rafaeloc15/mistral-small-v3

README.md

@@ -20,7 +20,7 @@ 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: 0.0265
+- Loss: 0.0468
 
 ## Model description
 
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0368        | 1.0   | 252  | 0.0340          |
-| 0.0297        | 2.0   | 504  | 0.0265          |
+| 0.104         | 1.0   | 47   | 0.0775          |
+| 0.0552        | 2.0   | 94   | 0.0468          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "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:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
-size 48
+oid sha256:08b322fa53e7ff551da9b7692d2da38c452db49feeafe179687f27145452e844
+size 109069176

runs/Apr10_18-36-13_4259648ece10/events.out.tfevents.1712774203.4259648ece10.45718.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce0b08f7bc1677c04f5178efc35df90935bfb50542c5c7f1c7e76e776f4a3cc
+size 7804

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e52f679f57d97978696c01e6a8fa9dcb1fd8f9a8af20b8a41e39e6fd45ceba
+oid sha256:1eae1f7bd446e23aecfe0d68ed2de2c33ea764e55b0f0d47593fa0683be61487
 size 4920