Training in progress, step 400

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": 32000
 }

runs/Jul02_16-26-27_n136-082-130/events.out.tfevents.1719908809.n136-082-130.246420.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d99b8ebbcf6cf0342d1f7126f3c1d401fe99879c94b22688dcfadc79fc5f24f7
-size 26347
+oid sha256:2f433c1ff1b681430f74ad161937073c74753db3bf9801d10c213515f42647e7
+size 33227

tokenizer.json

@@ -134,6 +134,7 @@
     "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 sha256:0dbff6071c55671d44cac95124a8b52fa521ae57b58e89f00a53c9ffd395eeac
-size 6328
+oid sha256:1987847d5ecd496557addb7e51b8b1d07a504e606fde07b6cd2c8c2d0088225b
+size 6520