End of training
Browse files- README.md +65 -0
- config.json +78 -0
- model.safetensors +3 -0
- runs/Jun25_01-08-16_Centauri/events.out.tfevents.1719245307.Centauri.48816.0 +3 -0
- tmp-checkpoint-3900/config.json +78 -0
- tmp-checkpoint-3900/model.safetensors +3 -0
- tmp-checkpoint-3900/optimizer.pt +3 -0
- tmp-checkpoint-3900/rng_state.pth +3 -0
- tmp-checkpoint-3900/scheduler.pt +3 -0
- tmp-checkpoint-3900/trainer_state.json +879 -0
- tmp-checkpoint-3900/training_args.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: nvidia/mit-b5
|
| 4 |
+
tags:
|
| 5 |
+
- vision
|
| 6 |
+
- image-segmentation
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: segformer-b5-miic-tl
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# segformer-b5-miic-tl
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on the yijisuk/ic-chip-sample dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- eval_loss: 0.2028
|
| 21 |
+
- eval_mean_iou: 0.3885
|
| 22 |
+
- eval_mean_accuracy: 0.7770
|
| 23 |
+
- eval_overall_accuracy: 0.7770
|
| 24 |
+
- eval_accuracy_unlabeled: nan
|
| 25 |
+
- eval_accuracy_circuit: 0.7770
|
| 26 |
+
- eval_iou_unlabeled: 0.0
|
| 27 |
+
- eval_iou_circuit: 0.7770
|
| 28 |
+
- eval_dice_coefficient: 0.7854
|
| 29 |
+
- eval_runtime: 1.8601
|
| 30 |
+
- eval_samples_per_second: 5.376
|
| 31 |
+
- eval_steps_per_second: 2.688
|
| 32 |
+
- epoch: 48.75
|
| 33 |
+
- step: 3900
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 6e-05
|
| 53 |
+
- train_batch_size: 2
|
| 54 |
+
- eval_batch_size: 2
|
| 55 |
+
- seed: 42
|
| 56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
+
- lr_scheduler_type: linear
|
| 58 |
+
- num_epochs: 50
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- Transformers 4.36.2
|
| 63 |
+
- Pytorch 1.11.0+cu115
|
| 64 |
+
- Datasets 2.15.0
|
| 65 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 768,
|
| 9 |
+
"depths": [
|
| 10 |
+
3,
|
| 11 |
+
6,
|
| 12 |
+
40,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"downsampling_rates": [
|
| 16 |
+
1,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": 0.1,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.0,
|
| 24 |
+
"hidden_sizes": [
|
| 25 |
+
64,
|
| 26 |
+
128,
|
| 27 |
+
320,
|
| 28 |
+
512
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "circuit"
|
| 33 |
+
},
|
| 34 |
+
"image_size": 224,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"circuit": 1,
|
| 38 |
+
"unlabeled": 0
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-06,
|
| 41 |
+
"mlp_ratios": [
|
| 42 |
+
4,
|
| 43 |
+
4,
|
| 44 |
+
4,
|
| 45 |
+
4
|
| 46 |
+
],
|
| 47 |
+
"model_type": "segformer",
|
| 48 |
+
"num_attention_heads": [
|
| 49 |
+
1,
|
| 50 |
+
2,
|
| 51 |
+
5,
|
| 52 |
+
8
|
| 53 |
+
],
|
| 54 |
+
"num_channels": 3,
|
| 55 |
+
"num_encoder_blocks": 4,
|
| 56 |
+
"patch_sizes": [
|
| 57 |
+
7,
|
| 58 |
+
3,
|
| 59 |
+
3,
|
| 60 |
+
3
|
| 61 |
+
],
|
| 62 |
+
"reshape_last_stage": true,
|
| 63 |
+
"semantic_loss_ignore_index": 255,
|
| 64 |
+
"sr_ratios": [
|
| 65 |
+
8,
|
| 66 |
+
4,
|
| 67 |
+
2,
|
| 68 |
+
1
|
| 69 |
+
],
|
| 70 |
+
"strides": [
|
| 71 |
+
4,
|
| 72 |
+
2,
|
| 73 |
+
2,
|
| 74 |
+
2
|
| 75 |
+
],
|
| 76 |
+
"torch_dtype": "float32",
|
| 77 |
+
"transformers_version": "4.36.2"
|
| 78 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e35fc8bcd4651cf773a75e287a51ef9161809701c7c3e96a41600f707c72346
|
| 3 |
+
size 338528440
|
runs/Jun25_01-08-16_Centauri/events.out.tfevents.1719245307.Centauri.48816.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c72bdde5145333272f093b32604319475c0368d38481363d843c5d75d058a69
|
| 3 |
+
size 39611
|
tmp-checkpoint-3900/config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "nvidia/mit-b5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"SegformerForSemanticSegmentation"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"classifier_dropout_prob": 0.1,
|
| 8 |
+
"decoder_hidden_size": 768,
|
| 9 |
+
"depths": [
|
| 10 |
+
3,
|
| 11 |
+
6,
|
| 12 |
+
40,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
"downsampling_rates": [
|
| 16 |
+
1,
|
| 17 |
+
4,
|
| 18 |
+
8,
|
| 19 |
+
16
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": 0.1,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.0,
|
| 24 |
+
"hidden_sizes": [
|
| 25 |
+
64,
|
| 26 |
+
128,
|
| 27 |
+
320,
|
| 28 |
+
512
|
| 29 |
+
],
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "unlabeled",
|
| 32 |
+
"1": "circuit"
|
| 33 |
+
},
|
| 34 |
+
"image_size": 224,
|
| 35 |
+
"initializer_range": 0.02,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"circuit": 1,
|
| 38 |
+
"unlabeled": 0
|
| 39 |
+
},
|
| 40 |
+
"layer_norm_eps": 1e-06,
|
| 41 |
+
"mlp_ratios": [
|
| 42 |
+
4,
|
| 43 |
+
4,
|
| 44 |
+
4,
|
| 45 |
+
4
|
| 46 |
+
],
|
| 47 |
+
"model_type": "segformer",
|
| 48 |
+
"num_attention_heads": [
|
| 49 |
+
1,
|
| 50 |
+
2,
