Model save

README.md

@@ -36,20 +36,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.002
+- learning_rate: 0.0002
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 42
+- seed: 4269
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1
 - num_epochs: 1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.10.0

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c1138c4597aff02dee6c79861e100c73244184a15c227f66054f1223228ee9
+oid sha256:79cf4849132a2098f10c59f47222c8f12ad2fdd76c6f3bd311012f57446bf5bf
 size 109069176

runs/Apr14_22-29-34_ubuntu/events.out.tfevents.1713108584.ubuntu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a1884652aae41ca380cd25fd44d348bd14320ae9a90c645e902e6adcdfd202
+size 5053

runs/Apr14_22-32-20_ubuntu/events.out.tfevents.1713108755.ubuntu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f90e34e1ad0b245c85cbe4d0ef905f515b9534e56d52bd49a89baafbf1aa49
+size 83032

runs/Apr15_10-46-36_ubuntu/events.out.tfevents.1713152828.ubuntu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d2721602df64e0525a4b4b1e22128e6a00cf572ba588493922af04c103f86a
+size 10514

runs/Apr15_11-06-02_ubuntu/events.out.tfevents.1713153964.ubuntu

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fafeaf0b125ba9692a139c0872a9e378c42f03ce425160250307ffbad9339d
+size 591912

tokenizer_config.json

@@ -32,6 +32,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
+  "max_seq_length": 1024,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39cc1f1c552f6a1a6b9aa497b2f9196590d0df3f8e0aad992a42c041114d6a8f
+oid sha256:7ef14cbbaa82c9476964a862acb20d4f9512f4fdd2dd3044e9cf6352408a41d8
 size 4984