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_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:db02ccb636f57d6e534ec02cba31e6cc7318969faa4b4f1e5cfe1badb0c36915
-size 20910
+oid sha256:2dd295ca2613c3763a3149476930eb476d026b055a727ffa12cc704c76ac482c
+size 28530

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:dadd16e859cce8223cbc036d0b14a858573a3c16794cd0290547847afa9ddb52
-size 6264
+oid sha256:df9dd9975041330cb3031003f27f8952f7657e67478afc48ee43616047d272ea
+size 6520