language: en
license: mit
tags:
- summarization
model-index:
- name: SamuelAllen123/t5-efficient-large-nl36_fine_tune_sum_V2
results:
- task:
type: summarization
name: Summarization
dataset:
name: samsum
type: samsum
config: samsum
split: test
metrics:
- type: rouge
value: 50.5049
name: ROUGE-1
verified: true
- type: rouge
value: 25.6469
name: ROUGE-2
verified: true
- type: rouge
value: 41.7544
name: ROUGE-L
verified: true
- type: rouge
value: 46.2055
name: ROUGE-LSUM
verified: true
- type: loss
value: 1.5158178806304932
name: loss
verified: true
- type: gen_len
value: 24.0342
name: gen_len
verified: true
- task:
type: summarization
name: Summarization
dataset:
name: cnn_dailymail
type: cnn_dailymail
config: 3.0.0
split: test
metrics:
- type: rouge
value: 34.4055
name: ROUGE-1
verified: true
- type: rouge
value: 14.127
name: ROUGE-2
verified: true
- type: rouge
value: 24.3353
name: ROUGE-L
verified: true
- type: rouge
value: 31.6582
name: ROUGE-LSUM
verified: true
- type: loss
value: 2.4456119537353516
name: loss
verified: true
- type: gen_len
value: 45.928
name: gen_len
verified: true
- task:
type: summarization
name: Summarization
dataset:
name: samsum
type: samsum
config: samsum
split: train
metrics:
- type: rouge
value: 54.933
name: ROUGE-1
verified: true
- type: rouge
value: 31.7965
name: ROUGE-2
verified: true
- type: rouge
value: 47.0057
name: ROUGE-L
verified: true
- type: rouge
value: 51.2027
name: ROUGE-LSUM
verified: true
- type: loss
value: 1.130684494972229
name: loss
verified: true
- type: gen_len
value: 23.7989
name: gen_len
verified: true
- task:
type: summarization
name: Summarization
dataset:
name: scientific_papers
type: scientific_papers
config: pubmed
split: train
metrics:
- type: rouge
value: 23.6698
name: ROUGE-1
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTg4OTMwYjkyNmU1ZjdmN2Q4MWE4YzFkZjUyMDZhNDNhYjBkODg3ZjI5NDQxMTcyNDUyMzkwNDZlNjNhZGRiOSIsInZlcnNpb24iOjF9.0kRK7iA642z0YWAH81v1_-pil6TyM3bezGfZtqGev5O7AgGkxzfQaIDNhkVVvVIJdUPJFD7L36XyLx3AWO5BCQ
- type: rouge
value: 7.5691
name: ROUGE-2
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2Q2MDc1ZjZlYjRmZDZkNjY3MmFhODAzZWUwZjA1M2RlZGUwYTY2ZjM2ZTM1NzQ3YjAxMDFiMWZlMGMwNTgyOCIsInZlcnNpb24iOjF9._Y59aEEGLn0Ij622V8Rwljp-h4uTuCfoPgJdvMN6GvCyKRzwugHo8tedfTpbTAb6cicjiWjKvKurqXTjpw1KAw
- type: rouge
value: 15.6071
name: ROUGE-L
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNjMwM2Q2ODYwZWE4MzNhNDNlNzlhNjU2NGUxYjlhNDM3MzM5MmJjNzU4YTYxNzI4ZmQ3YzQ1YjMzMDZkMTQ4ZCIsInZlcnNpb24iOjF9.zyfiVsuCEXCTkGAqNxCZ8hTKVxAE0JmJRbNZ04HoBi7qYFB13_7JTB6tOvAEH34W-2yvpOs4cBsFqtXg7RvnCA
- type: rouge
value: 21.4565
name: ROUGE-LSUM
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTE4MjVlZjI5NDBkZjRmODA3MmIzY2I0YWUwZjEyMzYwNjFjNTY3N2NjMmY3ZThlODBjN2VhZWZlODliZmEyZSIsInZlcnNpb24iOjF9.RFZbr5R9cJtrhzWMKys62fiBxKv8MYe6_115NBjEZ6wOwzVih5SdJE8r2EK-1wdCMF_jLGPYQvZ-zyj3KHGWCw
- type: loss
value: 3.9369945526123047
name: loss
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTc3MzMwYTg5OWIyZGQxNGJlYzExNTY0MjUyY2M5M2NiOGQ2ODI0MWFiMzJjYWY4ZGNkZmY2MmUyZjVjODRiYSIsInZlcnNpb24iOjF9.iDxSfTwZRV5VboHLjF4a47kPXagG7bY78WIejIM37ykpksXxVYssZlmK6UxtkEmZuWypqbQjz6oOjTjy6x3tDQ
- type: gen_len
value: 65.9987
name: gen_len
verified: true
verifyToken: >-
eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODdmYzFiNzU3N2VlMWMyMGEwZmFkZmExZWRlN2NjNWI3ZGJjNmYzMWExYWM5MWY2MzJkMmY0ZGE2NjFjMjRjYyIsInZlcnNpb24iOjF9.3ByM1s1Ux-PDBBnf6i3FUtFLzpmZXcikIfrsR3vTIi9567r789Wm8sW81blFHNfnST-ZHQxPKJOuv4ho8S4eCg
NOT SELF REPORTED VALUES FOR THE LEADERBOARD, I HAVE NO CLUE WHY ITS BROKE. CHECK PULL REQUEST
Use summarization without adding summarize to the start of the string.
Trained on Samsum train split.
Parameters for training:
no_decay = ["bias", "LayerNorm.weight", "layer_norm.weight"] optimizer_grouped_parameters = [ { "params": [p for n, p in model.named_parameters() if not any(nd in n for nd in no_decay)], "weight_decay": 0.0, }, { "params": [p for n, p in model.named_parameters() if any(nd in n for nd in no_decay)], "weight_decay": 0.0, }, ]
lr = 0.00005 optimizer = torch.optim.RAdam(optimizer_grouped_parameters, lr=lr)
lr_scheduler = get_scheduler( name="linear", optimizer=optimizer, num_warmup_steps=0, num_training_steps=50005)
This was only for 10K steps with a batch size of 10
If you want more info, feel free to message me or email me at: [email protected]