Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EleutherAI/pythia-160m",
+  "_name_or_path": "EleutherAI/pythia-410m",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -10,14 +10,14 @@
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3af734a23e1c31e3442d6915ac565177f3499f4868fc23f0e4973e342afb097
-size 324662984
+oid sha256:b77432ffab4ab9408659cdc88b613f2b0acf65ef8c474fcdd1ca7481a2de55bd
+size 810702192

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e4fb9d6ad65e78b809e88e17ab389f940df50a48f82467810a5274cd4f5b07
+oid sha256:4a432f4f3c5e8de4bfd15d9ef766992e36eef8b51f7bbd2bf29a249637b725c6
 size 4411