Xmm
/

background-summaries-flan-t5-xl

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: google/flan-t5-large
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Rouge1
       type: rouge
-      value: 39.8
 widget:
 - text: "summarize:  Date: 2008-09-07, Update: The government seizes control of mortgage giants Fannie Mae and Freddie Mac, promising to inject up to $100 billion into each if they fail. In recent months, the two companies funded more than two-thirds of all home loans in the United States. Treasury Secretary Henry Paulson says the government will initially buy mortgage-backed securities worth up to $5 billion."
   example_title: "Example 1"
@@ -41,16 +41,13 @@ should probably proofread and complete it, then remove this comment. -->
 # background-summaries-flan-t5-large
-This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the background_summ dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3928
-- Rouge1: 39.8
-- Rouge2: 18.8
-- Rougel: 26.7
-- Rougelsum: 36.1
-- Bertscore Precision: 88.4
-- Bertscore Recall: 86.8
-- Bertscore F1: 87.5
 ## Model description
@@ -70,32 +67,36 @@ More information needed
 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
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------------------:|:----------------:|:------------:|
-| 1.6858        | 1.0   | 714  | 2.0262          | 41.1   | 19.3   | 27.1   | 37.3      | 87.9                | 87.1             | 87.5         |
-| 1.1309        | 2.0   | 1428 | 2.0889          | 40.8   | 19.6   | 27.3   | 37.1      | 87.8                | 87.1             | 87.4         |
-| 0.7568        | 3.0   | 2142 | 2.1569          | 40.8   | 19.1   | 27.3   | 37.0      | 87.8                | 87.0             | 87.4         |
-| 0.6779        | 4.0   | 2856 | 2.1800          | 39.5   | 18.4   | 26.4   | 35.9      | 87.8                | 86.7             | 87.2         |
-| 0.5567        | 5.0   | 3570 | 2.2454          | 40.1   | 19.0   | 26.8   | 36.6      | 88.2                | 86.8             | 87.4         |
-| 0.5264        | 6.0   | 4284 | 2.3172          | 38.8   | 18.1   | 26.1   | 35.2      | 88.0                | 86.6             | 87.3         |
-| 0.5046        | 7.0   | 4998 | 2.3409          | 40.1   | 19.0   | 27.0   | 36.4      | 88.4                | 86.8             | 87.6         |
-| 0.4465        | 8.0   | 5712 | 2.3751          | 39.8   | 18.7   | 26.7   | 36.1      | 88.4                | 86.7             | 87.6         |
-| 0.4524        | 9.0   | 6426 | 2.3824          | 40.0   | 19.0   | 27.1   | 36.4      | 88.5                | 86.8             | 87.6         |
-| 0.4308        | 10.0  | 7140 | 2.3928          | 39.8   | 18.8   | 26.7   | 36.1      | 88.4                | 86.8             | 87.5         |
 ### Framework versions
-- Transformers 4.33.1
-- Pytorch 1.13.1
-- Datasets 2.14.5
 - Tokenizers 0.13.3

 ---
 license: apache-2.0
+base_model: google/flan-t5-xl
 tags:
 - generated_from_trainer
 datasets:
     metrics:
     - name: Rouge1
       type: rouge
+      value: 43.0
 widget:
 - text: "summarize:  Date: 2008-09-07, Update: The government seizes control of mortgage giants Fannie Mae and Freddie Mac, promising to inject up to $100 billion into each if they fail. In recent months, the two companies funded more than two-thirds of all home loans in the United States. Treasury Secretary Henry Paulson says the government will initially buy mortgage-backed securities worth up to $5 billion."
   example_title: "Example 1"
 # background-summaries-flan-t5-large
+This model is a fine-tuned version of [google/flan-t5-xl](https://huggingface.co/google/flan-t5-xl) on the hf_dataset_script dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.1489
+- Rouge1: 43.0
+- Rouge2: 20.2
+- Rougel: 28.9
+- Rougelsum: 39.5
 ## Model description
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 10
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
+| No log        | 1.0   | 45   | 1.7449          | 37.9   | 17.2   | 25.4   | 34.5      |
+| No log        | 2.0   | 90   | 1.7964          | 40.8   | 19.0   | 27.5   | 37.3      |
+| No log        | 3.0   | 135  | 1.8705          | 39.5   | 18.2   | 26.7   | 36.1      |
+| No log        | 4.0   | 180  | 1.9253          | 40.1   | 18.7   | 27.0   | 36.6      |
+| No log        | 5.0   | 225  | 1.9471          | 41.8   | 19.6   | 28.0   | 38.4      |
+| No log        | 6.0   | 270  | 2.0004          | 42.5   | 20.0   | 28.5   | 39.0      |
+| No log        | 7.0   | 315  | 1.9927          | 43.2   | 20.6   | 29.1   | 39.7      |
+| No log        | 8.0   | 360  | 2.0119          | 42.6   | 20.4   | 28.8   | 39.1      |
+| No log        | 9.0   | 405  | 2.0653          | 42.7   | 20.3   | 28.7   | 39.1      |
+| No log        | 10.0  | 450  | 2.1489          | 43.0   | 20.2   | 28.9   | 39.5      |
 ### Framework versions
+- Transformers 4.27.4
+- Pytorch 2.0.0+cu118
+- Datasets 2.11.0
 - Tokenizers 0.13.3