BertSeqCls_full_data

README.md

@@ -1,6 +1,6 @@
 ---
-license: cc-by-sa-4.0
-base_model: nlpaueb/bert-base-uncased-contracts
+license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [nlpaueb/bert-base-uncased-contracts](https://huggingface.co/nlpaueb/bert-base-uncased-contracts) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6712
-- Accuracy: 0.8288
-- Precision: 0.8218
-- Recall: 0.8288
-- F1: 0.8182
+- Loss: 0.7643
+- Accuracy: 0.8686
+- Precision: 0.8681
+- Recall: 0.8686
+- F1: 0.8673
 
 ## Model description
 
@@ -44,8 +44,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -53,19 +53,20 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.6899        | 1.0   | 2036  | 0.6712          | 0.8288   | 0.8218    | 0.8288 | 0.8182 |
-| 0.4942        | 2.0   | 4072  | 0.7382          | 0.8306   | 0.8386    | 0.8306 | 0.8265 |
-| 0.3387        | 3.0   | 6108  | 0.7275          | 0.8487   | 0.8568    | 0.8487 | 0.8473 |
-| 0.1892        | 4.0   | 8144  | 0.7668          | 0.8642   | 0.8626    | 0.8642 | 0.8600 |
-| 0.125         | 5.0   | 10180 | 0.8604          | 0.8583   | 0.8581    | 0.8583 | 0.8556 |
-| 0.0673        | 6.0   | 12216 | 0.8526          | 0.8649   | 0.8651    | 0.8649 | 0.8629 |
-| 0.0237        | 7.0   | 14252 | 0.8789          | 0.8657   | 0.8660    | 0.8657 | 0.8649 |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.2969        | 1.0   | 505  | 0.6707          | 0.8376   | 0.8375    | 0.8376 | 0.8320 |
+| 0.2567        | 2.0   | 1010 | 0.6184          | 0.8572   | 0.8516    | 0.8572 | 0.8519 |
+| 0.1496        | 3.0   | 1515 | 0.6471          | 0.8693   | 0.8637    | 0.8693 | 0.8651 |
+| 0.0826        | 4.0   | 2020 | 0.6897          | 0.8641   | 0.8600    | 0.8641 | 0.8604 |
+| 0.0467        | 5.0   | 2525 | 0.7378          | 0.8676   | 0.8671    | 0.8676 | 0.8663 |
+| 0.0229        | 6.0   | 3030 | 0.7521          | 0.8678   | 0.8670    | 0.8678 | 0.8666 |
+| 0.01          | 7.0   | 3535 | 0.7643          | 0.8686   | 0.8681    | 0.8686 | 0.8673 |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
+- Transformers 4.36.2
+- Pytorch 2.0.0
+- Datasets 2.1.0
 - Tokenizers 0.15.0

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "nlpaueb/bert-base-uncased-contracts",
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "eos_token_ids": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -76,12 +76,11 @@
   "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
-  "pad_token_id": null,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.36.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58349c1559534a94a68e159607cb60a7ee7a67052bb97fa3398b5d0ec3ab9960
+oid sha256:bbe1c54359e68c9536eb85f9e3580a84a859f7422e0f334837af91ca7cd873c9
 size 438038624

runs/Jan18_16-55-16_5ec55a6fdce0/events.out.tfevents.1705596917.5ec55a6fdce0.78.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55b3f3ea0b7ee5f61f18c62d2055560c3a16c49078d7e5c6a7d6565c08ba8cb
+size 5501

runs/Jan18_16-59-35_5ec55a6fdce0/events.out.tfevents.1705597179.5ec55a6fdce0.78.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4b68d19d946d1eea6798db6175d2f422a3cf0f1bf1aeb09d9f1ac71bf58a11
+size 5709

runs/Jan18_17-15-17_5ec55a6fdce0/events.out.tfevents.1705598121.5ec55a6fdce0.78.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cefbaa4274862529f561b7afc12a3137af53140fdf975866e55d204169d50661
+size 5552

runs/Jan18_17-18-29_5ec55a6fdce0/events.out.tfevents.1705598312.5ec55a6fdce0.78.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332b63fef931f1289bc85268c65282241c374ad5c4022a0ffc309ffb3eb391f0
+size 10308

runs/Jan18_17-18-29_5ec55a6fdce0/events.out.tfevents.1705604756.5ec55a6fdce0.78.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c469c90bb492b8a90324918d479ea999cf4a12954ab856e4c9f6a2e94800eaa3
+size 560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2dfafe79973f72a8575ee5c187fb5c7bc6edb61a0915813fc419e9b36af91e5
-size 4536
+oid sha256:c45b306b3826b810461f9faa6f05db7ef28855b121ee9e6693c984e8a7cabaea
+size 4219