datajose/pruebas-ft

README.md

@@ -16,7 +16,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3561
+- Loss: 0.5016
 
 ## Model description
 
@@ -45,27 +45,28 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
 - num_epochs: 10
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.0594        | 0.96  | 20   | 3.3561          |
-| 3.869         | 1.98  | 41   | 3.3561          |
-| 3.8571        | 2.99  | 62   | 3.3561          |
-| 3.8601        | 4.0   | 83   | 3.3561          |
-| 4.0594        | 4.96  | 103  | 3.3561          |
-| 3.8631        | 5.98  | 124  | 3.3561          |
-| 3.8601        | 6.99  | 145  | 3.3561          |
-| 3.8601        | 8.0   | 166  | 3.3561          |
-| 4.0594        | 8.96  | 186  | 3.3561          |
-| 3.7054        | 9.64  | 200  | 3.3561          |
+| 2.2715        | 0.96  | 20   | 1.7064          |
+| 0.71          | 1.98  | 41   | 1.1687          |
+| 0.5515        | 2.99  | 62   | 1.0146          |
+| 0.5052        | 4.0   | 83   | 0.8605          |
+| 0.4887        | 4.96  | 103  | 0.7023          |
+| 0.4311        | 5.98  | 124  | 0.6066          |
+| 0.418         | 6.99  | 145  | 0.5606          |
+| 0.4088        | 8.0   | 166  | 0.5206          |
+| 0.4243        | 8.96  | 186  | 0.5048          |
+| 0.3898        | 9.64  | 200  | 0.5016          |
 
 
 ### Framework versions
 
 - PEFT 0.9.0
-- Transformers 4.38.1
-- Pytorch 2.2.1+cu121
-- Datasets 2.14.7
+- Transformers 4.38.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
 - Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49d9fd541a28ee6ed8974fec9be8bfc3c4b2dd9690a6c3982e88002209982b5
-size 4202736
+oid sha256:4b8f41a103ccfef48a0c7101fd706957a4b02d57796fae22b701eec88a4af294
+size 8397056

runs/Mar12_13-41-31_57d4afd0bde0/events.out.tfevents.1710250893.57d4afd0bde0.3382.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428c8c736b5c0e189a5d69d91ad1de488c85399c37b59fbd0cbb352e736b0326
+size 10328

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6f5199f8b126b43f6323b676a22a650ffbc456ba6813422151c0fd8ef8efbc
-size 4920
+oid sha256:30e010fd8cbc265a352f57d16ac7c99310ada8ea19b2d05a7f4aa4a081d8dd63
+size 4856