End of training

README.md

@@ -0,0 +1,85 @@
+---
+license: bsd-3-clause
+base_model: LongSafari/hyenadna-medium-160k-seqlen-hf
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: hyenadna-medium-160k-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-medium-160k-seqlen-hf_ft_BioS73_1kbpHG19_DHSs_H3K27AC
+
+This model is a fine-tuned version of [LongSafari/hyenadna-medium-160k-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-medium-160k-seqlen-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5049
+- F1 Score: 0.8498
+- Precision: 0.8092
+- Recall: 0.8946
+- Accuracy: 0.8312
+- Auc: 0.9050
+- Prc: 0.8919
+
+## 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: 16
+- eval_batch_size: 16
+- 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.4658        | 0.3726 | 500  | 0.4353          | 0.8344   | 0.7760    | 0.9022 | 0.8088   | 0.8792 | 0.8707 |
+| 0.4465        | 0.7452 | 1000 | 0.4110          | 0.8362   | 0.8066    | 0.8680 | 0.8185   | 0.8881 | 0.8822 |
+| 0.4114        | 1.1177 | 1500 | 0.3973          | 0.8398   | 0.7786    | 0.9113 | 0.8144   | 0.8952 | 0.8901 |
+| 0.3962        | 1.4903 | 2000 | 0.4114          | 0.8288   | 0.8245    | 0.8331 | 0.8163   | 0.8981 | 0.8925 |
+| 0.3888        | 1.8629 | 2500 | 0.3946          | 0.8529   | 0.7811    | 0.9392 | 0.8271   | 0.9034 | 0.8962 |
+| 0.3713        | 2.2355 | 3000 | 0.3950          | 0.8505   | 0.7984    | 0.9099 | 0.8293   | 0.9022 | 0.8959 |
+| 0.357         | 2.6080 | 3500 | 0.3787          | 0.8476   | 0.8081    | 0.8911 | 0.8289   | 0.9044 | 0.8980 |
+| 0.3466        | 2.9806 | 4000 | 0.3876          | 0.8538   | 0.7936    | 0.9239 | 0.8312   | 0.9075 | 0.8995 |
+| 0.3164        | 3.3532 | 4500 | 0.3935          | 0.8513   | 0.8097    | 0.8973 | 0.8327   | 0.9059 | 0.8937 |
+| 0.33          | 3.7258 | 5000 | 0.4684          | 0.8245   | 0.8426    | 0.8073 | 0.8166   | 0.9083 | 0.9012 |
+| 0.31          | 4.0984 | 5500 | 0.4464          | 0.8520   | 0.7870    | 0.9288 | 0.8278   | 0.9049 | 0.8975 |
+| 0.2786        | 4.4709 | 6000 | 0.4071          | 0.8506   | 0.8159    | 0.8883 | 0.8334   | 0.9028 | 0.8933 |
+| 0.2874        | 4.8435 | 6500 | 0.3797          | 0.8640   | 0.8040    | 0.9337 | 0.8431   | 0.9050 | 0.8913 |
+| 0.2567        | 5.2161 | 7000 | 0.4544          | 0.8517   | 0.7925    | 0.9204 | 0.8289   | 0.8983 | 0.8855 |
+| 0.2388        | 5.5887 | 7500 | 0.4834          | 0.8415   | 0.8340    | 0.8492 | 0.8293   | 0.9032 | 0.8919 |
+| 0.2386        | 5.9613 | 8000 | 0.4892          | 0.8533   | 0.8033    | 0.9099 | 0.8330   | 0.9003 | 0.8847 |
+| 0.1956        | 6.3338 | 8500 | 0.5595          | 0.8511   | 0.8348    | 0.8680 | 0.8379   | 0.8992 | 0.8811 |
+| 0.2257        | 6.7064 | 9000 | 0.5049          | 0.8498   | 0.8092    | 0.8946 | 0.8312   | 0.9050 | 0.8919 |
+
+
+### 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-medium-160k-seqlen-hf",
+  "activation_freq": 10,
+  "architectures": [
+    "HyenaDNAForSequenceClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "LongSafari/hyenadna-medium-160k-seqlen-hf--configuration_hyena.HyenaConfig",
+    "AutoModel": "LongSafari/hyenadna-medium-160k-seqlen-hf--modeling_hyena.HyenaDNAModel",
+    "AutoModelForCausalLM": "LongSafari/hyenadna-medium-160k-seqlen-hf--modeling_hyena.HyenaDNAForCausalLM",
+    "AutoModelForSequenceClassification": "LongSafari/hyenadna-medium-160k-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": 160002,
+  "model_type": "hyenadna",
+  "n_layer": 8,
+  "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 sha256:543448c674705949224f67ddf65fdca36ffc9d6d27845b2cbd53dfd0d8b47278
+size 57008026

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-medium-160k-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": 160002,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "HyenaDNATokenizer",
+  "unk_token": "[UNK]"
+}