End of training

README.md

@@ -0,0 +1,82 @@
+---
+license: bsd-3-clause
+base_model: LongSafari/hyenadna-medium-450k-seqlen-hf
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: hyenadna-medium-450k-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-450k-seqlen-hf_ft_BioS73_1kbpHG19_DHSs_H3K27AC
+
+This model is a fine-tuned version of [LongSafari/hyenadna-medium-450k-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-medium-450k-seqlen-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4797
+- F1 Score: 0.8324
+- Precision: 0.8063
+- Recall: 0.8603
+- Accuracy: 0.8151
+- Auc: 0.8805
+- Prc: 0.8644
+
+## 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.4819        | 0.3726 | 500  | 0.4409          | 0.8212   | 0.7769    | 0.8708 | 0.7976   | 0.8718 | 0.8657 |
+| 0.4306        | 0.7452 | 1000 | 0.4281          | 0.8181   | 0.8103    | 0.8261 | 0.8040   | 0.8826 | 0.8790 |
+| 0.4073        | 1.1177 | 1500 | 0.4115          | 0.8310   | 0.7977    | 0.8673 | 0.8118   | 0.8884 | 0.8864 |
+| 0.3903        | 1.4903 | 2000 | 0.4011          | 0.8345   | 0.8096    | 0.8610 | 0.8177   | 0.8902 | 0.8832 |
+| 0.3808        | 1.8629 | 2500 | 0.4221          | 0.8295   | 0.8075    | 0.8527 | 0.8129   | 0.8865 | 0.8788 |
+| 0.3713        | 2.2355 | 3000 | 0.4126          | 0.8305   | 0.8212    | 0.8401 | 0.8170   | 0.8959 | 0.8883 |
+| 0.3587        | 2.6080 | 3500 | 0.4023          | 0.8469   | 0.7937    | 0.9078 | 0.8248   | 0.8936 | 0.8857 |
+| 0.3362        | 2.9806 | 4000 | 0.4117          | 0.8489   | 0.7852    | 0.9239 | 0.8245   | 0.8925 | 0.8829 |
+| 0.3075        | 3.3532 | 4500 | 0.4235          | 0.8295   | 0.8120    | 0.8478 | 0.8140   | 0.8946 | 0.8877 |
+| 0.319         | 3.7258 | 5000 | 0.4154          | 0.8497   | 0.8096    | 0.8939 | 0.8312   | 0.8959 | 0.8868 |
+| 0.2986        | 4.0984 | 5500 | 0.4481          | 0.8377   | 0.8028    | 0.8757 | 0.8189   | 0.8929 | 0.8835 |
+| 0.2712        | 4.4709 | 6000 | 0.4398          | 0.8281   | 0.8005    | 0.8575 | 0.8099   | 0.8833 | 0.8708 |
+| 0.2819        | 4.8435 | 6500 | 0.4465          | 0.8324   | 0.8189    | 0.8464 | 0.8181   | 0.8904 | 0.8828 |
+| 0.245         | 5.2161 | 7000 | 0.4827          | 0.8294   | 0.8125    | 0.8471 | 0.8140   | 0.8853 | 0.8713 |
+| 0.2318        | 5.5887 | 7500 | 0.4797          | 0.8324   | 0.8063    | 0.8603 | 0.8151   | 0.8805 | 0.8644 |
+
+
+### 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-450k-seqlen-hf",
+  "activation_freq": 10,
+  "architectures": [
+    "HyenaDNAForSequenceClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "LongSafari/hyenadna-medium-450k-seqlen-hf--configuration_hyena.HyenaConfig",
+    "AutoModel": "LongSafari/hyenadna-medium-450k-seqlen-hf--modeling_hyena.HyenaDNAModel",
+    "AutoModelForCausalLM": "LongSafari/hyenadna-medium-450k-seqlen-hf--modeling_hyena.HyenaDNAForCausalLM",
+    "AutoModelForSequenceClassification": "LongSafari/hyenadna-medium-450k-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": 450002,
+  "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 sha256:36d05e6ffc941bed45daf1cdc5878a2d6a6f2e3a3e63bb68542b21fe3013573f
+size 112688026

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-450k-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": 450002,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "HyenaDNATokenizer",
+  "unk_token": "[UNK]"
+}