Training in progress, step 200

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/Jul03_19-50-46_n136-082-130/events.out.tfevents.1720007704.n136-082-130.727289.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81c378ce5ae0776216d55dbc1ac4ba2a8613125203a92a38c1640fd5b3cd40d
-size 12655
+oid sha256:a12aa3fe11b2cb838147caf6b8f0c6a1bf1155413581380f19f2a2ee44bb3b17
+size 19511

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 sha256:5fc17d04ff8999b784673094bfc94f340bf1b82c104ffe64c18c7d2f2ea8b9f4
-size 6328
+oid sha256:26744db2cfaad1ba924f198a0f7777d66f0f42a1cfd7425001f46a0c8be3dcff
+size 6520