Run 4. Outer Step 98. Inner Step 10.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "markalan324/minor2",
   "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": [
-    5693130,
-    5693162
+    5693374,
+    5693408
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 8,
+  "inner_step": 10,
   "inner_steps": 0,
   "last_allreduce_block": 5687981,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de11103d0107a2c6cd52ce3bfc8db8f142a6023a6b319bcdaf79de2c42a08098
+oid sha256:537d36845347685adc997fb12693fd3260cc90a941b9dfcc2441bc8f77221ded
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2c9a8956a1118bb02a0b360cf9413d69915e60aacdab404d5d8c0ca6452d4e
+oid sha256:a5b5ff82336db0e4336e52c38a1899ddc311f7ddd1d979c6f6b4e63dff05e150
 size 4040701744