|
| 51 |
+
5,
|
| 52 |
+
8
|
| 53 |
+
],
|
| 54 |
+
"num_channels": 3,
|
| 55 |
+
"num_encoder_blocks": 4,
|
| 56 |
+
"patch_sizes": [
|
| 57 |
+
7,
|
| 58 |
+
3,
|
| 59 |
+
3,
|
| 60 |
+
3
|
| 61 |
+
],
|
| 62 |
+
"reshape_last_stage": true,
|
| 63 |
+
"semantic_loss_ignore_index": 255,
|
| 64 |
+
"sr_ratios": [
|
| 65 |
+
8,
|
| 66 |
+
4,
|
| 67 |
+
2,
|
| 68 |
+
1
|
| 69 |
+
],
|
| 70 |
+
"strides": [
|
| 71 |
+
4,
|
| 72 |
+
2,
|
| 73 |
+
2,
|
| 74 |
+
2
|
| 75 |
+
],
|
| 76 |
+
"torch_dtype": "float32",
|
| 77 |
+
"transformers_version": "4.36.2"
|
| 78 |
+
}
|
tmp-checkpoint-3900/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e35fc8bcd4651cf773a75e287a51ef9161809701c7c3e96a41600f707c72346
|
| 3 |
+
size 338528440
|
tmp-checkpoint-3900/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc3c254abfc94f4b40ad524b1a11110d3af1b035f2c9fb583e881fd0f3397dfa
|
| 3 |
+
size 677444919
|
tmp-checkpoint-3900/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4199f274b07c23eb24419af17eb3ec62c31b2561f8e91f7baa16bfb69ab61943
|
| 3 |
+
size 14503
|
tmp-checkpoint-3900/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d34ca61207e2f29e11d42e5d71991b4ca14def9dda65a6d3fb3c00c22ed63b4
|
| 3 |
+
size 623
|
tmp-checkpoint-3900/trainer_state.json
ADDED
|
@@ -0,0 +1,879 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.19604873657226562,
|
| 3 |
+
"best_model_checkpoint": "trained-params/segformer-b5-miic-tl\\checkpoint-3300",
|
| 4 |
+
"epoch": 48.75,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 3900,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.25,
|
| 13 |
+
"learning_rate": 5.85e-05,
|
| 14 |
+
"loss": 0.6335,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.25,
|
| 19 |
+
"eval_accuracy_circuit": 0.3880364398760599,
|
| 20 |
+
"eval_accuracy_unlabeled": NaN,
|
| 21 |
+
"eval_dice_coefficient": 0.24241378903388977,
|
| 22 |
+
"eval_iou_circuit": 0.3880364398760599,
|
| 23 |
+
"eval_iou_unlabeled": 0.0,
|
| 24 |
+
"eval_loss": 0.4939822256565094,
|
| 25 |
+
"eval_mean_accuracy": 0.3880364398760599,
|
| 26 |
+
"eval_mean_iou": 0.19401821993802995,
|
| 27 |
+
"eval_overall_accuracy": 0.3880364398760599,
|
| 28 |
+
"eval_runtime": 1.8415,
|
| 29 |
+
"eval_samples_per_second": 5.43,
|
| 30 |
+
"eval_steps_per_second": 2.715,
|
| 31 |
+
"step": 100
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.5,
|
| 35 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 36 |
+
"loss": 0.55,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 2.5,
|
| 41 |
+
"eval_accuracy_circuit": 0.8800740846647581,
|
| 42 |
+
"eval_accuracy_unlabeled": NaN,
|
| 43 |
+
"eval_dice_coefficient": 0.763485312461853,
|
| 44 |
+
"eval_iou_circuit": 0.8800740846647581,
|
| 45 |
+
"eval_iou_unlabeled": 0.0,
|
| 46 |
+
"eval_loss": 0.3936663568019867,
|
| 47 |
+
"eval_mean_accuracy": 0.8800740846647581,
|
| 48 |
+
"eval_mean_iou": 0.44003704233237906,
|
| 49 |
+
"eval_overall_accuracy": 0.8800740846647581,
|
| 50 |
+
"eval_runtime": 1.9006,
|
| 51 |
+
"eval_samples_per_second": 5.262,
|
| 52 |
+
"eval_steps_per_second": 2.631,
|
| 53 |
+
"step": 200
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.75,
|
| 57 |
+
"learning_rate": 5.550000000000001e-05,
|
| 58 |
+
"loss": 0.553,
|
| 59 |
+
"step": 300
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 3.75,
|
| 63 |
+
"eval_accuracy_circuit": 0.8640216796962398,
|
| 64 |
+
"eval_accuracy_unlabeled": NaN,
|
| 65 |
+
"eval_dice_coefficient": 0.7592071294784546,
|
| 66 |
+
"eval_iou_circuit": 0.8640216796962398,
|
| 67 |
+
"eval_iou_unlabeled": 0.0,
|
| 68 |
+
"eval_loss": 0.3638363480567932,
|
| 69 |
+
"eval_mean_accuracy": 0.8640216796962398,
|
| 70 |
+
"eval_mean_iou": 0.4320108398481199,
|
| 71 |
+
"eval_overall_accuracy": 0.8640216796962398,
|
| 72 |
+
"eval_runtime": 1.8486,
|
| 73 |
+
"eval_samples_per_second": 5.409,
|
| 74 |
+
"eval_steps_per_second": 2.705,
|
| 75 |
+
"step": 300
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.0,
|
| 79 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 80 |
+
"loss": 0.5158,
|
| 81 |
+
"step": 400
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.0,
|
| 85 |
+
"eval_accuracy_circuit": 0.7826529687890519,
|
| 86 |
+
"eval_accuracy_unlabeled": NaN,
|
| 87 |
+
"eval_dice_coefficient": 0.709518313407898,
|
| 88 |
+
"eval_iou_circuit": 0.7826529687890519,
|
| 89 |
+
"eval_iou_unlabeled": 0.0,
|
| 90 |
+
"eval_loss": 0.303494393825531,
|
| 91 |
+
"eval_mean_accuracy": 0.7826529687890519,
|
| 92 |
+
"eval_mean_iou": 0.39132648439452594,
|
| 93 |
+
"eval_overall_accuracy": 0.7826529687890519,
|
| 94 |
+
"eval_runtime": 1.8534,
|
| 95 |
+
"eval_samples_per_second": 5.396,
|
| 96 |
+
"eval_steps_per_second": 2.698,
|
| 97 |
+
"step": 400
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 6.25,
|
| 101 |
+
"learning_rate": 5.25e-05,
|
| 102 |
+
"loss": 0.4876,
|
| 103 |
+
"step": 500
