adding core files to run smaller bioformer8L model

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "bioformers/bioformer-8L",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "O",
+    "1": "B-chemical",
+    "2": "B-species",
+    "3": "B-gene",
+    "4": "I-gene",
+    "5": "B-taxonomy_domain",
+    "6": "I-chemical",
+    "7": "B-protein_type",
+    "8": "B-experimental_method",
+    "9": "I-experimental_method",
+    "10": "I-protein_type",
+    "11": "I-species",
+    "12": "B-evidence",
+    "13": "I-evidence",
+    "14": "B-protein",
+    "15": "I-protein",
+    "16": "B-protein_state",
+    "17": "B-site",
+    "18": "I-site",
+    "19": "B-structure_element",
+    "20": "I-structure_element",
+    "21": "B-complex_assembly",
+    "22": "I-protein_state",
+    "23": "I-complex_assembly",
+    "24": "B-ptm",
+    "25": "B-mutant",
+    "26": "I-mutant",
+    "27": "B-oligomeric_state",
+    "28": "B-residue_name_number",
+    "29": "B-bond_interaction",
+    "30": "I-bond_interaction",
+    "31": "B-residue_range",
+    "32": "I-residue_range",
+    "33": "B-residue_name",
+    "34": "B-residue_number",
+    "35": "I-ptm",
+    "36": "I-taxonomy_domain",
+    "37": "I-oligomeric_state",
+    "38": "I-residue_name_number",
+    "39": "I-residue_name",
+    "40": "I-residue_number"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "label2id": {
+    "B-bond_interaction": 29,
+    "B-chemical": 1,
+    "B-complex_assembly": 21,
+    "B-evidence": 12,
+    "B-experimental_method": 8,
+    "B-gene": 3,
+    "B-mutant": 25,
+    "B-oligomeric_state": 27,
+    "B-protein": 14,
+    "B-protein_state": 16,
+    "B-protein_type": 7,
+    "B-ptm": 24,
+    "B-residue_name": 33,
+    "B-residue_name_number": 28,
+    "B-residue_number": 34,
+    "B-residue_range": 31,
+    "B-site": 17,
+    "B-species": 2,
+    "B-structure_element": 19,
+    "B-taxonomy_domain": 5,
+    "I-bond_interaction": 30,
+    "I-chemical": 6,
+    "I-complex_assembly": 23,
+    "I-evidence": 13,
+    "I-experimental_method": 9,
+    "I-gene": 4,
+    "I-mutant": 26,
+    "I-oligomeric_state": 37,
+    "I-protein": 15,
+    "I-protein_state": 22,
+    "I-protein_type": 10,
+    "I-ptm": 35,
+    "I-residue_name": 39,
+    "I-residue_name_number": 38,
+    "I-residue_number": 40,
+    "I-residue_range": 32,
+    "I-site": 18,
+    "I-species": 11,
+    "I-structure_element": 20,
+    "I-taxonomy_domain": 36,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32768
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39ef12875e83f443c75ec35530cc20fe735318dc7da605d6e6d7e502e61b775
+size 338331642

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0361d9b66b17de750435cff934d86df55f0ae401007e95b46cb7b866adf00f2e
+size 169176682

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73c2594a1e721a20cff9f81a9c6b35735e5ef856ae026e6f451a155090123133
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a2812a42769889644fb265b287a3cb6966f030d4b6988b60a19dba3930cea8
+size 1064

