Run 4. Outer Step 63. Inner Step 44.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "philip324mark/mark6",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -268,15 +268,15 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5645474,
-    5645503
+    5645621,
+    5645651
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 44,
   "inner_steps": 0,
   "last_allreduce_block": 5641040,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887424a9f8c49ceae9f9165f90c7567796f264c5b50c4c59c621d599bfac1016
+oid sha256:5af414a54f0d5178f54f5ca48af933c174e945ff29d297e5a18b01ee555a6039
 size 8081782503

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b142478039582211854e6b2165fbf192fc134a7b331e95f1de8a45d01fc0a1
+oid sha256:4ea675f721c40da1a331ada8e236b80e25875ea911c14f6e8f679ef0f2bc500a
 size 4040701744