Outer Step 8. Inner Step 276. Batch Size 108

config.json

@@ -268,23 +268,23 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5293166,
-    5293170,
-    5293172,
-    5293177,
-    5293178,
-    5293184,
-    5293188,
-    5293191,
-    5293194,
-    5293198
+    5293254,
+    5293254,
+    5293260,
+    5293265,
+    5293266,
+    5293271,
+    5293276,
+    5293278,
+    5293283,
+    5293284
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 262,
+  "inner_step": 276,
   "inner_steps": 0,
   "last_allreduce_block": 5283755,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea5f771d03cc41d6b86b37e239ca29a7dc8a87b5b18f8388ec8d8c24884e6a22
+oid sha256:aea5fe295d63379a8084682badfe49fdb5735fb048f84cdeb568e055b2b37f21
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fc50a1e114c378ce4d015585b92d9e0d017af89095460632569ccee3363ba8
+oid sha256:2f2e8f2e768f1a0f32263738dba733bca56ed2d2d93c1bbcb3a6c284f41b4c74
 size 4040701744