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: ybelkada/mistral-7b-instruct-v0.1-sharded
 model-index:
 - name: data_experiment
   results: []
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # data_experiment
 
-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 [ybelkada/mistral-7b-instruct-v0.1-sharded](https://huggingface.co/ybelkada/mistral-7b-instruct-v0.1-sharded) on an unknown dataset.
 
 ## Model description
 
@@ -40,13 +39,8 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: constant
-- num_epochs: 10
-- mixed_precision_training: Native AMP
-
-### Training results
-
-
+- lr_scheduler_type: cosine
+- num_epochs: 5
 
 ### 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": "ybelkada/mistral-7b-instruct-v0.1-sharded",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,14 +19,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "lm_head",
-    "q_proj",
     "k_proj",
-    "down_proj",
-    "o_proj",
+    "q_proj",
+    "gate_proj",
     "up_proj",
-    "gate_proj"
+    "o_proj",
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8850961d4e9b588991621616cef460b4b357d717b5708a847b1822f00f3adf
+oid sha256:091d01db986b82b92baec6e38e1e57fcecacb667928926185a1d2a60ab9799c8
 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": false
+  "use_default_system_prompt": true
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5084b6220077ec47cb290257b691492aa4fe49992f105b31821a3a0b7226f299
+oid sha256:22aa1809070ec5ae84dd334a6296b3604ca00810b74ceef5aaef78ce9a9a5d30
 size 4728