Run 4. Outer Step 58. Inner Step 32.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5604658,
-    5604663,
-    5604667,
-    5604671,
-    5604675
+    5604680,
+    5604684,
+    5604689,
+    5604693,
+    5604697
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 31,
+  "inner_step": 32,
   "inner_steps": 0,
   "last_allreduce_block": 5602341,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3250a79e69dc0b270bbb3c9af6e1aab31edc0e04cd626992ece7503025994adf
+oid sha256:cbf240a1ec7a34c61a69132296e6e3c1fa9c6fb2c96c180e13697a56e6082019
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4fc4a459ac5279722e724ac4e29034c291673948231e0f44867b4ed0b40af49
+oid sha256:b7992803a2dbc8e68cd1336c274b139cfa6ec401d7991c6cc5ffcd6933114618
 size 4040701744