phi-2-storygen-reward-model-v2

README.md

@@ -36,7 +36,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
+- train_batch_size: 32
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -49,8 +49,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.39.3
-- Pytorch 2.1.2
+- PEFT 0.10.1.dev0
+- Transformers 4.41.0.dev0
+- Pytorch 2.2.2+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -14,14 +14,17 @@
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
   "peft_type": "LORA",
   "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee531d9d73100221be4efc2d5ae4a30e97fe5128661fd7e327977b93bd449c5d
+oid sha256:ce151f599bbead7df3101c683be03ff97216b70384daedaae270261f21f5b5e0
 size 5270056

tokenizer.json

@@ -396,6 +396,7 @@
     "end_of_word_suffix": "",
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -319,6 +319,7 @@
   "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75be32db41c635c9a45d80f0b0471d79a1a517e6623d2269b4bb11e0a6ac3ee7
+oid sha256:b6908f52ca677ab5f42c1a3faa15a34b053fe7a0d439cc8b29a1ad37726023d3
 size 4984