new model, loss -0.10

config.json

@@ -1,11 +1,13 @@
 {
-  "_name_or_path": "/workspace/pretraining/my_prerain/upload",
+  "_name_or_path": "encrypt_v2",
+  "_attn_implementation": "eager",
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "attention_bias": false,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
   "hidden_act": "silu",
   "hidden_size": 2048,
   "initializer_range": 0.02,
@@ -21,7 +23,7 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
-  "use_cache": true,
+  "transformers_version": "4.38.0",
+  "use_cache": false,
   "vocab_size": 50257
-}
+}

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.34.1"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f300b5e75738e733c384a8cf73e8811f46c8a088af59b3d8f03b50d4c68121
-size 3079115120
+oid sha256:c84330509262ed356903a60ff36f9d57c4d3d4bd2d718ed52824ae46dc199850
+size 3079341512