Upload folder using huggingface_hub

training_checkpoints/checkpoint-3215/config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "law-ai/InLegalBERT",
+  "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": "Issue",
+    "1": "Court Discourse",
+    "2": "Conclusion",
+    "3": "Precedent Analysis",
+    "4": "Section Analysis",
+    "5": "Argument by Petitioner",
+    "6": "Fact",
+    "7": "Argument by Respondent",
+    "8": "Ratio",
+    "9": "Appellant",
+    "10": "Respondent",
+    "11": "Argument by Appellant",
+    "12": "Petitioner",
+    "13": "Judge",
+    "14": "Argument by Defendant"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Appellant": 9,
+    "Argument by Appellant": 11,
+    "Argument by Defendant": 14,
+    "Argument by Petitioner": 5,
+    "Argument by Respondent": 7,
+    "Conclusion": 2,
+    "Court Discourse": 1,
+    "Fact": 6,
+    "Issue": 0,
+    "Judge": 13,
+    "Petitioner": 12,
+    "Precedent Analysis": 3,
+    "Ratio": 8,
+    "Respondent": 10,
+    "Section Analysis": 4
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

training_checkpoints/checkpoint-3215/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b15401fe33efa92d6e384fb8d182acdb897146fb4f943c19e62bed5666f3e1
+size 437998636

training_checkpoints/checkpoint-3215/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe5cd6726593ce25f02875dd3c6c8c5e5debb1e8ba41dcbd628f4c8ce223490
+size 876118266

training_checkpoints/checkpoint-3215/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5662d221ca869b9dbc9995e00e8b25d4919f153e8325e372bdb05543c92bc976
+size 14244

training_checkpoints/checkpoint-3215/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf5ea58a6a370f2ffd2025b333a1f3443949fe0f9e0434cf8500c9084225fa0
+size 1064

