Tarun Anand commited on
Commit
c9747f1
1 Parent(s): 97640bb
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - squad_v2
7
+ model-index:
8
+ - name: roberta-base-finetuned-squad2
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # roberta-base-finetuned-squad2
16
+
17
+ This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the squad_v2 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.9325
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 16
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 3
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 0.88 | 1.0 | 8160 | 0.8129 |
51
+ | 0.6643 | 2.0 | 16320 | 0.8567 |
52
+ | 0.5096 | 3.0 | 24480 | 0.9325 |
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.12.2
58
+ - Pytorch 1.9.0+cu111
59
+ - Datasets 1.14.0
60
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.12.2",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdf6163701ac9ff46bb6267ea20b8aea334cab6b251af286184e6cf71624950
3
+ size 496311025
runs/Nov01_11-22-11_f2b310c58ae9/1635765747.1314385/events.out.tfevents.1635765747.f2b310c58ae9.92.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ad04a723cc990bb107898db6455d403c87f4d2d798b1ed0401f8063cbb38f8
3
+ size 4546
runs/Nov01_11-22-11_f2b310c58ae9/events.out.tfevents.1635765747.f2b310c58ae9.92.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3514b07816793dc47c8c241739ffd71149a8a7b3f9610e7ff76261b7655aa76f
3
+ size 3190
runs/Nov01_11-24-34_f2b310c58ae9/1635765883.224008/events.out.tfevents.1635765883.f2b310c58ae9.586.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e5627b8fb08f2683a626810dde8170ff7a9a3b8238afc26165deaa787e40e6d
3
+ size 4546
runs/Nov01_11-24-34_f2b310c58ae9/events.out.tfevents.1635765883.f2b310c58ae9.586.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd642171623a5a9f8e9083dd7c05646163c6e87c7baa580d2f9330cbf53e54cb
3
+ size 11952
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e39df2f15b412dca47865c14f129fc93ae9edf6b554aa16b95699ed2c97deb
3
+ size 2863
vocab.json ADDED
The diff for this file is too large to render. See raw diff