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 6.25,
|
| 107 |
+
"eval_accuracy_circuit": 0.720841168721603,
|
| 108 |
+
"eval_accuracy_unlabeled": NaN,
|
| 109 |
+
"eval_dice_coefficient": 0.6600955724716187,
|
| 110 |
+
"eval_iou_circuit": 0.720841168721603,
|
| 111 |
+
"eval_iou_unlabeled": 0.0,
|
| 112 |
+
"eval_loss": 0.3579980432987213,
|
| 113 |
+
"eval_mean_accuracy": 0.720841168721603,
|
| 114 |
+
"eval_mean_iou": 0.3604205843608015,
|
| 115 |
+
"eval_overall_accuracy": 0.720841168721603,
|
| 116 |
+
"eval_runtime": 1.8586,
|
| 117 |
+
"eval_samples_per_second": 5.381,
|
| 118 |
+
"eval_steps_per_second": 2.69,
|
| 119 |
+
"step": 500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 7.5,
|
| 123 |
+
"learning_rate": 5.1e-05,
|
| 124 |
+
"loss": 0.4716,
|
| 125 |
+
"step": 600
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 7.5,
|
| 129 |
+
"eval_accuracy_circuit": 0.830260114881435,
|
| 130 |
+
"eval_accuracy_unlabeled": NaN,
|
| 131 |
+
"eval_dice_coefficient": 0.7596594095230103,
|
| 132 |
+
"eval_iou_circuit": 0.830260114881435,
|
| 133 |
+
"eval_iou_unlabeled": 0.0,
|
| 134 |
+
"eval_loss": 0.2591872811317444,
|
| 135 |
+
"eval_mean_accuracy": 0.830260114881435,
|
| 136 |
+
"eval_mean_iou": 0.4151300574407175,
|
| 137 |
+
"eval_overall_accuracy": 0.830260114881435,
|
| 138 |
+
"eval_runtime": 1.8886,
|
| 139 |
+
"eval_samples_per_second": 5.295,
|
| 140 |
+
"eval_steps_per_second": 2.647,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 8.75,
|
| 145 |
+
"learning_rate": 4.95e-05,
|
| 146 |
+
"loss": 0.4555,
|
| 147 |
+
"step": 700
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 8.75,
|
| 151 |
+
"eval_accuracy_circuit": 0.9281712722196696,
|
| 152 |
+
"eval_accuracy_unlabeled": NaN,
|
| 153 |
+
"eval_dice_coefficient": 0.7989642024040222,
|
| 154 |
+
"eval_iou_circuit": 0.9281712722196696,
|
| 155 |
+
"eval_iou_unlabeled": 0.0,
|
| 156 |
+
"eval_loss": 0.2810139060020447,
|
| 157 |
+
"eval_mean_accuracy": 0.9281712722196696,
|
| 158 |
+
"eval_mean_iou": 0.4640856361098348,
|
| 159 |
+
"eval_overall_accuracy": 0.9281712722196696,
|
| 160 |
+
"eval_runtime": 1.8951,
|
| 161 |
+
"eval_samples_per_second": 5.277,
|
| 162 |
+
"eval_steps_per_second": 2.638,
|
| 163 |
+
"step": 700
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 10.0,
|
| 167 |
+
"learning_rate": 4.8e-05,
|
| 168 |
+
"loss": 0.4174,
|
| 169 |
+
"step": 800
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 10.0,
|
| 173 |
+
"eval_accuracy_circuit": 0.8431605382379681,
|
| 174 |
+
"eval_accuracy_unlabeled": NaN,
|
| 175 |
+
"eval_dice_coefficient": 0.7649561762809753,
|
| 176 |
+
"eval_iou_circuit": 0.8431605382379681,
|
| 177 |
+
"eval_iou_unlabeled": 0.0,
|
| 178 |
+
"eval_loss": 0.350821316242218,
|
| 179 |
+
"eval_mean_accuracy": 0.8431605382379681,
|
| 180 |
+
"eval_mean_iou": 0.42158026911898405,
|
| 181 |
+
"eval_overall_accuracy": 0.8431605382379681,
|
| 182 |
+
"eval_runtime": 1.8632,
|
| 183 |
+
"eval_samples_per_second": 5.367,
|
| 184 |
+
"eval_steps_per_second": 2.684,
|
| 185 |
+
"step": 800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 11.25,
|
| 189 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 190 |
+
"loss": 0.4348,
|
| 191 |
+
"step": 900
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 11.25,
|
| 195 |
+
"eval_accuracy_circuit": 0.8319266924165811,
|
| 196 |
+
"eval_accuracy_unlabeled": NaN,
|
| 197 |
+
"eval_dice_coefficient": 0.7888613939285278,
|
| 198 |
+
"eval_iou_circuit": 0.8319266924165811,
|
| 199 |
+
"eval_iou_unlabeled": 0.0,
|
| 200 |
+
"eval_loss": 0.22976386547088623,
|
| 201 |
+
"eval_mean_accuracy": 0.8319266924165811,
|
| 202 |
+
"eval_mean_iou": 0.41596334620829056,
|
| 203 |
+
"eval_overall_accuracy": 0.8319266924165811,
|
| 204 |
+
"eval_runtime": 1.8732,
|
| 205 |
+
"eval_samples_per_second": 5.338,
|
| 206 |
+
"eval_steps_per_second": 2.669,
|
| 207 |
+
"step": 900
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 12.5,
|
| 211 |
+
"learning_rate": 4.5e-05,
|
| 212 |
+
"loss": 0.4215,
|
| 213 |
+
"step": 1000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 12.5,
|
| 217 |
+
"eval_accuracy_circuit": 0.7035958565848367,
|
| 218 |
+
"eval_accuracy_unlabeled": NaN,
|
| 219 |
+
"eval_dice_coefficient": 0.7077653408050537,
|
| 220 |
+
"eval_iou_circuit": 0.7035958565848367,
|
| 221 |
+
"eval_iou_unlabeled": 0.0,
|
| 222 |
+
"eval_loss": 0.246572807431221,
|
| 223 |
+
"eval_mean_accuracy": 0.7035958565848367,
|
| 224 |
+
"eval_mean_iou": 0.35179792829241835,
|
| 225 |
+
"eval_overall_accuracy": 0.7035958565848367,
|
| 226 |
+
"eval_runtime": 1.8657,
|
| 227 |
+
"eval_samples_per_second": 5.36,
|
| 228 |
+
"eval_steps_per_second": 2.68,
|
| 229 |
+
"step": 1000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 13.75,
|
| 233 |
+
"learning_rate": 4.35e-05,
|
| 234 |
+
"loss": 0.3917,
|
| 235 |
