nathanReitinger/scotusPRED

README.md

@@ -1,22 +1,26 @@
 ---
+license: apache-2.0
+base_model: allenai/longformer-base-4096
 tags:
-- generated_from_keras_callback
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
 model-index:
-- name: nathanReitinger/scotusPRED
+- name: scotusPRED
   results: []
 ---
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-# nathanReitinger/scotusPRED
+# scotusPRED
 
-This model is a fine-tuned version of [pile-of-law/legalbert-large-1.7M-2](https://huggingface.co/pile-of-law/legalbert-large-1.7M-2) on an unknown dataset.
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.6960
-- Validation Loss: 0.6932
-- Train Accuracy: 0.4809
-- Epoch: 1
+- Loss: 0.6335
+- Accuracy: 0.6735
+- F1: 0.0
 
 ## Model description
 
@@ -35,20 +39,28 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 72, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
-- training_precision: float32
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 1
+- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Train Loss | Validation Loss | Train Accuracy | Epoch |
-|:----------:|:---------------:|:--------------:|:-----:|
-| 0.7225     | 0.6917          | 0.5191         | 0     |
-| 0.6960     | 0.6932          | 0.4809         | 1     |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1  |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|
+| 0.6824        | 1.0   | 195  | 0.6335          | 0.6735   | 0.0 |
 
 
 ### Framework versions
 
-- Transformers 4.30.2
-- TensorFlow 2.11.0
-- Datasets 2.13.2
-- Tokenizers 0.13.3
+- Transformers 4.39.3
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -1,35 +1,44 @@
 {
-  "_name_or_path": "pile-of-law/legalbert-large-1.7M-2",
+  "_name_or_path": "allenai/longformer-base-4096",
   "architectures": [
-    "BertForSequenceClassification"
+    "LongformerForSequenceClassification"
   ],
+  "attention_mode": "longformer",
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "directionality": "bidi",
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
-  "id2label": {
-    "0": "Reversing",
-    "1": "Affirming"
-  },
+  "hidden_size": 768,
+  "ignore_attention_mask": false,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "Affirming": 1,
-    "Reversing": 0
-  },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
-  "tokenizer_class": "BertTokenizer",
-  "transformers_version": "4.30.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 32000
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "problem_type": "single_label_classification",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88fd233f0fdc4119a58ecf2a7387ff2910aefcbcc1d40b13d108a187642a8867
+size 594678184

runs/Apr17_15-04-04_tron01.umiacs.umd.edu/events.out.tfevents.1713380645.tron01.umiacs.umd.edu.723909.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e0c3ae2cfcdc4f2f4a0596e10c2fcc9e9e91ed4e2da1ff0ee1cdaf62696edd
+size 15536

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a48b9430ef930f72b59bac60ca43c1258fa403d12d04c4938856f69443622f6
+size 4984