Training in progress, step 100

config.json

@@ -20,7 +20,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": true,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0",
   "use_cache": false,
   "use_sliding_window": false,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e66d9268c1792ea69bdd3dda299f7587cdfa38a1e8f8f73a7d16a6b09222b8a
+size 3087467144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e2742f525ff6e5d2a33b18c40657bb039867960153ecebd179eb3a9141affe2
-size 6136
+oid sha256:f6f5424261f8374187f7669efe9ad4d4aa89d9ae8fef091844fab8f9b23688b8
+size 7544