End of training

README.md

@@ -0,0 +1,78 @@
+---
+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_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-medium-450k-seqlen-hf_ft_BioS74_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: 0.4642
+- F1 Score: 0.8034
+- Precision: 0.7730
+- Recall: 0.8363
+- Accuracy: 0.7857
+- Auc: 0.8626
+- Prc: 0.8590
+
+## 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.5486        | 0.2629 | 500  | 0.5108          | 0.7728   | 0.7601    | 0.7860 | 0.7581   | 0.8210 | 0.8101 |
+| 0.4949        | 0.5258 | 1000 | 0.4955          | 0.7852   | 0.7800    | 0.7906 | 0.7736   | 0.8368 | 0.8242 |
+| 0.4746        | 0.7886 | 1500 | 0.4766          | 0.7948   | 0.7728    | 0.8182 | 0.7789   | 0.8464 | 0.8356 |
+| 0.4782        | 1.0515 | 2000 | 0.4691          | 0.7927   | 0.7933    | 0.7921 | 0.7831   | 0.8544 | 0.8480 |
+| 0.4619        | 1.3144 | 2500 | 0.4738          | 0.8016   | 0.7614    | 0.8463 | 0.7807   | 0.8506 | 0.8398 |
+| 0.45          | 1.5773 | 3000 | 0.4861          | 0.8063   | 0.7462    | 0.8769 | 0.7794   | 0.8530 | 0.8446 |
+| 0.4429        | 1.8402 | 3500 | 0.4836          | 0.7840   | 0.8013    | 0.7675 | 0.7786   | 0.8553 | 0.8508 |
+| 0.4459        | 2.1030 | 4000 | 0.4606          | 0.8006   | 0.7833    | 0.8187 | 0.7865   | 0.8616 | 0.8588 |
+| 0.413         | 2.3659 | 4500 | 0.4687          | 0.7903   | 0.7931    | 0.7875 | 0.7812   | 0.8600 | 0.8572 |
+| 0.4162        | 2.6288 | 5000 | 0.4616          | 0.8036   | 0.7786    | 0.8302 | 0.7875   | 0.8600 | 0.8555 |
+| 0.4196        | 2.8917 | 5500 | 0.4642          | 0.8034   | 0.7730    | 0.8363 | 0.7857   | 0.8626 | 0.8590 |
+
+
+### 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 sha256:2c1fecd3ffc7ef941a970b9b51c2a03e88ac9a0a375395a6f7486e1e54351759
+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]"
+}