touhidulislam
commited on
Commit
•
c1b0907
1
Parent(s):
a49a4f9
End of training
Browse files- README.md +12 -11
- config.json +7 -5
- model.safetensors +3 -0
- pytorch_model.bin +1 -1
- runs/Sep30_02-09-34_uc2n265.localdomain/events.out.tfevents.1727654975.uc2n265.localdomain.792160.0 +3 -0
- runs/Sep30_03-10-57_uc2n265.localdomain/events.out.tfevents.1727658658.uc2n265.localdomain.792160.1 +3 -0
- runs/Sep30_03-12-33_uc2n265.localdomain/events.out.tfevents.1727658760.uc2n265.localdomain.792160.2 +3 -0
- runs/Sep30_03-15-52_uc2n265.localdomain/events.out.tfevents.1727658955.uc2n265.localdomain.839845.0 +3 -0
- runs/Sep30_03-46-52_uc2n265.localdomain/events.out.tfevents.1727660812.uc2n265.localdomain.842046.0 +3 -0
- runs/Sep30_03-46-52_uc2n265.localdomain/events.out.tfevents.1727661254.uc2n265.localdomain.842046.1 +3 -0
- runs/Sep30_03-55-14_uc2n265.localdomain/events.out.tfevents.1727661315.uc2n265.localdomain.842545.0 +3 -0
- runs/Sep30_04-15-59_uc2n265.localdomain/events.out.tfevents.1727662560.uc2n265.localdomain.843776.0 +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# my_awesome_eli5_mlm_model
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 3.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -40,20 +41,20 @@ The following hyperparameters were used during training:
|
|
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 |
|
50 |
-
| No log | 2.0 |
|
51 |
-
| No log | 3.0 |
|
52 |
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
-
- Transformers 4.
|
57 |
- Pytorch 2.1.0+cu121
|
58 |
-
- Datasets
|
59 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
+
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: vinai/bertweet-base
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
|
|
14 |
|
15 |
# my_awesome_eli5_mlm_model
|
16 |
|
17 |
+
This model is a fine-tuned version of [vinai/bertweet-base](https://huggingface.co/vinai/bertweet-base) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 3.9677
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
+
- num_epochs: 3.0
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| No log | 1.0 | 2 | 4.1429 |
|
51 |
+
| No log | 2.0 | 4 | 4.6141 |
|
52 |
+
| No log | 3.0 | 6 | 5.0930 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
+
- Transformers 4.45.1
|
58 |
- Pytorch 2.1.0+cu121
|
59 |
+
- Datasets 3.0.1
|
60 |
+
- Tokenizers 0.20.0
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
@@ -7,21 +7,23 @@
|
|
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":
|
17 |
"model_type": "roberta",
|
18 |
"num_attention_heads": 12,
|
19 |
-
"num_hidden_layers":
|
20 |
"pad_token_id": 1,
|
21 |
"position_embedding_type": "absolute",
|
|
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"type_vocab_size": 1,
|
25 |
"use_cache": true,
|
26 |
-
"vocab_size":
|
27 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "vinai/bertweet-base",
|
3 |
"architectures": [
|
4 |
"RobertaForMaskedLM"
|
5 |
],
|
|
|
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": 768,
|
14 |
"initializer_range": 0.02,
|
15 |
"intermediate_size": 3072,
|
16 |
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 130,
|
18 |
"model_type": "roberta",
|
19 |
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
"pad_token_id": 1,
|
22 |
"position_embedding_type": "absolute",
|
23 |
+
"tokenizer_class": "BertweetTokenizer",
|
24 |
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.45.1",
|
26 |
"type_vocab_size": 1,
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 64001
|
29 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7ca76ca708e9d22ff69d948122e6d804b3c32d54b81bde16de6312c1fc8780
|
3 |
+
size 539886236
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328715954
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1409c3891cb4bc953e07f89d5cd6094011810d7288b1f6406b6edec9340a6399
|
3 |
size 328715954
|
runs/Sep30_02-09-34_uc2n265.localdomain/events.out.tfevents.1727654975.uc2n265.localdomain.792160.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42980c4fac57b1a05c2059d0388df3786406aeb68f72b4b2e33aa5a76349c76f
|
3 |
+
size 4227
|
runs/Sep30_03-10-57_uc2n265.localdomain/events.out.tfevents.1727658658.uc2n265.localdomain.792160.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac4ee619bc485eac2df4c65ef1a28038b698b0ab1a850288a5b0b615054f330a
|
3 |
+
size 4158
|
runs/Sep30_03-12-33_uc2n265.localdomain/events.out.tfevents.1727658760.uc2n265.localdomain.792160.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0a921ff5338e343c23f07530fa202f8c40c5fe9d0568a7d7c9f108324ef4acf
|
3 |
+
size 4158
|
runs/Sep30_03-15-52_uc2n265.localdomain/events.out.tfevents.1727658955.uc2n265.localdomain.839845.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea1896098971b61ac1c0c366bbc59d1ef412a9bce03b118ccf8f324b79628cb2
|
3 |
+
size 5304
|
runs/Sep30_03-46-52_uc2n265.localdomain/events.out.tfevents.1727660812.uc2n265.localdomain.842046.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83a21bb2fa9614a9953f840df9c05fdc818a41b3fae4ed84c05cddd620f3728c
|
3 |
+
size 5304
|
runs/Sep30_03-46-52_uc2n265.localdomain/events.out.tfevents.1727661254.uc2n265.localdomain.842046.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bda9dc04fd6626da2e7dbccfb94644dba4af03a92b50eebfe4f6d76ae9a20c0
|
3 |
+
size 354
|
runs/Sep30_03-55-14_uc2n265.localdomain/events.out.tfevents.1727661315.uc2n265.localdomain.842545.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f46de6613fab87ff1fb9390cbd09c9c865fe7030b52356053256606d57a6a05
|
3 |
+
size 5304
|
runs/Sep30_04-15-59_uc2n265.localdomain/events.out.tfevents.1727662560.uc2n265.localdomain.843776.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:416f135ef17ed1460d94316625add62088098ba123e85db44269662cabbc0845
|
3 |
+
size 5304
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc6717532bceccdd93f9408262c994414f0679462a2899dc4c4de5353df41836
|
3 |
+
size 5176
|