Upload folder using huggingface_hub
Browse files- checkpoint-250/config.json +46 -0
- checkpoint-250/model.safetensors +3 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/preprocessor_config.json +24 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/trainer_state.json +44 -0
- checkpoint-250/training_args.bin +3 -0
- checkpoint-500/config.json +46 -0
- checkpoint-500/model.safetensors +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/preprocessor_config.json +24 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/trainer_state.json +61 -0
- checkpoint-500/training_args.bin +3 -0
- checkpoint-750/config.json +46 -0
- checkpoint-750/model.safetensors +3 -0
- checkpoint-750/optimizer.pt +3 -0
- checkpoint-750/preprocessor_config.json +24 -0
- checkpoint-750/rng_state.pth +3 -0
- checkpoint-750/scheduler.pt +3 -0
- checkpoint-750/trainer_state.json +71 -0
- checkpoint-750/training_args.bin +3 -0
- config.json +46 -0
- model.safetensors +3 -0
- preprocessor_config.json +24 -0
- training_args.bin +3 -0
checkpoint-250/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "food",
|
7 |
+
"1": "not-food"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"food": 0,
|
12 |
+
"not-food": 1
|
13 |
+
},
|
14 |
+
"model_type": "siglip",
|
15 |
+
"problem_type": "single_label_classification",
|
16 |
+
"text_config": {
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"hidden_act": "gelu_pytorch_tanh",
|
19 |
+
"hidden_size": 768,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-06,
|
22 |
+
"max_position_embeddings": 64,
|
23 |
+
"model_type": "siglip_text_model",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"projection_size": 768,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"vocab_size": 256000
|
29 |
+
},
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.50.0",
|
32 |
+
"vision_config": {
|
33 |
+
"attention_dropout": 0.0,
|
34 |
+
"hidden_act": "gelu_pytorch_tanh",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"image_size": 224,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"layer_norm_eps": 1e-06,
|
39 |
+
"model_type": "siglip_vision_model",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"torch_dtype": "float32"
|
45 |
+
}
|
46 |
+
}
|
checkpoint-250/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87bb4a7a40723b9a7ec31e7b6cc8103dcb40248d2dbf8810bf43a4e0c7a7e72c
|
3 |
+
size 371567992
|
checkpoint-250/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6ca302c709c8f03d118c5fdd3515fbcfac8fff9d6e3fdba767814e717f3f43
|
3 |
+
size 686555770
|
checkpoint-250/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-250/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54d4fd8f59db3dde04b8ce82e5cab58faa0585dc1fbf6df449410d0014a09fc3
|
3 |
+
size 14244
|
checkpoint-250/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56263c95f47d650ebdbeb2924e939a7f3797eb4e9bac4e6f68466a812b9ef7ed
|
3 |
+
size 1064
|
checkpoint-250/trainer_state.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 250,
|
3 |
+
"best_metric": 0.4259241223335266,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-250",
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 250,
|
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": 0.806875,
|
15 |
+
"eval_loss": 0.4259241223335266,
|
16 |
+
"eval_model_preparation_time": 0.0023,
|
17 |
+
"eval_runtime": 116.0639,
|
18 |
+
"eval_samples_per_second": 68.928,
|
19 |
+
"eval_steps_per_second": 8.616,
|
20 |
+
"step": 250
|
21 |
+
}
|
22 |
+
],
|
23 |
+
"logging_steps": 500,
|
24 |
+
"max_steps": 750,
|
25 |
+
"num_input_tokens_seen": 0,
|
26 |
+
"num_train_epochs": 3,
|
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": 6.70043966570496e+17,
|
41 |
+
"train_batch_size": 32,
|
42 |
+
"trial_name": null,
|
43 |
+
"trial_params": null
|
44 |
+
}
|
checkpoint-250/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d732915852aa8238abe1f128b3231ab9d60325b25b8e62363150b9e372e24184
|
3 |
+
size 5304
|
checkpoint-500/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "food",
|
7 |
+
"1": "not-food"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"food": 0,
|
12 |
+
"not-food": 1
|
13 |
+
},
|
14 |
+
"model_type": "siglip",
|
15 |
+
"problem_type": "single_label_classification",
|
16 |
+
"text_config": {
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"hidden_act": "gelu_pytorch_tanh",
|
19 |
+
"hidden_size": 768,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-06,
|
22 |
+
