Training loss: 27.7508

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "prepared_model",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -8,15 +9,15 @@
   "eos_token_id": 2,
   "head_dim": 16,
   "hidden_act": "silu",
-  "hidden_size": 896,
+  "hidden_size": 1008,
   "initializer_range": 0.02,
-  "intermediate_size": 3584,
+  "intermediate_size": 4032,
   "max_position_embeddings": 512,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 56,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 56,
+  "num_attention_heads": 63,
+  "num_hidden_layers": 31,
+  "num_key_value_heads": 63,
   "pad_token_id": 1,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
@@ -24,7 +25,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 52000
 }

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 0,
   "eos_token_id": 2,
   "pad_token_id": 1,
-  "transformers_version": "4.46.3"
+  "transformers_version": "4.47.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc7a0f19de5025dd4236021c9865746a284fcb94d4f613980895cdf79dc7292
-size 1811615296
+oid sha256:9ca4a6178b6d31e3ff7e01f3c8bf73a952f00b68054b55d2dd1b76da356e6987
+size 2435485272