phi-2-role-play

README.md

@@ -35,13 +35,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 0.0005
 - train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 5
 
 ### Training results
 
@@ -50,7 +50,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.13.0
-- Transformers 4.45.0
+- Transformers 4.45.1
 - Pytorch 2.4.0
 - Datasets 3.0.1
 - Tokenizers 0.20.0

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "q_proj",
     "v_proj",
+    "dense",
+    "fc1",
     "fc2",
     "k_proj",
-    "fc1"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3ac91cb8a8feec3780359fdc7d567a49c4ab5cf02fafa35a412acadfc2e4b0
+oid sha256:c27288bcc18eafc048522763d1477df6d19e883927bf87497aecab898ecf475e
 size 94422368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058878bfc3b66ef82ff7fc7bd821e6b981f638f16a676034cf01020c865b3550
+oid sha256:d205614049fd5077c9cf76935781ed60ab0676a774cc78ae3478c97229285497
 size 5496