Epoch 1. Batch Size 0. Peers 2.

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/root/optimized-gpt2-1b",
+  "_name_or_path": "distributed/optimized-gpt2-1b-stable-embeddings",
   "activation_function": "gelu_new",
   "all_reduce_scores": {
     "0": "NON_PARTICIPATING",
@@ -264,9 +264,10 @@
   ],
   "attn_pdrop": 0.1,
   "auto_map": {
-    "AutoConfig": "configuration_gpt_optimized.GPTOptimConfig",
-    "AutoModelForCausalLM": "modeling_gpt_optimized.GPTOptim"
+    "AutoConfig": "distributed/optimized-gpt2-1b-stable-embeddings--configuration_gpt_optimized.GPTOptimConfig",
+    "AutoModelForCausalLM": "distributed/optimized-gpt2-1b-stable-embeddings--modeling_gpt_optimized.GPTOptim"
   },
+  "block_list": [],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86048048139b2cae7b486e2da9b4abc53112e9290d190f6d23bec864a1fdfa3b
+oid sha256:54d9e99f8451fe278d65595bbd0ad5a2a9d1f6a379edfd0489025d474229ce09
 size 4040722640

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3a91f39e56e9767b1752df2d7083e1af943596962205f984b491c915006da6
+size 4040823418