?? cheers
Browse files- README.md +27 -21
- all_results.json +17 -15
- config.json +2 -2
- eval_results.json +13 -10
- model.safetensors +1 -1
- runs/Mar25_13-36-15_hossayui-MacBook-Pro.local/events.out.tfevents.1711341376.hossayui-MacBook-Pro.local.16803.0 +3 -0
- runs/Mar25_13-45-43_hossayui-MacBook-Pro.local/events.out.tfevents.1711341944.hossayui-MacBook-Pro.local.19761.0 +3 -0
- runs/Mar25_13-45-43_hossayui-MacBook-Pro.local/events.out.tfevents.1711343922.hossayui-MacBook-Pro.local.19761.1 +3 -0
- train_results.json +5 -5
- trainer_state.json +800 -72
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
| 5 |
- image-classification
|
| 6 |
- generated_from_trainer
|
|
@@ -9,9 +9,6 @@ datasets:
|
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
| 11 |
- f1
|
| 12 |
-
widget:
|
| 13 |
-
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
|
| 14 |
-
example_title: sample1
|
| 15 |
model-index:
|
| 16 |
- name: stool-condition-classification
|
| 17 |
results:
|
|
@@ -30,8 +27,7 @@ model-index:
|
|
| 30 |
value: 0.941747572815534
|
| 31 |
- name: F1
|
| 32 |
type: f1
|
| 33 |
-
value: 0.
|
| 34 |
-
pipeline_tag: image-classification
|
| 35 |
---
|
| 36 |
|
| 37 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -39,14 +35,17 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 39 |
|
| 40 |
# stool-condition-classification
|
| 41 |
|
| 42 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224
|
| 43 |
It achieves the following results on the evaluation set:
|
| 44 |
-
- Loss: 0.
|
| 45 |
-
- Auroc: 0.
|
| 46 |
- Accuracy: 0.9417
|
| 47 |
-
- Sensitivity: 0.
|
| 48 |
-
- Specificty: 0.
|
| 49 |
-
-
|
|
|
|
|
|
|
|
|
|
| 50 |
|
| 51 |
## Model description
|
| 52 |
|
|
@@ -71,20 +70,27 @@ The following hyperparameters were used during training:
|
|
| 71 |
- seed: 42
|
| 72 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 73 |
- lr_scheduler_type: linear
|
| 74 |
-
- num_epochs:
|
| 75 |
-
- mixed_precision_training: Native AMP
|
| 76 |
|
| 77 |
### Training results
|
| 78 |
|
| 79 |
-
| Training Loss | Epoch | Step | Validation Loss | Auroc | Accuracy | Sensitivity | Specificty | F1 |
|
| 80 |
-
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 83 |
|
| 84 |
|
| 85 |
### Framework versions
|
| 86 |
|
| 87 |
-
- Transformers 4.
|
| 88 |
- Pytorch 2.0.1
|
| 89 |
-
- Datasets 2.
|
| 90 |
-
- Tokenizers 0.15.
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224
|
| 4 |
tags:
|
| 5 |
- image-classification
|
| 6 |
- generated_from_trainer
|
|
|
|
| 9 |
metrics:
|
| 10 |
- accuracy
|
| 11 |
- f1
|
|
|
|
|
|
|
|
|
|
| 12 |
model-index:
|
| 13 |
- name: stool-condition-classification
|
| 14 |
results:
|
|
|
|
| 27 |
value: 0.941747572815534
|
| 28 |
- name: F1
|
| 29 |
type: f1
|
| 30 |
+
value: 0.9302325581395349
|
|
|
|
| 31 |
---
|
| 32 |
|
| 33 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 35 |
|
| 36 |
# stool-condition-classification
|
| 37 |
|
| 38 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the stool-image dataset.
