Training in progress, step 300

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/Jun22_01-20-30_n136-082-130/events.out.tfevents.1718990449.n136-082-130.2356232.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dac6f3fe1ffb9d40dbcddfc2aaaf3df24e7d45016f307837bf4caf43d4b9f3e
-size 19419
+oid sha256:55b32c4fc97434051659c62cb32eef050c92d40dfc0b29ca9be12b1a36d6715f
+size 26299

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:ebbdccfc2781f7a4458a1845ec8442290325390296b7b72a0183570bd0fbffb0
-size 6264
+oid sha256:bf765daeff145762a3fa632b01cccb18d8d1f4664dc9658a48bcbecb448c6367
+size 6520