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,226 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.659090909090908,
+  "global_step": 8500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.8863636363636366e-05,
+      "loss": 0.9603,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.917317101584343,
+      "eval_f1": 0.780907047467936,
+      "eval_loss": 0.3360126316547394,
+      "eval_precision": 0.7684100962789487,
+      "eval_recall": 0.7938172043010753,
+      "eval_runtime": 4.4585,
+      "eval_samples_per_second": 211.507,
+      "eval_steps_per_second": 42.391,
+      "step": 880
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.772727272727273e-05,
+      "loss": 0.4145,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.6590909090909094e-05,
+      "loss": 0.2846,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.940004659832246,
+      "eval_f1": 0.8470136913817051,
+      "eval_loss": 0.23408983647823334,
+      "eval_precision": 0.8338325302773799,
+      "eval_recall": 0.8606182795698925,
+      "eval_runtime": 5.0803,
+      "eval_samples_per_second": 185.62,
+      "eval_steps_per_second": 37.203,
+      "step": 1760
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.5454545454545454e-05,
+      "loss": 0.2114,
+      "step": 2000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.431818181818182e-05,
+      "loss": 0.1634,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9476351351351351,
+      "eval_f1": 0.8742690058479533,
+      "eval_loss": 0.20282697677612305,
+      "eval_precision": 0.8646161934805467,
+      "eval_recall": 0.8841397849462366,
+      "eval_runtime": 3.3011,
+      "eval_samples_per_second": 285.658,
+      "eval_steps_per_second": 57.253,
+      "step": 2640
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 1.3181818181818183e-05,
+      "loss": 0.1243,
+      "step": 3000
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 1.2045454545454547e-05,
+      "loss": 0.1158,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9500232991612302,
+      "eval_f1": 0.8811803278688525,
+      "eval_loss": 0.1980859786272049,
+      "eval_precision": 0.8603072983354674,
+      "eval_recall": 0.9030913978494624,
+      "eval_runtime": 4.9698,
+      "eval_samples_per_second": 189.745,
+      "eval_steps_per_second": 38.03,
+      "step": 3520
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.0808,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9508970177073626,
+      "eval_f1": 0.8861842105263158,
+      "eval_loss": 0.19827169179916382,
+      "eval_precision": 0.8679123711340206,
+      "eval_recall": 0.905241935483871,
+      "eval_runtime": 4.2259,
+      "eval_samples_per_second": 223.15,
+      "eval_steps_per_second": 44.725,
+      "step": 4400
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 9.772727272727273e-06,
+      "loss": 0.0809,
+      "step": 4500
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 8.636363636363637e-06,
+      "loss": 0.0679,
+      "step": 5000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.952673578751165,
+      "eval_f1": 0.89337822671156,
+      "eval_loss": 0.1982535719871521,
+      "eval_precision": 0.8779032048786817,
+      "eval_recall": 0.9094086021505376,
+      "eval_runtime": 4.536,
+      "eval_samples_per_second": 207.892,
+      "eval_steps_per_second": 41.667,
+      "step": 5280
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.0582,
+      "step": 5500
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 0.0468,
+      "step": 6000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9559354613233924,
+      "eval_f1": 0.9001193792280144,
+      "eval_loss": 0.20358432829380035,
+      "eval_precision": 0.8884524744697565,
+      "eval_recall": 0.9120967741935484,
+      "eval_runtime": 4.9544,
+      "eval_samples_per_second": 190.337,
+      "eval_steps_per_second": 38.148,
+      "step": 6160
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 5.2272727272727274e-06,
+      "loss": 0.0436,
+      "step": 6500
+    },
+    {
+      "epoch": 7.95,
+      "learning_rate": 4.0909090909090915e-06,
+      "loss": 0.0403,
+      "step": 7000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.955527726001864,
+      "eval_f1": 0.8995240613432047,
+      "eval_loss": 0.20606616139411926,
+      "eval_precision": 0.8850156087408949,
+      "eval_recall": 0.9145161290322581,
+      "eval_runtime": 3.9742,
+      "eval_samples_per_second": 237.282,
+      "eval_steps_per_second": 47.557,
+      "step": 7040
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 2.954545454545455e-06,
+      "loss": 0.0336,
+      "step": 7500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9554694780987885,
+      "eval_f1": 0.9019062748212867,
+      "eval_loss": 0.21168170869350433,
+      "eval_precision": 0.8884976525821596,
+      "eval_recall": 0.915725806451613,
+      "eval_runtime": 2.986,
+      "eval_samples_per_second": 315.802,
+      "eval_steps_per_second": 63.294,
+      "step": 7920
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 0.0328,
+      "step": 8000
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 6.818181818181818e-07,
+      "loss": 0.0312,
+      "step": 8500
+    }
+  ],
+  "max_steps": 8800,
+  "num_train_epochs": 10,
+  "total_flos": 408432261397380.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b551fbf29c3318236ff0e19876fb0afff99641683390db79faf1b4fadab8b042
+size 4088