DariaaaS/9test-ft

README.md

@@ -16,7 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8982
+- eval_loss: 2.2801
+- eval_runtime: 2283.0172
+- eval_samples_per_second: 4.671
+- eval_steps_per_second: 1.168
+- epoch: 1.9998
+- step: 5332
 
 ## Model description
 
@@ -47,22 +52,6 @@ The following hyperparameters were used during training:
 - num_epochs: 10
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.9139        | 0.9991 | 794  | 1.8822          |
-| 1.8456        | 1.9994 | 1589 | 1.8719          |
-| 1.8174        | 2.9997 | 2384 | 1.8706          |
-| 1.7946        | 4.0    | 3179 | 1.8729          |
-| 1.7776        | 4.9991 | 3973 | 1.8769          |
-| 1.7587        | 5.9994 | 4768 | 1.8817          |
-| 1.7447        | 6.9997 | 5563 | 1.8872          |
-| 1.733         | 8.0    | 6358 | 1.8913          |
-| 1.7246        | 8.9991 | 7152 | 1.8959          |
-| 1.714         | 9.9906 | 7940 | 1.8982          |
-
-
 ### Framework versions
 
 - PEFT 0.10.0

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28068f8be130447fbd06403f26d4a0767432e7319e212aec0834d53ce6e94a6
+oid sha256:3d4030cb64427de011fe577b46daf97ec11b9fa5451d2d8b749c3c6ae508f8f7
 size 8397056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:907667b3061fe05e70cb5edccfef5b5e08322abc727ae5880e43a97e656a126c
+oid sha256:e118e15ded9fcb6949ebe40d61d5783c7d620789190b6bb169d0ac7dc5fca1e5
 size 4984