Run 4. Outer Step 54. Inner Step 78.

config.json

@@ -268,18 +268,19 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5580675,
-    5580689,
-    5580716,
-    5580721,
-    5580725
+    5580729,
+    5580733,
+    5580737,
+    5580742,
+    5580746,
+    5580750
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 77,
+  "inner_step": 78,
   "inner_steps": 0,
   "last_allreduce_block": 5577515,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857e383c52d4c28aff61d3ad232e7fef26c6986332bda7530851f545ed5e9eac
+oid sha256:677347a9df6ba9d5f72aff75e522ff78daf02d6f515dabab21ccf37d53a9e9f2
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fbbcfadb260177ba509b0d83040014451b2da58904baa2ab5ed2f465e8b3815
+oid sha256:0519fa20efa4b39450773d4e06b809e5e258f113f91c5e1a6380f521c7d940c8
 size 4040701744