End of training

README.md

@@ -0,0 +1,77 @@
+---
+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_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-medium-450k-seqlen-hf_ft_BioS45_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: 0.4842
+- F1 Score: 0.8087
+- Precision: 0.7837
+- Recall: 0.8355
+- Accuracy: 0.7939
+- Auc: 0.8682
+- Prc: 0.8657
+
+## 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.5149        | 0.4205 | 500  | 0.4843          | 0.8028   | 0.7336    | 0.8863 | 0.7728   | 0.8553 | 0.8481 |
+| 0.4584        | 0.8410 | 1000 | 0.4805          | 0.8075   | 0.7280    | 0.9065 | 0.7745   | 0.8632 | 0.8518 |
+| 0.4489        | 1.2616 | 1500 | 0.4646          | 0.8115   | 0.7566    | 0.875  | 0.7880   | 0.8676 | 0.8583 |
+| 0.4367        | 1.6821 | 2000 | 0.4406          | 0.8133   | 0.7810    | 0.8484 | 0.7968   | 0.8720 | 0.8645 |
+| 0.4138        | 2.1026 | 2500 | 0.4448          | 0.8189   | 0.7825    | 0.8589 | 0.8019   | 0.8732 | 0.8666 |
+| 0.3859        | 2.5231 | 3000 | 0.4459          | 0.8010   | 0.8019    | 0.8    | 0.7926   | 0.8681 | 0.8619 |
+| 0.4117        | 2.9437 | 3500 | 0.4532          | 0.8040   | 0.8024    | 0.8056 | 0.7951   | 0.8699 | 0.8678 |
+| 0.3722        | 3.3642 | 4000 | 0.4556          | 0.7973   | 0.7969    | 0.7976 | 0.7884   | 0.8665 | 0.8668 |
+| 0.3493        | 3.7847 | 4500 | 0.4849          | 0.7944   | 0.8121    | 0.7774 | 0.7901   | 0.8704 | 0.8684 |
+| 0.313         | 4.2052 | 5000 | 0.4842          | 0.8087   | 0.7837    | 0.8355 | 0.7939   | 0.8682 | 0.8657 |
+
+
+### 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 sha256:54c1c26a0e2abb6a6e1a3f045dfd2ace4b9bf59772d1558a9cc9f3629c4c9149
+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]"
+}