init

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "magicslabnu/DNABERT-2-finetuned-tf4",
+  "alibi_starting_size": 512,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "zhihan1996/DNABERT-2-117M--configuration_bert.BertConfig",
+    "AutoModel": "zhihan1996/DNABERT-2-117M--bert_layers.BertModel",
+    "AutoModelForMaskedLM": "zhihan1996/DNABERT-2-117M--bert_layers.BertForMaskedLM",
+    "AutoModelForSequenceClassification": "zhihan1996/DNABERT-2-117M--bert_layers.BertForSequenceClassification"
+  },
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 4096
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c120c04282a12878bccdcf95454f1da7b1f4888b0ce11f4233d5a01526e864db
+size 468296408

optimizer_state_dict.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc75703f97c4e5f3f007521fcb506fbeb9ded3facdee0d40c932bdb02b2ea5ed
+size 936682546

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 +1,53 @@
+{
+  "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
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 256,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_metric": 0.3535642921924591,
+  "best_model_checkpoint": "output_pipe/tf4/origin/checkpoint-600",
+  "epoch": 4.0,
+  "eval_steps": 200,
+  "global_step": 1188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3367003367003367,
+      "grad_norm": 2.2151033878326416,
+      "learning_rate": 2.873462214411248e-05,
+      "loss": 0.5935,
+      "step": 100
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 2.771702766418457,
+      "learning_rate": 2.609841827768014e-05,
+      "loss": 0.4335,
+      "step": 200
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "eval_accuracy": 0.814,
+      "eval_f1": 0.813456037806243,
+      "eval_loss": 0.4449627697467804,
+      "eval_matthews_correlation": 0.6336383152068563,
+      "eval_precision": 0.8190322044142642,
+      "eval_recall": 0.8146214621462147,
+      "eval_runtime": 0.1565,
+      "eval_samples_per_second": 6390.502,
+      "eval_steps_per_second": 102.248,
+      "step": 200
+    },
+    {
+      "epoch": 1.0101010101010102,
+      "grad_norm": 1.9664157629013062,
+      "learning_rate": 2.3462214411247803e-05,
+      "loss": 0.3857,
+      "step": 300
+    },
+    {
+      "epoch": 1.3468013468013469,
+      "grad_norm": 6.839441299438477,
+      "learning_rate": 2.0826010544815465e-05,
+      "loss": 0.3196,
+      "step": 400
+    },
+    {
+      "epoch": 1.3468013468013469,
+      "eval_accuracy": 0.85,
+      "eval_f1": 0.849913550204918,
+      "eval_loss": 0.3645921051502228,
+      "eval_matthews_correlation": 0.7017964476602436,
+      "eval_precision": 0.8514723529954769,
+      "eval_recall": 0.8503250325032503,
+      "eval_runtime": 0.1517,
+      "eval_samples_per_second": 6592.371,
+      "eval_steps_per_second": 105.478,
+      "step": 400
+    },
+    {
+      "epoch": 1.6835016835016834,
+      "grad_norm": 2.5494678020477295,
+      "learning_rate": 1.8189806678383127e-05,
+      "loss": 0.2899,
+      "step": 500
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "grad_norm": 2.965630292892456,
+      "learning_rate": 1.5553602811950793e-05,
+      "loss": 0.2922,
+      "step": 600
+    },
+    {
+      "epoch": 2.0202020202020203,
+      "eval_accuracy": 0.854,
+      "eval_f1": 0.8539713783901646,
+      "eval_loss": 0.3535642921924591,
+      "eval_matthews_correlation": 0.7079700941012794,
+      "eval_precision": 0.8540247040040974,
+      "eval_recall": 0.853945394539454,
+      "eval_runtime": 0.1549,
+      "eval_samples_per_second": 6455.149,
+      "eval_steps_per_second": 103.282,
+      "step": 600
+    },
+    {
+      "epoch": 2.356902356902357,
+      "grad_norm": 3.694185972213745,
+      "learning_rate": 1.2917398945518455e-05,
+      "loss": 0.2066,
+      "step": 700
+    },
+    {
+      "epoch": 2.6936026936026938,
+      "grad_norm": 3.392780065536499,
+      "learning_rate": 1.0281195079086117e-05,
+      "loss": 0.2035,
+      "step": 800
+    },
+    {
+      "epoch": 2.6936026936026938,
+      "eval_accuracy": 0.868,
+      "eval_f1": 0.8675230830991569,
+      "eval_loss": 0.3822917342185974,
+      "eval_matthews_correlation": 0.7394238770890715,
+      "eval_precision": 0.871950602287681,
+      "eval_recall": 0.8674867486748675,
+      "eval_runtime": 0.1506,
+      "eval_samples_per_second": 6637.954,
+      "eval_steps_per_second": 106.207,
+      "step": 800
+    },
+    {
+      "epoch": 3.0303030303030303,
+      "grad_norm": 2.4913880825042725,
+      "learning_rate": 7.644991212653779e-06,
+      "loss": 0.1855,
+      "step": 900
+    },
+    {
+      "epoch": 3.3670033670033668,
+      "grad_norm": 6.169365882873535,
+      "learning_rate": 5.0087873462214405e-06,
+      "loss": 0.1312,
+      "step": 1000
+    },
+    {
+      "epoch": 3.3670033670033668,
+      "eval_accuracy": 0.875,
+      "eval_f1": 0.8749898741798086,
+      "eval_loss": 0.38816502690315247,
+      "eval_matthews_correlation": 0.7499814986043926,
+      "eval_precision": 0.8749839989759345,
+      "eval_recall": 0.874997499749975,
+      "eval_runtime": 0.1522,
+      "eval_samples_per_second": 6571.394,
+      "eval_steps_per_second": 105.142,
+      "step": 1000
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 3.955672025680542,
+      "learning_rate": 2.3725834797891038e-06,
+      "loss": 0.1255,
+      "step": 1100
+    },
+    {
+      "epoch": 4.0,
+      "step": 1188,
+      "total_flos": 1506515345232000.0,
+      "train_loss": 0.2757887061597522,
+      "train_runtime": 50.1812,
+      "train_samples_per_second": 1514.512,
+      "train_steps_per_second": 23.674
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1188,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1506515345232000.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:048ce07eafc589f6df1eb8566307e64e75331fc73fb899d52df4d59bbae4f365
+size 5368