add baseline-200k SFT checkpoint: tf/1

GUE/tf/1/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "EvoLenTokenizer/base-200k",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_length": 512,
+  "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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 5120
+}

GUE/tf/1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa59224116725e97cba33f32ca2bde23217f4d0c18d2721c67f1cdc37f742abe
+size 359923616

GUE/tf/1/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

GUE/tf/1/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "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
+    }
+  },
+  "cache_dir": null,
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 30,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "trust_remote_code": true,
+  "unk_token": "[UNK]",
+  "use_fast": true
+}

GUE/tf/1/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.7640635683025929,
+  "best_model_checkpoint": "/home/n5huang/dna_token/mario/best_hp_runs/GUE_task/output_best_gue_base_5120_200k/tf/1/base_5120_200k/lr3e-5_wd0.0_wr0.06_ep8_seed42\r/checkpoint-720",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 720,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.586206896551724e-05,
+      "loss": 0.5669,
+      "step": 100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 2.8603104212860313e-05,
+      "loss": 0.5,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.758,
+      "eval_f1": 0.7561113261093911,
+      "eval_loss": 0.5009490847587585,
+      "eval_matthews_correlation": 0.5264775087287643,
+      "eval_precision": 0.767802729199788,
+      "eval_recall": 0.7587525601638505,
+      "eval_runtime": 0.1678,
+      "eval_samples_per_second": 5960.934,
+      "eval_steps_per_second": 47.687,
+      "step": 240
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.6940133037694013e-05,
+      "loss": 0.4768,
+      "step": 300
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.5277161862527717e-05,
+      "loss": 0.4664,
+      "step": 400
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.764,
+      "eval_f1": 0.7638857206888134,
+      "eval_loss": 0.48274871706962585,
+      "eval_matthews_correlation": 0.5291488035776915,
+      "eval_precision": 0.7649243554571561,
+      "eval_recall": 0.7642249103942653,
+      "eval_runtime": 0.1563,
+      "eval_samples_per_second": 6399.268,
+      "eval_steps_per_second": 51.194,
+      "step": 480
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2.361419068736142e-05,
+      "loss": 0.4454,
+      "step": 500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.195121951219512e-05,
+      "loss": 0.4096,
+      "step": 600
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 2.0288248337028824e-05,
+      "loss": 0.4159,
+      "step": 700
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.765,
+      "eval_f1": 0.7640635683025929,
+      "eval_loss": 0.47934937477111816,
+      "eval_matthews_correlation": 0.5327952539921941,
+      "eval_precision": 0.7682632981636304,
+      "eval_recall": 0.7645449308755761,
+      "eval_runtime": 0.1653,
+      "eval_samples_per_second": 6049.707,
+      "eval_steps_per_second": 48.398,
+      "step": 720
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1920,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "total_flos": 1324007719453440.0,
+  "trial_name": null,
+  "trial_params": null
+}

GUE/tf/1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e9504902a286da6ade47c1a259c302291f5e7e9e9dde5df8d9e10f701f5824
+size 5457