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 sha256:50ed8e4236840c8739550987ab1f190c2d7716dfdbb94472150a975a0c1fe891
+size 468296408

optimizer_state_dict.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48625cac3b92d149691171d37d7b23d87724f77bee6344b6d270d323093d64fa
+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 +1,96 @@
+{
+  "best_metric": 0.43876591324806213,
+  "best_model_checkpoint": "output_pipe/0/origin/checkpoint-400",
+  "epoch": 4.0,
+  "eval_steps": 200,
+  "global_step": 408,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 4.340454578399658,
+      "learning_rate": 2.6061452513966484e-05,
+      "loss": 0.6743,
+      "step": 100
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 4.347059726715088,
+      "learning_rate": 1.7681564245810057e-05,
+      "loss": 0.4757,
+      "step": 200
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "eval_accuracy": 0.8098765432098766,
+      "eval_f1": 0.8095002474022761,
+      "eval_loss": 0.45168113708496094,
+      "eval_matthews_correlation": 0.626803554022576,
+      "eval_precision": 0.8153468923901698,
+      "eval_recall": 0.8114686594479182,
+      "eval_runtime": 0.1311,
+      "eval_samples_per_second": 6180.527,
+      "eval_steps_per_second": 99.194,
+      "step": 200
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 6.6639485359191895,
+      "learning_rate": 9.301675977653631e-06,
+      "loss": 0.3291,
+      "step": 300
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "grad_norm": 6.7193684577941895,
+      "learning_rate": 9.217877094972066e-07,
+      "loss": 0.2513,
+      "step": 400
+    },
+    {
+      "epoch": 3.9215686274509802,
+      "eval_accuracy": 0.8333333333333334,
+      "eval_f1": 0.8333025904792685,
+      "eval_loss": 0.43876591324806213,
+      "eval_matthews_correlation": 0.669050678827637,
+      "eval_precision": 0.8348738262910798,
+      "eval_recall": 0.8341772151898734,
+      "eval_runtime": 0.1238,
+      "eval_samples_per_second": 6544.22,
+      "eval_steps_per_second": 105.031,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "step": 408,
+      "total_flos": 531354250802880.0,
+      "train_loss": 0.4285174494280535,
+      "train_runtime": 23.4588,
+      "train_samples_per_second": 1104.575,
+      "train_steps_per_second": 17.392
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 408,
+  "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": 531354250802880.0,
+  "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 sha256:1f5b87f984dc290198519933dbb3d3673d556d0ccad7a7bb47f705d449ca00bd
+size 5368