Training in progress, step 4500

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6421
+- Loss: 3.6424
 
 ## Model description
 
@@ -45,14 +46,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.7604        | 1.0   | 2334 | 3.6658          |
-| 3.6531        | 2.0   | 4668 | 3.6478          |
-| 3.6015        | 3.0   | 7002 | 3.6421          |
+| 3.7578        | 1.0   | 2334 | 3.6665          |
+| 3.6405        | 2.0   | 4668 | 3.6480          |
+| 3.5943        | 3.0   | 7002 | 3.6424          |
 
 
 ### Framework versions
 
-- Transformers 4.30.2
+- Transformers 4.31.0.dev0
 - Pytorch 2.0.1+cu117
 - Datasets 2.13.1
 - Tokenizers 0.13.3

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e148fd0faf8d817002dbf8cbbb8564a688a288ef39a6003c7819a84b7ab5091
+oid sha256:dc08b41e72d776dd9d093714d19cc0fb68ef03d9e6bb0a29a093daeaa8c70eac
 size 327674773

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53ab0c774e6b3211603139e12415ac5d8e98f84422d691978457c012a6c4fd8
+oid sha256:731a47137aa43055111afb795a7ec496c9ac63ff5a322d2974e0ad73885071a0
 size 4027