add baseline-200k SFT checkpoint: mouse/2

GUE/mouse/2/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/mouse/2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afe1c9bf10a9f3eafb63fca476d5664a13dffa006abee374322d644ad71c8e7
+size 359923616

GUE/mouse/2/special_tokens_map.json

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

GUE/mouse/2/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/mouse/2/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.8566953288403439,
+  "best_model_checkpoint": "/home/n5huang/dna_token/mario/best_hp_runs/GUE_task/output_best_gue_base_5120_200k/mouse/2/base_5120_200k/lr3e-5_wd0.01_wr0.06_ep8_seed42\r/checkpoint-105",
+  "epoch": 5.0,
+  "eval_steps": 100,
+  "global_step": 105,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.75,
+      "eval_f1": 0.7435545385202136,
+      "eval_loss": 0.4690381586551666,
+      "eval_matthews_correlation": 0.5240990003731415,
+      "eval_precision": 0.7757151677299856,
+      "eval_recall": 0.7490611637850901,
+      "eval_runtime": 0.0734,
+      "eval_samples_per_second": 4468.635,
+      "eval_steps_per_second": 40.872,
+      "step": 21
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8475609756097561,
+      "eval_f1": 0.8475383013535625,
+      "eval_loss": 0.3496690094470978,
+      "eval_matthews_correlation": 0.6951396454874186,
+      "eval_precision": 0.8476215271320713,
+      "eval_recall": 0.8475181260457334,
+      "eval_runtime": 0.0682,
+      "eval_samples_per_second": 4807.36,
+      "eval_steps_per_second": 43.97,
+      "step": 42
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8384146341463414,
+      "eval_f1": 0.8382928848497251,
+      "eval_loss": 0.3434397876262665,
+      "eval_matthews_correlation": 0.677350773710334,
+      "eval_precision": 0.8390727489564699,
+      "eval_recall": 0.8382784904257297,
+      "eval_runtime": 0.0837,
+      "eval_samples_per_second": 3920.379,
+      "eval_steps_per_second": 35.857,
+      "step": 63
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8536585365853658,
+      "eval_f1": 0.8535223847270292,
+      "eval_loss": 0.42560020089149475,
+      "eval_matthews_correlation": 0.7080625988799476,
+      "eval_precision": 0.8545590154764124,
+      "eval_recall": 0.8535043688417921,
+      "eval_runtime": 0.0703,
+      "eval_samples_per_second": 4663.292,
+      "eval_steps_per_second": 42.652,
+      "step": 84
+    },
+    {
+      "epoch": 4.76,
+      "learning_rate": 1.2993630573248408e-05,
+      "loss": 0.2825,
+      "step": 100
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8567073170731707,
+      "eval_f1": 0.8566953288403439,
+      "eval_loss": 0.4490540325641632,
+      "eval_matthews_correlation": 0.7137889631479755,
+      "eval_precision": 0.8569940476190476,
+      "eval_recall": 0.8567949432980108,
+      "eval_runtime": 0.0824,
+      "eval_samples_per_second": 3978.506,
+      "eval_steps_per_second": 36.389,
+      "step": 105
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 168,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "total_flos": 168298575450000.0,
+  "trial_name": null,
+  "trial_params": null
+}

GUE/mouse/2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e2251ef3657528986f359d40bb12436087faf7ca6d5810ddd0df8f2db93e53
+size 5457