Run 4. Outer Step 53. Inner Step 89.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5589062,
-    5589066,
-    5589071,
-    5589076,
-    5589080
+    5589085,
+    5589089,
+    5589093,
+    5589097,
+    5589100,
+    5589105
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 88,
+  "inner_step": 89,
   "inner_steps": 0,
   "last_allreduce_block": 5565072,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29f665858d2d8ba827659031227ab092d3eff0d28c720b5441b7ffcb62b7887
+oid sha256:d84f6c47eedfa5941bc1d356318e145361dbc199fcccf948bda8c95eb1783fa0
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca85ca9d57462476164d61f6eeac1a9223d83267afb523429e25bb2966c243ea
+oid sha256:32eef7d9011ff5d1e3fde16992d81d55457497de65e25195138ba79322482238
 size 4040701744