Run 4. Outer Step 3. Inner Step 142.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484847,
-    5484849,
-    5484852,
-    5484855,
-    5484858,
-    5484860,
-    5484863,
-    5484865
+    5484868,
+    5484871,
+    5484875,
+    5484877,
+    5484879
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 141,
+  "inner_step": 142,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3d7c8142205002c11315552338a3136fdd02d70d05fd930cf163331a140e2e
+oid sha256:49f73cbf30592519a9e84c8231dd0267e1f63ec141dbc89216a2918f42350a25
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4aef68d5ebbb6d3df6ef0d36ec4947be7c9cd5d642febad880b9f7707916511
+oid sha256:b924e1439c718c6a0842130109d2c78d2b79d0277220ddb2940da1b09471df60
 size 4040701744