anyiwang/data_experiment

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
 
@@ -39,9 +40,9 @@ 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: cosine
-- num_epochs: 8
-- mixed_precision_training: Native AMP
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 5
 
 ### Training results
 
@@ -51,6 +52,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.7.1
 - Transformers 4.36.2
-- Pytorch 2.1.2
+- Pytorch 2.0.1
 - Datasets 2.16.1
 - Tokenizers 0.15.0

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,
@@ -9,24 +9,21 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
     "q_proj",
+    "gate_proj",
     "v_proj",
     "o_proj",
-    "k_proj",
-    "up_proj",
-    "lm_head"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744d8c0d91a593b105ee52c3f5453c887b91cdb869414dcb79df299ae8139345
-size 694431312
+oid sha256:ed120ac8d7522db4f9101829c975460bda398cefd4b44970d8106bf785117f50
+size 369142184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fca3c7cae03502c7e2fd66bd8662325107c83fe508b11a1bda904de7ff9e1cb
-size 4728
+oid sha256:e80e558428c4c40d7b80999899b890f6315f923a048e345b84618930fa60b130
+size 4219