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

README.md

@@ -13,6 +13,7 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/theubaada/huggingface/runs/iqgj3vcb)
 # long-t5-tglobal-base
 
 This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset.
@@ -44,13 +45,13 @@ The following hyperparameters were used during training:
 - eval_batch_size: 1
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 2
+- num_devices: 4
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
-- total_eval_batch_size: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 9
+- num_epochs: 13
 
 ### Training results
 
@@ -69,7 +70,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.40.2
+- Transformers 4.41.0
 - Pytorch 2.2.0
 - Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -29,7 +29,7 @@
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.0",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -1,9 +1,10 @@
 {
+  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "max_length": 2048,
   "num_beams": 5,
   "pad_token_id": 0,
   "repetition_penalty": 2.0,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.41.0"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c611d9f9ff8ec098da6eb03453782a6458e06a90779c1927d1d621248f690dfb
-size 6776
+oid sha256:74aca712e060cee865ad4838d5b8a095000e733bff434150a5184cdcfed49e2a
+size 6968