strollingorange
commited on
Commit
•
eeef70f
1
Parent(s):
a726d7d
upload checkpoints
Browse files- README.md +48 -6
- all_results.json +7 -0
- config.json +22 -0
- model.safetensors +3 -0
- train_results.json +7 -0
- trainer_state.json +90 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,9 +1,51 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
-
- openai/clip-vit-base-patch32
|
5 |
-
pipeline_tag: zero-shot-image-classification
|
6 |
tags:
|
7 |
-
-
|
8 |
-
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: laion/CLIP-ViT-B-32-laion2B-s34B-b79K
|
|
|
|
|
4 |
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: laion-finetuned_v5e7_epoch10_fold0_threshold3
|
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 |
+
# laion-finetuned_v5e7_epoch10_fold0_threshold3
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [laion/CLIP-ViT-B-32-laion2B-s34B-b79K](https://huggingface.co/laion/CLIP-ViT-B-32-laion2B-s34B-b79K) on an unknown 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: 1e-06
|
36 |
+
- train_batch_size: 384
|
37 |
+
- eval_batch_size: 24
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
|
45 |
+
|
46 |
+
### Framework versions
|
47 |
+
|
48 |
+
- Transformers 4.37.2
|
49 |
+
- Pytorch 2.0.1+cu117
|
50 |
+
- Datasets 2.14.4
|
51 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 2.881923577724359,
|
4 |
+
"train_runtime": 3987.6216,
|
5 |
+
"train_samples_per_second": 38.263,
|
6 |
+
"train_steps_per_second": 0.098
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "laion/CLIP-ViT-B-32-laion2B-s34B-b79K",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPModel"
|
5 |
+
],
|
6 |
+
"initializer_factor": 1.0,
|
7 |
+
"logit_scale_init_value": 2.6592,
|
8 |
+
"model_type": "clip",
|
9 |
+
"projection_dim": 512,
|
10 |
+
"text_config": {
|
11 |
+
"dropout": 0.0,
|
12 |
+
"hidden_act": "gelu",
|
13 |
+
"model_type": "clip_text_model"
|
14 |
+
},
|
15 |
+
"torch_dtype": "float32",
|
16 |
+
"transformers_version": "4.37.2",
|
17 |
+
"vision_config": {
|
18 |
+
"dropout": 0.0,
|
19 |
+
"hidden_act": "gelu",
|
20 |
+
"model_type": "clip_vision_model"
|
21 |
+
}
|
22 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63332bfdd9c35ab710bf744df92a7a6de2261ca269c7a63d035187fdaae46d2b
|
3 |
+
size 605156676
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 2.881923577724359,
|
4 |
+
"train_runtime": 3987.6216,
|
5 |
+
"train_samples_per_second": 38.263,
|
6 |
+
"train_steps_per_second": 0.098
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 390,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"learning_rate": 9e-07,
|
14 |
+
"loss": 3.1249,
|
15 |
+
"step": 39
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 2.0,
|
19 |
+
"learning_rate": 8e-07,
|
20 |
+
"loss": 2.9372,
|
21 |
+
"step": 78
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 3.0,
|
25 |
+
"learning_rate": 7e-07,
|
26 |
+
"loss": 2.8912,
|
27 |
+
"step": 117
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 4.0,
|
31 |
+
"learning_rate": 6e-07,
|
32 |
+
"loss": 2.8686,
|
33 |
+
"step": 156
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 5.0,
|
37 |
+
"learning_rate": 5e-07,
|
38 |
+
"loss": 2.8503,
|
39 |
+
"step": 195
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 6.0,
|
43 |
+
"learning_rate": 4e-07,
|
44 |
+
"loss": 2.8397,
|
45 |
+
"step": 234
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 7.0,
|
49 |
+
"learning_rate": 3e-07,
|
50 |
+
"loss": 2.8334,
|
51 |
+
"step": 273
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 8.0,
|
55 |
+
"learning_rate": 2e-07,
|
56 |
+
"loss": 2.8271,
|
57 |
+
"step": 312
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 9.0,
|
61 |
+
"learning_rate": 1e-07,
|
62 |
+
"loss": 2.8268,
|
63 |
+
"step": 351
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 10.0,
|
67 |
+
"learning_rate": 0.0,
|
68 |
+
"loss": 2.82,
|
69 |
+
"step": 390
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 10.0,
|
73 |
+
"step": 390,
|
74 |
+
"total_flos": 8711089615388160.0,
|
75 |
+
"train_loss": 2.881923577724359,
|
76 |
+
"train_runtime": 3987.6216,
|
77 |
+
"train_samples_per_second": 38.263,
|
78 |
+
"train_steps_per_second": 0.098
|
79 |
+
}
|
80 |
+
],
|
81 |
+
"logging_steps": 500,
|
82 |
+
"max_steps": 390,
|
83 |
+
"num_input_tokens_seen": 0,
|
84 |
+
"num_train_epochs": 10,
|
85 |
+
"save_steps": 500,
|
86 |
+
"total_flos": 8711089615388160.0,
|
87 |
+
"train_batch_size": 384,
|
88 |
+
"trial_name": null,
|
89 |
+
"trial_params": null
|
90 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a138c79b11f259d6a0c3679b10d8c637d0ff2d78606b99a0988162aa0c9d4608
|
3 |
+
size 4347
|