Run 4. Outer Step 48. Inner Step 38.

config.json

@@ -268,19 +268,20 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5569905,
-    5569909,
-    5569913,
-    5569917,
-    5569922,
-    5569927
+    5569933,
+    5569937,
+    5569941,
+    5569945,
+    5569949,
+    5569953,
+    5569958
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 37,
+  "inner_step": 38,
   "inner_steps": 0,
   "last_allreduce_block": 5523943,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de10219d650aa244b816f2604582828664d5e3dce3710a86f1e3bbd5e340b1ec
+oid sha256:69728ab5e1b64e98b70549275849c784eb6e0710130aa1e120c04fb104146a2c
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d7ca608563553dbe69df6ac90e0328bfda7260d95fac41f7fb40661ea90b61c
+oid sha256:5f8b333e2d40b4c5133c649a34d72544eee6e3ede2a83f0f669eb7df3dc47d5f
 size 4040701744