Training in progress, step 200

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.41.1",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Jun13_15-36-58_n136-082-130/events.out.tfevents.1718264350.n136-082-130.1562673.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9670f5289ee8360425b0387bcf1356dd3fb9180f90e4228e0e0ac6a2f3cb773b
-size 12562
+oid sha256:c60551fa1e8d7c3702153f6370990b3bbed1d83c06a66cf0bc47f947d6587776
+size 19418

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:e1a894b0e10102e8950d92b348d06aa16065b48524d69136e685c40807cd80d7
-size 6456
+oid sha256:e1e65f3a4ce8099904ca2b95025889fcfc0edceb7030f9631332b64c0ff76cff
+size 6520