Upload folder using huggingface_hub
Browse files- checkpoint-158/config.json +54 -0
- checkpoint-158/model.safetensors +3 -0
- checkpoint-158/optimizer.pt +3 -0
- checkpoint-158/preprocessor_config.json +24 -0
- checkpoint-158/rng_state.pth +3 -0
- checkpoint-158/scheduler.pt +3 -0
- checkpoint-158/trainer_state.json +44 -0
- checkpoint-158/training_args.bin +3 -0
- checkpoint-316/config.json +54 -0
- checkpoint-316/model.safetensors +3 -0
- checkpoint-316/optimizer.pt +3 -0
- checkpoint-316/preprocessor_config.json +24 -0
- checkpoint-316/rng_state.pth +3 -0
- checkpoint-316/scheduler.pt +3 -0
- checkpoint-316/trainer_state.json +54 -0
- checkpoint-316/training_args.bin +3 -0
- config.json +54 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- training_args.bin +3 -0
checkpoint-158/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "cardboard",
|
7 |
+
"1": "glass",
|
8 |
+
"2": "metal",
|
9 |
+
"3": "paper",
|
10 |
+
"4": "plastic",
|
11 |
+
"5": "trash"
|
12 |
+
},
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"label2id": {
|
15 |
+
"cardboard": 0,
|
16 |
+
"glass": 1,
|
17 |
+
"metal": 2,
|
18 |
+
"paper": 3,
|
19 |
+
"plastic": 4,
|
20 |
+
"trash": 5
|
21 |
+
},
|
22 |
+
"model_type": "siglip",
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"text_config": {
|
25 |
+
"attention_dropout": 0.0,
|
26 |
+
"hidden_act": "gelu_pytorch_tanh",
|
27 |
+
"hidden_size": 768,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"layer_norm_eps": 1e-06,
|
30 |
+
"max_position_embeddings": 64,
|
31 |
+
"model_type": "siglip_text_model",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"projection_size": 768,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"vocab_size": 256000
|
37 |
+
},
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.50.2",
|
40 |
+
"vision_config": {
|
41 |
+
"attention_dropout": 0.0,
|
42 |
+
"hidden_act": "gelu_pytorch_tanh",
|
43 |
+
"hidden_size": 768,
|
44 |
+
"image_size": 224,
|
45 |
+
"intermediate_size": 3072,
|
46 |
+
"layer_norm_eps": 1e-06,
|
47 |
+
"model_type": "siglip_vision_model",
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_channels": 3,
|
50 |
+
"num_hidden_layers": 12,
|
51 |
+
"patch_size": 16,
|
52 |
+
"torch_dtype": "float32"
|
53 |
+
}
|
54 |
+
}
|
checkpoint-158/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f5b77035116d339936199d82fa2e83d1c7e3062c18e22ee10ad7edc7259129e
|
3 |
+
size 371580296
|
checkpoint-158/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68b7bb1207871f6c09a3c5219fe32e00b36831c7d67c0331f7e9b2d86857b81b
|
3 |
+
size 686580346
|
checkpoint-158/preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.5,
|
8 |
+
0.5,
|
9 |
+
0.5
|
10 |
+
],
|
11 |
+
"image_processor_type": "SiglipImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"processor_class": "SiglipProcessor",
|
18 |
+
"resample": 2,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 224,
|
22 |
+
"width": 224
|
23 |
+
}
|
24 |
+
}
|
checkpoint-158/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73c47f198038c3b0a57bcd8f95457fb502c0796774d00e2e97827c9ea75f33c
|
3 |
+
size 14244
|
checkpoint-158/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52cbeeb82fc37248a008ac9ae3e9562500f9e03188de7a3fa592a33f360dfdd5
|
3 |
+
size 1064
|
checkpoint-158/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 158,
|
3 |
+
"best_metric": 0.6894865036010742,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-158",
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 158,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 1.0,
|
14 |
+
"eval_accuracy": 0.7774040364068064,
|
15 |
+
"eval_loss": 0.6894865036010742,
|
16 |
+
"eval_model_preparation_time": 0.0023,
|
17 |
+
"eval_runtime": 647.2265,
|
18 |
+
