Run 4. Outer Step 3. Inner Step 138.

config.json

@@ -268,18 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484839,
-    5484842,
-    5484844,
-    5484849,
-    5484851
+    5484854,
+    5484856,
+    5484858,
+    5484861,
+    5484864,
+    5484867,
+    5484869,
+    5484872,
+    5484874,
+    5484877
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 137,
+  "inner_step": 138,
   "inner_steps": 0,
   "last_allreduce_block": 5477809,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a63b20d44c6dfb670170189d5c71099c70f4a6699741715a1db6d7da249282
+oid sha256:3d5d3e165b956134cbaa569a04ec33325889ad5a8f7ef4c333fc904a543efd3e
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b12ec10fdde313309a9c297e0388cd2d0283db9e396e58165f4f3f664cfbf39f
+oid sha256:640d204b59b16a0ccad8e1c152c1028474e562b2cdde59e10a929e8250f65ea8
 size 4040701744