End of training

README.md

@@ -3,11 +3,9 @@ library_name: transformers
 license: mit
 base_model: gpt2
 tags:
-- trl
-- sft
 - generated_from_trainer
 datasets:
-- generator
+- scitldr
 model-index:
 - name: output_dir
   results: []
@@ -18,7 +16,9 @@ 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 generator dataset.
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the scitldr dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3648
 
 ## Model description
 
@@ -37,16 +37,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 8
+- learning_rate: 2e-05
+- train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3.0
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 125  | 3.4195          |
+| No log        | 2.0   | 250  | 3.3752          |
+| No log        | 3.0   | 375  | 3.3648          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5534479af1099859a988a67bda6350171e8f67f37926313c06b25c061a9bd2c
+oid sha256:4976df38c10136e8a181e491a9238313ff312b3b7bc70932fa975447e1a3f752
 size 497774208

runs/Oct02_00-33-26_1bd55d887019/events.out.tfevents.1727829208.1bd55d887019.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c63dcac070e9c53edb02969468a226054650e8fe127bb9619705839958dd142
+size 6332

runs/Oct02_00-33-26_1bd55d887019/events.out.tfevents.1727829648.1bd55d887019.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26f21accf1224814757ba0bce9a53edab10985a752713b0e4bdd2e5cac329bf2
+size 359

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673ec8b679beebddf9c88db8b17e5ce3dbfbeddad0cc5b5e699f479888f62354
-size 5496
+oid sha256:c598273ea12d192c47f16251e35c9978e0c43ecc582ecfeab217a4e4bb52e0e2
+size 5240