Run 4. Outer Step 33. Inner Step 18.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5544603,
-    5544604,
-    5544609,
-    5544611,
-    5544613
+    5544616,
+    5544619,
+    5544622,
+    5544626,
+    5544628,
+    5544631,
+    5544634,
+    5544637
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 17,
+  "inner_step": 18,
   "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 sha256:21907bd872336f45d51bb9654e48cc8814b5b3a447d77d978602cc8d952ea8f1
+oid sha256:4e27156c29762069b6177b135aac8f56d4c6113969143b2cf1d7886dc16470d3
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0e5dcdfa0b365dff086fb0d72b32bcc2601f2d3aa4deed9fd48d839d30f237
+oid sha256:e9074b9756c698c5d194c3ba16c9c08a91713b4d12eb156803527f74fe20ff43
 size 4040701744