Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EleutherAI/pythia-2.8b",
+  "_name_or_path": "/workspace/files/EleutherAI--pythia-12b-deduped/",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -10,14 +10,14 @@
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 2560,
+  "hidden_size": 5120,
   "initializer_range": 0.02,
-  "intermediate_size": 10240,
+  "intermediate_size": 20480,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
+  "num_attention_heads": 40,
+  "num_hidden_layers": 36,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1af2bf02ad89461c25664840d6cc0bbd718010fe3579b0412e0899069601c34e
-size 5816
+oid sha256:224b1fd4c94d58dad8baadce90ab96267dfc959712dc95b3e5971d09ab8216b2
+size 5880