KarthikAlagarsamy
commited on
Commit
•
385f3b1
1
Parent(s):
dd8e301
End of training
Browse files- README.md +59 -0
- config.json +24 -0
- model.safetensors +3 -0
- runs/Apr03_20-09-08_PC/events.out.tfevents.1712200149.PC.4360.0 +3 -0
- runs/Apr03_20-11-09_PC/events.out.tfevents.1712200270.PC.4360.1 +3 -0
- runs/Apr03_20-12-50_PC/events.out.tfevents.1712200370.PC.4360.2 +3 -0
- runs/Apr03_20-13-15_PC/events.out.tfevents.1712200396.PC.4360.3 +3 -0
- runs/Apr03_20-28-32_PC/events.out.tfevents.1712201312.PC.4360.5 +3 -0
- runs/Apr03_20-31-09_PC/events.out.tfevents.1712201470.PC.13900.0 +3 -0
- runs/Apr03_20-45-15_PC/events.out.tfevents.1712202413.PC.13900.1 +3 -0
- runs/Apr03_20-57-38_PC/events.out.tfevents.1712203059.PC.13900.2 +3 -0
- runs/Apr05_10-40-18_PC/events.out.tfevents.1712293820.PC.11556.0 +3 -0
- runs/Apr05_10-40-18_PC/events.out.tfevents.1712294162.PC.11556.1 +3 -0
- runs/Apr05_10-40-18_PC/events.out.tfevents.1712294474.PC.11556.2 +3 -0
- runs/Apr05_10-40-18_PC/events.out.tfevents.1712299489.PC.11556.3 +3 -0
- runs/Apr05_12-18-35_PC/events.out.tfevents.1712299719.PC.9836.0 +3 -0
- runs/Apr05_17-35-38_PC/events.out.tfevents.1712318738.PC.9836.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: my_awesome_qa_model
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# my_awesome_qa_model
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 5.8070
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 16
|
39 |
+
- eval_batch_size: 16
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 3 | 5.8810 |
|
50 |
+
| No log | 2.0 | 6 | 5.8290 |
|
51 |
+
| No log | 3.0 | 9 | 5.8070 |
|
52 |
+
|
53 |
+
|
54 |
+
### Framework versions
|
55 |
+
|
56 |
+
- Transformers 4.38.0
|
57 |
+
- Pytorch 2.2.2+cpu
|
58 |
+
- Datasets 2.17.0
|
59 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForQuestionAnswering"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.38.0",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be760ae5fcd122def7adba3e9e7c310226e7d9382bee69f7142e267d70c4cc30
|
3 |
+
size 265470032
|
runs/Apr03_20-09-08_PC/events.out.tfevents.1712200149.PC.4360.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45d535e1fd19af8f48d366f0e0cd3d9aa899368e3ba00768da8a49347631d22a
|
3 |
+
size 4477
|
runs/Apr03_20-11-09_PC/events.out.tfevents.1712200270.PC.4360.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0639713f232037fd78aa0af0fa3f16b0989ee1d47611b313338a1f4ea491a254
|
3 |
+
size 4477
|
runs/Apr03_20-12-50_PC/events.out.tfevents.1712200370.PC.4360.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23d4902f2fa507dfc74868fdc1660705238a43c706104c85f00786ea07dd7a63
|
3 |
+
size 4477
|
runs/Apr03_20-13-15_PC/events.out.tfevents.1712200396.PC.4360.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecc9285e5c39e6e318df3cdba67ef434f4e132e81a6de7430ed837caca849a38
|
3 |
+
size 4476
|
runs/Apr03_20-28-32_PC/events.out.tfevents.1712201312.PC.4360.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33f041e5169829ce5196e2961ed536177add3a6dd738da66bd3a1e9781b08b16
|
3 |
+
size 4476
|
runs/Apr03_20-31-09_PC/events.out.tfevents.1712201470.PC.13900.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cadfaecf389c2e683bb4e74312418d7bf27e7581f6c044f8d052c6a7a2725f1e
|
3 |
+
size 4476
|
runs/Apr03_20-45-15_PC/events.out.tfevents.1712202413.PC.13900.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b867a25b514f559d448f033a3b1d1fcffa78f9930334d17705aa5a3fec7aa05
|
3 |
+
size 4476
|
runs/Apr03_20-57-38_PC/events.out.tfevents.1712203059.PC.13900.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76a90d7e3aa1884ca0effee7e4f4468e460d0643c5afd731efa9251506699a4e
|
3 |
+
size 4476
|
runs/Apr05_10-40-18_PC/events.out.tfevents.1712293820.PC.11556.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c74bdd3d1d9dea874febe5b673a56bcb3caeea69c114f81db0f6f88d4aa78cc2
|
3 |
+
size 4476
|
runs/Apr05_10-40-18_PC/events.out.tfevents.1712294162.PC.11556.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38bbebb4eb6bec23f02eaa402520b713db18a2c89285e25439d0c6f4ea65132b
|
3 |
+
size 4476
|
runs/Apr05_10-40-18_PC/events.out.tfevents.1712294474.PC.11556.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bf033db2c83a96c9ea0a0eaa0b404e0ba27b9fe9a51e64400b5e0d88c7d4be9
|
3 |
+
size 4476
|
runs/Apr05_10-40-18_PC/events.out.tfevents.1712299489.PC.11556.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59c56f4d5384960442412912268385825f2fc115292469659d4e0def7d65109a
|
3 |
+
size 4476
|
runs/Apr05_12-18-35_PC/events.out.tfevents.1712299719.PC.9836.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74d7565724d0aa033bb0235b22518a77c7aa7ba8791957e8b9c2780ade91fe0d
|
3 |
+
size 4444
|
runs/Apr05_17-35-38_PC/events.out.tfevents.1712318738.PC.9836.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32165bce04a3f5648702f46afddfaa66225924abddaa33319f07a3698e28f4ca
|
3 |
+
size 5590
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5548c200e1f6a4bdb1aa8f54037993a65524f965f775579450257055b33139c2
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|