DNA-LLM/virus_pythia_14_1024_cross_entropy

README.md

@@ -32,8 +32,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 40
-- eval_batch_size: 40
+- train_batch_size: 80
+- eval_batch_size: 80
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.40.0
+- Transformers 4.40.1
 - Pytorch 2.2.1+cu121
 - Datasets 2.19.0
 - Tokenizers 0.19.1

config.json

@@ -23,7 +23,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.40.1",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 9

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.40.0"
+  "transformers_version": "4.40.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7198f04c137198d2bcfa67ede584dc8c96153d88304bc53355cb603c34d29666
+oid sha256:8e06adf92fe753dc442723db3d871fa396947156cca82c3799c7de511737a02b
 size 4777048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68f63195edd8ab732fe7d4f1db65872537bae4e94e35c4eaabf8c8034cf8b7fc
+oid sha256:30599c12bfd41d82381809d03b7c0350b5f494e08d13f33d6b14050decb9696b
 size 4984