Training in progress, step 8000

config.json

@@ -20,7 +20,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.38.2",
   "use_cache": false,
   "vocab_size": 32002
 }

runs/Apr23_17-57-53_n136-085-012/events.out.tfevents.1713866692.n136-085-012.1067198.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42c6e0e4fa7306af13667c42e4687931bb11eae3cad6c5b260ee7a5a8cfd4fcc
-size 322202
+oid sha256:685d6e4f2d877db8805d81cb4cb35535a894db1c58f658919065a68b16addb1b
+size 343302

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:ce2fd167e13d2ed98b2df24741f56e1db29830406234c6bbe7c5bc2a74cfd42a
-size 6200
+oid sha256:68fc3a7e01a1f972df57dda16dff653580f8f62565e152a4811780709f9e6544
+size 6136