Training in progress, step 200

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad9cc7f4beddacbec9c8276122fd42a150b617af6356a01908319580f9077b51
+oid sha256:0fa2da824fe76b51a31adc346b27214db6db2f1bf53b97c2bbf11ad69a49a120
 size 4988522632

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53dec1875128efa82de06236dd55fe8736578a95d2178a096dd73ca1c0bb2884
-size 1856315036
+oid sha256:12b7875946fdd1ddd66c50db49968c586f2c781bf771cf10300dbb8211ef5bf5
+size 2795955204

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16749197212
+    "total_size": 17688835996
   },
   "weight_map": {
     "adapter.bias": "model-00004-of-00004.safetensors",
@@ -14,16 +14,30 @@
     "codec_decoding_heads.5.weight": "model-00004-of-00004.safetensors",
     "codec_decoding_heads.6.weight": "model-00004-of-00004.safetensors",
     "codec_decoding_heads.7.weight": "model-00004-of-00004.safetensors",
-    "fuser.linear1.bias": "model-00004-of-00004.safetensors",
-    "fuser.linear1.weight": "model-00004-of-00004.safetensors",
-    "fuser.linear2.bias": "model-00004-of-00004.safetensors",
-    "fuser.linear2.weight": "model-00004-of-00004.safetensors",
-    "fuser.linear3.bias": "model-00004-of-00004.safetensors",
-    "fuser.linear3.weight": "model-00004-of-00004.safetensors",
-    "fuser.linear4.bias": "model-00004-of-00004.safetensors",
-    "fuser.linear4.weight": "model-00004-of-00004.safetensors",
-    "fuser.linear5.bias": "model-00004-of-00004.safetensors",
-    "fuser.linear5.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.0.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.0.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.1.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.1.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.10.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.10.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.11.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.11.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.2.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.2.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.3.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.3.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.4.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.4.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.5.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.5.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.6.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.6.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.7.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.7.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.8.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.8.weight": "model-00004-of-00004.safetensors",
+    "fuser.linears.9.bias": "model-00004-of-00004.safetensors",
+    "fuser.linears.9.weight": "model-00004-of-00004.safetensors",
     "layer_norm.bias": "model-00004-of-00004.safetensors",
     "layer_norm.weight": "model-00004-of-00004.safetensors",
     "learned_layer_weight": "model-00001-of-00004.safetensors",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59699c20e1a688f83b7fd22a794114528507d9486108d14371000973ff19a6af
+oid sha256:537a51edfc2b5fa49fb8ac77d7cef18fe1c1b5fec55ff4c127e7cbd280efbadf
 size 7672