update model card README.md
Browse files- .ipynb_checkpoints/all_results-checkpoint.json +22 -0
- README.md +62 -0
.ipynb_checkpoints/all_results-checkpoint.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_gen_len": 41.562881562881564,
|
| 3 |
+
"eval_loss": 1.869093418121338,
|
| 4 |
+
"eval_rouge1": 35.1506,
|
| 5 |
+
"eval_rouge2": 16.0888,
|
| 6 |
+
"eval_rougeL": 29.7007,
|
| 7 |
+
"eval_rougeLsum": 32.4251,
|
| 8 |
+
"eval_runtime": 261.235,
|
| 9 |
+
"eval_samples": 819,
|
| 10 |
+
"eval_samples_per_second": 3.135,
|
| 11 |
+
"eval_steps_per_second": 0.199,
|
| 12 |
+
"predict_gen_len": 41.73230769230769,
|
| 13 |
+
"predict_loss": 1.8758330345153809,
|
| 14 |
+
"predict_rouge1": 35.1974,
|
| 15 |
+
"predict_rouge2": 16.4972,
|
| 16 |
+
"predict_rougeL": 30.2616,
|
| 17 |
+
"predict_rougeLsum": 32.5539,
|
| 18 |
+
"predict_runtime": 419.3492,
|
| 19 |
+
"predict_samples": 1300,
|
| 20 |
+
"predict_samples_per_second": 3.1,
|
| 21 |
+
"predict_steps_per_second": 0.196
|
| 22 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- navjordj/SNL_summarization
|
| 6 |
+
model-index:
|
| 7 |
+
- name: t5-large-snl-2
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# t5-large-snl-2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [navjordj/t5-large-snl](https://huggingface.co/navjordj/t5-large-snl) on the navjordj/SNL_summarization dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- eval_loss: 1.8691
|
| 19 |
+
- eval_rouge1: 35.1506
|
| 20 |
+
- eval_rouge2: 16.0888
|
| 21 |
+
- eval_rougeL: 29.7007
|
| 22 |
+
- eval_rougeLsum: 32.4251
|
| 23 |
+
- eval_gen_len: 41.5629
|
| 24 |
+
- eval_runtime: 261.235
|
| 25 |
+
- eval_samples_per_second: 3.135
|
| 26 |
+
- eval_steps_per_second: 0.199
|
| 27 |
+
- step: 0
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 16
|
| 49 |
+
- seed: 42
|
| 50 |
+
- distributed_type: multi-GPU
|
| 51 |
+
- gradient_accumulation_steps: 4
|
| 52 |
+
- total_train_batch_size: 64
|
| 53 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
+
- lr_scheduler_type: linear
|
| 55 |
+
- num_epochs: 20.0
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- Transformers 4.27.0.dev0
|
| 60 |
+
- Pytorch 1.13.1
|
| 61 |
+
- Datasets 2.10.1
|
| 62 |
+
- Tokenizers 0.13.2
|