KhaiQuang/ApecGPT-v1

README.md

@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- training_steps: 800
+- training_steps: 1200
 
 ### Training results
 
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.38.2
+- Transformers 4.40.0
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.0
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "ffn.down_proj",
     "attn.Wqkv",
     "attn.out_proj",
+    "ffn.down_proj",
     "ffn.up_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21383d93680ce54c704a91e50d764c3ab23bcdeb799d55a77a2665fd2851c6ab
+oid sha256:9e55b70b47419dafe45d1c4bff9237c734d1194ebef192f9c3b96eb9a94524c8
 size 100698208

runs/Apr23_03-34-53_3d9417d4d3ef/events.out.tfevents.1713843296.3d9417d4d3ef.1224.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f82a486589f1e8e09438e01a0f3ac36a18a40b4b755ee61fb1d251f0da15a0a
+size 31390

tokenizer.json

@@ -85,6 +85,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba5f26d01464601557c220fc65bd39eb3c82020154f3c6f2f8bc54d34ca5cb2
-size 4856
+oid sha256:aec37191d8a4bb5ee355449b33126dae7f0a3c3a2289b8f27b56fa2294c800d9
+size 4984