e6cd5bda588fe87007cfb19bf96cf183c3f052581230
-size 6264
+oid sha256:a43f1ec98d2c131b691a4a61be956ba111c56fde1b5474a028ba22f1faa2a663
+size 6520