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_BioS74_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_BioS74_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: 0.4605
+- F1 Score: 0.8107
+- Precision: 0.7689
+- Recall: 0.8574
+- Accuracy: 0.7904
+- Auc: 0.8669
+- Prc: 0.8594
+
+## 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.5565        | 0.1314 | 500  | 0.5060          | 0.7829   | 0.7556    | 0.8122 | 0.7641   | 0.8275 | 0.8077 |
+| 0.4991        | 0.2629 | 1000 | 0.5124          | 0.7801   | 0.7916    | 0.7690 | 0.7731   | 0.8364 | 0.8255 |
+| 0.494         | 0.3943 | 1500 | 0.4957          | 0.7822   | 0.8035    | 0.7619 | 0.7778   | 0.8460 | 0.8325 |
+| 0.4752        | 0.5258 | 2000 | 0.5005          | 0.7964   | 0.7661    | 0.8292 | 0.7781   | 0.8496 | 0.8368 |
+| 0.4546        | 0.6572 | 2500 | 0.4923          | 0.8041   | 0.7414    | 0.8785 | 0.7760   | 0.8515 | 0.8359 |
+| 0.4858        | 0.7886 | 3000 | 0.4669          | 0.8017   | 0.7556    | 0.8538 | 0.7789   | 0.8495 | 0.8355 |
+| 0.4677        | 0.9201 | 3500 | 0.4842          | 0.8019   | 0.7881    | 0.8162 | 0.7889   | 0.8583 | 0.8467 |
+| 0.4695        | 1.0515 | 4000 | 0.4893          | 0.7893   | 0.8102    | 0.7695 | 0.7849   | 0.8616 | 0.8504 |
+| 0.4576        | 1.1830 | 4500 | 0.4612          | 0.8078   | 0.7760    | 0.8423 | 0.7902   | 0.8599 | 0.8482 |
+| 0.4574        | 1.3144 | 5000 | 0.4591          | 0.8122   | 0.7633    | 0.8679 | 0.7899   | 0.8629 | 0.8519 |
+| 0.445         | 1.4458 | 5500 | 0.5035          | 0.7831   | 0.8194    | 0.7499 | 0.7825   | 0.8640 | 0.8589 |
+| 0.4302        | 1.5773 | 6000 | 0.4984          | 0.8064   | 0.7856    | 0.8282 | 0.7917   | 0.8622 | 0.8502 |
+| 0.4252        | 1.7087 | 6500 | 0.4651          | 0.8007   | 0.7973    | 0.8041 | 0.7904   | 0.8642 | 0.8551 |
+| 0.4408        | 1.8402 | 7000 | 0.4837          | 0.7988   | 0.8103    | 0.7875 | 0.7923   | 0.8619 | 0.8567 |
+| 0.4444        | 1.9716 | 7500 | 0.4605          | 0.8107   | 0.7689    | 0.8574 | 0.7904   | 0.8669 | 0.8594 |
+
+
+### 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 sha256:04442c6f3a6fdbb5ee2188f61e51bc714b1a0bf9350b514db10717a80a5fae55
+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]"
+}