Add corrected README.md

README.md

@@ -0,0 +1,60 @@
+---
+library_name: transformers
+license: other
+base_model: QizhiPei/BioMatrix-4B-Base
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft_pk_checkpoint_cpt_4b_biom_cpt_ds_32gpus_z0_merge_all_v1_ml2048_eps5_seed42
+  results: []
+---
+
+<!-- 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. -->
+
+# sft_pk_checkpoint_cpt_4b_biom_cpt_ds_32gpus_z0_merge_all_v1_ml2048_eps5_seed42
+
+This model is a fine-tuned version of [QizhiPei/BioMatrix-4B-Base](https://huggingface.co/QizhiPei/BioMatrix-4B-Base) on the guacamol_smi, the guacamol_sfi, the moses_smi, the moses_sfi, the pdbbind_v2020_mol_first_train, the pdbbind_v2020_mol_first_train, the pdbbind_v2020_mol_first_train, the pdbbind_v2020_mol_first_train, the knowmol_smi_history, the knowmol_smi_nohistory, the knowmol_sfi_history, the knowmol_sfi_nohistory, the mol_smi_all_dy, the mol_sfi_all_dy, the pro_all_zm_v1, the megascience, the yeast_peer, the yeast_peer, the human_peer, the human_peer, the ppi_affinity_peer, the ppi_affinity_peer, the pdbbind_peer, the pdbbind_peer, the bindingdb_peer, the bindingdb_peer, the qm9_2014_uncond, the qm9_2014_uncond, the qm9_2014_uncond, the qm9_2014_uncond, the qm9_2014_condx10, the qm9_2014_condx10, the qm9_2014_condx10, the pfud_3d_1d, the pfud_3d_1d, the pfud_3d_1d, the pfud_3d_1d, the dplm_1d_to_3d, the dplm_1d_to_3d, the dplm_1d_to_3d, the dplm_1d_to_3d, the dplm_1d_to_3d, the dplm_1d_to_3d, the dplm_1d_to_3d, the dplm_1d_to_3d, the dplm_3d_to_1d, the dplm_3d_to_1d, the dplm_3d_to_1d, the dplm_3d_to_1d, the dplm_3d_to_1d, the dplm_3d_to_1d, the dplm_3d_to_1d, the dplm_3d_to_1d, the dplm_1d_3d, the dplm_1d_3d, the dplm_1d_3d, the dplm_1d_3d, the dplm_1d_3d, the dplm_1d_3d, the dplm_1d_3d, the dplm_1d_3d, the dplm_3d_1d, the dplm_3d_1d, the dplm_3d_1d, the dplm_3d_1d, the dplm_3d_1d, the dplm_3d_1d, the dplm_3d_1d and the dplm_3d_1d datasets.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine_with_min_lr
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1