Upload folder using huggingface_hub

config.json

@@ -0,0 +1,52 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "ProteomeLMForMaskedLM"
+  ],
+  "attention_dropout": 0.1,
+  "batch_size": 64,
+  "beta1": 0.9,
+  "beta2": 0.999,
+  "dataloader_num_workers": 8,
+  "db_path": "/home/malbrank/training/",
+  "dim": 128,
+  "dropout": 0.1,
+  "dtype": "bfloat16",
+  "eval_accumulation_steps": 1,
+  "eval_epochs": 1,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": false,
+  "hidden_dim": 128,
+  "initializer_range": 0.02,
+  "input_size": 1152,
+  "learning_rate": 0.0003,
+  "logging_steps": 10,
+  "loss_choice": "polar",
+  "loss_type": "mse",
+  "mask_fraction": 0.5,
+  "max_grad_norm": 1.0,
+  "max_position_embeddings": 512,
+  "max_steps": 1000000,
+  "min_taxid_size": 200,
+  "model_type": "distilbert",
+  "n_heads": 8,
+  "n_inner": null,
+  "n_layers": 6,
+  "namedir": "ProteomeLM-XXS-Kuma",
+  "num_epochs": 2000,
+  "output_dir": "/home/malbrank/ProteomeLM/output/",
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "save_epochs": 15,
+  "scheduler": "cosine",
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": true,
+  "use_one_gpu": "0",
+  "vocab_size": 30522,
+  "wandb_project": "proteomelm",
+  "warmup_steps": 500,
+  "weight_decay": 0.01
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86307b3130acb78a073df385abbd0ee2ea077c5d62e9e07eb7340c08c3b498e1
+size 11339908

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ac13792d86a35055882ac2630a6050da43d85199f99258f8380fc7e79aab78c
+size 4246337

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21574f7b3c3648309222a1ccfb91e1cec2979cabcd91e89380e9973b46f6b57
+size 14443

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b8adca72c79a24af6c7c1fc23ff8437f4bac3cf4189b3d54558f42c0a773a1c
+size 1263

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:902e67761854588e8a4d111789440b874e556eaca2883c5806427b5a14b150f6
+size 5571