Outer Step 9. Inner Step 3. Batch Size 292

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distributed/optimized-gpt2-1b",
+  "_name_or_path": "snoopsy/xb2a",
   "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": [
+    5315392,
+    5315393,
+    5315396,
+    5315398,
+    5315400,
+    5315402,
+    5315405,
+    5315407,
+    5315409,
+    5315411
+  ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 0,
+  "inner_step": 3,
   "inner_steps": 0,
   "last_allreduce_block": 5297756,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d241a16916cb5a41ac6f7276ebeabdd3b67a2aff7c39511e0c4239428992fb55
-size 2944
+oid sha256:01b661698fc357c575bbe4cf939f7281f0c66b6d482884099e1c35cdda2ace26
+size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb2d6803d7f8fa6434db62fea3b146b1f4ff23b347ced174e318c748a5efaa80
+oid sha256:cb51fe8c528050995c9e333270195231d64fdb28244b74f9148df64b43fd1731
 size 4040701744