Training in progress, step 250

config.json

@@ -146,7 +146,7 @@
   ],
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
-  "use_cache": true,
+  "use_cache": false,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f4ada2639c9b19d45b18ff31068a5b127212978582a597b51ce20cc2f0b906
+oid sha256:8bfe96b8ea2e56b4120682297a426744c23b327440f4687a9158ec765d218ec8
 size 966995080

runs/Apr19_10-49-43_5b967a9dce61/events.out.tfevents.1713523784.5b967a9dce61.11660.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d438d6f84fb48ee7deb49bd99bb568857ef38f48145ebed188f58083f31ab7
+size 8867

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2132043fee1e3cf417ae5b7b32fc79d2d6ac456c4291da331a0902a8975934e7
+oid sha256:f33addf0387065c0075894b052c729d1ad409bb4767fcd9d391682909f67a6f8
 size 5176