Run 4. Outer Step 3. Inner Step 138.

config.json

@@ -268,21 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484848,
-    5484850,
-    5484852,
-    5484854,
-    5484857,
-    5484860,
-    5484862,
-    5484864
+    5484868,
+    5484869,
+    5484872,
+    5484874,
+    5484876
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 137,
+  "inner_step": 138,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65527cbee830ee813e1be362680834583e26e7e15ea1f71bc942ef766016ac5
+oid sha256:2a440ffa7a73f114fbd38df2c5eeeb520ca751c565304fa5e09206295dfe588d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12fa42c72667ed386f09fb131680214796926c1082fdf5fa44ac0bcdc353bbaa
+oid sha256:41d5120e827902473812cd2d05a93fa6d6ff721927a1202711f224e64a909813
 size 4040701744