End of training

README.md

@@ -41,7 +41,9 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - 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: 10
+- mixed_precision_training: Native AMP
 
 ### Training results
 

adapter_config.json

@@ -24,12 +24,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc1",
     "o_proj",
-    "fc2",
-    "v_proj",
     "q_proj",
-    "k_proj"
+    "encoder.attention.*",
+    "decoder.attention.*",
+    "k_proj",
+    "fc2",
+    "fc1",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c17dff717eef7fd0584a9cb9f9776c3c282a4f3b74f72e70a726eed201c3a0
+oid sha256:d6ecda24970dd9cf9085a0ab88f71a28359adbea58cbac69db8ca42c3b1c1692
 size 10839776

runs/May22_14-37-56_abcc76a0a741/events.out.tfevents.1747924680.abcc76a0a741.173.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b23ddc174b13f93dcdbe7aa7d25e526da2562b0381816c1e3d72640af968f04
+size 12502

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73931a9c256fd27404e8fd8b7548e346fa309daa1b54a57a8703ab52f2aaf228
+oid sha256:7711e99e61b0522e4293e8730354a4c6e514da526cb975503f606c9eab1a16c7
 size 5304