End of training

README.md

@@ -1,10 +1,11 @@
 ---
+license: apache-2.0
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: ybelkada/mistral-7b-instruct-v0.1-sharded
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
 - name: data_experiment
   results: []
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # data_experiment
 
-This model is a fine-tuned version of [ybelkada/mistral-7b-instruct-v0.1-sharded](https://huggingface.co/ybelkada/mistral-7b-instruct-v0.1-sharded) on an unknown dataset.
+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.
 
 ## Model description
 
@@ -34,12 +35,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 0.0002
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: constant
 - num_epochs: 5
 - mixed_precision_training: Native AMP
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "ybelkada/mistral-7b-instruct-v0.1-sharded",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
+    "down_proj",
     "v_proj",
-    "gate_proj",
     "up_proj",
     "q_proj",
-    "k_proj",
-    "down_proj",
-    "lm_head"
+    "lm_head",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e5036027d29b3dd0fc1844fcd7123b891811a8293dcb3ed8749eeeda1037c2
+oid sha256:9eb9f4305592c59e81d8e71302f47f82add0b03c09e4dfe01f5a1ac259b0ff61
 size 694431312

tokenizer_config.json

@@ -29,7 +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 %}",
+  "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,
@@ -39,5 +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:ff5e764e5cabadb57bc416e98fab1cbac80a37615838ae36efc98e3ff4ec8907
+oid sha256:a87c98eb0151dad759c0c84aaeb7a6378998f4809a3413b83befa91d56db89a2
 size 4728