Training in progress, step 500

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Apr21_13-50-04_n136-128-070/events.out.tfevents.1713678734.n136-128-070.503227.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b255359cb138302c5891ad472708c2dbcee99acb73c6539b512586b8e271b071
+size 26127

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 sha256:4b0d1860a8699ef12a9fb178408ee4b12bf54aba671d7e715a9313b88d8a2182
-size 6136
+oid sha256:330917557ede2a250eade0e84f45bb1090836d04a0c50f1b118489cb97966077
+size 6264