Upload folder using huggingface_hub

ins_model/README.md

@@ -0,0 +1,88 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+datasets:
+- crispr_data
+model-index:
+- name: SX_spymac_Lindel_ins
+  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. -->
+
+# SX_spymac_Lindel_ins
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the crispr_data dataset.
+It achieves the following results on the evaluation set:
+- Loss: 119.2468
+
+## 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: 0.001
+- train_batch_size: 100
+- eval_batch_size: 100
+- seed: 63036
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 30.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2556.3674     | 1.0   | 327  | 2267.2915       |
+| 1854.776      | 2.0   | 654  | 1407.0547       |
+| 1097.5239     | 3.0   | 981  | 812.6055        |
+| 630.9811      | 4.0   | 1308 | 467.9777        |
+| 370.5749      | 5.0   | 1635 | 283.4810        |
+| 236.7095      | 6.0   | 1962 | 193.0472        |
+| 173.0947      | 7.0   | 2289 | 152.0597        |
+| 144.8752      | 8.0   | 2616 | 134.1329        |
+| 132.4725      | 9.0   | 2943 | 126.2140        |
+| 126.8917      | 10.0  | 3270 | 122.6400        |
+| 124.3303      | 11.0  | 3597 | 120.9474        |
+| 123.1025      | 12.0  | 3924 | 120.1213        |
+| 122.4976      | 13.0  | 4251 | 119.7383        |
+| 122.1977      | 14.0  | 4578 | 119.6165        |
+| 122.0415      | 15.0  | 4905 | 119.4864        |
+| 121.9523      | 16.0  | 5232 | 119.4457        |
+| 121.8987      | 17.0  | 5559 | 119.3924        |
+| 121.8588      | 18.0  | 5886 | 119.3609        |
+| 121.8288      | 19.0  | 6213 | 119.3318        |
+| 121.8026      | 20.0  | 6540 | 119.2987        |
+| 121.7802      | 21.0  | 6867 | 119.3034        |
+| 121.7603      | 22.0  | 7194 | 119.2751        |
+| 121.7477      | 23.0  | 7521 | 119.2694        |
+| 121.7309      | 24.0  | 7848 | 119.2594        |
+| 121.7196      | 25.0  | 8175 | 119.2585        |
+| 121.7066      | 26.0  | 8502 | 119.2561        |
+| 121.6949      | 27.0  | 8829 | 119.2545        |
+| 121.6839      | 28.0  | 9156 | 119.2495        |
+| 121.6734      | 29.0  | 9483 | 119.2465        |
+| 121.6636      | 30.0  | 9810 | 119.2468        |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.19.1

ins_model/config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "/home/ljw/sdc1/CRISPR_results/Lindel/SX_spymac_Lindel_ins",
   "architectures": [
     "LindelModel"
   ],

ins_model/model.py

@@ -0,0 +1,73 @@
+from transformers import PretrainedConfig, PreTrainedModel
+import torch.nn as nn
+import torch
+import torch.nn.functional as F
+
+class LindelConfig(PretrainedConfig):
+    model_type = "Lindel"
+    label_names = ["count"]
+
+    def __init__(
+        self,
+        dlen = 30, # the upper limit of deletion length (strictly less than dlen)
+        mh_len = 4, # the upper limit of micro-homology length
+        model = "indel", # the actual model, should be "indel", "del", or "ins"
+        reg_mode = "l2", # regularization method, should be "l2" or "l1"
+        reg_const = 0.01, # regularization coefficient
+        seed = 63036, # random seed for intialization
+        **kwargs,
+    ):
+        self.dlen = dlen
+        self.mh_len = mh_len
+        self.model = model
+        self.reg_mode = reg_mode
+        self.reg_const = reg_const
+        self.seed = seed
+        super().__init__(**kwargs)
+
+class LindelModel(PreTrainedModel):
+    config_class = LindelConfig
+
+    def __init__(self, config) -> None:
+        super().__init__(config)
+        # In more recent versions of PyTorch, you no longer need to explicitly register_parameter, it's enough to set a member of your nn.Module with nn.Parameter to "notify" pytorch that this variable should be treated as a trainable parameter (https://stackoverflow.com/questions/59234238/how-to-add-parameters-in-module-class-in-pytorch-custom-model).
+        self.generator = torch.Generator().manual_seed(config.seed)
+        self.reg_mode = config.reg_mode
+        self.reg_const = config.reg_const
+        if config.model == "indel":
+            # onehotencoder(ref[cut-17:cut+3])
+            feature_dim = 20 * 4 + 19 * 16
+            class_dim = 2
+        elif config.model == "ins":
+            # onehotencoder(ref[cut-3:cut+3])
+            feature_dim = 6 * 4 + 5 * 16
+            class_dim = 21
+        elif config.model == "del":
+            class_dim = (4 + 1 + 4 + config.dlen - 1) * (config.dlen - 1) // 2
+            # concatenate get_feature and onehotencoder(ref[cut-17:cut+3])
+            feature_dim = class_dim * (config.mh_len + 1) + 20 * 4 + 19 * 16
+        self.linear = nn.Linear(in_features=feature_dim, out_features=class_dim)
+        self.initialize_weights()
+
+    def initialize_weights(self):
+        for m in self.modules():
+            if isinstance(m, nn.Linear):
+                nn.init.normal_(m.weight, mean=0, std=1, generator=self.generator)
+                if m.bias is not None:
+                    nn.init.constant_(m.bias, 0)
+
+    def forward(self, input, count=None) -> torch.Tensor:
+        logit = self.linear(input)
+        if count is not None:
+            return {
+                "logit": logit,
+                "loss": self.cross_entropy_reg(logit, count)
+            }
+        return {"logit": logit}
+
+    def cross_entropy_reg(self, logit, count):
+        if self.reg_mode == "l2":
+            reg_term = (self.linear.weight ** 2).sum()
+        elif self.reg_mode == "l1":
+            reg_term = abs(self.linear.weight).sum()
+        return -(F.log_softmax(logit, dim=1) * F.normalize(count.to(torch.float32), p=1.0, dim=1)).sum() + logit.shape[0] * self.reg_const * reg_term

ins_model/runs/Nov20_10-39-06_ljw-System-Product-Name/events.out.tfevents.1732071299.ljw-System-Product-Name.1207628.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc226724cd177a32319de0a533584f945aed223c607ea92374225170bd7f4a62
+size 19399

ins_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c005e7ea435126b1519e6f31e72b44b1d280ed91d1a896dc30926f4eee0d10
+size 5304