ymath/mistral-7binstruct-summary-100s

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5630
+- Loss: 1.4548
 
 ## Model description
 
@@ -44,15 +44,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
-- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_steps: 0.03
 - training_steps: 50
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.7534        | 0.0146 | 25   | 1.6425          |
-| 1.5934        | 0.0292 | 50   | 1.5630          |
+| 1.5408        | 0.2174 | 25   | 1.4671          |
+| 1.5391        | 0.4348 | 50   | 1.4548          |
 
 
 ### 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": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307cbfb57f0e9094daef5267d3820b6358dbc9da4d7e7dd4ef2a8593d1fbdc7d
-size 27280152
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e74ecdcb2ac946470fc3c457994018fb47a37d0417de6ab8073ec010bb4a126
+oid sha256:ab7a0b65ef9047dcc97d854d90a9d95a84ffe9da19cc079646fcd22c3754844e
 size 4984