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/May29_23-19-57_n136-082-130/events.out.tfevents.1716996015.n136-082-130.3142878.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42df6e7bfa84da8ee5002e9b0566d68492bfcd856bc7cf245da60bede35a8d83
-size 13314
+oid sha256:db02ccb636f57d6e534ec02cba31e6cc7318969faa4b4f1e5cfe1badb0c36915
+size 20910

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:f12534ec97524a7ec9e6f49254f2d7c136effd4b9c7c6c3b620ad060e3d17807
-size 6264
+oid sha256:df9dd9975041330cb3031003f27f8952f7657e67478afc48ee43616047d272ea
+size 6520