|
| 39 |
It achieves the following results on the evaluation set:
|
| 40 |
+
- Loss: 0.4237
|
| 41 |
+
- Auroc: 0.9418
|
| 42 |
- Accuracy: 0.9417
|
| 43 |
+
- Sensitivity: 0.9091
|
| 44 |
+
- Specificty: 0.9661
|
| 45 |
+
- Ppv: 0.9524
|
| 46 |
+
- Npv: 0.9344
|
| 47 |
+
- F1: 0.9302
|
| 48 |
+
- Model Selection: 0.9215
|
| 49 |
|
| 50 |
## Model description
|
| 51 |
|
|
|
|
| 70 |
- seed: 42
|
| 71 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 72 |
- lr_scheduler_type: linear
|
| 73 |
+
- num_epochs: 10
|
|
|
|
| 74 |
|
| 75 |
### Training results
|
| 76 |
|
| 77 |
+
| Training Loss | Epoch | Step | Validation Loss | Auroc | Accuracy | Sensitivity | Specificty | Ppv | Npv | F1 | Model Selection |
|
| 78 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:-----------:|:----------:|:------:|:------:|:------:|:---------------:|
|
| 79 |
+
| 0.5076 | 0.98 | 100 | 0.5361 | 0.8538 | 0.7731 | 0.5393 | 0.9801 | 0.96 | 0.7061 | 0.6906 | 0.5592 |
|
| 80 |
+
| 0.4086 | 1.96 | 200 | 0.4857 | 0.8728 | 0.7836 | 0.6011 | 0.9453 | 0.9068 | 0.7280 | 0.7230 | 0.6558 |
|
| 81 |
+
| 0.5208 | 2.94 | 300 | 0.5109 | 0.8059 | 0.7599 | 0.6124 | 0.8905 | 0.8321 | 0.7218 | 0.7055 | 0.7218 |
|
| 82 |
+
| 0.474 | 3.92 | 400 | 0.5212 | 0.8601 | 0.7995 | 0.6180 | 0.9602 | 0.9322 | 0.7395 | 0.7432 | 0.6578 |
|
| 83 |
+
| 0.4285 | 4.9 | 500 | 0.4511 | 0.8728 | 0.7757 | 0.7472 | 0.8010 | 0.7688 | 0.7816 | 0.7578 | 0.9462 |
|
| 84 |
+
| 0.3506 | 5.88 | 600 | 0.4716 | 0.8691 | 0.8047 | 0.6798 | 0.9154 | 0.8768 | 0.7635 | 0.7658 | 0.7644 |
|
| 85 |
+
| 0.4239 | 6.86 | 700 | 0.5043 | 0.8517 | 0.8100 | 0.6685 | 0.9353 | 0.9015 | 0.7611 | 0.7677 | 0.7332 |
|
| 86 |
+
| 0.2447 | 7.84 | 800 | 0.5804 | 0.8592 | 0.8074 | 0.6910 | 0.9104 | 0.8723 | 0.7689 | 0.7712 | 0.7806 |
|
| 87 |
+
| 0.1739 | 8.82 | 900 | 0.6225 | 0.8562 | 0.8074 | 0.7135 | 0.8905 | 0.8523 | 0.7783 | 0.7768 | 0.8229 |
|
| 88 |
+
| 0.2888 | 9.8 | 1000 | 0.5807 | 0.8570 | 0.8047 | 0.7528 | 0.8507 | 0.8171 | 0.7953 | 0.7836 | 0.9021 |
|
| 89 |
|
| 90 |
|
| 91 |
### Framework versions
|
| 92 |
|
| 93 |
+
- Transformers 4.38.2
|
| 94 |
- Pytorch 2.0.1
|
| 95 |
+
- Datasets 2.14.7
|
| 96 |
+
- Tokenizers 0.15.2
|
all_results.json
CHANGED
|
@@ -1,18 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_accuracy": 0.941747572815534,
|
| 4 |
-
"eval_auroc": 0.
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
|
|
|
|
|
|
| 18 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
"eval_accuracy": 0.941747572815534,
|
| 4 |
+
"eval_auroc": 0.941833590138675,
|
| 5 |
+
"eval_f1": 0.9302325581395349,
|
| 6 |
+
"eval_loss": 0.42368707060813904,
|
| 7 |
+
"eval_model_selection": 0.9215271357644239,
|
| 8 |
+
"eval_npv": 0.9344262295081968,
|
| 9 |
+
"eval_ppv": 0.9523809523809523,
|
| 10 |
+
"eval_runtime": 71.7641,
|
| 11 |
+
"eval_samples_per_second": 15.314,
|
| 12 |
+
"eval_sensitivity": 0.9090909090909091,
|
| 13 |
+
"eval_specificty": 0.9661016949152542,
|
| 14 |
+
"eval_steps_per_second": 1.923,
|
| 15 |
+
"step": 1020,
|
| 16 |
+
"train_loss": 0.40091259911948557,
|
| 17 |
+
"train_runtime": 1906.0636,
|
| 18 |
+
"train_samples_per_second": 8.525,
|
| 19 |
+
"train_steps_per_second": 0.535
|
| 20 |
}
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
|
@@ -28,5 +28,5 @@
|
|
| 28 |
"problem_type": "single_label_classification",
|
| 29 |
"qkv_bias": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
-
"transformers_version": "4.
|
| 32 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
"architectures": [
|
| 4 |
"ViTForImageClassification"
|
| 5 |
],
|
|
|
|
| 28 |
"problem_type": "single_label_classification",
|
| 29 |
"qkv_bias": true,
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.38.2"
|
| 32 |
}
|
eval_results.json
CHANGED
|
@@ -1,13 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"eval_accuracy": 0.941747572815534,
|
| 4 |
-
"eval_auroc": 0.
|
| 5 |
-
"eval_f1": 0.
|
| 6 |
-
"eval_loss": 0.
