Hugging Face's logo

zabir735
/
clip-seed-vit-roberta

Zero-Shot Image Classification
Transformers
Safetensors
clip
Generated from Trainer
Inference Endpoints
Model card Files Community
zabir735 commited on
Commit
7cd4c5e
•
1 Parent(s): 1bda192

End of training

Browse files
Files changed (9) hide show
  1. all_results.json +7 -0
  2. merges.txt +0 -0
  3. preprocessor_config.json +27 -0
  4. special_tokens_map.json +15 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. train_results.json +7 -0
  8. trainer_state.json +48 -0
  9. vocab.json +0 -0
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "train_loss": 1.7032232240999126,
4
+ "train_runtime": 7389.9923,
5
+ "train_samples_per_second": 1.897,
6
+ "train_steps_per_second": 0.237
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.0,
3
+ "train_loss": 1.7032232240999126,
4
+ "train_runtime": 7389.9923,
5
+ "train_samples_per_second": 1.897,
6
+ "train_steps_per_second": 0.237
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1752,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 2.28,
13
+ "learning_rate": 3.573059360730594e-05,
14
+ "loss": 1.993,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 4.57,
19
+ "learning_rate": 2.1461187214611872e-05,
20
+ "loss": 1.7625,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 6.85,
25
+ "learning_rate": 7.191780821917809e-06,
26
+ "loss": 1.5289,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 8.0,
31
+ "step": 1752,
32
+ "total_flos": 803810618658432.0,
33
+ "train_loss": 1.7032232240999126,
34
+ "train_runtime": 7389.9923,
35
+ "train_samples_per_second": 1.897,
36
+ "train_steps_per_second": 0.237
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 1752,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 8,
43
+ "save_steps": 500,
44
+ "total_flos": 803810618658432.0,
45
+ "train_batch_size": 8,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff