Run 4. Outer Step 33. Inner Step 106.

config.json

@@ -268,22 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5546990,
-    5546994,
-    5546996,
-    5546998,
-    5547000,
-    5547002,
-    5547003,
-    5547004,
-    5547006
+    5547009,
+    5547012,
+    5547014,
+    5547016,
+    5547017
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 105,
+  "inner_step": 106,
   "inner_steps": 0,
   "last_allreduce_block": 5543976,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c41d5426f8c64c6b48e71a3aba9833611c2029d9a874a6cfc765a029a2197b
+oid sha256:50effcc02e7769e7ff289cabeb88a63518ea7e7b5616cf9ba3b9b2fccd6e47e1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f401dcd0e42fcc6df215b47973575cee58391c0f24972c894c35f551186d38
+oid sha256:2e3f1877575c3489375337b02dc0de7a5712aaf52cd5e20aba56768ab6075c23
 size 4040701744