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
|
|
|
|
|
|
|
|
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
"eval_accuracy": 0.941747572815534,
|
| 4 |
+
"eval_auroc": 0.941833590138675,
|
| 5 |
+
"eval_f1": 0.9302325581395349,
|
| 6 |
+
"eval_loss": 0.42368707060813904,
|
| 7 |
+
"eval_model_selection": 0.9215271357644239,
|
| 8 |
+
"eval_npv": 0.9344262295081968,
|
| 9 |
+
"eval_ppv": 0.9523809523809523,
|
| 10 |
+
"eval_runtime": 71.7641,
|
| 11 |
+
"eval_samples_per_second": 15.314,
|
| 12 |
+
"eval_sensitivity": 0.9090909090909091,
|
| 13 |
+
"eval_specificty": 0.9661016949152542,
|
| 14 |
+
"eval_steps_per_second": 1.923,
|
| 15 |
+
"step": 1020
|
| 16 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343223968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fdffa8dcb5521aaaf65199131a22b2f9e3ffd93affffbecddd23b9618cd79847
|
| 3 |
size 343223968
|
runs/Mar25_13-36-15_hossayui-MacBook-Pro.local/events.out.tfevents.1711341376.hossayui-MacBook-Pro.local.16803.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a0127361630d75eb5ba92ec8e18c8500613e62e4ffdc0892f7f7bcaaf542472
|
| 3 |
+
size 12254
|
runs/Mar25_13-45-43_hossayui-MacBook-Pro.local/events.out.tfevents.1711341944.hossayui-MacBook-Pro.local.19761.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cd7f410d31b290e5aaca8c98bd26d36a3bd6cd2823dfdd5bdec7ce8825d6d0d
|
| 3 |
+
size 33240
|
runs/Mar25_13-45-43_hossayui-MacBook-Pro.local/events.out.tfevents.1711343922.hossayui-MacBook-Pro.local.19761.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9fa2444f6073bdab54b37d73731443a87b71acd5e78d270f84aae76d49cd7877
|
| 3 |
+
size 768
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second":
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.40091259911948557,
|
| 4 |
+
"train_runtime": 1906.0636,
|
| 5 |
+
"train_samples_per_second": 8.525,
|
| 6 |
+
"train_steps_per_second": 0.535
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,175 +1,903 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.1,
|
| 13 |
-
"
|
| 14 |
-
"
|
|
|
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.2,
|
| 19 |
-
"
|
| 20 |
-
"
|
|
|
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.29,
|
| 25 |
-
"
|
| 26 |
-
"
|
|
|
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.39,
|
| 31 |
-
"
|
| 32 |
-
"
|
|
|
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.49,
|
| 37 |
-
"
|
| 38 |
-
"
|
|
|
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.59,
|
| 43 |
-
"
|
| 44 |
-
"
|
|
|
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.69,
|
| 49 |
-
"
|
| 50 |
-
"
|
|
|
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.78,
|
| 55 |
-
"
|
| 56 |
-
"
|
|
|
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.88,
|
| 61 |
-
"
|
| 62 |
-
"
|
|
|
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.98,
|
| 67 |
-
"
|
| 68 |
-
"
|
|
|
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.98,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_auroc": 0.
|
| 75 |
-
"eval_f1": 0.
|
| 76 |
-
"eval_loss": 0.
