Training in progress, step 300

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.41.1",
+  "transformers_version": "4.39.3",
   "use_cache": false,
   "vocab_size": 32000
 }

runs/Jun22_10-12-16_n136-129-074/events.out.tfevents.1719022369.n136-129-074.445700.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065c271a8b1a60ab6cebdf89938466463c0b975202cd67c4ac9d0f86ab98d7db
-size 19211
+oid sha256:e022233200fa60f7285445505f9fc22bb99a1ff42a57630604c9a47c7955a0cb
+size 26091

tokenizer.json

@@ -134,7 +134,6 @@
     "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 sha256:6819c1dd4414cf3e1008e039028d4a09c333504f352311e2138049a4cec39cd4
-size 6520
+oid sha256:0a0444b55e899bda2b049d57e26db7ba9934f12da1827bec93bef3d39b6e277a
+size 6264