"max_position_embeddings": 64,
|
23 |
+
"model_type": "siglip_text_model",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"projection_size": 768,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"vocab_size": 256000
|
29 |
+
},
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.50.0",
|
32 |
+
"vision_config": {
|
33 |
+
"attention_dropout": 0.0,
|
34 |
+
"hidden_act": "gelu_pytorch_tanh",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"image_size": 224,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"layer_norm_eps": 1e-06,
|
39 |
+
"model_type": "siglip_vision_model",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"torch_dtype": "float32"
|
45 |
+
}
|
46 |
+
}
|
checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e81762f3877395900d7376e88f4332fc35a219a94387773cf024fdb19419bab0
|
3 |
+
size 371567992
|
checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46be3caf5dff453421d9c08514084ed3a57cfa3e4f71079866b7054753cc0975
|
3 |
+
size 686555770
|
checkpoint-500/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-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93d90d15e2a70e932ff8ba985d12ef89d76689887a4662b71b47cc0114a3f071
|
3 |
+
size 14244
|
checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6258cc6e0af2554194af846e068d1d4c6bd02dc0286c9c30da6e00cb88e5da5
|
3 |
+
size 1064
|
checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 500,
|
3 |
+
"best_metric": 0.41451969742774963,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-500",
|
5 |
+
"epoch": 2.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 500,
|
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": 0.806875,
|
15 |
+
"eval_loss": 0.4259241223335266,
|
16 |
+
"eval_model_preparation_time": 0.0023,
|
17 |
+
"eval_runtime": 116.0639,
|
18 |
+
"eval_samples_per_second": 68.928,
|
19 |
+
"eval_steps_per_second": 8.616,
|
20 |
+
"step": 250
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"grad_norm": 8.506980895996094,
|
25 |
+
"learning_rate": 7.142857142857143e-05,
|
26 |
+
"loss": 0.5089,
|
27 |
+
"step": 500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.0,
|
31 |
+
"eval_accuracy": 0.814125,
|
32 |
+
"eval_loss": 0.41451969742774963,
|
33 |
+
"eval_model_preparation_time": 0.0023,
|
34 |
+
"eval_runtime": 115.6232,
|
35 |
+
"eval_samples_per_second": 69.19,
|
36 |
+
"eval_steps_per_second": 8.649,
|
37 |
+
"step": 500
|
38 |
+
}
|
39 |
+
],
|
40 |
+
"logging_steps": 500,
|
41 |
+
"max_steps": 750,
|
42 |
+
"num_input_tokens_seen": 0,
|
43 |
+
"num_train_epochs": 3,
|
44 |
+
"save_steps": 500,
|
45 |
+
"stateful_callbacks": {
|
46 |
+
"TrainerControl": {
|
47 |
+
"args": {
|
48 |
+
"should_epoch_stop": false,
|
49 |
+
"should_evaluate": false,
|
50 |
+
"should_log": false,
|
51 |
+
"should_save": true,
|
52 |
+
"should_training_stop": false
|
53 |
+
},
|
54 |
+
"attributes": {}
|
55 |
+
}
|
56 |
+
},
|
57 |
+
"total_flos": 1.340087933140992e+18,
|
58 |
+
"train_batch_size": 32,
|
59 |
+
"trial_name": null,
|
60 |
+
"trial_params": null
|
61 |
+
}
|
checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d732915852aa8238abe1f128b3231ab9d60325b25b8e62363150b9e372e24184
|
3 |
+
size 5304
|
checkpoint-750/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "food",
|
7 |
+
"1": "not-food"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"food": 0,
|
12 |
+
"not-food": 1
|
13 |
+
},
|
14 |
+
"model_type": "siglip",
|
15 |
+
"problem_type": "single_label_classification",
|
16 |
+
"text_config": {
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"hidden_act": "gelu_pytorch_tanh",
|
19 |
+
"hidden_size": 768,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-06,
|
22 |
+
"max_position_embeddings": 64,
|
23 |
+
"model_type": "siglip_text_model",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"projection_size": 768,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"vocab_size": 256000
|
29 |
+
},
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.50.0",
|
32 |
+
"vision_config": {
|
33 |
+
"attention_dropout": 0.0,
|
34 |
+
"hidden_act": "gelu_pytorch_tanh",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"image_size": 224,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"layer_norm_eps": 1e-06,
|
39 |
+
"model_type": "siglip_vision_model",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"torch_dtype": "float32"
|
45 |
+
}
|
46 |
+
}
|
checkpoint-750/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89607d83959b24790c73cc701f1e93bea9f81896d5abbaa87299a88feac3e3fd
