phi-2-tmo

README.md

@@ -43,10 +43,14 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 1
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.39.3
+- Transformers 4.40.0
 - Pytorch 2.1.2
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "v_proj",
     "fc2",
-    "fc1",
+    "q_proj",
+    "v_proj",
+    "dense",
     "k_proj",
-    "q_proj"
+    "fc1"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2fcc08da9a362d76e52920be5ae74708e566d8495e5a5eb41ae41b5aac4884
+oid sha256:0bb78e6ee91b63673781259838e85818b71eb3a91a1652375e4c98a645119444
 size 94422368

tokenizer.json

@@ -387,6 +387,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -319,6 +319,7 @@
   "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ba3583b231298355f5133e5cc9f8234f0f53a8552b42d2341f8ec7bb3b501b7
-size 4920
+oid sha256:db8dc83ff543e15d32f0ed53102d4fc2f5ffc51c6238e442e87362695602351d
+size 4984