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
|
|
|
|
|
|
|
|
|
| 82 |
"step": 100
|
| 83 |
},
|
| 84 |
{
|
| 85 |
"epoch": 1.08,
|
| 86 |
-
"
|
| 87 |
-
"
|
|
|
|
| 88 |
"step": 110
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 1.18,
|
| 92 |
-
"
|
| 93 |
-
"
|
|
|
|
| 94 |
"step": 120
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 1.27,
|
| 98 |
-
"
|
| 99 |
-
"
|
|
|
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 1.37,
|
| 104 |
-
"
|
| 105 |
-
"
|
|
|
|
| 106 |
"step": 140
|
| 107 |
},
|
| 108 |
{
|
| 109 |
"epoch": 1.47,
|
| 110 |
-
"
|
| 111 |
-
"
|
|
|
|
| 112 |
"step": 150
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.57,
|
| 116 |
-
"
|
| 117 |
-
"
|
|
|
|
| 118 |
"step": 160
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 1.67,
|
| 122 |
-
"
|
| 123 |
-
"
|
|
|
|
| 124 |
"step": 170
|
| 125 |
},
|
| 126 |
{
|
| 127 |
"epoch": 1.76,
|
| 128 |
-
"
|
| 129 |
-
"
|
|
|
|
| 130 |
"step": 180
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.86,
|
| 134 |
-
"
|
| 135 |
-
"
|
|
|
|
| 136 |
"step": 190
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 1.96,
|
| 140 |
-
"
|
| 141 |
-
"
|
|
|
|
| 142 |
"step": 200
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 1.96,
|
| 146 |
-
"eval_accuracy": 0.
|
| 147 |
-
"eval_auroc": 0.
|
| 148 |
-
"eval_f1": 0.
|
| 149 |
-
"eval_loss": 0.
|
| 150 |
-
"
|
| 151 |
-
"
|
| 152 |
-
"
|
| 153 |
-
"
|
| 154 |
-
"
|
|
|
|
|
|
|
|
|
|
| 155 |
"step": 200
|
| 156 |
},
|
| 157 |
{
|
| 158 |
-
"epoch": 2.
|
| 159 |
-
"
|
| 160 |
-
"
|
| 161 |
-
"
|
| 162 |
-
"
|
| 163 |
-
|
| 164 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 165 |
}
|
| 166 |
],
|
| 167 |
"logging_steps": 10,
|
| 168 |
-
"max_steps":
|
| 169 |
"num_input_tokens_seen": 0,
|
| 170 |
-
"num_train_epochs":
|
| 171 |
"save_steps": 100,
|
| 172 |
-
"total_flos":
|
| 173 |
"train_batch_size": 16,
|
| 174 |
"trial_name": null,
|
| 175 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8728268768516966,
|
| 3 |
+
"best_model_checkpoint": "stool-condition-classification/checkpoint-500",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1020,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.1,
|
| 13 |
+
"grad_norm": 7.584359169006348,
|
| 14 |
+
"learning_rate": 0.00019803921568627454,
|
| 15 |
+
"loss": 0.6059,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.2,
|
| 20 |
+
"grad_norm": 3.984663486480713,
|
| 21 |
+
"learning_rate": 0.000196078431372549,
|
| 22 |
+
"loss": 0.69,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.29,
|
| 27 |
+
"grad_norm": 5.750972270965576,
|
| 28 |
+
"learning_rate": 0.00019411764705882354,
|
| 29 |
+
"loss": 0.652,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.39,
|
| 34 |
+
"grad_norm": 5.540163993835449,
|
| 35 |
+
"learning_rate": 0.00019215686274509807,
|
| 36 |
+
"loss": 0.567,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.49,
|
| 41 |
+
"grad_norm": 12.890495300292969,
|
| 42 |
+
"learning_rate": 0.00019019607843137254,
|
| 43 |
+
"loss": 0.5255,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.59,
|
| 48 |
+
"grad_norm": 11.914591789245605,
|
| 49 |
+
"learning_rate": 0.00018823529411764707,
|
| 50 |
+
"loss": 0.5776,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.69,
|
| 55 |
+
"grad_norm": 8.995306015014648,
|
| 56 |
+
"learning_rate": 0.00018627450980392157,
|
| 57 |
+
"loss": 0.4868,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.78,
|
| 62 |
+
"grad_norm": 7.732036590576172,
|
| 63 |
+
"learning_rate": 0.00018431372549019607,
|
| 64 |
+
"loss": 0.6819,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.88,
|
| 69 |
+
"grad_norm": 9.876835823059082,
|
| 70 |
+
"learning_rate": 0.0001823529411764706,
|
| 71 |
+
"loss": 0.5809,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.98,
|
| 76 |
+
"grad_norm": 6.603707790374756,
