Upload 7 files

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "nlpaueb/legal-bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_ids": 0,
+  "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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66815cdffb861cebbb52584724e094825dcfe3beca72cc1cd707ef00fae93dc
+size 437980180

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe97faf37b5cd125eebb77c73e5f0305e85d4d51f8a8f5866126199945ae461
+size 876081402

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63908b9b6cb9dc8256eb102fb72e85adf43f9a90fe59c17cb4d0af307898b5d
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb9d01b2114ccf0ac9b7e628c01b27cf404ad5e739c736ab2e280aab8a242e1
+size 1064

trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 0.7635786873553013,
+  "best_model_checkpoint": "model_checkpoint/fine-tuned_legalbert_multilabel_original_train/checkpoint-783",
+  "epoch": 2.997129186602871,
+  "eval_steps": 500,
+  "global_step": 783,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.999043062200957,
+      "eval_A_f1": 0.0,
+      "eval_A_precision": 0.0,
+      "eval_A_recall": 0.0,
+      "eval_CH_f1": 0.0,
+      "eval_CH_precision": 0.0,
+      "eval_CH_recall": 0.0,
+      "eval_CR_f1": 0.0,
+      "eval_CR_precision": 0.0,
+      "eval_CR_recall": 0.0,
+      "eval_FAIR_f1": 0.9544351203273459,
+      "eval_FAIR_precision": 0.9774147727272727,
+      "eval_FAIR_recall": 0.9325111803767449,
+      "eval_J_f1": 0.0,
+      "eval_J_precision": 0.0,
+      "eval_J_recall": 0.0,
+      "eval_LAW_f1": 0.0,
+      "eval_LAW_precision": 0.0,
+      "eval_LAW_recall": 0.0,
+      "eval_LTD_f1": 0.6153846153846154,
+      "eval_LTD_precision": 0.7472527472527473,
+      "eval_LTD_recall": 0.5230769230769231,
+      "eval_TER_f1": 0.0,
+      "eval_TER_precision": 0.0,
+      "eval_TER_recall": 0.0,
+      "eval_USE_f1": 0.017241379310344827,
+      "eval_USE_precision": 1.0,
+      "eval_USE_recall": 0.008695652173913044,
+      "eval_accuracy": 0.8484116439183477,
+      "eval_f1_macro": 0.17634012389136736,
+      "eval_loss": 0.06019286438822746,
+      "eval_precision_macro": 0.3027408355533356,
+      "eval_recall_macro": 0.1626981950697312,
+      "eval_runtime": 894.9212,
+      "eval_samples_per_second": 9.251,
+      "eval_steps_per_second": 0.579,
+      "step": 261
+    },
+    {
+      "epoch": 1.9138755980861244,
+      "grad_norm": 0.9339248538017273,
+      "learning_rate": 1.8135376756066413e-05,
+      "loss": 0.0784,
+      "step": 500
+    },
+    {
+      "epoch": 1.998086124401914,
+      "eval_A_f1": 0.5909090909090909,
+      "eval_A_precision": 1.0,
+      "eval_A_recall": 0.41935483870967744,
+      "eval_CH_f1": 0.4873096446700508,
+      "eval_CH_precision": 0.8571428571428571,
+      "eval_CH_recall": 0.3404255319148936,
+      "eval_CR_f1": 0.0,
+      "eval_CR_precision": 0.0,
+      "eval_CR_recall": 0.0,
+      "eval_FAIR_f1": 0.9716993725804298,
+      "eval_FAIR_precision": 0.9573852426673681,
+      "eval_FAIR_recall": 0.9864480281881014,
+      "eval_J_f1": 0.8623853211009175,
+      "eval_J_precision": 0.9038461538461539,
+      "eval_J_recall": 0.8245614035087719,
+      "eval_LAW_f1": 0.7927927927927928,
+      "eval_LAW_precision": 0.88,
+      "eval_LAW_recall": 0.7213114754098361,
+      "eval_LTD_f1": 0.6752688172043011,
+      "eval_LTD_precision": 0.7658536585365854,
+      "eval_LTD_recall": 0.6038461538461538,
+      "eval_TER_f1": 0.6990881458966566,
+      "eval_TER_precision": 0.7419354838709677,
+      "eval_TER_recall": 0.6609195402298851,
+      "eval_USE_f1": 0.6632124352331606,
+      "eval_USE_precision": 0.8205128205128205,
+      "eval_USE_recall": 0.5565217391304348,
+      "eval_accuracy": 0.9299432298586786,
+      "eval_f1_macro": 0.6380739578208222,
+      "eval_loss": 0.04580436274409294,
+      "eval_precision_macro": 0.7696306907307503,
+      "eval_recall_macro": 0.568154301215306,
+      "eval_runtime": 898.3262,
+      "eval_samples_per_second": 9.216,
+      "eval_steps_per_second": 0.577,
+      "step": 522
+    },
+    {
+      "epoch": 2.997129186602871,
+      "eval_A_f1": 0.7,
+      "eval_A_precision": 0.7241379310344828,
+      "eval_A_recall": 0.6774193548387096,
+      "eval_CH_f1": 0.72,
+      "eval_CH_precision": 0.8256880733944955,
+      "eval_CH_recall": 0.6382978723404256,
+      "eval_CR_f1": 0.6301369863013698,
+      "eval_CR_precision": 0.8214285714285714,
+      "eval_CR_recall": 0.5111111111111111,
+      "eval_FAIR_f1": 0.9708172523529014,
+      "eval_FAIR_precision": 0.9700947225981056,
+      "eval_FAIR_recall": 0.9715408591950129,
+      "eval_J_f1": 0.9026548672566371,
+      "eval_J_precision": 0.9107142857142857,
+      "eval_J_recall": 0.8947368421052632,
+      "eval_LAW_f1": 0.8035714285714286,
+      "eval_LAW_precision": 0.8823529411764706,
+      "eval_LAW_recall": 0.7377049180327869,
+      "eval_LTD_f1": 0.7022900763358778,
+      "eval_LTD_precision": 0.696969696969697,
+      "eval_LTD_recall": 0.7076923076923077,
+      "eval_TER_f1": 0.7440476190476191,
+      "eval_TER_precision": 0.7716049382716049,
+      "eval_TER_recall": 0.7183908045977011,
+      "eval_USE_f1": 0.6986899563318777,
+      "eval_USE_precision": 0.7017543859649122,
+      "eval_USE_recall": 0.6956521739130435,
+      "eval_accuracy": 0.9356202439908201,
+      "eval_f1_macro": 0.7635786873553013,
+      "eval_loss": 0.043075863271951675,
+      "eval_precision_macro": 0.8116383940614028,
+      "eval_recall_macro": 0.7280606937584846,
+      "eval_runtime": 894.9343,
+      "eval_samples_per_second": 9.251,
+      "eval_steps_per_second": 0.579,
+      "step": 783
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 783,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3294883706222592.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1d8a075ceb58ad8c3f4a09475bd1ae53dd27990dbb37f3b38b21e1112bbf586
+size 5368