End of training

README.md

@@ -0,0 +1,76 @@
+---
+license: bsd-3-clause
+base_model: LongSafari/hyenadna-large-1m-seqlen-hf
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: hyenadna-large-1m-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-large-1m-seqlen-hf_ft_BioS45_1kbpHG19_DHSs_H3K27AC
+
+This model is a fine-tuned version of [LongSafari/hyenadna-large-1m-seqlen-hf](https://huggingface.co/LongSafari/hyenadna-large-1m-seqlen-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4729
+- F1 Score: 0.7992
+- Precision: 0.7837
+- Recall: 0.8153
+- Accuracy: 0.7863
+- Auc: 0.8620
+- Prc: 0.8573
+
+## 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.5614        | 0.2103 | 500  | 0.5009          | 0.7805   | 0.7671    | 0.7944 | 0.7669   | 0.8336 | 0.8188 |
+| 0.5053        | 0.4207 | 1000 | 0.4788          | 0.7845   | 0.7926    | 0.7766 | 0.7775   | 0.8507 | 0.8450 |
+| 0.489         | 0.6310 | 1500 | 0.5526          | 0.7506   | 0.8293    | 0.6855 | 0.7623   | 0.8459 | 0.8500 |
+| 0.4836        | 0.8414 | 2000 | 0.4708          | 0.8145   | 0.7455    | 0.8976 | 0.7867   | 0.8677 | 0.8623 |
+| 0.4673        | 1.0517 | 2500 | 0.4755          | 0.7935   | 0.7847    | 0.8024 | 0.7821   | 0.8609 | 0.8575 |
+| 0.4694        | 1.2621 | 3000 | 0.4953          | 0.7730   | 0.8156    | 0.7347 | 0.7749   | 0.8622 | 0.8598 |
+| 0.4622        | 1.4724 | 3500 | 0.4560          | 0.8055   | 0.7899    | 0.8218 | 0.7930   | 0.8664 | 0.8659 |
+| 0.4537        | 1.6828 | 4000 | 0.4548          | 0.8070   | 0.8013    | 0.8129 | 0.7972   | 0.8741 | 0.8724 |
+| 0.4561        | 1.8931 | 4500 | 0.4729          | 0.7992   | 0.7837    | 0.8153 | 0.7863   | 0.8620 | 0.8573 |
+
+
+### 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-large-1m-seqlen-hf",
+  "activation_freq": 10,
+  "architectures": [
+    "HyenaDNAForSequenceClassification"
+  ],
+  "auto_map": {
+    "AutoConfig": "LongSafari/hyenadna-large-1m-seqlen-hf--configuration_hyena.HyenaConfig",
+    "AutoModel": "LongSafari/hyenadna-large-1m-seqlen-hf--modeling_hyena.HyenaDNAModel",
+    "AutoModelForCausalLM": "LongSafari/hyenadna-large-1m-seqlen-hf--modeling_hyena.HyenaDNAForCausalLM",
+    "AutoModelForSequenceClassification": "LongSafari/hyenadna-large-1m-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": 1000002,
+  "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 sha256:2a00f1e11febe3209b9272866d67e2fc04017f67d2377ac4ac1981d6b011415d
+size 218288026

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-large-1m-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": 1000002,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "HyenaDNATokenizer",
+  "unk_token": "[UNK]"
+}