llamantino7b_2_question-answering

README.md

@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 5
+- num_epochs: 14
 
 ### Training results
 
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.8.2
-- Transformers 4.38.0.dev0
+- Transformers 4.39.0.dev0
 - Pytorch 2.0.1+cu117
 - Datasets 2.16.1
 - Tokenizers 0.15.2

adapter_config.json

@@ -19,14 +19,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
-    "down_proj",
     "q_proj",
-    "v_proj",
+    "gate_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj"
+    "k_proj",
+    "o_proj",
+    "v_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 sha256:2607c5f230285c3c1c9175320dbc3ea51fb6ab1a5f1f4419832fbc72c854fbc1
+oid sha256:fc5f825d4cdee80e1f3ac5c8aab194d2aaaa5a7d66d1ddab9b3c31616fd6ad06
 size 639691872

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 250,
+    "max_length": 700,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6579f09f6bad01c6bab89da6134e31b132cc362e1e7afafcdf94b3fe9eded66
-size 4347
+oid sha256:039ee6bcc800f9ccf323738be238b42dc6b00907ba7be0d99f0347e75dfa4c9c
+size 4539