DNA-LLM/synth_model_medium_v2

README.md

@@ -1,7 +1,6 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: DNA-LLM/virus-pythia-19M-2048-two_d_plus_ce
+base_model: DNA-LLM/virus-pythia-19M-2048-ce_plus_energy
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # virus-pythia-19M-2048-ce_synthetic
 
-This model is a fine-tuned version of [DNA-LLM/virus-pythia-19M-2048-two_d_plus_ce](https://huggingface.co/DNA-LLM/virus-pythia-19M-2048-two_d_plus_ce) on an unknown dataset.
+This model is a fine-tuned version of [DNA-LLM/virus-pythia-19M-2048-ce_plus_energy](https://huggingface.co/DNA-LLM/virus-pythia-19M-2048-ce_plus_energy) on an unknown dataset.
 
 ## Model description
 
@@ -34,11 +33,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 48
-- eval_batch_size: 8
+- train_batch_size: 128
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 192
+- total_train_batch_size: 512
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 1
@@ -50,7 +49,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.45.1
-- Pytorch 2.4.0
+- Transformers 4.45.2
+- Pytorch 2.4.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.20.0
+- Tokenizers 0.20.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "DNA-LLM/virus-pythia-19M-2048-two_d_plus_ce",
+  "_name_or_path": "DNA-LLM/virus-pythia-19M-2048-ce_plus_energy",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -25,7 +25,7 @@
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.45.1",
+  "transformers_version": "4.45.2",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 1867

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.45.1"
+  "transformers_version": "4.45.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac180df7a9c3a09eb86040645375c3a78c54cd287ef00e5ac25364f060908ee
+oid sha256:d80a8e79f90d760ce9417525e72ee2e5b6bb74ab5db6b212d7ba4e9311199528
 size 83317056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d4c926f7ba5b6b82bae13321a935906609289f44d93ee6b743f281feb11110d
+oid sha256:2f6aacc867ad3688cf967956533cd9bd382cab3a7c095197a5590851a755c56a
 size 5176