Run 4. Outer Step 3. Inner Step 137.

config.json

@@ -268,18 +268,21 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5484842,
-    5484845,
-    5484847,
-    5484849,
-    5484850
+    5484854,
+    5484857,
+    5484860,
+    5484862,
+    5484864,
+    5484866,
+    5484868,
+    5484871
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 136,
+  "inner_step": 137,
   "inner_steps": 0,
   "last_allreduce_block": 5480541,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c91689d78277ddfef303043e7ccd6eecb697543178d7dda2f45a46d8e6cb48c
+oid sha256:38427a19f186d67ef00ac669f4fac16ed5e414742a8c570747ae47599b1a0a8d
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e6aaf6d38c7e407ba2f48cb68570c6f9c0b487af9db4bc96fc779beac2a337
+oid sha256:793378c5999de145cc4a19dbd9a4830f769443d5550f2cacb50c35c1d8b11aa0
 size 4040701744