Run 4. Outer Step 43. Inner Step 86.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5563273,
-    5563277,
-    5563281,
-    5563285,
-    5563289
+    5563294,
+    5563298,
+    5563302,
+    5563307,
+    5563311
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 85,
+  "inner_step": 86,
   "inner_steps": 0,
   "last_allreduce_block": 5541234,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9dc1708d19141284c167469bee1e84fc7fcde7360de08f0ac7769a8a0a6c66e
+oid sha256:bd9d4fb20d25dc22e9250ae5d62052276904cfa7cdc1d785f41c7ecb9b7dba5a
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e844c951e8ee6c10415a7c39b4bc5a2f42b387d42edd912696efc56e6ac23611
+oid sha256:6f740dc6f9878b8e9f137b2a0705286f75efe1a58e676fb3db863775874d4343
 size 4040701744