Run 4. Outer Step 58. Inner Step 17.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603031,
-    5603038,
-    5603044,
-    5603050,
-    5603056
+    5603063,
+    5603069,
+    5603076,
+    5603082,
+    5603088
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 16,
+  "inner_step": 17,
   "inner_steps": 0,
   "last_allreduce_block": 5576204,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5498995da0271469dd46de85f1fe4a5ffbb5073976c61af1f63e831b623b7840
+oid sha256:a0bcb0c4dbd9f43496f89ed73b0e72ef73d80ac9a9d95f2c4b18d176b275c376
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499f69d3a75c6ef83b3b0afa297d8f6591531e7c2e27b6ccc428fbbf3b8556be
+oid sha256:ff380f6fa0de92473e617f42be5b94335feb1b285fe40d51fb52fcabfdcce535
 size 4040701744