+
"step": 1100
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 13.75,
|
| 239 |
+
"eval_accuracy_circuit": 0.8747709410869753,
|
| 240 |
+
"eval_accuracy_unlabeled": NaN,
|
| 241 |
+
"eval_dice_coefficient": 0.817740797996521,
|
| 242 |
+
"eval_iou_circuit": 0.8747709410869753,
|
| 243 |
+
"eval_iou_unlabeled": 0.0,
|
| 244 |
+
"eval_loss": 0.21436497569084167,
|
| 245 |
+
"eval_mean_accuracy": 0.8747709410869753,
|
| 246 |
+
"eval_mean_iou": 0.43738547054348764,
|
| 247 |
+
"eval_overall_accuracy": 0.8747709410869753,
|
| 248 |
+
"eval_runtime": 1.9253,
|
| 249 |
+
"eval_samples_per_second": 5.194,
|
| 250 |
+
"eval_steps_per_second": 2.597,
|
| 251 |
+
"step": 1100
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 15.0,
|
| 255 |
+
"learning_rate": 4.2e-05,
|
| 256 |
+
"loss": 0.3965,
|
| 257 |
+
"step": 1200
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 15.0,
|
| 261 |
+
"eval_accuracy_circuit": 0.8348472958769941,
|
| 262 |
+
"eval_accuracy_unlabeled": NaN,
|
| 263 |
+
"eval_dice_coefficient": 0.7990642786026001,
|
| 264 |
+
"eval_iou_circuit": 0.8348472958769941,
|
| 265 |
+
"eval_iou_unlabeled": 0.0,
|
| 266 |
+
"eval_loss": 0.22340206801891327,
|
| 267 |
+
"eval_mean_accuracy": 0.8348472958769941,
|
| 268 |
+
"eval_mean_iou": 0.41742364793849707,
|
| 269 |
+
"eval_overall_accuracy": 0.8348472958769941,
|
| 270 |
+
"eval_runtime": 1.865,
|
| 271 |
+
"eval_samples_per_second": 5.362,
|
| 272 |
+
"eval_steps_per_second": 2.681,
|
| 273 |
+
"step": 1200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 16.25,
|
| 277 |
+
"learning_rate": 4.05e-05,
|
| 278 |
+
"loss": 0.3685,
|
| 279 |
+
"step": 1300
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 16.25,
|
| 283 |
+
"eval_accuracy_circuit": 0.9429696512629209,
|
| 284 |
+
"eval_accuracy_unlabeled": NaN,
|
| 285 |
+
"eval_dice_coefficient": 0.846348762512207,
|
| 286 |
+
"eval_iou_circuit": 0.9429696512629209,
|
| 287 |
+
"eval_iou_unlabeled": 0.0,
|
| 288 |
+
"eval_loss": 0.2239874303340912,
|
| 289 |
+
"eval_mean_accuracy": 0.9429696512629209,
|
| 290 |
+
"eval_mean_iou": 0.47148482563146044,
|
| 291 |
+
"eval_overall_accuracy": 0.9429696512629209,
|
| 292 |
+
"eval_runtime": 1.9367,
|
| 293 |
+
"eval_samples_per_second": 5.163,
|
| 294 |
+
"eval_steps_per_second": 2.582,
|
| 295 |
+
"step": 1300
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 17.5,
|
| 299 |
+
"learning_rate": 3.9e-05,
|
| 300 |
+
"loss": 0.3774,
|
| 301 |
+
"step": 1400
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 17.5,
|
| 305 |
+
"eval_accuracy_circuit": 0.8867163838650847,
|
| 306 |
+
"eval_accuracy_unlabeled": NaN,
|
| 307 |
+
"eval_dice_coefficient": 0.8314148783683777,
|
| 308 |
+
"eval_iou_circuit": 0.8867163838650847,
|
| 309 |
+
"eval_iou_unlabeled": 0.0,
|
| 310 |
+
"eval_loss": 0.2103152573108673,
|
| 311 |
+
"eval_mean_accuracy": 0.8867163838650847,
|
| 312 |
+
"eval_mean_iou": 0.44335819193254233,
|
| 313 |
+
"eval_overall_accuracy": 0.8867163838650847,
|
| 314 |
+
"eval_runtime": 1.8595,
|
| 315 |
+
"eval_samples_per_second": 5.378,
|
| 316 |
+
"eval_steps_per_second": 2.689,
|
| 317 |
+
"step": 1400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 18.75,
|
| 321 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 322 |
+
"loss": 0.3546,
|
| 323 |
+
"step": 1500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 18.75,
|
| 327 |
+
"eval_accuracy_circuit": 0.8007233841455762,
|
| 328 |
+
"eval_accuracy_unlabeled": NaN,
|
| 329 |
+
"eval_dice_coefficient": 0.7820441126823425,
|
| 330 |
+
"eval_iou_circuit": 0.8007233841455762,
|
| 331 |
+
"eval_iou_unlabeled": 0.0,
|
| 332 |
+
"eval_loss": 0.2279864251613617,
|
| 333 |
+
"eval_mean_accuracy": 0.8007233841455762,
|
| 334 |
+
"eval_mean_iou": 0.4003616920727881,
|
| 335 |
+
"eval_overall_accuracy": 0.8007233841455762,
|
| 336 |
+
"eval_runtime": 1.8688,
|
| 337 |
+
"eval_samples_per_second": 5.351,
|
| 338 |
+
"eval_steps_per_second": 2.676,
|
| 339 |
+
"step": 1500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 20.0,
|
| 343 |
+
"learning_rate": 3.6e-05,
|
| 344 |
+
"loss": 0.3405,
|
| 345 |
+
"step": 1600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 20.0,
|
| 349 |
+
"eval_accuracy_circuit": 0.7007658398535769,
|
| 350 |
+
"eval_accuracy_unlabeled": NaN,
|
| 351 |
+
"eval_dice_coefficient": 0.7185879945755005,
|
| 352 |
+
"eval_iou_circuit": 0.7007658398535769,
|
| 353 |
+
"eval_iou_unlabeled": 0.0,
|
| 354 |
+
"eval_loss": 0.2274409830570221,
|
| 355 |
+
"eval_mean_accuracy": 0.7007658398535769,
|
| 356 |
+
"eval_mean_iou": 0.35038291992678844,
|
| 357 |
+
"eval_overall_accuracy": 0.7007658398535769,
|
| 358 |
+
"eval_runtime": 1.8599,
|
| 359 |
+
"eval_samples_per_second": 5.377,
|
| 360 |
+
"eval_steps_per_second": 2.688,
|
| 361 |
+
"step": 1600
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 21.25,
|
| 365 |
