greatakela/mistral_instruct_classify10k_adapters

README.md

@@ -1,8 +1,13 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-7B-Instruct-v0.1
+library_name: peft
 tags:
+- trl
+- sft
 - generated_from_trainer
+datasets:
+- generator
+base_model: mistralai/Mistral-7B-Instruct-v0.1
 model-index:
 - name: mistral_instruct_classify10k
   results: []
@@ -13,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_instruct_classify10k
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6008
+- Loss: 0.6021
 
 ## Model description
 
@@ -47,16 +52,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.7492        | 0.04  | 48   | 0.7265          |
-| 0.6609        | 1.04  | 96   | 0.6719          |
-| 0.5933        | 2.04  | 144  | 0.6383          |
-| 0.5361        | 3.04  | 192  | 0.6149          |
-| 0.475         | 4.04  | 240  | 0.6008          |
+| 0.7548        | 1.0   | 49   | 0.7252          |
+| 0.6684        | 2.0   | 98   | 0.6725          |
+| 0.5849        | 3.0   | 147  | 0.6398          |
+| 0.5236        | 4.0   | 196  | 0.6159          |
+| 0.4733        | 5.0   | 245  | 0.6021          |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.1+cu121
-- Datasets 2.15.0
-- Tokenizers 0.15.0
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -19,10 +19,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "v_proj",
-    "q_proj"
+    "q_proj",
+    "o_proj",
+    "k_proj"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d9cfb741585d64078882e23c778fc87493090e3b89251b89814d8e0a8a4dc8
+oid sha256:170fe642770cdfddeb9c5b302a20e1706ac5e4b2d6ff86f8bdb1eac6d989e862
 size 218138576

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
@@ -37,5 +39,5 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
-  "use_default_system_prompt": true
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0460fd214e311723889719080cc888269aeda57150e4224ba7f702b5ab6dcb77
-size 4600
+oid sha256:2647418726458fe8c42ad91926ebc4d538d170a90a91458aab481d6c4c5a44f8
+size 4728