training_checkpoints/checkpoint-3215/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": 0.7985673319510695,
+  "best_model_checkpoint": "InLegalBERT/checkpoint-3215",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 3215,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.78,
+      "grad_norm": 6.225058078765869,
+      "learning_rate": 4.742871954380509e-05,
+      "loss": 1.065,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7993803253292022,
+      "eval_f1_macro": 0.6028764374506596,
+      "eval_f1_micro": 0.7993803253292022,
+      "eval_f1_weighted": 0.780434475079005,
+      "eval_loss": 0.6395189166069031,
+      "eval_macro_fpr": 0.01853296480715729,
+      "eval_macro_sensitivity": 0.6307714529979154,
+      "eval_macro_specificity": 0.9847175193097543,
+      "eval_precision": 0.7817573111259606,
+      "eval_precision_macro": 0.6194286814679265,
+      "eval_recall": 0.7993803253292022,
+      "eval_recall_macro": 0.6307714529979154,
+      "eval_runtime": 29.4696,
+      "eval_samples_per_second": 43.808,
+      "eval_steps_per_second": 5.497,
+      "eval_weighted_fpr": 0.017610661589719183,
+      "eval_weighted_sensitivity": 0.7993803253292022,
+      "eval_weighted_specificity": 0.9713824643171124,
+      "step": 643
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 8.756747245788574,
+      "learning_rate": 4.483670295489891e-05,
+      "loss": 0.5866,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8187451587916343,
+      "eval_f1_macro": 0.7276084501581802,
+      "eval_f1_micro": 0.8187451587916342,
+      "eval_f1_weighted": 0.8152450677099363,
+      "eval_loss": 0.6906521916389465,
+      "eval_macro_fpr": 0.01610571025604924,
+      "eval_macro_sensitivity": 0.7365748487318147,
+      "eval_macro_specificity": 0.9863504064994671,
+      "eval_precision": 0.8198905458065566,
+      "eval_precision_macro": 0.7284980957351811,
+      "eval_recall": 0.8187451587916343,
+      "eval_recall_macro": 0.7365748487318147,
+      "eval_runtime": 57.1075,
+      "eval_samples_per_second": 22.606,
+      "eval_steps_per_second": 2.837,
+      "eval_weighted_fpr": 0.015566790846194785,
+      "eval_weighted_sensitivity": 0.8187451587916343,
+      "eval_weighted_specificity": 0.976510938700373,
+      "step": 1286
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 8.241662979125977,
+      "learning_rate": 4.224468636599274e-05,
+      "loss": 0.4622,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8179705654531371,
+      "eval_f1_macro": 0.7282676953256336,
+      "eval_f1_micro": 0.817970565453137,
+      "eval_f1_weighted": 0.8150036178041801,
+      "eval_loss": 0.8055915236473083,
+      "eval_macro_fpr": 0.016168738933500626,
+      "eval_macro_sensitivity": 0.737597935006265,
+      "eval_macro_specificity": 0.9862931306285473,
+      "eval_precision": 0.8137371356291269,
+      "eval_precision_macro": 0.7226669118270935,
+      "eval_recall": 0.8179705654531371,
+      "eval_recall_macro": 0.737597935006265,
+      "eval_runtime": 56.5581,
+      "eval_samples_per_second": 22.826,
+      "eval_steps_per_second": 2.864,
+      "eval_weighted_fpr": 0.01564684732671949,
+      "eval_weighted_sensitivity": 0.8179705654531371,
+      "eval_weighted_specificity": 0.9764263939750704,
+      "step": 1929
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 5.718050003051758,
+      "learning_rate": 3.9652669777086575e-05,
+      "loss": 0.346,
+      "step": 2000
+    },
+    {
+      "epoch": 3.89,
+      "grad_norm": 28.698440551757812,
+      "learning_rate": 3.7060653188180404e-05,
+      "loss": 0.2398,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8171959721146398,
+      "eval_f1_macro": 0.7407336443567221,
+      "eval_f1_micro": 0.8171959721146398,
+      "eval_f1_weighted": 0.8160506897887181,
+      "eval_loss": 0.9310164451599121,
+      "eval_macro_fpr": 0.016134598971936556,
+      "eval_macro_sensitivity": 0.7424877811517157,
+      "eval_macro_specificity": 0.9862275325034797,
+      "eval_precision": 0.8234764041889034,
+      "eval_precision_macro": 0.7660803499273104,
+      "eval_recall": 0.8171959721146398,
+      "eval_recall_macro": 0.7424877811517157,
+      "eval_runtime": 58.71,
+      "eval_samples_per_second": 21.989,
+      "eval_steps_per_second": 2.759,
+      "eval_weighted_fpr": 0.015727042516326804,
+      "eval_weighted_sensitivity": 0.8171959721146398,
+      "eval_weighted_specificity": 0.9762170154375561,
+      "step": 2572
+    },
+    {
+      "epoch": 4.67,
+      "grad_norm": 8.432526588439941,
+      "learning_rate": 3.447382063245205e-05,
+      "loss": 0.1611,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8303640588690937,
+      "eval_f1_macro": 0.7985673319510695,
+      "eval_f1_micro": 0.8303640588690937,
+      "eval_f1_weighted": 0.8304130023375266,
+      "eval_loss": 1.0763046741485596,
+      "eval_macro_fpr": 0.014791024663918677,
+      "eval_macro_sensitivity": 0.7918299512118986,
+      "eval_macro_specificity": 0.9872504344639083,
+      "eval_precision": 0.8362631231068205,
+      "eval_precision_macro": 0.8174407838611729,
+      "eval_recall": 0.8303640588690937,
+      "eval_recall_macro": 0.7918299512118986,
+      "eval_runtime": 71.8128,
+      "eval_samples_per_second": 17.977,
+      "eval_steps_per_second": 2.256,
+      "eval_weighted_fpr": 0.014382347146516056,
+      "eval_weighted_sensitivity": 0.8303640588690937,
+      "eval_weighted_specificity": 0.978392458089531,
+      "step": 3215
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9645,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 6760111972239360.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-3215/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d67f433b74e0c5015495d7470ff35e34ab20bb7abc2e1887dfc6d557fdf2970
+size 4920