initial commit
Browse files- README.md +64 -0
- all_results.json +12 -0
- config.json +51 -0
- eval_results.json +7 -0
- model.safetensors +3 -0
- train_results.json +8 -0
- trainer_state.json +89 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: microsoft/resnet-50
|
4 |
+
tags:
|
5 |
+
- image-classification
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- imagefolder
|
9 |
+
model-index:
|
10 |
+
- name: tumour
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# tumour
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the essam24/brain-tumour-v1 dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.8286
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 16
|
42 |
+
- eval_batch_size: 16
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 5
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
52 |
+
| No log | 1.0 | 195 | 4.5083 |
|
53 |
+
| No log | 2.0 | 390 | 1.4575 |
|
54 |
+
| 3.0791 | 3.0 | 585 | 0.9050 |
|
55 |
+
| 3.0791 | 4.0 | 780 | 0.8538 |
|
56 |
+
| 3.0791 | 5.0 | 975 | 0.8286 |
|
57 |
+
|
58 |
+
|
59 |
+
### Framework versions
|
60 |
+
|
61 |
+
- Transformers 4.42.4
|
62 |
+
- Pytorch 2.4.0+cu121
|
63 |
+
- Datasets 2.21.0
|
64 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.8285718560218811,
|
4 |
+
"eval_runtime": 79.5915,
|
5 |
+
"eval_samples_per_second": 10.177,
|
6 |
+
"eval_steps_per_second": 0.641,
|
7 |
+
"total_flos": 3.588142521058099e+17,
|
8 |
+
"train_loss": 1.746917755909455,
|
9 |
+
"train_runtime": 2049.8226,
|
10 |
+
"train_samples_per_second": 7.584,
|
11 |
+
"train_steps_per_second": 0.476
|
12 |
+
}
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/resnet-50",
|
3 |
+
"architectures": [
|
4 |
+
"ResNetForImageClassification"
|
5 |
+
],
|
6 |
+
"depths": [
|
7 |
+
3,
|
8 |
+
4,
|
9 |
+
6,
|
10 |
+
3
|
11 |
+
],
|
12 |
+
"downsample_in_bottleneck": false,
|
13 |
+
"downsample_in_first_stage": false,
|
14 |
+
"embedding_size": 64,
|
15 |
+
"hidden_act": "relu",
|
16 |
+
"hidden_sizes": [
|
17 |
+
256,
|
18 |
+
512,
|
19 |
+
1024,
|
20 |
+
2048
|
21 |
+
],
|
22 |
+
"id2label": {
|
23 |
+
"0": "LABEL_0",
|
24 |
+
"1": "LABEL_1",
|
25 |
+
"2": "LABEL_2"
|
26 |
+
},
|
27 |
+
"label2id": {
|
28 |
+
"LABEL_0": 0,
|
29 |
+
"LABEL_1": 1,
|
30 |
+
"LABEL_2": 2
|
31 |
+
},
|
32 |
+
"layer_type": "bottleneck",
|
33 |
+
"model_type": "resnet",
|
34 |
+
"num_channels": 3,
|
35 |
+
"out_features": [
|
36 |
+
"stage4"
|
37 |
+
],
|
38 |
+
"out_indices": [
|
39 |
+
4
|
40 |
+
],
|
41 |
+
"problem_type": "single_label_classification",
|
42 |
+
"stage_names": [
|
43 |
+
"stem",
|
44 |
+
"stage1",
|
45 |
+
"stage2",
|
46 |
+
"stage3",
|
47 |
+
"stage4"
|
48 |
+
],
|
49 |
+
"torch_dtype": "float32",
|
50 |
+
"transformers_version": "4.42.4"
|
51 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_loss": 0.8285718560218811,
|
4 |
+
"eval_runtime": 79.5915,
|
5 |
+
"eval_samples_per_second": 10.177,
|
6 |
+
"eval_steps_per_second": 0.641
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37fa127051fc098b066f9ca7f1cea2ec9da8e44b26064c29f3ed3772c0cddfd0
|
3 |
+
size 102482856
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"total_flos": 3.588142521058099e+17,
|
4 |
+
"train_loss": 1.746917755909455,
|
5 |
+
"train_runtime": 2049.8226,
|
6 |
+
"train_samples_per_second": 7.584,
|
7 |
+
"train_steps_per_second": 0.476
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8285718560218811,
|
3 |
+
"best_model_checkpoint": "./results/resnet/tumour/checkpoint-975",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 975,
|
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 |
+
"eval_loss": 4.508346080780029,
|
14 |
+
"eval_runtime": 77.3249,
|
15 |
+
"eval_samples_per_second": 10.475,
|
16 |
+
"eval_steps_per_second": 0.66,
|
17 |
+
"step": 195
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 2.0,
|
21 |
+
"eval_loss": 1.457480549812317,
|
22 |
+
"eval_runtime": 77.608,
|
23 |
+
"eval_samples_per_second": 10.437,
|
24 |
+
"eval_steps_per_second": 0.657,
|
25 |
+
"step": 390
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.564102564102564,
|
29 |
+
"grad_norm": 205.6478729248047,
|
30 |
+
"learning_rate": 9.743589743589744e-06,
|
31 |
+
"loss": 3.0791,
|
32 |
+
"step": 500
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 3.0,
|
36 |
+
"eval_loss": 0.9050098657608032,
|
37 |
+
"eval_runtime": 78.6283,
|
38 |
+
"eval_samples_per_second": 10.302,
|
39 |
+
"eval_steps_per_second": 0.649,
|
40 |
+
"step": 585
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 4.0,
|
44 |
+
"eval_loss": 0.8538194298744202,
|
45 |
+
"eval_runtime": 79.9143,
|
46 |
+
"eval_samples_per_second": 10.136,
|
47 |
+
"eval_steps_per_second": 0.638,
|
48 |
+
"step": 780
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 5.0,
|
52 |
+
"eval_loss": 0.8285718560218811,
|
53 |
+
"eval_runtime": 79.1036,
|
54 |
+
"eval_samples_per_second": 10.24,
|
55 |
+
"eval_steps_per_second": 0.645,
|
56 |
+
"step": 975
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 5.0,
|
60 |
+
"step": 975,
|
61 |
+
"total_flos": 3.588142521058099e+17,
|
62 |
+
"train_loss": 1.746917755909455,
|
63 |
+
"train_runtime": 2049.8226,
|
64 |
+
"train_samples_per_second": 7.584,
|
65 |
+
"train_steps_per_second": 0.476
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"logging_steps": 500,
|
69 |
+
"max_steps": 975,
|
70 |
+
"num_input_tokens_seen": 0,
|
71 |
+
"num_train_epochs": 5,
|
72 |
+
"save_steps": 500,
|
73 |
+
"stateful_callbacks": {
|
74 |
+
"TrainerControl": {
|
75 |
+
"args": {
|
76 |
+
"should_epoch_stop": false,
|
77 |
+
"should_evaluate": false,
|
78 |
+
"should_log": false,
|
79 |
+
"should_save": true,
|
80 |
+
"should_training_stop": true
|
81 |
+
},
|
82 |
+
"attributes": {}
|
83 |
+
}
|
84 |
+
},
|
85 |
+
"total_flos": 3.588142521058099e+17,
|
86 |
+
"train_batch_size": 16,
|
87 |
+
"trial_name": null,
|
88 |
+
"trial_params": null
|
89 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4e97623442022402f79f1623334ea54b7d135672ddc957c9104a54108dfe17d
|
3 |
+
size 5112
|