Model save

README.md

@@ -1,8 +1,9 @@
 ---
 license: mit
-base_model: microsoft/phi-2
+library_name: peft
 tags:
 - generated_from_trainer
+base_model: microsoft/phi-2
 model-index:
 - name: phi-2-finetuned
   results: []
@@ -33,12 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- num_epochs: 5
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 20
 
 ### Training results
 
@@ -46,7 +50,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.35.2
+- PEFT 0.7.1
+- Transformers 4.36.0
 - Pytorch 2.1.0+cu121
 - Datasets 2.16.1
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -9,18 +9,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "Wqkv",
-    "out_proj"
+    "fc1",
+    "lm_head",
+    "fc2",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4df7325080423adeedaaa1ed0ec3efbfd2a5a24cf444c3497925b8add516fb
-size 62931408
+oid sha256:6138b3893e6e44c9fe18b3f0aebcb7b4c4214d1d5beaae8ec322c75312525af0
+size 347895224

runs/Jan12_04-01-39_b3be375e58ed/events.out.tfevents.1705032105.b3be375e58ed.157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5289985b3ddd04836ed15b8b563425ae2bc87a523e81e35381a556e6c1352094
+size 5549

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051643a4d73b5ab606d4ad87fd0164e759007e3002e069475d2b9ec4f6c1679c
-size 4600
+oid sha256:5b7c8bb8d4339fa7bfee37f1783b0e8244d19d07328a7beb9d45a5fe4df442b6
+size 4728