+
"learning_rate": 3.45e-05,
|
| 366 |
+
"loss": 0.3448,
|
| 367 |
+
"step": 1700
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 21.25,
|
| 371 |
+
"eval_accuracy_circuit": 0.7553961859712808,
|
| 372 |
+
"eval_accuracy_unlabeled": NaN,
|
| 373 |
+
"eval_dice_coefficient": 0.7602112889289856,
|
| 374 |
+
"eval_iou_circuit": 0.7553961859712808,
|
| 375 |
+
"eval_iou_unlabeled": 0.0,
|
| 376 |
+
"eval_loss": 0.2249414026737213,
|
| 377 |
+
"eval_mean_accuracy": 0.7553961859712808,
|
| 378 |
+
"eval_mean_iou": 0.3776980929856404,
|
| 379 |
+
"eval_overall_accuracy": 0.7553961859712808,
|
| 380 |
+
"eval_runtime": 1.8349,
|
| 381 |
+
"eval_samples_per_second": 5.45,
|
| 382 |
+
"eval_steps_per_second": 2.725,
|
| 383 |
+
"step": 1700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 22.5,
|
| 387 |
+
"learning_rate": 3.3e-05,
|
| 388 |
+
"loss": 0.3378,
|
| 389 |
+
"step": 1800
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 22.5,
|
| 393 |
+
"eval_accuracy_circuit": 0.7865372840788912,
|
| 394 |
+
"eval_accuracy_unlabeled": NaN,
|
| 395 |
+
"eval_dice_coefficient": 0.776802122592926,
|
| 396 |
+
"eval_iou_circuit": 0.7865372840788912,
|
| 397 |
+
"eval_iou_unlabeled": 0.0,
|
| 398 |
+
"eval_loss": 0.21100302040576935,
|
| 399 |
+
"eval_mean_accuracy": 0.7865372840788912,
|
| 400 |
+
"eval_mean_iou": 0.3932686420394456,
|
| 401 |
+
"eval_overall_accuracy": 0.7865372840788912,
|
| 402 |
+
"eval_runtime": 1.8753,
|
| 403 |
+
"eval_samples_per_second": 5.332,
|
| 404 |
+
"eval_steps_per_second": 2.666,
|
| 405 |
+
"step": 1800
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 23.75,
|
| 409 |
+
"learning_rate": 3.15e-05,
|
| 410 |
+
"loss": 0.3274,
|
| 411 |
+
"step": 1900
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 23.75,
|
| 415 |
+
"eval_accuracy_circuit": 0.7718644167688041,
|
| 416 |
+
"eval_accuracy_unlabeled": NaN,
|
| 417 |
+
"eval_dice_coefficient": 0.7673341631889343,
|
| 418 |
+
"eval_iou_circuit": 0.7718644167688041,
|
| 419 |
+
"eval_iou_unlabeled": 0.0,
|
| 420 |
+
"eval_loss": 0.21237103641033173,
|
| 421 |
+
"eval_mean_accuracy": 0.7718644167688041,
|
| 422 |
+
"eval_mean_iou": 0.38593220838440206,
|
| 423 |
+
"eval_overall_accuracy": 0.7718644167688041,
|
| 424 |
+
"eval_runtime": 1.8789,
|
| 425 |
+
"eval_samples_per_second": 5.322,
|
| 426 |
+
"eval_steps_per_second": 2.661,
|
| 427 |
+
"step": 1900
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 25.0,
|
| 431 |
+
"learning_rate": 3e-05,
|
| 432 |
+
"loss": 0.3185,
|
| 433 |
+
"step": 2000
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 25.0,
|
| 437 |
+
"eval_accuracy_circuit": 0.8367168749979537,
|
| 438 |
+
"eval_accuracy_unlabeled": NaN,
|
| 439 |
+
"eval_dice_coefficient": 0.8104449510574341,
|
| 440 |
+
"eval_iou_circuit": 0.8367168749979537,
|
| 441 |
+
"eval_iou_unlabeled": 0.0,
|
| 442 |
+
"eval_loss": 0.20555877685546875,
|
| 443 |
+
"eval_mean_accuracy": 0.8367168749979537,
|
| 444 |
+
"eval_mean_iou": 0.41835843749897683,
|
| 445 |
+
"eval_overall_accuracy": 0.8367168749979537,
|
| 446 |
+
"eval_runtime": 1.8857,
|
| 447 |
+
"eval_samples_per_second": 5.303,
|
| 448 |
+
"eval_steps_per_second": 2.652,
|
| 449 |
+
"step": 2000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 26.25,
|
| 453 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 454 |
+
"loss": 0.3225,
|
| 455 |
+
"step": 2100
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 26.25,
|
| 459 |
+
"eval_accuracy_circuit": 0.825157790076715,
|
| 460 |
+
"eval_accuracy_unlabeled": NaN,
|
| 461 |
+
"eval_dice_coefficient": 0.8050472140312195,
|
| 462 |
+
"eval_iou_circuit": 0.825157790076715,
|
| 463 |
+
"eval_iou_unlabeled": 0.0,
|
| 464 |
+
"eval_loss": 0.2054174840450287,
|
| 465 |
+
"eval_mean_accuracy": 0.825157790076715,
|
| 466 |
+
"eval_mean_iou": 0.4125788950383575,
|
| 467 |
+
"eval_overall_accuracy": 0.825157790076715,
|
| 468 |
+
"eval_runtime": 1.8934,
|
| 469 |
+
"eval_samples_per_second": 5.281,
|
| 470 |
+
"eval_steps_per_second": 2.641,
|
| 471 |
+
"step": 2100
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 27.5,
|
| 475 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 476 |
+
"loss": 0.3095,
|
| 477 |
+
"step": 2200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 27.5,
|
| 481 |
+
"eval_accuracy_circuit": 0.7891293742203266,
|
| 482 |
+
"eval_accuracy_unlabeled": NaN,
|
| 483 |
+
"eval_dice_coefficient": 0.7862051725387573,
|
| 484 |
+
"eval_iou_circuit": 0.7891293742203266,
|
| 485 |
+
"eval_iou_unlabeled": 0.0,
|
| 486 |
+
"eval_loss": 0.2073349505662918,
|
| 487 |
+
"eval_mean_accuracy": 0.7891293742203266,
|
| 488 |
+
"eval_mean_iou": 0.3945646871101633,
|
| 489 |
+
"eval_overall_accuracy": 0.7891293742203266,
|
| 490 |
+
"eval_runtime": 1.9031,
|
| 491 |
+
"eval_samples_per_second": 5.255,
|
| 492 |
+
"eval_steps_per_second": 2.627,
|
| 493 |
+
