Model save

README.md

@@ -2,7 +2,6 @@
 license: apache-2.0
 library_name: peft
 tags:
-- axolotl
 - generated_from_trainer
 base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
 model-index:
@@ -27,10 +26,10 @@ chat_template: inst
 dataset_prepared_path: last_run_prepared
 datasets:
 - conversation: mistral
-  path: 14050e2bd5b9487a9afae30b4c86d554/./data/with_function_response/function_not_used.jsonl
+  path: 497b7e7687f94b09b0e633b679727a04/./data/with_function_response/function_not_used_training.jsonl
   type: sharegpt
 - conversation: mistral
-  path: 14050e2bd5b9487a9afae30b4c86d554/./data/with_function_response/function_used.jsonl
+  path: 497b7e7687f94b09b0e633b679727a04/./data/with_function_response/function_used_training.jsonl
   type: sharegpt
 debug: null
 deepspeed: null
@@ -69,7 +68,7 @@ model_config:
 model_type: AutoModelForCausalLM
 num_epochs: 1
 optimizer: paged_adamw_8bit
-output_dir: 14050e2bd5b9487a9afae30b4c86d554/model
+output_dir: 497b7e7687f94b09b0e633b679727a04/model
 pad_to_sequence_len: true
 resume_from_checkpoint: null
 sample_packing: true
@@ -93,9 +92,7 @@ xformers_attention: null
 
 # mixtral-remove-negative-data
 
-This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0936
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on an unknown dataset.
 
 ## Model description
 
@@ -128,17 +125,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 10
 - num_epochs: 1
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 4.0791        | 0.0   | 1    | 4.0657          |
-| 0.1507        | 0.2   | 56   | 0.1291          |
-| 0.1178        | 0.4   | 112  | 0.1052          |
-| 0.1046        | 0.61  | 168  | 0.0977          |
-| 0.102         | 0.81  | 224  | 0.0936          |
-
-
 ### Framework versions
 
 - PEFT 0.8.2

adapter_config.json

@@ -20,9 +20,9 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
+    "k_proj",
     "o_proj",
-    "k_proj"
+    "q_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:baa33ea1c35f01d785b890afec3242a7156fda827d1569188ae1abf34c177d13
+oid sha256:e38812772ac55f93a5c705bc028f6bda448c0ea78a32f7b9be1d647caaba5224
 size 109086416

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ffdef099be9ab3284c1e5a2c92dfe97b9bbcd4e8428fcac33d5afa90f34ccc4
+oid sha256:6d41dbd958da6f59f7b0c8f21d54fd6a4ca27c71d3c6d51e8942b99a2c60ebf9
 size 5624