Training in progress, step 500

config.json

@@ -20,9 +20,9 @@
   "rope_theta": 1000000.0,
   "sliding_window": 131072,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.52.2",
-  "use_cache": true,
+  "use_cache": null,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7cf7b13e97ee2f312a84ca3a9abcca5ddda6f561c035eed3f5b3188532a0df
-size 1976163472
+oid sha256:f7c5e202bea6961d1444bbdd105cb37cda2a29ab2310b4b251d59d96e043a4bf
+size 988097824

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d61b6eb641fff680a854404401b93bcdf9a900e9a980f867db80f0f433b2e6
+size 6161