"step": 2200
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 28.75,
|
| 497 |
+
"learning_rate": 2.55e-05,
|
| 498 |
+
"loss": 0.3038,
|
| 499 |
+
"step": 2300
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 28.75,
|
| 503 |
+
"eval_accuracy_circuit": 0.8850978282104537,
|
| 504 |
+
"eval_accuracy_unlabeled": NaN,
|
| 505 |
+
"eval_dice_coefficient": 0.8418375849723816,
|
| 506 |
+
"eval_iou_circuit": 0.8850978282104537,
|
| 507 |
+
"eval_iou_unlabeled": 0.0,
|
| 508 |
+
"eval_loss": 0.19880831241607666,
|
| 509 |
+
"eval_mean_accuracy": 0.8850978282104537,
|
| 510 |
+
"eval_mean_iou": 0.44254891410522684,
|
| 511 |
+
"eval_overall_accuracy": 0.8850978282104537,
|
| 512 |
+
"eval_runtime": 1.8755,
|
| 513 |
+
"eval_samples_per_second": 5.332,
|
| 514 |
+
"eval_steps_per_second": 2.666,
|
| 515 |
+
"step": 2300
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 30.0,
|
| 519 |
+
"learning_rate": 2.4e-05,
|
| 520 |
+
"loss": 0.2933,
|
| 521 |
+
"step": 2400
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 30.0,
|
| 525 |
+
"eval_accuracy_circuit": 0.8413717231887838,
|
| 526 |
+
"eval_accuracy_unlabeled": NaN,
|
| 527 |
+
"eval_dice_coefficient": 0.8135576248168945,
|
| 528 |
+
"eval_iou_circuit": 0.8413717231887838,
|
| 529 |
+
"eval_iou_unlabeled": 0.0,
|
| 530 |
+
"eval_loss": 0.20930209755897522,
|
| 531 |
+
"eval_mean_accuracy": 0.8413717231887838,
|
| 532 |
+
"eval_mean_iou": 0.4206858615943919,
|
| 533 |
+
"eval_overall_accuracy": 0.8413717231887838,
|
| 534 |
+
"eval_runtime": 1.8492,
|
| 535 |
+
"eval_samples_per_second": 5.408,
|
| 536 |
+
"eval_steps_per_second": 2.704,
|
| 537 |
+
"step": 2400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 31.25,
|
| 541 |
+
"learning_rate": 2.25e-05,
|
| 542 |
+
"loss": 0.289,
|
| 543 |
+
"step": 2500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 31.25,
|
| 547 |
+
"eval_accuracy_circuit": 0.7590698598306792,
|
| 548 |
+
"eval_accuracy_unlabeled": NaN,
|
| 549 |
+
"eval_dice_coefficient": 0.7699534296989441,
|
| 550 |
+
"eval_iou_circuit": 0.7590698598306792,
|
| 551 |
+
"eval_iou_unlabeled": 0.0,
|
| 552 |
+
"eval_loss": 0.2080351561307907,
|
| 553 |
+
"eval_mean_accuracy": 0.7590698598306792,
|
| 554 |
+
"eval_mean_iou": 0.3795349299153396,
|
| 555 |
+
"eval_overall_accuracy": 0.7590698598306792,
|
| 556 |
+
"eval_runtime": 1.8538,
|
| 557 |
+
"eval_samples_per_second": 5.394,
|
| 558 |
+
"eval_steps_per_second": 2.697,
|
| 559 |
+
"step": 2500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 32.5,
|
| 563 |
+
"learning_rate": 2.1e-05,
|
| 564 |
+
"loss": 0.3045,
|
| 565 |
+
"step": 2600
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 32.5,
|
| 569 |
+
"eval_accuracy_circuit": 0.755483498481308,
|
| 570 |
+
"eval_accuracy_unlabeled": NaN,
|
| 571 |
+
"eval_dice_coefficient": 0.7673963904380798,
|
| 572 |
+
"eval_iou_circuit": 0.755483498481308,
|
| 573 |
+
"eval_iou_unlabeled": 0.0,
|
| 574 |
+
"eval_loss": 0.2087668925523758,
|
| 575 |
+
"eval_mean_accuracy": 0.755483498481308,
|
| 576 |
+
"eval_mean_iou": 0.377741749240654,
|
| 577 |
+
"eval_overall_accuracy": 0.755483498481308,
|
| 578 |
+
"eval_runtime": 1.8506,
|
| 579 |
+
"eval_samples_per_second": 5.404,
|
| 580 |
+
"eval_steps_per_second": 2.702,
|
| 581 |
+
"step": 2600
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 33.75,
|
| 585 |
+
"learning_rate": 1.95e-05,
|
| 586 |
+
"loss": 0.2842,
|
| 587 |
+
"step": 2700
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 33.75,
|
| 591 |
+
"eval_accuracy_circuit": 0.8520740541053796,
|
| 592 |
+
"eval_accuracy_unlabeled": NaN,
|
| 593 |
+
"eval_dice_coefficient": 0.8262351751327515,
|
| 594 |
+
"eval_iou_circuit": 0.8520740541053796,
|
| 595 |
+
"eval_iou_unlabeled": 0.0,
|
| 596 |
+
"eval_loss": 0.19945015013217926,
|
| 597 |
+
"eval_mean_accuracy": 0.8520740541053796,
|
| 598 |
+
"eval_mean_iou": 0.4260370270526898,
|
| 599 |
+
"eval_overall_accuracy": 0.8520740541053796,
|
| 600 |
+
"eval_runtime": 1.8567,
|
| 601 |
+
"eval_samples_per_second": 5.386,
|
| 602 |
+
"eval_steps_per_second": 2.693,
|
| 603 |
+
"step": 2700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 35.0,
|
| 607 |
+
"learning_rate": 1.8e-05,
|
| 608 |
+
"loss": 0.2761,
|
| 609 |
+
"step": 2800
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 35.0,
|
| 613 |
+
"eval_accuracy_circuit": 0.8814885473272004,
|
| 614 |
+
"eval_accuracy_unlabeled": NaN,
|
| 615 |
+
"eval_dice_coefficient": 0.8395698666572571,
|
| 616 |
+
"eval_iou_circuit": 0.8814885473272004,
|
| 617 |
+
"eval_iou_unlabeled": 0.0,
|
| 618 |
+
"eval_loss": 0.19794146716594696,
|
| 619 |
+
"eval_mean_accuracy": 0.8814885473272004,
|
| 620 |
+
"eval_mean_iou": 0.4407442736636002,
|
| 621 |
+
"eval_overall_accuracy": 0.8814885473272004,
|
| 622 |
+
"eval_runtime": 1.9067,
|
| 623 |
+
"eval_samples_per_second": 5.245,
|
| 624 |
+
