Model save

README.md

@@ -34,21 +34,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5.5e-05
-- train_batch_size: 32
-- eval_batch_size: 8
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 2
+- gradient_accumulation_steps: 4
 - total_train_batch_size: 64
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 3
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Framework versions
 
 - PEFT 0.15.2
-- Transformers 4.52.3
+- Transformers 4.52.4
 - Pytorch 2.6.0+cu124
 - Datasets 3.6.0
 - Tokenizers 0.21.1

adapter_config.json

@@ -27,10 +27,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "q_proj",
-    "o_proj",
-    "k_proj"
+    "v_proj",
+    "o_proj"
   ],
   "task_type": null,
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98fb01fc41430119ff64113ddf2d2588d7980066fbc4512c2bc0d45a9745930c
+oid sha256:aa142720e80dc427de5eb184ff6dbd425df016512dff4ca53db4072bf34bd319
 size 78677456

runs/May30_13-34-06_3a133184e7b6/events.out.tfevents.1748612059.3a133184e7b6.76765.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16594e3a785c1086324645b425c86891a719b9c210b726769e242a69008df3a6
+size 5779

runs/May30_13-38-56_3a133184e7b6/events.out.tfevents.1748612344.3a133184e7b6.76765.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22490fcbe77341597da8290f76bdc8cc1b89fbbf2dab1d9e17adbf8e4ab13489
+size 5779

runs/May30_13-41-29_3a133184e7b6/events.out.tfevents.1748612498.3a133184e7b6.76765.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f906d6d24fc314b5bea65c7f67bf67f53c5b414b6680747b56ee496567e129b1
+size 11426

runs/May30_13-41-29_3a133184e7b6/events.out.tfevents.1748612751.3a133184e7b6.76765.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6428b2238d8ad4353af80b8e05e38f4cdef0cb31ae831a3c272331637f425e2d
+size 5757

runs/May30_13-41-29_3a133184e7b6/events.out.tfevents.1748612872.3a133184e7b6.76765.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6a2b95bdd6c69a9d4350742707bca0e1e032fa24e70fff61a9da4717ae3df6
+size 5964

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87006930f24df5622768272be5325413bd12ab40ec6d7e94c8b32c9424d80178
+oid sha256:26cd6ba8f4f81b491eb0aa376a9d16b719450a68abb33db5020fe67822e4b8a5
 size 5560

training_log.json

@@ -1,9 +1 @@
-[
-  {
-    "loss": 0.7766,
-    "grad_norm": 0.9275875687599182,
-    "learning_rate": 0.0,
-    "epoch": 0.001190003966679889,
-    "step": 1
-  }
-]
+[]