mistral_7b_admiral_instruct

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2638
+- Loss: 1.2637
 
 ## Model description
 
@@ -52,11 +52,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6092        | 0.16  | 20   | 1.4551          |
-| 1.4237        | 0.33  | 40   | 1.3019          |
-| 1.3399        | 0.49  | 60   | 1.2806          |
-| 1.3411        | 0.65  | 80   | 1.2683          |
-| 1.3916        | 0.81  | 100  | 1.2638          |
+| 1.5871        | 0.16  | 20   | 1.4508          |
+| 1.4009        | 0.33  | 40   | 1.2985          |
+| 1.3499        | 0.49  | 60   | 1.2842          |
+| 1.3251        | 0.65  | 80   | 1.2721          |
+| 1.3741        | 0.81  | 100  | 1.2637          |
 
 
 ### Framework versions

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "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 sha256:27a3e547388fa34cebc8f54aad55f406d97eb9cce3995d50753d2dfb2fbac5e8
+oid sha256:61bc96c4e810998535ff7a8c957b0f5916ff3e922a2ca3eae05138e1c7f1b33f
 size 109069176

tokenizer_config.json

@@ -29,6 +29,7 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:effdc6d67ef82527a86815f254ba224832da83cca2cdc74dbc32d245a88824bd
+oid sha256:e795171346d7e37928821c285368490b74f64ec42779607dd3623f3663b97278
 size 4920