"eval_steps_per_second": 2.622,
|
| 625 |
+
"step": 2800
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 36.25,
|
| 629 |
+
"learning_rate": 1.65e-05,
|
| 630 |
+
"loss": 0.2846,
|
| 631 |
+
"step": 2900
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 36.25,
|
| 635 |
+
"eval_accuracy_circuit": 0.8062491746239286,
|
| 636 |
+
"eval_accuracy_unlabeled": NaN,
|
| 637 |
+
"eval_dice_coefficient": 0.7988327741622925,
|
| 638 |
+
"eval_iou_circuit": 0.8062491746239286,
|
| 639 |
+
"eval_iou_unlabeled": 0.0,
|
| 640 |
+
"eval_loss": 0.19883993268013,
|
| 641 |
+
"eval_mean_accuracy": 0.8062491746239286,
|
| 642 |
+
"eval_mean_iou": 0.4031245873119643,
|
| 643 |
+
"eval_overall_accuracy": 0.8062491746239286,
|
| 644 |
+
"eval_runtime": 1.855,
|
| 645 |
+
"eval_samples_per_second": 5.391,
|
| 646 |
+
"eval_steps_per_second": 2.695,
|
| 647 |
+
"step": 2900
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 37.5,
|
| 651 |
+
"learning_rate": 1.5e-05,
|
| 652 |
+
"loss": 0.2722,
|
| 653 |
+
"step": 3000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 37.5,
|
| 657 |
+
"eval_accuracy_circuit": 0.8571108945275793,
|
| 658 |
+
"eval_accuracy_unlabeled": NaN,
|
| 659 |
+
"eval_dice_coefficient": 0.827845573425293,
|
| 660 |
+
"eval_iou_circuit": 0.8571108945275793,
|
| 661 |
+
"eval_iou_unlabeled": 0.0,
|
| 662 |
+
"eval_loss": 0.196430042386055,
|
| 663 |
+
"eval_mean_accuracy": 0.8571108945275793,
|
| 664 |
+
"eval_mean_iou": 0.42855544726378964,
|
| 665 |
+
"eval_overall_accuracy": 0.8571108945275793,
|
| 666 |
+
"eval_runtime": 1.8615,
|
| 667 |
+
"eval_samples_per_second": 5.372,
|
| 668 |
+
"eval_steps_per_second": 2.686,
|
| 669 |
+
"step": 3000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 38.75,
|
| 673 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 674 |
+
"loss": 0.2913,
|
| 675 |
+
"step": 3100
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 38.75,
|
| 679 |
+
"eval_accuracy_circuit": 0.7619489898488293,
|
| 680 |
+
"eval_accuracy_unlabeled": NaN,
|
| 681 |
+
"eval_dice_coefficient": 0.7747573852539062,
|
| 682 |
+
"eval_iou_circuit": 0.7619489898488293,
|
| 683 |
+
"eval_iou_unlabeled": 0.0,
|
| 684 |
+
"eval_loss": 0.2070605456829071,
|
| 685 |
+
"eval_mean_accuracy": 0.7619489898488293,
|
| 686 |
+
"eval_mean_iou": 0.38097449492441465,
|
| 687 |
+
"eval_overall_accuracy": 0.7619489898488293,
|
| 688 |
+
"eval_runtime": 1.8551,
|
| 689 |
+
"eval_samples_per_second": 5.391,
|
| 690 |
+
"eval_steps_per_second": 2.695,
|
| 691 |
+
"step": 3100
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 40.0,
|
| 695 |
+
"learning_rate": 1.2e-05,
|
| 696 |
+
"loss": 0.2631,
|
| 697 |
+
"step": 3200
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 40.0,
|
| 701 |
+
"eval_accuracy_circuit": 0.822477296018877,
|
| 702 |
+
"eval_accuracy_unlabeled": NaN,
|
| 703 |
+
"eval_dice_coefficient": 0.8101258277893066,
|
| 704 |
+
"eval_iou_circuit": 0.822477296018877,
|
| 705 |
+
"eval_iou_unlabeled": 0.0,
|
| 706 |
+
"eval_loss": 0.19885489344596863,
|
| 707 |
+
"eval_mean_accuracy": 0.822477296018877,
|
| 708 |
+
"eval_mean_iou": 0.4112386480094385,
|
| 709 |
+
"eval_overall_accuracy": 0.822477296018877,
|
| 710 |
+
"eval_runtime": 1.8822,
|
| 711 |
+
"eval_samples_per_second": 5.313,
|
| 712 |
+
"eval_steps_per_second": 2.656,
|
| 713 |
+
"step": 3200
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 41.25,
|
| 717 |
+
"learning_rate": 1.05e-05,
|
| 718 |
+
"loss": 0.2649,
|
| 719 |
+
"step": 3300
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 41.25,
|
| 723 |
+
"eval_accuracy_circuit": 0.8814001434107978,
|
| 724 |
+
"eval_accuracy_unlabeled": NaN,
|
| 725 |
+
"eval_dice_coefficient": 0.8404178619384766,
|
| 726 |
+
"eval_iou_circuit": 0.8814001434107978,
|
| 727 |
+
"eval_iou_unlabeled": 0.0,
|
| 728 |
+
"eval_loss": 0.19604873657226562,
|
| 729 |
+
"eval_mean_accuracy": 0.8814001434107978,
|
| 730 |
+
"eval_mean_iou": 0.4407000717053989,
|
| 731 |
+
"eval_overall_accuracy": 0.8814001434107978,
|
| 732 |
+
"eval_runtime": 1.9145,
|
| 733 |
+
"eval_samples_per_second": 5.223,
|
| 734 |
+
"eval_steps_per_second": 2.612,
|
| 735 |
+
"step": 3300
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 42.5,
|
| 739 |
+
"learning_rate": 9e-06,
|
| 740 |
+
"loss": 0.2812,
|
| 741 |
+
"step": 3400
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 42.5,
|
| 745 |
+
"eval_accuracy_circuit": 0.8107686884242166,
|
| 746 |
+
"eval_accuracy_unlabeled": NaN,
|
| 747 |
+
"eval_dice_coefficient": 0.8038872480392456,
|
| 748 |
+
"eval_iou_circuit": 0.8107686884242166,
|
| 749 |
+
"eval_iou_unlabeled": 0.0,
|
| 750 |
+
"eval_loss": 0.19998733699321747,
|
| 751 |
+
"eval_mean_accuracy": 0.8107686884242166,
|
| 752 |
+
"eval_mean_iou": 0.4053843442121083,
|
| 753 |
+
"eval_overall_accuracy": 0.8107686884242166,
|
| 754 |
+
"eval_runtime": 1.8241,
|
| 755 |
