Model save

README.md

@@ -11,7 +11,7 @@ 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/flursky/ProteinLanguageModeling/runs/tk1vw8z4)
+[<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/flursky/ProteinLanguageModeling/runs/2x1ifd0f)
 # seq2seq-plm
 
 This model is a fine-tuned version of [khairi/seq2seq-plm](https://huggingface.co/khairi/seq2seq-plm) on an unknown dataset.
@@ -34,15 +34,15 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 112
-- eval_batch_size: 112
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 224
+- total_train_batch_size: 256
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2000
-- num_epochs: 5
+- lr_scheduler_warmup_steps: 6000
+- num_epochs: 20
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58df85599eae37b4b7ff8d8bd7ae0da17d0708f304641d51d4b2352452bfd822
+oid sha256:3db29b8bfb4f5b38fbce67d6ed992976f53fb5bd589c95c5942a369cffa9e305
 size 230058672