rafaeloc15/mistral-small-v5

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: 0.0433
+- Loss: 0.0738
 
 ## Model description
 
@@ -52,8 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0618        | 1.0   | 401  | 0.0579          |
-| 0.0471        | 2.0   | 802  | 0.0433          |
+| 0.1033        | 1.0   | 82   | 0.0988          |
+| 0.0809        | 2.0   | 164  | 0.0738          |
 
 
 ### Framework versions

adapter_config.json

@@ -6,6 +6,7 @@
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a8d440b290a6a7163205813497d5cf349c36710ffb0eb1ff86df6dd8b239003
+oid sha256:030fc4a3b11ca1f9daaf45430f913ce20e97bc6c9590d374f7f7a0a526cf0469
 size 109069176

runs/Apr18_11-19-03_eb7d68fc1d12/events.out.tfevents.1713439235.eb7d68fc1d12.465.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805b7ee66d8c2c9e4003c3da2920a2f498cf1adce3e2998b49bf9914a598fbbc
+size 9280

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a4a5e19f0f2e97a5899521a1e3351525fa6d1bd06675ca697824cbdf5b0eedf
+oid sha256:da7e101c0c35f47975325d91caa6d28dc01850bfc3bf2bd7059b7710c2810cb3
 size 4920