HarshalH/SFT_LoRA

README.md

@@ -3,9 +3,11 @@ library_name: transformers
 license: mit
 base_model: gpt2
 tags:
+- trl
+- sft
 - generated_from_trainer
 datasets:
-- scitldr
+- generator
 model-index:
 - name: output_dir
   results: []
@@ -16,9 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output_dir
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the scitldr dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3356
+- Loss: 2.4202
+- Model Preparation Time: 0.0039
 
 ## Model description
 
@@ -37,21 +40,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
+- learning_rate: 0.0002
+- train_batch_size: 4
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 249  | 3.3900          |
-| No log        | 2.0   | 498  | 3.3463          |
-| 3.5312        | 3.0   | 747  | 3.3356          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34034ee5f9269246d20da03d683b143174984ad2b730de1ac541543f758c28e0
+oid sha256:71ed609a2380b88caf4c1cd6b5a8b23ffe45d318b69c7234f2a9b3ca68930ba7
 size 497774208

runs/Oct06_04-12-39_a307efffef62/events.out.tfevents.1728187974.a307efffef62.30.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34117e5ad14042c61c0907dfc5bbdd083c61375e578bde62fb0c243536708f3c
+size 6105

runs/Oct06_04-12-39_a307efffef62/events.out.tfevents.1728188104.a307efffef62.30.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc9a4663d6a68e8708c05e10255c4018c724b9f43664e1a97d2265902862866
+size 425

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c3ef90b3f4968af27fb202950b04d7dcdd57e8b0133b9e4811a56dce1f3967e
-size 5240
+oid sha256:001ed3f93051497be8912b177276192701edca05cdcd60f16d6c9519a42961f4
+size 5496