hamedjahantigh
commited on
Commit
•
5d783dd
1
Parent(s):
88fc357
End of training
Browse files- README.md +62 -0
- config.json +3 -3
- model.safetensors +2 -2
- runs/Dec24_05-40-18_18a070d35f31/events.out.tfevents.1703396425.18a070d35f31.715.0 +3 -0
- runs/Dec24_05-43-30_18a070d35f31/events.out.tfevents.1703396617.18a070d35f31.2581.0 +3 -0
- runs/Dec24_05-49-05_18a070d35f31/events.out.tfevents.1703396951.18a070d35f31.3793.0 +3 -0
- training_args.bin +2 -2
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: mlm
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
# mlm
|
13 |
+
|
14 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
15 |
+
It achieves the following results on the evaluation set:
|
16 |
+
- Loss: 4.5428
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0001
|
36 |
+
- train_batch_size: 64
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- num_epochs: 200
|
42 |
+
|
43 |
+
### Training results
|
44 |
+
|
45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
46 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
47 |
+
| 5.9959 | 10.87 | 500 | 5.4385 |
|
48 |
+
| 4.974 | 21.74 | 1000 | 5.0920 |
|
49 |
+
| 4.2917 | 32.61 | 1500 | 4.7598 |
|
50 |
+
| 3.7303 | 43.48 | 2000 | 4.4384 |
|
51 |
+
| 3.2166 | 54.35 | 2500 | 4.3718 |
|
52 |
+
| 2.7673 | 65.22 | 3000 | 4.3775 |
|
53 |
+
| 2.3727 | 76.09 | 3500 | 4.4200 |
|
54 |
+
| 2.029 | 86.96 | 4000 | 4.5428 |
|
55 |
+
|
56 |
+
|
57 |
+
### Framework versions
|
58 |
+
|
59 |
+
- Transformers 4.35.2
|
60 |
+
- Pytorch 2.1.0+cu121
|
61 |
+
- Datasets 2.16.0
|
62 |
+
- Tokenizers 0.15.0
|
config.json
CHANGED
@@ -12,7 +12,7 @@
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
14 |
"layer_norm_eps": 1e-12,
|
15 |
-
"max_position_embeddings":
|
16 |
"model_type": "roberta",
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 6,
|
@@ -20,7 +20,7 @@
|
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.35.2",
|
23 |
-
"type_vocab_size":
|
24 |
"use_cache": true,
|
25 |
-
"vocab_size":
|
26 |
}
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
14 |
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
"model_type": "roberta",
|
17 |
"num_attention_heads": 12,
|
18 |
"num_hidden_layers": 6,
|
|
|
20 |
"position_embedding_type": "absolute",
|
21 |
"torch_dtype": "float32",
|
22 |
"transformers_version": "4.35.2",
|
23 |
+
"type_vocab_size": 1,
|
24 |
"use_cache": true,
|
25 |
+
"vocab_size": 52000
|
26 |
}
|
model.safetensors
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 sha256:8db4ca6b2663f15f34a7036242711b2002440c5cd72259f959b551d652340555
|
3 |
+
size 334030264
|
runs/Dec24_05-40-18_18a070d35f31/events.out.tfevents.1703396425.18a070d35f31.715.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57baf8dcfd8f77b4ea9d6523af6e145403521ed05ddc3e0512fdd6a6ab9d4361
|
3 |
+
size 4322
|
runs/Dec24_05-43-30_18a070d35f31/events.out.tfevents.1703396617.18a070d35f31.2581.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8740c8ab166c40ec75bb61e10f806cfdc0b605e44d379be3cad563e2d28d0179
|
3 |
+
size 4322
|
runs/Dec24_05-49-05_18a070d35f31/events.out.tfevents.1703396951.18a070d35f31.3793.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4b1520a39d7bd336e61916795e0c2fe0d7ab1a1d7f9dc37073f4c472b3244c5
|
3 |
+
size 8098
|
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:f80f90c1ca2528469387ffe852392697e77bc5b6209710a83884d1bb999009e3
|
3 |
+
size 4536
|