Upload folder using huggingface_hub

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "zhihan1996/DNABERT-2-117M",
+  "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 sha256:58e9517e7a4d6788b4d7f7d7d091fa94b5ec9c50fe93a5d75cb4991e118a91ce
+size 468296408

optimizer_state_dict.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a6ca920780aa3e815613431d8082056a732a6af01c812b00dbeddf0610a4c2
+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 +1,130 @@
+{
+  "best_metric": 0.3388816714286804,
+  "best_model_checkpoint": "output_pipe/H3/origin/checkpoint-400",
+  "epoch": 4.0,
+  "eval_steps": 200,
+  "global_step": 752,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 3.271205186843872,
+      "learning_rate": 2.7905982905982907e-05,
+      "loss": 0.4975,
+      "step": 100
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 2.864509105682373,
+      "learning_rate": 2.3675213675213678e-05,
+      "loss": 0.3341,
+      "step": 200
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "eval_accuracy": 0.8530394121576487,
+      "eval_f1": 0.8526495695903502,
+      "eval_loss": 0.39090028405189514,
+      "eval_matthews_correlation": 0.7136100520955398,
+      "eval_precision": 0.8593835475000997,
+      "eval_recall": 0.8542450050886496,
+      "eval_runtime": 1.0296,
+      "eval_samples_per_second": 1454.027,
+      "eval_steps_per_second": 23.311,
+      "step": 200
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 4.730978012084961,
+      "learning_rate": 1.9401709401709403e-05,
+      "loss": 0.2516,
+      "step": 300
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 3.8016724586486816,
+      "learning_rate": 1.5128205128205129e-05,
+      "loss": 0.2295,
+      "step": 400
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_accuracy": 0.8710754843019372,
+      "eval_f1": 0.8708394112779532,
+      "eval_loss": 0.3388816714286804,
+      "eval_matthews_correlation": 0.7481606535429142,
+      "eval_precision": 0.8760406029091775,
+      "eval_recall": 0.8721302694306068,
+      "eval_runtime": 0.4404,
+      "eval_samples_per_second": 3399.504,
+      "eval_steps_per_second": 54.501,
+      "step": 400
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 10.54096794128418,
+      "learning_rate": 1.0854700854700855e-05,
+      "loss": 0.1705,
+      "step": 500
+    },
+    {
+      "epoch": 3.1914893617021276,
+      "grad_norm": 2.985470771789551,
+      "learning_rate": 6.581196581196582e-06,
+      "loss": 0.1594,
+      "step": 600
+    },
+    {
+      "epoch": 3.1914893617021276,
+      "eval_accuracy": 0.8704074816299265,
+      "eval_f1": 0.8702058700494475,
+      "eval_loss": 0.41333696246147156,
+      "eval_matthews_correlation": 0.7461913593958502,
+      "eval_precision": 0.8747972958363663,
+      "eval_recall": 0.8714017890620815,
+      "eval_runtime": 0.4419,
+      "eval_samples_per_second": 3387.747,
+      "eval_steps_per_second": 54.313,
+      "step": 600
+    },
+    {
+      "epoch": 3.723404255319149,
+      "grad_norm": 5.1116228103637695,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 0.1197,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "step": 752,
+      "total_flos": 3764005349807280.0,
+      "train_loss": 0.24375706911087036,
+      "train_runtime": 63.2773,
+      "train_samples_per_second": 756.733,
+      "train_steps_per_second": 11.884
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 752,
+  "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": 3764005349807280.0,
+  "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 sha256:10668afdc6c2167e2f97dd6e12539b3288fe9518621351c19e128cc09026db9f
+size 5368