Training in progress, step 200

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/Jun18_02-21-39_n136-112-146/events.out.tfevents.1718649051.n136-112-146.1324127.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0790de6487b80463975112c7eb0c4a1dd854228b9ebade6f60f75c352993414
-size 12347
+oid sha256:1c87c66cac2138057c4d310d55269b213af27f2b384f549c0908b83b6463d524
+size 19203

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 sha256:91a455adcc1dd46693a6fa3188bc76c135951e0b0806108b876f1cac5c69def0
-size 6520
+oid sha256:fe7ad1d1edbbc30b461a2666bb026f02d74c0c127226e41e03c561f18f18d157
+size 6328