chohi/Llama-test-Ko-3-8B

README.md

@@ -36,8 +36,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
@@ -50,8 +50,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.40.1
-- Pytorch 2.2.1+cu121
-- Datasets 2.19.0
-- Tokenizers 0.19.1
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -6,7 +6,6 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
-  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -20,10 +19,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
-  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9b5666cb86aa361b546261210825407a64e7b345d06ef9a4130e460f37ef41
+oid sha256:6275229f94e2fb49cb663256ae3d0bc2a97e4b1afca817823ac8db0160096e09
 size 109069176

runs/May09_11-39-13_cbnu-DGX-Station/events.out.tfevents.1715222380.cbnu-DGX-Station.2148635.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fdc29a9bb2b44d685308aceaa9a5e206a875b155fa704596c523e9cd3c9586
+size 5131

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -2407,7 +2412,6 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
-    "ignore_merges": true,
     "vocab": {
       "!": 0,
       "\"": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4411bed28119bf1d109631a50f48615e4cea0882da43936974a8109076f24f51
-size 4984
+oid sha256:1246dbc4e8cc43cd2c44dab983a1fe34be1a732bb8708f8fbdee815a0f6a477d
+size 4664