llamantino7b_2_question-answering

README.md

@@ -40,9 +40,9 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
+- lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 12
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -19,7 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "k_proj",
     "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a509da10156f2a9777c807582ca3dd9abd8155b9a0ea413b3c44728093354591
-size 134235048
+oid sha256:c006866d469082b9c690f800f41c4b651f5a78551af86bf7516513d61591ce7f
+size 639691872

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 250,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9ebe0a7b90736f325119071254de3f4c85abf7016447bc6a63f57cf8b26099
+oid sha256:16b167fc1bb2c80959ef12219c01118c4d159f5cea90d842a88d203c5b826916
 size 4347