irenewds/shawgpt-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: 1.8528
+- Loss: 1.3449
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.00015
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
@@ -44,28 +44,32 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 16
+- num_epochs: 20
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch   | Step | Validation Loss |
 |:-------------:|:-------:|:----:|:---------------:|
-| 4.6193        | 0.9231  | 3    | 4.1003          |
-| 4.3201        | 1.8462  | 6    | 3.8086          |
-| 3.9755        | 2.7692  | 9    | 3.5351          |
-| 2.7376        | 4.0     | 13   | 3.1911          |
-| 3.3753        | 4.9231  | 16   | 2.9601          |
-| 3.0944        | 5.8462  | 19   | 2.7577          |
-| 2.8686        | 6.7692  | 22   | 2.5897          |
-| 2.0042        | 8.0     | 26   | 2.3885          |
-| 2.4887        | 8.9231  | 29   | 2.2642          |
-| 2.3262        | 9.8462  | 32   | 2.1536          |
-| 2.2109        | 10.7692 | 35   | 2.0500          |
-| 1.5436        | 12.0    | 39   | 1.9406          |
-| 1.9916        | 12.9231 | 42   | 1.8923          |
-| 1.9223        | 13.8462 | 45   | 1.8639          |
-| 1.4561        | 14.7692 | 48   | 1.8528          |
+| 4.6041        | 0.9231  | 3    | 4.0265          |
+| 4.1638        | 1.8462  | 6    | 3.6005          |
+| 3.6673        | 2.7692  | 9    | 3.1980          |
+| 2.4141        | 4.0     | 13   | 2.7386          |
+| 2.8477        | 4.9231  | 16   | 2.4608          |
+| 2.4935        | 5.8462  | 19   | 2.2101          |
+| 2.1854        | 6.7692  | 22   | 1.9968          |
+| 1.4482        | 8.0     | 26   | 1.7341          |
+| 1.7153        | 8.9231  | 29   | 1.6110          |
+| 1.5533        | 9.8462  | 32   | 1.5225          |
+| 1.496         | 10.7692 | 35   | 1.4710          |
+| 1.0532        | 12.0    | 39   | 1.4317          |
+| 1.394         | 12.9231 | 42   | 1.4079          |
+| 1.3338        | 13.8462 | 45   | 1.3799          |
+| 1.3201        | 14.7692 | 48   | 1.3639          |
+| 0.9838        | 16.0    | 52   | 1.3533          |
+| 1.2802        | 16.9231 | 55   | 1.3484          |
+| 1.2627        | 17.8462 | 58   | 1.3456          |
+| 0.8898        | 18.4615 | 60   | 1.3449          |
 
 
 ### Framework versions

runs/Oct24_20-41-29_1f4e1c060daf/events.out.tfevents.1729802489.1f4e1c060daf.28754.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24734943728a43573a5f773459a269d1ce6bae88a1a398dfad2f8134fe75000e
+size 14918

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8dd5606dde3b3d0a9d92cb351e389c57acbd5f33650e941bd71a5c754645df9
+oid sha256:711d6f1814311fd895eb82fdbec70097c51d4b0396ae6716d60eed4ebf06d7b1
 size 5176