Run 4. Outer Step 58. Inner Step 37.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5603366,
-    5603370,
-    5603374,
-    5603379,
-    5603383
+    5603388,
+    5603392,
+    5603396,
+    5603400,
+    5603404
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 36,
+  "inner_step": 37,
   "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 sha256:176ff1c5260211ca939cf4341b9dd0bd3db6d57be92d4385a7b80917c05c5de2
+oid sha256:ba0506fec07bac43a59941fa407f594c281e431d2cc623f607c643554d241dbd
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3400f7a637f243edef0173fe8e3f9c5596a9fd4b546098abb4f48051a6842d
+oid sha256:02875bcd9f273289b8c836396710e66900f55063a6266a7c2d00bdf333bc7324
 size 4040701744