+
"eval_samples_per_second": 5.482,
|
| 756 |
+
"eval_steps_per_second": 2.741,
|
| 757 |
+
"step": 3400
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 43.75,
|
| 761 |
+
"learning_rate": 7.5e-06,
|
| 762 |
+
"loss": 0.2522,
|
| 763 |
+
"step": 3500
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 43.75,
|
| 767 |
+
"eval_accuracy_circuit": 0.8161209452888898,
|
| 768 |
+
"eval_accuracy_unlabeled": NaN,
|
| 769 |
+
"eval_dice_coefficient": 0.806645393371582,
|
| 770 |
+
"eval_iou_circuit": 0.8161209452888898,
|
| 771 |
+
"eval_iou_unlabeled": 0.0,
|
| 772 |
+
"eval_loss": 0.19722411036491394,
|
| 773 |
+
"eval_mean_accuracy": 0.8161209452888898,
|
| 774 |
+
"eval_mean_iou": 0.4080604726444449,
|
| 775 |
+
"eval_overall_accuracy": 0.8161209452888898,
|
| 776 |
+
"eval_runtime": 1.8752,
|
| 777 |
+
"eval_samples_per_second": 5.333,
|
| 778 |
+
"eval_steps_per_second": 2.666,
|
| 779 |
+
"step": 3500
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 45.0,
|
| 783 |
+
"learning_rate": 6e-06,
|
| 784 |
+
"loss": 0.264,
|
| 785 |
+
"step": 3600
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 45.0,
|
| 789 |
+
"eval_accuracy_circuit": 0.8064063371419777,
|
| 790 |
+
"eval_accuracy_unlabeled": NaN,
|
| 791 |
+
"eval_dice_coefficient": 0.8012853860855103,
|
| 792 |
+
"eval_iou_circuit": 0.8064063371419777,
|
| 793 |
+
"eval_iou_unlabeled": 0.0,
|
| 794 |
+
"eval_loss": 0.19993409514427185,
|
| 795 |
+
"eval_mean_accuracy": 0.8064063371419777,
|
| 796 |
+
"eval_mean_iou": 0.40320316857098887,
|
| 797 |
+
"eval_overall_accuracy": 0.8064063371419777,
|
| 798 |
+
"eval_runtime": 1.8665,
|
| 799 |
+
"eval_samples_per_second": 5.358,
|
| 800 |
+
"eval_steps_per_second": 2.679,
|
| 801 |
+
"step": 3600
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 46.25,
|
| 805 |
+
"learning_rate": 4.5e-06,
|
| 806 |
+
"loss": 0.2604,
|
| 807 |
+
"step": 3700
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 46.25,
|
| 811 |
+
"eval_accuracy_circuit": 0.8446448509084321,
|
| 812 |
+
"eval_accuracy_unlabeled": NaN,
|
| 813 |
+
"eval_dice_coefficient": 0.8228257894515991,
|
| 814 |
+
"eval_iou_circuit": 0.8446448509084321,
|
| 815 |
+
"eval_iou_unlabeled": 0.0,
|
| 816 |
+
"eval_loss": 0.19786684215068817,
|
| 817 |
+
"eval_mean_accuracy": 0.8446448509084321,
|
| 818 |
+
"eval_mean_iou": 0.42232242545421605,
|
| 819 |
+
"eval_overall_accuracy": 0.8446448509084321,
|
| 820 |
+
"eval_runtime": 1.9162,
|
| 821 |
+
"eval_samples_per_second": 5.219,
|
| 822 |
+
"eval_steps_per_second": 2.609,
|
| 823 |
+
"step": 3700
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 47.5,
|
| 827 |
+
"learning_rate": 3e-06,
|
| 828 |
+
"loss": 0.2555,
|
| 829 |
+
"step": 3800
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 47.5,
|
| 833 |
+
"eval_accuracy_circuit": 0.8151583248658388,
|
| 834 |
+
"eval_accuracy_unlabeled": NaN,
|
| 835 |
+
"eval_dice_coefficient": 0.8071210980415344,
|
| 836 |
+
"eval_iou_circuit": 0.8151583248658388,
|
| 837 |
+
"eval_iou_unlabeled": 0.0,
|
| 838 |
+
"eval_loss": 0.1972045600414276,
|
| 839 |
+
"eval_mean_accuracy": 0.8151583248658388,
|
| 840 |
+
"eval_mean_iou": 0.4075791624329194,
|
| 841 |
+
"eval_overall_accuracy": 0.8151583248658388,
|
| 842 |
+
"eval_runtime": 1.8971,
|
| 843 |
+
"eval_samples_per_second": 5.271,
|
| 844 |
+
"eval_steps_per_second": 2.636,
|
| 845 |
+
"step": 3800
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 48.75,
|
| 849 |
+
"learning_rate": 1.5e-06,
|
| 850 |
+
"loss": 0.2804,
|
| 851 |
+
"step": 3900
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 48.75,
|
| 855 |
+
"eval_accuracy_circuit": 0.7769918439201571,
|
| 856 |
+
"eval_accuracy_unlabeled": NaN,
|
| 857 |
+
"eval_dice_coefficient": 0.7854458093643188,
|
| 858 |
+
"eval_iou_circuit": 0.7769918439201571,
|
| 859 |
+
"eval_iou_unlabeled": 0.0,
|
| 860 |
+
"eval_loss": 0.20280936360359192,
|
| 861 |
+
"eval_mean_accuracy": 0.7769918439201571,
|
| 862 |
+
"eval_mean_iou": 0.38849592196007854,
|
| 863 |
+
"eval_overall_accuracy": 0.7769918439201571,
|
| 864 |
+
"eval_runtime": 1.8601,
|
| 865 |
+
"eval_samples_per_second": 5.376,
|
| 866 |
+
"eval_steps_per_second": 2.688,
|
| 867 |
+
"step": 3900
|
| 868 |
+
}
|
| 869 |
+
],
|
| 870 |
+
"logging_steps": 100,
|
| 871 |
+
"max_steps": 4000,
|
| 872 |
+
"num_input_tokens_seen": 0,
|
| 873 |
+
"num_train_epochs": 50,
|
| 874 |
+
"save_steps": 100,
|
| 875 |
+
"total_flos": 3.113516120879923e+18,
|
| 876 |
+
"train_batch_size": 2,
|
| 877 |
+
"trial_name": null,
|
| 878 |
+
"trial_params": null
|
| 879 |
+
}
|
tmp-checkpoint-3900/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94654457e2d7e87d35a2f014d69c570d1c31dbeaeaf92cfdb3454121f6592a08
|
| 3 |
+
size 4271
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94654457e2d7e87d35a2f014d69c570d1c31dbeaeaf92cfdb3454121f6592a08
|
| 3 |
+
size 4271
|