part 4/10 of experiment 7 as described in logbook 2023-03-03

pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ebaf8cc27fb934f6f88a2ed5825feefe0565df2720cd6fb6bc58f8ccca27efb
+oid sha256:88ba2b44537f444e3fad92dff6962ac8c0b983427523484f98e7acf2d71fd65e
 size 10581615331

pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdda631a6dbdb8d84abe2734231e5429d2a5975cd1eb742b8e0fb1b94c05bca
+oid sha256:5c9aabb90f1f0004ec6c406366d65484a29c3de927b7561ad52ac8036b2be48e
 size 5810125147

pytorch_model.bin.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 12219206136
+    "total_size": 12116445688.0
   },
   "weight_map": {
     "lm_head.bias": "pytorch_model-00002-of-00002.bin",
@@ -205,8 +205,8 @@
     "transformer.h.23.attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
     "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
     "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
-    "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00002-of-00002.bin",
-    "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.fc_in.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.fc_in.weight": "pytorch_model-00001-of-00002.bin",
     "transformer.h.23.mlp.fc_out.bias": "pytorch_model-00002-of-00002.bin",
     "transformer.h.23.mlp.fc_out.weight": "pytorch_model-00002-of-00002.bin",
     "transformer.h.24.attn.bias": "pytorch_model-00002-of-00002.bin",