"eval_samples_per_second": 7.809,
|
19 |
+
"eval_steps_per_second": 0.976,
|
20 |
+
"step": 158
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"logging_steps": 500,
|
24 |
+
"max_steps": 316,
|
25 |
+
"num_input_tokens_seen": 0,
|
26 |
+
"num_train_epochs": 2,
|
27 |
+
"save_steps": 500,
|
28 |
+
"stateful_callbacks": {
|
29 |
+
"TrainerControl": {
|
30 |
+
"args": {
|
31 |
+
"should_epoch_stop": false,
|
32 |
+
"should_evaluate": false,
|
33 |
+
"should_log": false,
|
34 |
+
"should_save": true,
|
35 |
+
"should_training_stop": false
|
36 |
+
},
|
37 |
+
"attributes": {}
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"total_flos": 4.233143166245683e+17,
|
41 |
+
"train_batch_size": 32,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
checkpoint-158/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:035d5f50831a3a5d7cd09a166c9fa2c85bfdb9d0d1888ae17611b61aaa610ef2
|
3 |
+
size 5304
|
checkpoint-316/config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "cardboard",
|
7 |
+
"1": "glass",
|
8 |
+
"2": "metal",
|
9 |
+
"3": "paper",
|
10 |
+
"4": "plastic",
|
11 |
+
"5": "trash"
|
12 |
+
},
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"label2id": {
|
15 |
+
"cardboard": 0,
|
16 |
+
"glass": 1,
|
17 |
+
"metal": 2,
|
18 |
+
"paper": 3,
|
19 |
+
"plastic": 4,
|
20 |
+
"trash": 5
|
21 |
+
},
|
22 |
+
"model_type": "siglip",
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"text_config": {
|
25 |
+
"attention_dropout": 0.0,
|
26 |
+
"hidden_act": "gelu_pytorch_tanh",
|
27 |
+
"hidden_size": 768,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"layer_norm_eps": 1e-06,
|
30 |
+
"max_position_embeddings": 64,
|
31 |
+
"model_type": "siglip_text_model",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"projection_size": 768,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"vocab_size": 256000
|
37 |
+
},
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.50.2",
|
40 |
+
"vision_config": {
|
41 |
+
"attention_dropout": 0.0,
|
42 |
+
"hidden_act": "gelu_pytorch_tanh",
|
43 |
+
"hidden_size": 768,
|
44 |
+
"image_size": 224,
|
45 |
+
"intermediate_size": 3072,
|
46 |
+
"layer_norm_eps": 1e-06,
|
47 |
+
"model_type": "siglip_vision_model",
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_channels": 3,
|
50 |
+
"num_hidden_layers": 12,
|
51 |
+
"patch_size": 16,
|
52 |
+
"torch_dtype": "float32"
|
53 |
+
}
|
54 |
+
}
|
checkpoint-316/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a67e2f6a82914be03cfb85218bc4e7683c8e81fe3fc4a5f9bed3abc8e93757c8
|
3 |
+
size 371580296
|
checkpoint-316/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fa53293f7dbd4484e12f74c8033d9111c4d54f78b01c22efee89f1637280303
|
3 |
+
size 686580346
|
checkpoint-316/preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.5,
|
8 |
+
0.5,
|
9 |
+
0.5
|
10 |
+
],
|
11 |
+
"image_processor_type": "SiglipImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"processor_class": "SiglipProcessor",
|
18 |
+
"resample": 2,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 224,
|
22 |
+
"width": 224
|
23 |
+
}
|
24 |
+
}
|
checkpoint-316/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c8865ded46a66eb66fccfeedc443b6225e55f1d60041177130965083ad92094
|
3 |
+
size 14244
|
checkpoint-316/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:858e01ad468a2f543304dbbef309d8534371bd1a1c1e6dbef8bbf0eaccbcdf4c
|
3 |
+
size 1064
|
checkpoint-316/trainer_state.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 316,
|
3 |
+
"best_metric": 0.12271355837583542,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-316",
|
5 |
+
"epoch": 2.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 316,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 1.0,
|
14 |
+
