vgarg/context_flag_model_v3

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: bert-base-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6240
+
+## 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: 2e-05
+- train_batch_size: 512
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 1    | 0.6822          |
+| No log        | 2.0   | 2    | 0.6416          |
+| No log        | 3.0   | 3    | 0.6240          |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "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 sha256:888537990175ff64427f0e887d8fa01ee055e3e85e17c983fcedff85d438f473
+size 437958648

runs/May27_12-09-36_d41b09c529c5/events.out.tfevents.1716811776.d41b09c529c5.9226.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0739bfd605d63cdf1742403600a1997f380063ef4e51793c2675e0ae03dd2c77
+size 4779

runs/May27_12-14-52_d41b09c529c5/events.out.tfevents.1716812093.d41b09c529c5.9226.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22430f9524317474c9c10cb75fb8ce8c5ddde9dbdc97644c18b88f4b124ed45a
+size 4779

runs/May27_12-15-52_d41b09c529c5/events.out.tfevents.1716812153.d41b09c529c5.9226.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ecbdc8d50baef5375fcaa20c5aad718483ab6956605692841b4bc53a3433e89
+size 4779

runs/May27_12-18-07_d41b09c529c5/events.out.tfevents.1716812288.d41b09c529c5.9226.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ea157de05ed887d06fca5f4a910fbc2b03ffabb1fc0ed9059e2f81f9e8f67d
+size 4779

runs/May27_12-20-25_d41b09c529c5/events.out.tfevents.1716812425.d41b09c529c5.9226.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2dccf072f406e63e79b3a1f48d479d99b6ad1c7c43c9bb2a8d203fb4a36a756
+size 5922

runs/May27_12-21-51_d41b09c529c5/events.out.tfevents.1716812511.d41b09c529c5.9226.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fec690d65e09bd4e5c37bb5dfd044011ff183c09beff9d34e67adb76a74ec85
+size 5925

runs/May27_12-21-51_d41b09c529c5/events.out.tfevents.1716812544.d41b09c529c5.9226.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3feef9fcccd82e3c6695c55a128374ef438c1276392068df769542cff5a0c75
+size 620

runs/May27_12-25-05_d41b09c529c5/events.out.tfevents.1716812706.d41b09c529c5.9226.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1feb2ee71ad3dcd44eaf15371d46d875844593594a6a38f32403bd4a9a6435cb
+size 5927

runs/May27_12-25-05_d41b09c529c5/events.out.tfevents.1716812713.d41b09c529c5.9226.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5648fd4df0357a2550929ba3ae06c26a9da7bf8c092036bc88f7ab04e9cf727
+size 354

runs/May27_12-25-40_d41b09c529c5/events.out.tfevents.1716812740.d41b09c529c5.9226.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44400e734c32dfcc26befa43d26c66b8d41ab0651635a97b9714ed331b59f981
+size 5928

runs/May27_12-25-40_d41b09c529c5/events.out.tfevents.1716812746.d41b09c529c5.9226.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9038b83d3a289b2bcbb7d8b662b5c1bd530926a135675db693965a839dab5f
+size 354

runs/May27_12-26-17_d41b09c529c5/events.out.tfevents.1716812778.d41b09c529c5.9226.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01bb29962a05cf2453ee0cb8a9eac94394de4d545c0417f1949b1d253b7ead8c
+size 5928

runs/May27_12-26-17_d41b09c529c5/events.out.tfevents.1716812779.d41b09c529c5.9226.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc951c124b2e9a8eb5d52ad4d8f0f2cf30ba0957c31396fac4804c8910c47bd
+size 354

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4927a335787cd07e598e2f4f5059a3198a6c30ef3d5d28c70350b967751b133
+size 5112