BioBERT V1.1 model trained on FrenchMedMCQA using Wikipedia BM25 external knowledge

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "dmis-lab/biobert-v1.1",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c59e476f258026c1224572d39dd2749b94a080f47f527d5cf41713cffaddc727
+size 866789277

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a1d14e1a7ae3a933e64a02529d84ca875185eb6eedbe2da6f776a2cd2563eb9
+size 433407405

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac35a75470483733ef2559b641f153185f391fe23c7947bd33323cbccf35cc5
+size 17563

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703982142fcedd14e5792d976b42adce5e182c36b7f363756bb8375901668f30
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/users/ylabrak/.cache/huggingface/transformers/118da8438a7854000cfcf052566f83ae4f4159ac25796e49e16c3b18746041b4.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "dmis-lab/biobert-v1.1", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.16666666666666666,
+  "best_model_checkpoint": "biobert-v1.1-finetuned-frenchmedmcqa/checkpoint-952",
+  "epoch": 7.0,
+  "global_step": 952,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.13782051282051283,
+      "eval_f1": 0.03338750451426508,
+      "eval_loss": 3.1616480350494385,
+      "eval_precision": 0.01899449375410914,
+      "eval_recall": 0.13782051282051283,
+      "eval_runtime": 5.2204,
+      "eval_samples_per_second": 59.765,
+      "eval_steps_per_second": 3.831,
+      "step": 136
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.16025641025641027,
+      "eval_f1": 0.06942300892072582,
+      "eval_loss": 2.8957390785217285,
+      "eval_precision": 0.04520268867434859,
+      "eval_recall": 0.16025641025641027,
+      "eval_runtime": 5.1606,
+      "eval_samples_per_second": 60.458,
+      "eval_steps_per_second": 3.875,
+      "step": 272
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.15384615384615385,
+      "eval_f1": 0.0817681987234755,
+      "eval_loss": 2.722668170928955,
+      "eval_precision": 0.10610228539576365,
+      "eval_recall": 0.15384615384615385,
+      "eval_runtime": 5.1585,
+      "eval_samples_per_second": 60.483,
+      "eval_steps_per_second": 3.877,
+      "step": 408
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 1.2647058823529412e-05,
+      "loss": 3.2368,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.15705128205128205,
+      "eval_f1": 0.06610402141868449,
+      "eval_loss": 2.653123617172241,
+      "eval_precision": 0.061101876500489406,
+      "eval_recall": 0.15705128205128205,
+      "eval_runtime": 5.1556,
+      "eval_samples_per_second": 60.516,
+      "eval_steps_per_second": 3.879,
+      "step": 544
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.15384615384615385,
+      "eval_f1": 0.08432282082065398,
+      "eval_loss": 2.648888349533081,
+      "eval_precision": 0.08665532400061121,
+      "eval_recall": 0.15384615384615385,
+      "eval_runtime": 5.1699,
+      "eval_samples_per_second": 60.349,
+      "eval_steps_per_second": 3.869,
+      "step": 680
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.13782051282051283,
+      "eval_f1": 0.08504238712449276,
+      "eval_loss": 2.684257745742798,
+      "eval_precision": 0.08323137866407097,
+      "eval_recall": 0.13782051282051283,
+      "eval_runtime": 5.1788,
+      "eval_samples_per_second": 60.246,
+      "eval_steps_per_second": 3.862,
+      "step": 816
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.16666666666666666,
+      "eval_f1": 0.11330544110085618,
+      "eval_loss": 2.5864272117614746,
+      "eval_precision": 0.12433231913455035,
+      "eval_recall": 0.16666666666666666,
+      "eval_runtime": 5.1662,
+      "eval_samples_per_second": 60.393,
+      "eval_steps_per_second": 3.871,
+      "step": 952
+    }
+  ],
+  "max_steps": 1360,
+  "num_train_epochs": 10,
+  "total_flos": 1979672148207138.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba052851e122ec4dd03692c037212e78abde9529a4aa1aad00013df9555ad07
+size 3119