Training in progress, step 100

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.1",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7968f911198f1df818789d9432468d37b593ccfd8b3bcbea76bd037d88ecbffa
+oid sha256:1775a787cea99895d1f7ceac82dca90710f3f544fede4cc40fc241a273195101
 size 2200136248

runs/Sep22_21-06-18_nova.cs.ucla.edu/events.out.tfevents.1727064531.nova.cs.ucla.edu.485295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29ff0d8800d49239f0d4a5fa798bf1a7530edc0ec0409ca92a842b779361721
+size 9329

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb5cf384760e2b870077d119543a7c0ec374bf1b40bc3c29f9076d13a8291be9
-size 6264
+oid sha256:c9a1e1c411a908542d59830f8645303efef128003dcb536704609fb9fbd470cf
+size 6328