|
3 |
+
size 371567992
|
checkpoint-750/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4ad1b166ceb4d21f55483e0c807fb20f46f38d0ba1723063292ba84210882e4
|
3 |
+
size 686555770
|
checkpoint-750/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-750/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2d6d45b4f20b7eb7d3cce5b23a58a8f2685e512b3e6a24098180adc8755354e
|
3 |
+
size 14244
|
checkpoint-750/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab03192a60c4fb6ec6096a859424dfb24171c6b3fc801b38b85ab0fd723b1704
|
3 |
+
size 1064
|
checkpoint-750/trainer_state.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": 750,
|
3 |
+
"best_metric": 0.28985536098480225,
|
4 |
+
"best_model_checkpoint": "siglip2-finetune-full/checkpoint-750",
|
5 |
+
"epoch": 3.0,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 750,
|
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": 0.806875,
|
15 |
+
"eval_loss": 0.4259241223335266,
|
16 |
+
"eval_model_preparation_time": 0.0023,
|
17 |
+
"eval_runtime": 116.0639,
|
18 |
+
"eval_samples_per_second": 68.928,
|
19 |
+
"eval_steps_per_second": 8.616,
|
20 |
+
"step": 250
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 2.0,
|
24 |
+
"grad_norm": 8.506980895996094,
|
25 |
+
"learning_rate": 7.142857142857143e-05,
|
26 |
+
"loss": 0.5089,
|
27 |
+
"step": 500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.0,
|
31 |
+
"eval_accuracy": 0.814125,
|
32 |
+
"eval_loss": 0.41451969742774963,
|
33 |
+
"eval_model_preparation_time": 0.0023,
|
34 |
+
"eval_runtime": 115.6232,
|
35 |
+
"eval_samples_per_second": 69.19,
|
36 |
+
"eval_steps_per_second": 8.649,
|
37 |
+
"step": 500
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 3.0,
|
41 |
+
"eval_accuracy": 0.877375,
|
42 |
+
"eval_loss": 0.28985536098480225,
|
43 |
+
"eval_model_preparation_time": 0.0023,
|
44 |
+
"eval_runtime": 115.8177,
|
45 |
+
"eval_samples_per_second": 69.074,
|
46 |
+
"eval_steps_per_second": 8.634,
|
47 |
+
"step": 750
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"logging_steps": 500,
|
51 |
+
"max_steps": 750,
|
52 |
+
"num_input_tokens_seen": 0,
|
53 |
+
"num_train_epochs": 3,
|
54 |
+
"save_steps": 500,
|
55 |
+
"stateful_callbacks": {
|
56 |
+
"TrainerControl": {
|
57 |
+
"args": {
|
58 |
+
"should_epoch_stop": false,
|
59 |
+
"should_evaluate": false,
|
60 |
+
"should_log": false,
|
61 |
+
"should_save": true,
|
62 |
+
"should_training_stop": true
|
63 |
+
},
|
64 |
+
"attributes": {}
|
65 |
+
}
|
66 |
+
},
|
67 |
+
"total_flos": 2.010131899711488e+18,
|
68 |
+
"train_batch_size": 32,
|
69 |
+
"trial_name": null,
|
70 |
+
"trial_params": null
|
71 |
+
}
|
checkpoint-750/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d732915852aa8238abe1f128b3231ab9d60325b25b8e62363150b9e372e24184
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SiglipForImageClassification"
|
4 |
+
],
|
5 |
+
"id2label": {
|
6 |
+
"0": "food",
|
7 |
+
"1": "not-food"
|
8 |
+
},
|
9 |
+
"initializer_factor": 1.0,
|
10 |
+
"label2id": {
|
11 |
+
"food": 0,
|
12 |
+
"not-food": 1
|
13 |
+
},
|
14 |
+
"model_type": "siglip",
|
15 |
+
"problem_type": "single_label_classification",
|
16 |
+
"text_config": {
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"hidden_act": "gelu_pytorch_tanh",
|
19 |
+
"hidden_size": 768,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"layer_norm_eps": 1e-06,
|
22 |
+
"max_position_embeddings": 64,
|
23 |
+
"model_type": "siglip_text_model",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"projection_size": 768,
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"vocab_size": 256000
|
29 |
+
},
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.50.0",
|
32 |
+
"vision_config": {
|
33 |
+
"attention_dropout": 0.0,
|
34 |
+
"hidden_act": "gelu_pytorch_tanh",
|
35 |
+
"hidden_size": 768,
|
36 |
+
"image_size": 224,
|
37 |
+
"intermediate_size": 3072,
|
38 |
+
"layer_norm_eps": 1e-06,
|
39 |
+
"model_type": "siglip_vision_model",
|
40 |
+
"num_attention_heads": 12,
|
41 |
+
"num_channels": 3,
|
42 |
+
"num_hidden_layers": 12,
|
43 |
+
"patch_size": 16,
|
44 |
+
"torch_dtype": "float32"
|
45 |
+
}
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89607d83959b24790c73cc701f1e93bea9f81896d5abbaa87299a88feac3e3fd
|
3 |
+
size 371567992
|
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:d732915852aa8238abe1f128b3231ab9d60325b25b8e62363150b9e372e24184
|
3 |
+
size 5304
|