End of training

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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6421
+- Loss: 2.3852
 
 ## Model description
 
@@ -45,14 +46,13 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.7602        | 1.0   | 2334 | 3.6669          |
-| 3.653         | 2.0   | 4668 | 3.6472          |
-| 3.6006        | 3.0   | 7002 | 3.6421          |
+| 2.6974        | 1.0   | 2015 | 2.5232          |
+| 2.5708        | 2.0   | 4030 | 2.4168          |
+| 2.5374        | 3.0   | 6045 | 2.3852          |
 
 
 ### Framework versions
 
-- Transformers 4.30.0
+- Transformers 4.38.2
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.13.3
+- Tokenizers 0.15.2

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 50256,
   "eos_token_id": 50256,
-  "transformers_version": "4.30.0"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a015e2d537daee9f3b841726aa7df661e4bc343d1a1ef6b2f09a0b646cd9aed7
+oid sha256:5a6ebd2380d428d358ad46b2d77a22816e9f92de52d835da74db96845081ea9b
 size 327657928

runs/Apr10_05-01-44_02397241b260/events.out.tfevents.1712725305.02397241b260.426.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bbf45f67f7e39c8a18d069bd939a85ef5f2ed3fe65d9f0ab31e405853501390
-size 8017
+oid sha256:980048bdcad737c880939724c60c5293db23fa87128475fc8d9f79bec69a031a
+size 8642

runs/Apr10_05-01-44_02397241b260/events.out.tfevents.1712727204.02397241b260.426.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb88dca7ba0c2336493fce55e9e9a55e1eeebae3914abcdbdded8e9b658a6481
+size 359