Run 4. Outer Step 97. Inner Step 0.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "zeras141a/d8",
+  "_name_or_path": "distributed/optimized-gpt2-1b",
   "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": [
-    5691594,
-    5691615
+    5691604,
+    5691621
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 34,
+  "inner_step": 0,
   "inner_steps": 0,
   "last_allreduce_block": 5686307,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fac967aadc7dddb0400003c1658b4b118d8d273359ccbcb20bfa9ac68c8afae
+oid sha256:dcccb5cf1429e33c70ab3e666b5d71059cd8d61d5b6c34a365c139d710d0ebf1
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c375d0089d928ba7c83721c5b46a2d47fed1670e2c9d5984af27283184a8934
+oid sha256:7c1c9d1a1404d4868456a8aa94ec1f1f5302743f5916afa51be39e767632ae84
 size 4040701744