Run 4. Outer Step 54. Inner Step 137.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5597976,
-    5597980,
-    5597984,
-    5597988,
-    5597992
+    5597997,
+    5598001,
+    5598005,
+    5598009,
+    5598013
   ],
   "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": 5570305,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf34790232e997b74ccfd5e457334a55db3f2001499e606da61d583a8c5bef9e
+oid sha256:bdb33f36f3a1f30d3cc3361d292a40c94149a5530ce0f2f8261c04341f645e73
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6584e012024926a401b500ca5ada4cd98387b5f3b229808c61ef0e347e87f45
+oid sha256:029c0134f4400d44ea38897556bd766ecc4ff22d2c9424c9bd0b91993a903b6e
 size 4040701744