Run 4. Outer Step 10. Inner Step 87.

config.json

@@ -268,19 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5506100,
-    5506104,
-    5506107,
-    5506111,
-    5506116,
-    5506120
+    5506124,
+    5506128,
+    5506131,
+    5506135,
+    5506139,
+    5506143
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 86,
+  "inner_step": 87,
   "inner_steps": 0,
   "last_allreduce_block": 5492224,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78c2b16fd8785111acca004a470911515efd16c263752ebcc0c32f83394ceb49
+oid sha256:ccdfbac9ce91dec765c7e2f416dd3e2f4fc428947680dfeb105b02421b7abc0d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1aae8defafdbb6afd8d29456a3f9138c7bb2b549fe8f869bcdc2c76825c4591
+oid sha256:13bc76913087a0f29e30469b136401d0370332e09c9d3b69fea7fe2922673ea9
 size 4040701744