Run 4. Outer Step 35. Inner Step 43.

config.json

@@ -268,20 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5549554,
-    5549557,
-    5549559,
-    5549561,
-    5549563,
-    5549566,
-    5549568
+    5549570,
+    5549573,
+    5549575,
+    5549577,
+    5549579
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 42,
+  "inner_step": 43,
   "inner_steps": 0,
   "last_allreduce_block": 5548219,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4d38445e6ef5fa7d018009b0687f463e9b5cae73d4d1e60560f8fa43242e25
+oid sha256:35ae47222e53e42338679de6c8517f2b77a34d0d0bedd46b3f65bd55df53fc53
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bde38c3b58671f7d7fd0b2a0ed5b29cd51fe4a572109a2c003f06c5e3d253c4
+oid sha256:1202bb819827b1bcf4c5957f41bd1db9695753822f0074c19dafce62a651b616
 size 4040701744