metadata

widget:
  - text: >-
      DOCTOR: We have to get to Triton, destroy all the Morpheus machines. End
      this. This is how we get home?

      CLARA: I've never been so pleased to see

      (Sandmen move between them and the Tardis. More approach from behind.)

      DOCTOR: Nagata!

      (He turns Nagata round and uses her helmet schematic projector on a copper
      sheet.)

      CLARA: Doctor, quickly!

      (The Doctor taps the projection of the anti-grav shield generators.)

      NAGATA: What did you just do?

      DOCTOR: Self-destructed the grav-shields.

      NAGATA: What?

      (The spacestation tilts. The women cry out.)

      DOCTOR: It's working!

      (Clara uses her key to open the Tardis door. The Sandmen are stationary,
      falling to pieces.)

      DOCTOR: Neptune's gravity is pulling them apart, bit by bit! It doesn't
      make sense. None of this makes any sense.

      (They run inside the Tardis and it dematerialises.)
  - text: >-
      Michael: I'm starting my own paper company. 

      Andy: No way!? 

      Michael: Yeah. 

      Andy: In this climate? 

      Michael: Yeah. In all climates. It's going to be worldwide. And I'm
      looking for some talented salesmen to join me. That's where you come in. 

      Andy: Ehh... [in accent] well it's a very intriguing concept, isn't it?
      Um... hmmm..

      [makes weird noises to stall, Dwight enters] Michael is starting his own
      paper company. What do you think about that? 

      Dwight: Your own paper company. 

      Michael: Can you believe it? Well, we'll see, we'll see. It's just a, just
      a nugget of an idea right now so 

      Dwight: Right... 

      Michael: Potential, lots of potential. yes. 

      Dwight: What a courageous venture. 

      Michael: It's... it's very courageous, very exciting. Um... 

      Dwight: Location is hard for me, with the farm and the
      responsibilities... 

      Michael: That's what I was thinking, with the farm, so... You getting to
      wherever I'm gonna put my thing. 

      Dwight: Okay. So yeah. 

      Michael: So think about it. Lets put a pin in it for now. 

      Dwight: You know, I would love to put a pin in that.
  - text: >-
      Penny: This is great. What’s the occasion? 

      Leonard: No occasion. You know, things have been a little weird between
      us, so I wanted to throw together a fun night just for you. 

      Penny: That is so sweet. 

      Leonard: I got all your favourites. Beer, wings, sliders. We can watch the
      football game. I even painted my stomach. 

      Penny: Go Sports? 

      Leonard: Well, in case you were in the mood for baseball, I didn’t want to
      look ridiculous. 

      Penny: This is awesome. I love it! 

      Leonard: Good, I’m glad. 

      Penny: Gosh, I worked my ass off today. This is exactly what I needed. 

      Leonard: Great. Just relax and enjoy. Tonight is all about you. 

      Penny: Ah, thank you! 

      Leonard: So, where exactly are we in this relationship? 

      Penny: Oh, come on. I just told you I had a hard day. 

      Leonard: You’re right, I’m sorry. Let’s watch the game. 

      Penny: Great.
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: distilbart-cnn-6-6-finetuned-summscreen-10-epochs
    results: []

distilbart-cnn-6-6-finetuned-summscreen-10-epochs

This model is a fine-tuned version of sshleifer/distilbart-cnn-6-6 on the SummScreen dataset. It achieves the following results on the evaluation set:

Loss: 3.4962
Rouge1: 26.3499
Rouge2: 7.3999
Rougel: 18.6087
Rougelsum: 23.17
Gen Len: 49.8609

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.1229	1.0	3673	3.1271	26.6959	7.4401	18.8303	23.7132	49.9763
2.8872	2.0	7346	3.0482	26.6447	7.5599	18.5921	23.2786	49.8195
2.5733	3.0	11019	3.0292	27.425	7.9963	19.3544	24.1281	49.8757
2.3886	4.0	14692	3.0625	27.1291	7.5541	18.9375	23.8729	49.8905
2.215	5.0	18365	3.1118	27.1773	7.551	19.0524	24.1015	49.9142
2.0377	6.0	22038	3.2086	27.2237	7.8821	19.2136	24.0477	49.784
1.9358	7.0	25711	3.3405	26.7555	7.6628	18.8609	23.5264	49.8343
1.8292	8.0	29384	3.4124	26.7741	7.4529	18.9276	23.5827	49.8757
1.7702	9.0	33057	3.4457	26.6281	7.4415	18.7932	23.4608	49.8639
1.7443	10.0	36730	3.4962	26.3499	7.3999	18.6087	23.17	49.8609

Framework versions

Transformers 4.26.0
Pytorch 1.13.1
Datasets 2.9.0
Tokenizers 0.13.2