Training in progress, step 400

config.json

@@ -20,7 +20,7 @@
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float32",
   "transformers_version": "4.51.1",
   "use_cache": true,
   "use_sliding_window": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0277a80515c990ec3595d6195b9a3f7fcc3a294f7e41a32102a4ac4abe10c5a
-size 868134176
+oid sha256:cff830396a2934f402ca3374a71f28321a6f2ec9fd0c4bc4d5161413c4e9370c
+size 1736236080

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542ea114bc65f40646f1ad93d9f8632a783311a1c30d71e915d110afa44450c7
-size 7307659
+oid sha256:ab149effcf19cd2a337ab6bc7abeb330fc6a5cc067c77eab681963df3e796381
+size 7307661

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db79957b932fb237a0ef948ecb4cabeb16c569c9a9b0088b2db33b98f3c6597c
+oid sha256:6e9c1bbef41255a846aa429ca871074fae2d8f3bd779a09912332a318bc5cb05
 size 5368