andrewverse/andrew-tweet-comment-ft

README.md

@@ -3,7 +3,7 @@ license: apache-2.0
 library_name: peft
 tags:
 - generated_from_trainer
-base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 model-index:
 - name: andewbot-ft
   results: []
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # andewbot-ft
 
-This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.6661
+- Loss: 0.6775
 
 ## Model description
 
@@ -51,22 +51,22 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.1587        | 0.95  | 10   | 2.6161          |
-| 1.7609        | 2.0   | 21   | 1.0614          |
-| 0.9542        | 2.95  | 31   | 0.7537          |
-| 0.72          | 4.0   | 42   | 0.6809          |
-| 0.7436        | 4.95  | 52   | 0.6734          |
-| 0.6609        | 6.0   | 63   | 0.6692          |
-| 0.7176        | 6.95  | 73   | 0.6672          |
-| 0.644         | 8.0   | 84   | 0.6661          |
-| 0.7019        | 8.95  | 94   | 0.6660          |
-| 0.613         | 9.52  | 100  | 0.6661          |
+| 4.1535        | 0.95  | 10   | 2.6726          |
+| 1.7854        | 2.0   | 21   | 1.1175          |
+| 0.9754        | 2.95  | 31   | 0.7767          |
+| 0.7311        | 4.0   | 42   | 0.7044          |
+| 0.7424        | 4.95  | 52   | 0.6842          |
+| 0.6566        | 6.0   | 63   | 0.6814          |
+| 0.7099        | 6.95  | 73   | 0.6785          |
+| 0.6374        | 8.0   | 84   | 0.6784          |
+| 0.6966        | 8.95  | 94   | 0.6776          |
+| 0.6014        | 9.52  | 100  | 0.6775          |
 
 
 ### Framework versions
 
-- PEFT 0.10.0
+- PEFT 0.8.2
 - Transformers 4.39.1
-- Pytorch 2.1.0+cu118
-- Datasets 2.18.0
+- Pytorch 2.2.0+cu121
+- Datasets 2.17.1
 - Tokenizers 0.15.2

adapter_config.json

@@ -1,12 +1,11 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
-  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -23,6 +22,5 @@
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",
-  "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c74b27c6fa4ee480a016d713a8ba54c244b9254ef74c67251a441279f2dc05
+oid sha256:337ad31ace741e9b61262d429e9632e8bcafd0893ce0d2987703d428a03b5a92
 size 8397056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645a341de43658aae1b21e944f7af5673c2200d636353b6617630dc796212a29
-size 4856
+oid sha256:4f64ebf22e5a56891a7604cd47565a595fb5c04071514fe2793059ee7f34560e
+size 4920