Training in progress, step 1

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.1",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86311a112e82f1728f0d54188b137d43adcc617c7a5f58e40b0a0254c1414683
+oid sha256:f3d24d8e5f2d74688b57b67cb7f3a3cb48857d7da53a2b22e41699d7baf46219
 size 4938985352

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467a9a6f68cd110482e71879c7e7a39bfcdc5d965911669861f384a19cf78df9
+oid sha256:0fc45a397c714c50f1b4be003342d781274dc379b7260da620ff8309ab585b2c
 size 4947390880

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3198d6e0b155f5c55514f892eda0faf716889c73bf61784331df5228e82b40c9
+oid sha256:4d7ce26565acdaef2d9ccea41ce48adada2955f61faea505be4a938b95ca614b
 size 3590488816

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf752cc282e23694f3250a04a5777b6939167545fb0096d8e363139def2e5f8
-size 7544
+oid sha256:bf5430ca5f8e4d587e26ad5d1b8e8ed2874c1020b92b124df38cf266014166e6
+size 7480