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_BioS45_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_BioS45_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: 0.5632
+- F1 Score: 0.8023
+- Precision: 0.8234
+- Recall: 0.7823
+- Accuracy: 0.7989
+- Auc: 0.8729
+- Prc: 0.8701
+
+## 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.5477        | 0.2103 | 500  | 0.4845          | 0.7868   | 0.7923    | 0.7815 | 0.7791   | 0.8482 | 0.8295 |
+| 0.4789        | 0.4207 | 1000 | 0.4609          | 0.8003   | 0.7943    | 0.8065 | 0.7901   | 0.8624 | 0.8547 |
+| 0.4505        | 0.6310 | 1500 | 0.4569          | 0.7972   | 0.8068    | 0.7879 | 0.7909   | 0.8700 | 0.8670 |
+| 0.4558        | 0.8414 | 2000 | 0.4471          | 0.8289   | 0.7664    | 0.9024 | 0.8056   | 0.8753 | 0.8637 |
+| 0.4376        | 1.0517 | 2500 | 0.4435          | 0.8324   | 0.7840    | 0.8871 | 0.8136   | 0.8786 | 0.8708 |
+| 0.4299        | 1.2621 | 3000 | 0.4596          | 0.8284   | 0.7795    | 0.8839 | 0.8090   | 0.8770 | 0.8676 |
+| 0.4329        | 1.4724 | 3500 | 0.4409          | 0.8133   | 0.8203    | 0.8065 | 0.8069   | 0.8805 | 0.8781 |
+| 0.4187        | 1.6828 | 4000 | 0.4495          | 0.8063   | 0.8246    | 0.7887 | 0.8023   | 0.8802 | 0.8798 |
+| 0.4211        | 1.8931 | 4500 | 0.4363          | 0.8303   | 0.7925    | 0.8718 | 0.8141   | 0.8807 | 0.8734 |
+| 0.3818        | 2.1035 | 5000 | 0.4506          | 0.8350   | 0.7932    | 0.8815 | 0.8183   | 0.8809 | 0.8717 |
+| 0.3524        | 2.3138 | 5500 | 0.4775          | 0.8184   | 0.7968    | 0.8411 | 0.8052   | 0.8785 | 0.8745 |
+| 0.3601        | 2.5242 | 6000 | 0.4678          | 0.8263   | 0.7770    | 0.8823 | 0.8065   | 0.8758 | 0.8688 |
+| 0.3708        | 2.7345 | 6500 | 0.4836          | 0.8226   | 0.8064    | 0.8395 | 0.8111   | 0.8769 | 0.8743 |
+| 0.3911        | 2.9449 | 7000 | 0.4733          | 0.8207   | 0.7912    | 0.8524 | 0.8056   | 0.8748 | 0.8666 |
+| 0.3136        | 3.1552 | 7500 | 0.5632          | 0.8023   | 0.8234    | 0.7823 | 0.7989   | 0.8729 | 0.8701 |
+
+
+### 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 sha256:9066d3fb8869eb280e6c00ae3b718efdefb57a061eea835388804d19471c56ad
+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]"
+}