Outer Step 8. Inner Step 6. Batch Size 48

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "Jacksss123/distributedTraining",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -267,13 +267,24 @@
     "AutoConfig": "distributed/optimized-gpt2-500m--configuration_gpt_optimized.GPTOptimConfig",
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
-  "block_list": [],
+  "block_list": [
+    5290877,
+    5290881,
+    5290884,
+    5290887,
+    5290891,
+    5290894,
+    5290898,
+    5290902,
+    5290905,
+    5290909
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 6,
   "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 sha256:492d06eeccafd6003662b45a8cb312d2adc5edf92fda9ed4fc27f30b35362c6a
-size 2944
+oid sha256:0db58b13d413e62194c31076081d6fcabed039883c8dc33b396575d82b5cebe4
+size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c933a9ed1f5f7c6efadfcb8d1009c01cfbc8fb83615528124ae7a9849a72cf46
+oid sha256:87fb520d88a83da31066d63675beda0a7f8edd77406ac6636d4f0ccc3df1a2d4
 size 4040701744