Run 4. Outer Step 58. Inner Step 26.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603415,
-    5603421,
-    5603427,
-    5603433,
-    5603439
+    5603446,
+    5603453,
+    5603459,
+    5603465,
+    5603471
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 25,
+  "inner_step": 26,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3a5203ac220832da043d4a3d1e504917eba6e585cbe8db39a87b51ce905d50
+oid sha256:944465ac30bbbd1676f4c75467440c5ba048c06efde515b1161c8da3d6a63783
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7bf553c0200b07d9b5ae7ce0e718bd277b6e1c4ce2712089d04112639fb79a0
+oid sha256:76f4538c0aece701f6631327c0c4e45458b76338c4d249729126a7efff3b4ed5
 size 4040701744