Training in progress, step 200

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe044ce5d51214e73ca72455dbfccb255ae4fd519897fb97b3bce4922e42951
+oid sha256:a21cdd6a199bd2a5d7bee12fe688b2156661f3a8e59df91591b5ded21ee03748
 size 4988522632

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a7819f4a4790741648a2492ef59b1eac2939c0f4220b600e8962567b9b572ac
-size 2795955204
+oid sha256:29f23d80a05ea9c787cf8867653e65d8f8416c992c1a5105a3e38dc17dc3011d
+size 1118042580

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 17688835996
+    "total_size": 16010925980
   },
   "weight_map": {
     "adapter.bias": "model-00004-of-00004.safetensors",
@@ -14,30 +14,6 @@
     "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.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:f3ab9f91d052aabdb9571865b25e61c857e346cfdfd4268af83ac9ccba304e5f
+oid sha256:78101b66ded748c0083521ed5e21081837d48b464e3fd3c8f0376354e4790490
 size 7672