Run 4. Outer Step 19. Inner Step 42.

config.json

@@ -268,21 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5523583,
-    5523587,
-    5523590,
-    5523594,
-    5523598,
-    5523601,
-    5523605,
-    5523608
+    5523612,
+    5523616,
+    5523620,
+    5523623,
+    5523627,
+    5523630,
+    5523634
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 41,
+  "inner_step": 42,
   "inner_steps": 0,
   "last_allreduce_block": 5522512,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb0ccab2fde3640279a062484ba0880b34e9986c4ce17d70fb3eb4ba97f50f5f
+oid sha256:6160360738162085bf3922be2eb270ae50ce070326d37a78764e8e7668ddbf4d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96ebb8e9456e2ba5cd8816e15f2ecc62ed0f5c816dbd20f6489eaa0a25a51cb1
+oid sha256:c0f0f18ed7b35e3f6e64869688e1b235f5978fb95d16172bce143933b105e58d
 size 4040701744