End of training

README.md

@@ -15,12 +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:
-- eval_loss: 2.5904
-- eval_runtime: 796.3196
-- eval_samples_per_second: 20.124
-- eval_steps_per_second: 2.517
-- epoch: 2.38
-- step: 56500
+- Loss: 3.6420
 
 ## Model description
 
@@ -47,9 +42,18 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3.0
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 3.7501        | 1.0   | 2334 | 3.6669          |
+| 3.6498        | 2.0   | 4668 | 3.6464          |
+| 3.6023        | 3.0   | 7002 | 3.6420          |
+
+
 ### Framework versions
 
-- Transformers 4.39.2
-- Pytorch 2.1.2.post3
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - 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": "4.39.2"
+  "transformers_version": "4.38.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525a769988059d6c7fdb09bf82e75143c115232cb09a3f29ace695521f2238e6
+oid sha256:29c0b1b219f9a3f81e189144427e66231012da2b4174e67f51fccf76d74adb53
 size 327657928

runs/Apr06_17-52-02_3f08951132dd/events.out.tfevents.1712425932.3f08951132dd.2242.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1322fd67e99e4c12f52e2c43735634699cb63d755f99d41e68f14f649705ea8c
-size 8439
+oid sha256:845c00c1a92ddbd74bfcbc563bb145a43f3f724f2afe6eaaf8e95c5b037b4aa8
+size 9064

runs/Apr06_17-52-02_3f08951132dd/events.out.tfevents.1712427542.3f08951132dd.2242.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b148b5eef4ea306e48f4c6384422eeb9853e98d67449f735005b9a89b2fc3e66
+size 359