End of training

README.md

@@ -33,13 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 5e-05
 - train_batch_size: 1
-- eval_batch_size: 8
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 4
 - total_train_batch_size: 4
-- optimizer: Use OptimizerNames.ADAMW_HF with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100
 - num_epochs: 3

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ccc79b49d6bd23cac7e4911cf4acb6b6d016b7982154a06a8817cd4d52f021
+oid sha256:547b578b7a1bc7d35dd51e3c368e39b9fd5b5339fc7f685303a596805e48d27b
 size 94420616

runs/Oct20_14-24-51_chimera12/events.out.tfevents.1729448695.chimera12.1223603.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a765b538b2247d50022f563f1e15883bf5e7b866517f7cc75034316a2f37656f
+size 11834

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e51228b4bcb1dc45ffeeb5bd449d631d4cf0646a6979163807166ba3ded45444
+oid sha256:1e9c72ec75bbbdb76e284d5ba58b97e8b61a7015d4f7c0f59c0787599d39d011
 size 5240