add model
Browse files- .gitignore +1 -0
- README.md +68 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- runs/Sep04_05-15-32_921c47264a6e/1630732916.3439543/events.out.tfevents.1630732916.921c47264a6e.4506.1 +3 -0
- runs/Sep04_05-15-32_921c47264a6e/1630732941.179093/events.out.tfevents.1630732941.921c47264a6e.4506.3 +3 -0
- runs/Sep04_05-15-32_921c47264a6e/events.out.tfevents.1630732916.921c47264a6e.4506.0 +3 -0
- runs/Sep04_05-15-32_921c47264a6e/events.out.tfevents.1630732941.921c47264a6e.4506.2 +3 -0
- runs/Sep04_05-28-33_921c47264a6e/1630733321.9114687/events.out.tfevents.1630733321.921c47264a6e.4854.1 +3 -0
- runs/Sep04_05-28-33_921c47264a6e/events.out.tfevents.1630733321.921c47264a6e.4854.0 +3 -0
- runs/Sep04_05-38-27_921c47264a6e/1630733916.6186223/events.out.tfevents.1630733916.921c47264a6e.5079.1 +3 -0
- runs/Sep04_05-38-27_921c47264a6e/events.out.tfevents.1630733916.921c47264a6e.5079.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- squad
|
6 |
+
model-index:
|
7 |
+
- name: xlm-roberta-large-finetuned-squad
|
8 |
+
results:
|
9 |
+
- task:
|
10 |
+
name: Question Answering
|
11 |
+
type: question-answering
|
12 |
+
dataset:
|
13 |
+
name: squad
|
14 |
+
type: squad
|
15 |
+
args: default
|
16 |
+
---
|
17 |
+
|
18 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
19 |
+
should probably proofread and complete it, then remove this comment. -->
|
20 |
+
|
21 |
+
# xlm-roberta-large-finetuned-squad
|
22 |
+
|
23 |
+
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the squad dataset.
|
24 |
+
It achieves the following results on the evaluation set:
|
25 |
+
- Loss: 1.0350
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 2e-05
|
45 |
+
- train_batch_size: 4
|
46 |
+
- eval_batch_size: 4
|
47 |
+
- seed: 42
|
48 |
+
- gradient_accumulation_steps: 8
|
49 |
+
- total_train_batch_size: 32
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 3
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 1.6093 | 1.0 | 620 | 1.0023 |
|
59 |
+
| 0.849 | 2.0 | 1240 | 0.9449 |
|
60 |
+
| 0.6693 | 3.0 | 1860 | 1.0350 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.10.0
|
66 |
+
- Pytorch 1.9.0+cu102
|
67 |
+
- Datasets 1.11.0
|
68 |
+
- Tokenizers 0.10.3
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForQuestionAnswering"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 1024,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 4096,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "xlm-roberta",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.10.0",
|
26 |
+
"type_vocab_size": 1,
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 250002
|
29 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7749dd404137e1f3749e1491da9358549f08ada34b249c350f30595a58640587
|
3 |
+
size 2235534897
|
runs/Sep04_05-15-32_921c47264a6e/1630732916.3439543/events.out.tfevents.1630732916.921c47264a6e.4506.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da74b5b88d66a80817473672afb0863ced3d7be8ade5270475af9739e220baf1
|
3 |
+
size 4200
|
runs/Sep04_05-15-32_921c47264a6e/1630732941.179093/events.out.tfevents.1630732941.921c47264a6e.4506.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc1205adda208e9d3716527691e684aaf80deca3fcae9d49c9233a720a65112c
|
3 |
+
size 4200
|
runs/Sep04_05-15-32_921c47264a6e/events.out.tfevents.1630732916.921c47264a6e.4506.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a69169ac352e23b615e8276ab854239587ce5d789724129e44c7b4e8a683afe
|
3 |
+
size 3039
|
runs/Sep04_05-15-32_921c47264a6e/events.out.tfevents.1630732941.921c47264a6e.4506.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a23714aefccd77d304ad55dc3e7b5d6cefca179fdd5fe641c1b51d3d105d2d2c
|
3 |
+
size 3039
|
runs/Sep04_05-28-33_921c47264a6e/1630733321.9114687/events.out.tfevents.1630733321.921c47264a6e.4854.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a1b9dc00e9d6510de57d7ec9ba4fb4a49516bc28069104a202c01e6da995acf
|
3 |
+
size 4200
|
runs/Sep04_05-28-33_921c47264a6e/events.out.tfevents.1630733321.921c47264a6e.4854.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:502ec408f3ecbf2e1647618fa19c8564814b32aa92ebe3ffad9d3f624c8d4e7d
|
3 |
+
size 3039
|
runs/Sep04_05-38-27_921c47264a6e/1630733916.6186223/events.out.tfevents.1630733916.921c47264a6e.5079.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:981a74abb7d9d12abf498af2a01d9be75dbdf4d75880264332b55a27eca63419
|
3 |
+
size 4200
|
runs/Sep04_05-38-27_921c47264a6e/events.out.tfevents.1630733916.921c47264a6e.5079.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64c471e3719cd14917d700305f67acc49d61e27f9dc030f25b9f57b6068dc179
|
3 |
+
size 4677
|
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 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-large", "tokenizer_class": "XLMRobertaTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:529a20ae434969a771808684b826509635bfd1a0788f33e8574d68d2631fd787
|
3 |
+
size 2671
|