Vishveshwara/NER-Contract

README.md

@@ -0,0 +1,72 @@
+---
+license: mit
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: roberta-large
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-large-token-classification
+  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. -->
+
+# bert-large-token-classification
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2157
+- Precision: 0.4271
+- Recall: 0.5155
+- F1: 0.4671
+- Accuracy: 0.9481
+
+## 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: 0.001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.3642        | 1.0   | 741  | 0.2888          | 0.2211    | 0.2315 | 0.2262 | 0.9264   |
+| 0.2508        | 2.0   | 1482 | 0.2862          | 0.3301    | 0.3645 | 0.3465 | 0.9217   |
+| 0.1609        | 3.0   | 2223 | 0.2247          | 0.3109    | 0.4309 | 0.3612 | 0.9411   |
+| 0.1404        | 4.0   | 2964 | 0.2391          | 0.3563    | 0.4669 | 0.4042 | 0.9303   |
+| 0.0937        | 5.0   | 3705 | 0.2157          | 0.4271    | 0.5155 | 0.4671 | 0.9481   |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "roberta-large",
+  "bias": "all",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query",
+    "value"
+  ],
+  "task_type": "TOKEN_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5dc2dc1fe8679f61efc98b00bafb4976c2bfbf7b50a8ce651b019fa59cc39af
+size 7495380

runs/Jun11_09-14-18_4dc680adc3cf/events.out.tfevents.1718097259.4dc680adc3cf.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:603eecb88e2bc318aa061db7382c057f29dca65893fd714ff93b2d5db72b48a3
+size 6349

runs/Jun11_09-48-27_4dc680adc3cf/events.out.tfevents.1718099308.4dc680adc3cf.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fa5405b7badd33537115731b76a017af7ec39d0acaf62b68709e499390d134
+size 9856

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0362557a76037a3da44819b81ce65c465331f7a67b87a61bc75f4253a69260
+size 5112