Run 4. Outer Step 29. Inner Step 36.

config.json

@@ -268,19 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539643,
-    5539646,
-    5539650,
-    5539653,
-    5539657,
-    5539659
+    5539662,
+    5539663,
+    5539665,
+    5539667,
+    5539670
   ],
   "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": 5538408,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:093b1c092a0a310f0d32a8a13bd8069b401757d0fe2877cd63b53258051b46c0
+oid sha256:dfcd48e0c32e95edf4997ad7b4aafd02a30f2bd5b3e38ac565d8a6d6dbcaf276
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81f269ad670fbd89158b3c35b74dec8d665ffe792b8f33ac3589fe5466ce74f4
+oid sha256:ecb14054029b96d8a94ad25417171fe7b5ef9c46a725b1aac07f7b5e0a57c9bf
 size 4040701744