Run 4. Outer Step 57. Inner Step 29.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5601759,
-    5601765,
-    5601770,
-    5601775,
-    5601779
+    5601784,
+    5601788,
+    5601793,
+    5601797,
+    5601801
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 28,
+  "inner_step": 29,
   "inner_steps": 0,
   "last_allreduce_block": 5599463,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8877990c6c3f2049b66cb54c958230543fd86c268211f912f87f41afda8f55
+oid sha256:5183958346f1c55ec72a816a67e247d234c3d01bf6812d0878143037ae669ac7
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5908dad09a4b14acead1280aa021445b94e90bb9194413f8611b5a83d456ae95
+oid sha256:93aeaf2deaa00a54a2dd0459fed8d424d2489830e649ab742bbd07a58c7860fa
 size 4040701744