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": 32002
 }

runs/Jun13_11-46-48_n136-100-194/events.out.tfevents.1718251003.n136-100-194.329209.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69cb4e517083462041b3ad6559c16dd43d5eb95c670272e184b7233040941ea
-size 13522
+oid sha256:22a391b98ca45ef2d7098ba2804ab928430247cac0ae9d1c8ee82b528b09b493
+size 22092

tokenizer.json

@@ -152,7 +152,6 @@
     "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 sha256:374090dab1472e47e0fe5d92b88b9a0e72a756de13d7112560b3adc44f64a7d7
-size 6520
+oid sha256:3f2b9e1c57de9f9c9a615f892ffe0065d1f1be8ee37a0e62c144462c1e1410ed
+size 6456