"eval_accuracy": 0.7774040364068064,
|
15 |
+
"eval_loss": 0.6894865036010742,
|
16 |
+
"eval_model_preparation_time": 0.0023,
|
17 |
+
"eval_runtime": 647.2265,
|
18 |
+
"eval_samples_per_second": 7.809,
|
19 |
+
"eval_steps_per_second": 0.976,
|
20 |
+
"step": 158
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"eval_accuracy": 0.9626038781163435,
|
25 |
+
"eval_loss": 0.12271355837583542,
|
26 |
+
"eval_model_preparation_time": 0.0023,
|
27 |
+
"eval_runtime": 661.2952,
|
28 |
+
"eval_samples_per_second": 7.643,
|
29 |
+
"eval_steps_per_second": 0.956,
|
30 |
+
"step": 316
|
31 |
+
}
|
32 |
+
],
|
33 |
+
"logging_steps": 500,
|
34 |
+
"max_steps": 316,
|
35 |
+
"num_input_tokens_seen": 0,
|
36 |
+
"num_train_epochs": 2,
|
37 |
+
"save_steps": 500,
|
38 |
+
"stateful_callbacks": {
|
39 |
+
"TrainerControl": {
|
40 |
+
"args": {
|
41 |
+
"should_epoch_stop": false,
|
42 |
+
"should_evaluate": false,
|
43 |
+
"should_log": false,
|
44 |
+
"should_save": true,
|
45 |
+
"should_training_stop": true
|
46 |
+
},
|
47 |
+
"attributes": {}
|
48 |
+
}
|
49 |
+
},
|
50 |
+
"total_flos": 8.466286332491366e+17,
|
51 |
+
"train_batch_size": 32,
|
52 |
+
"trial_name": null,
|
53 |
+
"trial_params": null
|
54 |
+
}
|
checkpoint-316/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:035d5f50831a3a5d7cd09a166c9fa2c85bfdb9d0d1888ae17611b61aaa610ef2
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "cardboard",
|
7 |
+
"1": "glass",
|
8 |
+
"2": "metal",
|
9 |
+
"3": "paper",
|
10 |
+
"4": "plastic",
|
11 |
+
"5": "trash"
|
12 |
+
},
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"label2id": {
|
15 |
+
"cardboard": 0,
|
16 |
+
"glass": 1,
|
17 |
+
"metal": 2,
|
18 |
+
"paper": 3,
|
19 |
+
"plastic": 4,
|
20 |
+
"trash": 5
|
21 |
+
},
|
22 |
+
"model_type": "siglip",
|
23 |
+
"problem_type": "single_label_classification",
|
24 |
+
"text_config": {
|
25 |
+
"attention_dropout": 0.0,
|
26 |
+
"hidden_act": "gelu_pytorch_tanh",
|
27 |
+
"hidden_size": 768,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"layer_norm_eps": 1e-06,
|
30 |
+
"max_position_embeddings": 64,
|
31 |
+
"model_type": "siglip_text_model",
|
32 |
+
"num_attention_heads": 12,
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"projection_size": 768,
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"vocab_size": 256000
|
37 |
+
},
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.50.2",
|
40 |
+
"vision_config": {
|
41 |
+
"attention_dropout": 0.0,
|
42 |
+
"hidden_act": "gelu_pytorch_tanh",
|
43 |
+
"hidden_size": 768,
|
44 |
+
"image_size": 224,
|
45 |
+
"intermediate_size": 3072,
|
46 |
+
"layer_norm_eps": 1e-06,
|
47 |
+
"model_type": "siglip_vision_model",
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_channels": 3,
|
50 |
+
"num_hidden_layers": 12,
|
51 |
+
"patch_size": 16,
|
52 |
+
"torch_dtype": "float32"
|
53 |
+
}
|
54 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a67e2f6a82914be03cfb85218bc4e7683c8e81fe3fc4a5f9bed3abc8e93757c8
|
3 |
+
size 371580296
|
preprocessor_config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_convert_rgb": null,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_rescale": true,
|
5 |
+
"do_resize": true,
|
6 |
+
"image_mean": [
|
7 |
+
0.5,
|
8 |
+
0.5,
|
9 |
+
0.5
|
10 |
+
],
|
11 |
+
"image_processor_type": "SiglipImageProcessor",
|
12 |
+
"image_std": [
|
13 |
+
0.5,
|
14 |
+
0.5,
|
15 |
+
0.5
|
16 |
+
],
|
17 |
+
"processor_class": "SiglipProcessor",
|
18 |
+
"resample": 2,
|
19 |
+
"rescale_factor": 0.00392156862745098,
|
20 |
+
"size": {
|
21 |
+
"height": 224,
|
22 |
+
"width": 224
|
23 |
+
}
|
24 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:035d5f50831a3a5d7cd09a166c9fa2c85bfdb9d0d1888ae17611b61aaa610ef2
|
3 |
+
size 5304
|