swaroopajit
commited on
Commit
•
b6d1eda
1
Parent(s):
7a7730a
End of training
Browse files- README.md +54 -0
- config.json +34 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/git-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: git-base-next
|
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 |
+
# git-base-next
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on the None dataset.
|
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: 5e-05
|
36 |
+
- train_batch_size: 16
|
37 |
+
- eval_batch_size: 16
|
38 |
+
- seed: 42
|
39 |
+
- gradient_accumulation_steps: 8
|
40 |
+
- total_train_batch_size: 128
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 30
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.33.1
|
52 |
+
- Pytorch 2.0.1+cu117
|
53 |
+
- Datasets 2.14.5
|
54 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/git-base",
|
3 |
+
"architectures": [
|
4 |
+
"GitForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 101,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 102,
|
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-12,
|
16 |
+
"max_position_embeddings": 1024,
|
17 |
+
"model_type": "git",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 6,
|
20 |
+
"num_image_with_embedding": null,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.33.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vision_config": {
|
28 |
+
"dropout": 0.0,
|
29 |
+
"initializer_factor": 1.0,
|
30 |
+
"model_type": "git_vision_model",
|
31 |
+
"projection_dim": 512
|
32 |
+
},
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 101,
|
4 |
+
"eos_token_id": 102,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.33.1"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a228478f90fe89d9fade123d1af921634ce70cb7d5ca1d23c25a024c205ebbe6
|
3 |
+
size 706584273
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:954cabe597f41e657c1308e93e8bde49df317c0981fd2e42f70fbc8247745db7
|
3 |
+
size 3963
|