End of training

README.md

@@ -0,0 +1,80 @@
+---
+base_model: AIRI-Institute/gena-lm-bigbird-base-t2t
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
+model-index:
+- name: gena-lm-bigbird-base-t2t_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. -->
+
+# gena-lm-bigbird-base-t2t_ft_BioS74_1kbpHG19_DHSs_H3K27AC
+
+This model is a fine-tuned version of [AIRI-Institute/gena-lm-bigbird-base-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bigbird-base-t2t) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3903
+- F1 Score: 0.8369
+- Precision: 0.8479
+- Recall: 0.8262
+- Accuracy: 0.8314
+- Auc: 0.9159
+- Prc: 0.9150
+
+## 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    |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:--------:|:------:|:------:|
+| 0.5065        | 0.1314 | 500  | 0.4874          | 0.8094   | 0.8042    | 0.8147 | 0.7991   | 0.8745 | 0.8648 |
+| 0.4714        | 0.2629 | 1000 | 0.5169          | 0.7982   | 0.8196    | 0.7780 | 0.7941   | 0.8816 | 0.8741 |
+| 0.4608        | 0.3943 | 1500 | 0.4256          | 0.8224   | 0.8137    | 0.8312 | 0.8120   | 0.8906 | 0.8850 |
+| 0.4365        | 0.5258 | 2000 | 0.5043          | 0.8323   | 0.7431    | 0.9458 | 0.8004   | 0.8970 | 0.8898 |
+| 0.4181        | 0.6572 | 2500 | 0.4206          | 0.8438   | 0.7824    | 0.9156 | 0.8225   | 0.9004 | 0.8946 |
+| 0.4426        | 0.7886 | 3000 | 0.3973          | 0.8417   | 0.8253    | 0.8589 | 0.8309   | 0.9043 | 0.9005 |
+| 0.4192        | 0.9201 | 3500 | 0.4847          | 0.8416   | 0.8209    | 0.8634 | 0.8299   | 0.9065 | 0.9000 |
+| 0.4267        | 1.0515 | 4000 | 0.4880          | 0.8264   | 0.8417    | 0.8117 | 0.8215   | 0.9053 | 0.8978 |
+| 0.3992        | 1.1830 | 4500 | 0.3852          | 0.8443   | 0.8152    | 0.8754 | 0.8309   | 0.9103 | 0.9095 |
+| 0.3973        | 1.3144 | 5000 | 0.4035          | 0.8341   | 0.8335    | 0.8348 | 0.8262   | 0.9100 | 0.9086 |
+| 0.3861        | 1.4458 | 5500 | 0.4904          | 0.8187   | 0.8696    | 0.7735 | 0.8207   | 0.9114 | 0.9103 |
+| 0.3703        | 1.5773 | 6000 | 0.4456          | 0.8306   | 0.8466    | 0.8152 | 0.8259   | 0.9130 | 0.9100 |
+| 0.3964        | 1.7087 | 6500 | 0.3778          | 0.8371   | 0.8368    | 0.8373 | 0.8293   | 0.9143 | 0.9142 |
+| 0.3744        | 1.8402 | 7000 | 0.3903          | 0.8369   | 0.8479    | 0.8262 | 0.8314   | 0.9159 | 0.9150 |
+
+
+### Framework versions
+
+- Transformers 4.42.3
+- Pytorch 2.3.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.0

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "AIRI-Institute/gena-lm-bigbird-base-t2t",
+  "architectures": [
+    "BigBirdForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 3,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d54ceb6128ec096d49014b8ee994bd2b88ee6d360bb7fdf3ace8ead6e849c8
+size 455871688

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "-",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea7444e2fb2ba5d31b57b0dbf3e83186891ef45a71a70563ca142b741de9548
+size 5240