Training in progress, step 600

config.json

@@ -24,7 +24,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_parallel_residual": true,
   "vocab_size": 50304
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee645992f24ee02b486f2e81b344b7a98df284d1f79aa4f2f1679fdd185f99d
+oid sha256:ff1a25bf3bc09a8d6f0b22779d9a70808a628c5f167790a80af1b75d4d200137
 size 2829330208

runs/Jul08_16-05-34_42dbe5cf9ed4/events.out.tfevents.1720455302.42dbe5cf9ed4.852680.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3390738a16dee7dba7e8f5130a65b9b133e556a4934976cebafb5e7733ed17d8
+size 15709

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e80f0082a759adf7bcdb9e73bc424e6165afc3e651a6c8bd1da644a92e628b
+oid sha256:df8eb58379003c8d1c0e5b85a621cdcf2482781ec6fcbf3c862ebe34bffa090e
 size 6264