Training in progress, step 100

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.39.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32001
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def68e8808c97e039dee5dba5be22e198c18b820a53c8f11f14d0927bdfd0e9c
+oid sha256:23fd61fb9bd6e6fd5cb8c4a5fea3e06b3e9cd582469bc08426c879877280f5ef
 size 2200128056

runs/May23_11-12-30_nova.cs.ucla.edu/events.out.tfevents.1716488476.nova.cs.ucla.edu.3155979.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179d9d7ad7facffca5e17a69881cb40861009508b1e2d1e3012c83b6e0b81ea3
+size 9214

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e1a843c2910863cdb8483cf7f65cfdec966d7e73a1556d9cd8bb6c84bd357d9
+oid sha256:f032da73ae0267df7dba2067e5b7dda34c005713caec53b4567d998ed39ff977
 size 6200