dheerajpai/patentbert-cased-2b

README.md

@@ -0,0 +1,53 @@
+---
+license: mit
+base_model: dheerajpai/patentbert
+tags:
+- generated_from_trainer
+model-index:
+- name: PATENT_BERT_2
+  results: []
+---
+
+<!-- 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. -->
+
+# PATENT_BERT_2
+
+This model is a fine-tuned version of [dheerajpai/patentbert](https://huggingface.co/dheerajpai/patentbert) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "dheerajpai/patentbert",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 256,
+  "model_type": "bert",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:023751f6b53e11feb2fd467be53f6def66b182eb2d1015548f79578ee87262c1
+size 81147512

runs/Mar08_10-38-40_ddo-MS-7D25/events.out.tfevents.1709912320.ddo-MS-7D25.780769.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e086aaaed4b8f235ec2c449a27b8521774aca3197d714fe9da4ebaae093884c8
+size 4883

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ebd46d76700bcfa920047dfb7fa841c9eb93836dc2f3b5151fbe67b563979e
+size 4920