qlora-llama2-7b-question-generation-eduqg

README.md

@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 9
 
 ### Training results
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.34.0.dev0
+- Transformers 4.35.0.dev0
 - Pytorch 2.0.0
 - Datasets 2.1.0
-- Tokenizers 0.14.0
+- Tokenizers 0.14.1

adapter_config.json

@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9aa0afbd0ed0c2d13594adde00f24c157f1c15361512c36135b62b5c1f065ce
+oid sha256:9026fa5734c7d8e195d928191eb11d32d5e05eb8455bc9bdc176dca77273c000
 size 16822989

special_tokens_map.json

@@ -1,6 +1,24 @@
 {
-  "bos_token": "<s>",
-  "eos_token": "</s>",
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "</s>",
-  "unk_token": "<unk>"
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

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": [
     {

tokenizer_config.json

@@ -25,16 +25,15 @@
       "special": true
     }
   },
-  "additional_special_tokens": [],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "</s>",
   "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f146539640000aadff9aadf10ec8aafaa5d72d8cc031bff3018a8d6528cdb40
+oid sha256:44ce4fd3212f03b378c2fd5c40f6ddeffb9fba512eb8f1a24e427ac892db9ec5
 size 4155