Training loss: 3.7654

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "prepared_model",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 0,
+  "dtype": "float32",
   "eos_token_id": 2,
-  "head_dim": 16,
+  "head_dim": 144,
   "hidden_act": "silu",
   "hidden_size": 1008,
   "initializer_range": 0.02,
@@ -15,17 +15,16 @@
   "max_position_embeddings": 512,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 63,
-  "num_hidden_layers": 31,
-  "num_key_value_heads": 63,
+  "num_attention_heads": 7,
+  "num_hidden_layers": 7,
+  "num_key_value_heads": 7,
   "pad_token_id": 1,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.47.0",
+  "transformers_version": "4.56.1",
   "use_cache": true,
   "vocab_size": 52000
 }

generation_config.json

@@ -1,7 +1,9 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "eos_token_id": 2,
+  "eos_token_id": [
+    2
+  ],
   "pad_token_id": 1,
-  "transformers_version": "4.47.0"
+  "transformers_version": "4.56.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f64efe6f76c85f1cbf15fa78fdefdbba04cea8f4bce81e1199be2864ea29975
-size 2435485272
+oid sha256:cd5717f825d3f3247097cbe0aff9e00aa417feabb5122d1ba21e2e24a6c559e6
+size 874592552