End of training

README.md

@@ -1,11 +1,10 @@
 ---
-license: apache-2.0
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: mistralai/Mistral-7B-Instruct-v0.2
+base_model: meta-llama/Llama-2-7b-chat-hf
 model-index:
 - name: output
   results: []
@@ -16,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3961
+- Loss: 1.5112
 
 ## Model description
 
@@ -52,18 +51,18 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.8031        | 0.29  | 1    | 1.4752          |
-| 1.7659        | 0.57  | 2    | 1.4449          |
-| 1.719         | 0.86  | 3    | 1.4310          |
-| 1.6627        | 1.14  | 4    | 1.4258          |
-| 1.6314        | 1.43  | 5    | 1.4145          |
-| 1.5923        | 1.71  | 6    | 1.4010          |
-| 1.5667        | 2.0   | 7    | 1.3915          |
-| 1.5096        | 2.29  | 8    | 1.3875          |
-| 1.5481        | 2.57  | 9    | 1.3872          |
-| 1.4877        | 2.86  | 10   | 1.3892          |
-| 1.39          | 3.14  | 11   | 1.3922          |
-| 1.4343        | 3.43  | 12   | 1.3961          |
+| 1.9596        | 0.29  | 1    | 1.7030          |
+| 2.0029        | 0.57  | 2    | 1.6746          |
+| 1.9649        | 0.86  | 3    | 1.6343          |
+| 1.8472        | 1.14  | 4    | 1.6023          |
+| 1.8243        | 1.43  | 5    | 1.5890          |
+| 1.8297        | 1.71  | 6    | 1.5809          |
+| 1.8483        | 2.0   | 7    | 1.5683          |
+| 1.7739        | 2.29  | 8    | 1.5528          |
+| 1.8205        | 2.57  | 9    | 1.5378          |
+| 1.7415        | 2.86  | 10   | 1.5262          |
+| 1.6532        | 3.14  | 11   | 1.5178          |
+| 1.7671        | 3.43  | 12   | 1.5112          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
     "v_proj",
-    "k_proj"
+    "q_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a68fa73c30d1c0658a4d832ac0889c4d1e5d9f8067ce000274b8db0ff189517
-size 54560368
+oid sha256:ae952f03c8703076c365c1f560e6bc44b26bdaeaff581851ad2b643316bb9b06
+size 67143296

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
-size 493443
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -27,16 +27,15 @@
       "special": true
     }
   },
-  "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 %}",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
-  "legacy": true,
+  "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false