End of training
Browse files- README.md +60 -0
- config.json +24 -0
- model.safetensors +3 -0
- runs/Feb03_19-10-50_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706980251.nikos-IdeaPad-Gaming-3-16ARH7.29289.0 +3 -0
- runs/Feb03_19-14-42_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706980483.nikos-IdeaPad-Gaming-3-16ARH7.29289.1 +3 -0
- runs/Feb03_19-57-03_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706983024.nikos-IdeaPad-Gaming-3-16ARH7.35006.0 +3 -0
- runs/Feb03_23-50-06_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706997006.nikos-IdeaPad-Gaming-3-16ARH7.17205.0 +3 -0
- runs/Feb03_23-54-05_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706997245.nikos-IdeaPad-Gaming-3-16ARH7.17205.1 +3 -0
- runs/Feb03_23-54-31_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706997271.nikos-IdeaPad-Gaming-3-16ARH7.17964.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: distilbert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: squad_distil_bert
|
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 |
+
# squad_distil_bert
|
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: 1.9852
|
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: 0.0001
|
38 |
+
- train_batch_size: 8
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 5
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| No log | 1.0 | 13 | 3.8482 |
|
50 |
+
| No log | 2.0 | 26 | 2.8740 |
|
51 |
+
| No log | 3.0 | 39 | 2.4083 |
|
52 |
+
| No log | 4.0 | 52 | 2.1060 |
|
53 |
+
| No log | 5.0 | 65 | 1.9852 |
|
54 |
+
|
55 |
+
|
56 |
+
### Framework versions
|
57 |
+
|
58 |
+
- Transformers 4.37.2
|
59 |
+
- Pytorch 2.2.0+cu121
|
60 |
+
- Tokenizers 0.15.1
|
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": "4.37.2",
|
23 |
+
"vocab_size": 30522
|
24 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9af21cf087d69e51f272b935099ea4b953ca6c0ae95e7682cd2b30850b5356ff
|
3 |
+
size 265470032
|
runs/Feb03_19-10-50_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706980251.nikos-IdeaPad-Gaming-3-16ARH7.29289.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d43d8d42ada28194d2c3e41131c291d35ffe0d21048c65f806f540033939b29
|
3 |
+
size 5329
|
runs/Feb03_19-14-42_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706980483.nikos-IdeaPad-Gaming-3-16ARH7.29289.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99a4a1ff7aac7d3127716fb948c1acf279cb83b39d6ffc0dde6acdb7af7e4bb7
|
3 |
+
size 5910
|
runs/Feb03_19-57-03_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706983024.nikos-IdeaPad-Gaming-3-16ARH7.35006.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c52862b6561c2177992c044fc179d2960f06b28fce50cb7fb9f5593e2b177eca
|
3 |
+
size 8105
|
runs/Feb03_23-50-06_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706997006.nikos-IdeaPad-Gaming-3-16ARH7.17205.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87e754b482a590cb4c0b33498b058cc672a43ffea75fc0b3697b94de4e860f33
|
3 |
+
size 4209
|
runs/Feb03_23-54-05_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706997245.nikos-IdeaPad-Gaming-3-16ARH7.17205.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eadf5e7d05b8d4760ef6c317b41c8d73e3d03dc907deee360de52d49c39f85fe
|
3 |
+
size 4210
|
runs/Feb03_23-54-31_nikos-IdeaPad-Gaming-3-16ARH7/events.out.tfevents.1706997271.nikos-IdeaPad-Gaming-3-16ARH7.17964.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b81cfb45cda0ed20643a262287ff492c8e0dc861ef803288ca7386a191e3193e
|
3 |
+
size 5888
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e6fab818e86d039750dfd235763ccab9eacbe03230d70091b091ab54f215d81
|
3 |
+
size 4792
|