ubaada/pegasus-x-large-booksum-16k

README.md

@@ -1,38 +1,12 @@
 ---
-base_model: google/pegasus-x-large
+base_model: ubaada/pegasus-x-large-booksum-16k
 tags:
-  - summarization
-  - summary
-  - booksum
-  - long-document
-  - long-form
-datasets:
-  - ubaada/booksum-complete-cleaned
-language:
-  - en
-pipeline_tag: summarization
+- generated_from_trainer
 metrics:
-  - rouge
+- rouge
 model-index:
-  - name: ubaada/pegasus-x-large-booksum-16k
-    results:
-      - task:
-          type: summarization
-          name: Summarization
-        dataset:
-          name: BookSum
-          type: ubaada/booksum-complete-cleaned
-          config: ubaada--booksum
-          split: test
-        metrics:
-          - type: rouge
-            value: 30.947853
-            name: ROUGE-1
-            verified: false
-          - type: rouge
-            value: 5.568146
-            name: ROUGE-2
-            verified: false
+- name: pegasus-x-large-booksum-16k
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # pegasus-x-large-booksum-16k
 
-This model is a fine-tuned version of [google/pegasus-x-large](https://huggingface.co/google/pegasus-x-large) on [ubaada/booksum-complete-cleaned](https://huggingface.co/datasets/ubaada/booksum-complete-cleaned). It was trained on the 'train' split of chapters sub-dataset.
+This model is a fine-tuned version of [ubaada/pegasus-x-large-booksum-16k](https://huggingface.co/ubaada/pegasus-x-large-booksum-16k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9677
-- Rouge1: 0.3504
-- Rouge2: 0.0525
-- Rougel: 0.1398
+- Loss: 1.9879
+- Rouge1: 0.2983
+- Rouge2: 0.0463
+- Rougel: 0.1367
 
 ## Model description
 
@@ -64,12 +38,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 8e-05
+- learning_rate: 4e-05
 - train_batch_size: 8
 - eval_batch_size: 1
 - seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 64
+- total_eval_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1
@@ -78,7 +55,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
 |:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
-| 1.417         | 0.9996 | 628  | 1.9677          | 0.3504 | 0.0525 | 0.1398 |
+| 1.3846        | 0.9992 | 314  | 1.9879          | 0.2983 | 0.0463 | 0.1367 |
 
 
 ### Framework versions
@@ -86,4 +63,4 @@ The following hyperparameters were used during training:
 - Transformers 4.40.2
 - Pytorch 2.2.0
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/pegasus-x-large",
+  "_name_or_path": "ubaada/pegasus-x-large-booksum-16k",
   "activation_dropout": 0.1,
   "activation_function": "relu",
   "add_bias_logits": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bc6703ce0f79f18f042278837400e453556b0eb53294f71494d559215d3ec4
+oid sha256:cf3259de6f0e881dfe94b5afa80f69b4c39f1896ae8744ea7a32db06b5ddb85a
 size 2274730128

tokenizer.json

@@ -2,12 +2,14 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 16384,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
-    "strategy": "BatchLongest",
+    "strategy": {
+      "Fixed": 1024
+    },
     "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 0,

tokenizer_config.json

@@ -958,10 +958,17 @@
   "full_tokenizer_file": null,
   "mask_token": "<mask_2>",
   "mask_token_sent": "<mask_1>",
-  "model_max_length": 16384,
+  "max_length": 16384,
+  "model_max_length": 12288,
   "offset": 103,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "PegasusTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4c0874fe606601da864bbc94c7fad30e9f3c27fcb820c0b4b500abef9ac29b
-size 6712
+oid sha256:c04a4fc24c48fd0c95b4c7009572759f86af67b73d4e2c597e72560a7a1f9afc
+size 6776