Run 4. Outer Step 29. Inner Step 39.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5539765,
-    5539768,
-    5539770,
-    5539772,
-    5539775
+    5539778,
+    5539781,
+    5539784,
+    5539786,
+    5539788,
+    5539789,
+    5539790,
+    5539791,
+    5539793,
+    5539796
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 38,
+  "inner_step": 39,
   "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:ca08f107cff94eac6f886c1c58c986587991cd2da0126ae5e61ce9a69138504d
+oid sha256:80808a4698ed197e836504a40da1bdd73406e45c73e5a5aa1c28361d5f046608
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5be71fa6e9e21d94131d6039365d9ba9a40f0d6156aead24f335c99f2c8f851
+oid sha256:a7da0d1138e9bf106878b69ff5a6f8f8e38b37f4e59bc0c134a0743985b2f516
 size 4040701744