Run 4. Outer Step 52. Inner Step 36.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5576089,
-    5576092,
-    5576095,
-    5576096,
-    5576099,
-    5576100,
-    5576102
+    5576106,
+    5576109,
+    5576111,
+    5576112,
+    5576116
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 35,
+  "inner_step": 36,
   "inner_steps": 0,
   "last_allreduce_block": 5574901,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad26cae1ffb11d892a3935b8c161624a8532157513ebef684d73c7d04c15c2fb
+oid sha256:aad161c32e24c35e71fcea6fdc061ac428f7081f0e3e284e68903f790d8b85aa
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1667e3b7372ce7f442c6b3c289aa4a16adcbf0bd9002850b001585c9c39cc36
+oid sha256:fac018f92a0421b6754bf8de905f82f42bccaceb98c2ed97a2407d88ee789297
 size 4040701744