Training in progress, step 300

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68e26b8bb7075ddd208155dc171926ef069882a45040d62edfc530a012e3f91
+oid sha256:2f535408f7c9de8f0a08d48c11b21bd78b4fe7a02bcb033ae0dddbe4412df957
 size 136062744

runs/Apr24_20-06-46_aga39/events.out.tfevents.1714007217.aga39.672468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafa990ad4bd44a2dde631e0cb4a84bd19c0683611c70bf23ba15e2764894046
+size 17477

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23054b72d8bf7f6d0b1444be2e2ce66385bedc8eb30293bd1e68f58cbd6033a
+oid sha256:45f8b6cc78440714767f67b8543c1cc3b8156360ee0d45609137cfc23fa9e437
 size 6072