Run 4. Outer Step 53. Inner Step 64.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5588491,
-    5588495,
-    5588500,
-    5588504,
-    5588508
+    5588513,
+    5588517,
+    5588522,
+    5588526,
+    5588531
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 63,
+  "inner_step": 64,
   "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 sha256:2c6cbb2fde83933fdf62906945d5aa82c4934c06f882850edffc16e0c69eebb4
+oid sha256:5e20639158b05bce7562fef5f5847b5f8115e59ee1fa436fb98c1551a38aabb3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d8e57623d56bd7e3b72508fff1edce29b8f7c45bfddf1ad5c017d4d6da0c55
+oid sha256:6792384cd363e48e828af9a3ffc798523b3b0abb51e32523c59ace278b6959f2
 size 4040701744