End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: bsd-3-clause
+base_model: LongSafari/hyenadna-small-32k-seqlen-hf
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: hyenadna-small-32k-seqlen-hf_ft_BioS73_1kbpHG19_DHSs_H3K27AC
+  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. -->
+
+# hyenadna-small-32k-seqlen-hf_ft_BioS73_1kbpHG19_DHSs_H3K27AC
+
+This model is a fine-tuned version of [LongSafari/hyenadna-small-32k-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-small-32k-seqlen-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4833
+- F1 Score: 0.8364
+- Precision: 0.8120
+- Recall: 0.8624
+- Accuracy: 0.8200
+- Auc: 0.8967
+- Prc: 0.8849
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | F1 Score | Precision | Recall | Accuracy | Auc    | Prc    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.481         | 0.1864 | 500  | 0.4460          | 0.8302   | 0.7734    | 0.8959 | 0.8043   | 0.8756 | 0.8562 |
+| 0.4329        | 0.3727 | 1000 | 0.4339          | 0.8343   | 0.8056    | 0.8652 | 0.8166   | 0.8840 | 0.8728 |
+| 0.4273        | 0.5591 | 1500 | 0.4282          | 0.8317   | 0.8105    | 0.8541 | 0.8155   | 0.8879 | 0.8797 |
+| 0.4207        | 0.7454 | 2000 | 0.4154          | 0.8442   | 0.7975    | 0.8966 | 0.8233   | 0.8906 | 0.8784 |
+| 0.4072        | 0.9318 | 2500 | 0.4407          | 0.8344   | 0.8149    | 0.8547 | 0.8189   | 0.8893 | 0.8806 |
+| 0.3884        | 1.1182 | 3000 | 0.4272          | 0.8471   | 0.7887    | 0.9148 | 0.8237   | 0.8936 | 0.8821 |
+| 0.3692        | 1.3045 | 3500 | 0.4085          | 0.8412   | 0.8148    | 0.8694 | 0.8248   | 0.8956 | 0.8854 |
+| 0.3814        | 1.4909 | 4000 | 0.3987          | 0.8379   | 0.8210    | 0.8554 | 0.8233   | 0.8977 | 0.8878 |
+| 0.3628        | 1.6772 | 4500 | 0.4825          | 0.8441   | 0.8040    | 0.8883 | 0.8248   | 0.8972 | 0.8885 |
+| 0.3816        | 1.8636 | 5000 | 0.4157          | 0.8482   | 0.8041    | 0.8973 | 0.8286   | 0.8944 | 0.8817 |
+| 0.3462        | 2.0499 | 5500 | 0.4931          | 0.8302   | 0.8431    | 0.8177 | 0.8215   | 0.8970 | 0.8868 |
+| 0.338         | 2.2363 | 6000 | 0.4842          | 0.8464   | 0.7970    | 0.9022 | 0.8252   | 0.8941 | 0.8802 |
+| 0.3356        | 2.4227 | 6500 | 0.4493          | 0.8434   | 0.8034    | 0.8876 | 0.8241   | 0.8896 | 0.8750 |
+| 0.3416        | 2.6090 | 7000 | 0.4466          | 0.8478   | 0.7920    | 0.9120 | 0.8252   | 0.8902 | 0.8744 |
+| 0.3339        | 2.7954 | 7500 | 0.4833          | 0.8364   | 0.8120    | 0.8624 | 0.8200   | 0.8967 | 0.8849 |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.0

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "LongSafari/hyenadna-small-32k-seqlen-hf",
+  "activation_freq": 10,
+  "architectures": [
+    "HyenaDNAForSequenceClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "LongSafari/hyenadna-small-32k-seqlen-hf--configuration_hyena.HyenaConfig",
+    "AutoModel": "LongSafari/hyenadna-small-32k-seqlen-hf--modeling_hyena.HyenaDNAModel",
+    "AutoModelForCausalLM": "LongSafari/hyenadna-small-32k-seqlen-hf--modeling_hyena.HyenaDNAForCausalLM",
+    "AutoModelForSequenceClassification": "LongSafari/hyenadna-small-32k-seqlen-hf--modeling_hyena.HyenaDNAForSequenceClassification"
+  },
+  "d_inner": 1024,
+  "d_model": 256,
+  "emb_dim": 5,
+  "embed_dropout": 0.1,
+  "filter_order": 64,
+  "hyena_dropout": 0.0,
+  "hyena_filter_dropout": 0.0,
+  "hyena_order": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_seq_len": 32770,
+  "model_type": "hyenadna",
+  "n_layer": 4,
+  "num_inner_mlps": 2,
+  "pad_token_id": 4,
+  "pad_vocab_size_multiple": 8,
+  "problem_type": "single_label_classification",
+  "short_filter_order": 3,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "train_freq": true,
+  "transformers_version": "4.42.3",
+  "use_bias": true,
+  "vocab_size": 12
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab35f89947918004e0025933d650f0af264029bada07bfb894fba9da19ecaa6
+size 16300602

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[BOS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[BOS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "LongSafari/hyenadna-small-32k-seqlen-hf--tokenization_hyena.HyenaDNATokenizer",
+      null
+    ]
+  },
+  "bos_token": "[BOS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 32770,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "HyenaDNATokenizer",
+  "unk_token": "[UNK]"
+}