phi-2-period

README.md

@@ -36,12 +36,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
@@ -52,5 +52,5 @@ The following hyperparameters were used during training:
 - PEFT 0.11.1
 - Transformers 4.41.2
 - Pytorch 2.1.2
-- Datasets 2.18.0
+- Datasets 2.19.2
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc1",
+    "q_proj",
+    "k_proj",
     "dense",
     "fc2",
-    "k_proj",
-    "q_proj",
+    "fc1",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8c7840a6b322ef38c8f9cfc28536be2f30da9c1ca1a434427368131ba0d92b
+oid sha256:1c684117edfa1ba204c3c44ca0c1aa848e5a0c6d4f03ef98a4bdb1800e4785d1
 size 94422368

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 200,
+    "max_length": 2048,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457218ce232804bbd18793ebeb318ae83f08be921900462bd28d5ebb36bc100a
+oid sha256:9c6d018f5c71130dea7cbb6e69b3c87ed1d241abbad65882f00ffe0e684b19f3
 size 5112