|
| 77 |
+
"learning_rate": 0.0001803921568627451,
|
| 78 |
+
"loss": 0.5076,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.98,
|
| 83 |
+
"eval_accuracy": 0.7730870712401056,
|
| 84 |
+
"eval_auroc": 0.8537928335848846,
|
| 85 |
+
"eval_f1": 0.6906474820143884,
|
| 86 |
+
"eval_loss": 0.5360854268074036,
|
| 87 |
+
"eval_model_selection": 0.559226340209067,
|
| 88 |
+
"eval_npv": 0.7060931899641577,
|
| 89 |
+
"eval_ppv": 0.96,
|
| 90 |
+
"eval_runtime": 21.3071,
|
| 91 |
+
"eval_samples_per_second": 17.787,
|
| 92 |
+
"eval_sensitivity": 0.5393258426966292,
|
| 93 |
+
"eval_specificty": 0.9800995024875622,
|
| 94 |
+
"eval_steps_per_second": 2.253,
|
| 95 |
"step": 100
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 1.08,
|
| 99 |
+
"grad_norm": 2.871717929840088,
|
| 100 |
+
"learning_rate": 0.00017843137254901963,
|
| 101 |
+
"loss": 0.6088,
|
| 102 |
"step": 110
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 1.18,
|
| 106 |
+
"grad_norm": 7.064380645751953,
|
| 107 |
+
"learning_rate": 0.00017647058823529413,
|
| 108 |
+
"loss": 0.5249,
|
| 109 |
"step": 120
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 1.27,
|
| 113 |
+
"grad_norm": 4.083934307098389,
|
| 114 |
+
"learning_rate": 0.00017450980392156863,
|
| 115 |
+
"loss": 0.5367,
|
| 116 |
"step": 130
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 1.37,
|
| 120 |
+
"grad_norm": 1.9436535835266113,
|
| 121 |
+
"learning_rate": 0.00017254901960784316,
|
| 122 |
+
"loss": 0.4674,
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 1.47,
|
| 127 |
+
"grad_norm": 2.449876308441162,
|
| 128 |
+
"learning_rate": 0.00017058823529411766,
|
| 129 |
+
"loss": 0.5506,
|
| 130 |
"step": 150
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.57,
|
| 134 |
+
"grad_norm": 2.2175521850585938,
|
| 135 |
+
"learning_rate": 0.00016862745098039216,
|
| 136 |
+
"loss": 0.4266,
|
| 137 |
"step": 160
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.67,
|
| 141 |
+
"grad_norm": 1.2798587083816528,
|
| 142 |
+
"learning_rate": 0.0001666666666666667,
|
| 143 |
+
"loss": 0.483,
|
| 144 |
"step": 170
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.76,
|
| 148 |
+
"grad_norm": 4.6635847091674805,
|
| 149 |
+
"learning_rate": 0.0001647058823529412,
|
| 150 |
+
"loss": 0.5022,
|
| 151 |
"step": 180
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 1.86,
|
| 155 |
+
"grad_norm": 10.006440162658691,
|
| 156 |
+
"learning_rate": 0.0001627450980392157,
|
| 157 |
+
"loss": 0.5173,
|
| 158 |
"step": 190
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.96,
|
| 162 |
+
"grad_norm": 43.053401947021484,
|
| 163 |
+
"learning_rate": 0.00016078431372549022,
|
| 164 |
+
"loss": 0.4086,
|
| 165 |
"step": 200
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 1.96,
|
| 169 |
+
"eval_accuracy": 0.783641160949868,
|
| 170 |
+
"eval_auroc": 0.8727989267147409,
|
| 171 |
+
"eval_f1": 0.722972972972973,
|
| 172 |
+
"eval_loss": 0.48566874861717224,
|
| 173 |
+
"eval_model_selection": 0.655849963664822,
|
| 174 |
+
"eval_npv": 0.7279693486590039,
|
| 175 |
+
"eval_ppv": 0.9067796610169492,
|
| 176 |
+
"eval_runtime": 20.6546,
|
| 177 |
+
"eval_samples_per_second": 18.349,
|
| 178 |
+
"eval_sensitivity": 0.601123595505618,
|
| 179 |
+
"eval_specificty": 0.945273631840796,
|
| 180 |
+
"eval_steps_per_second": 2.324,
|
| 181 |
"step": 200
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 2.06,
|
| 185 |
+
"grad_norm": 6.759799957275391,
|
| 186 |
+
"learning_rate": 0.0001588235294117647,
|
| 187 |
+
"loss": 0.4347,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.16,
|
| 192 |
+
"grad_norm": 1.868139386177063,
|
| 193 |
+
"learning_rate": 0.00015686274509803922,
|
| 194 |
+
"loss": 0.4856,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.25,
|
| 199 |
+
"grad_norm": 6.924500465393066,
|
| 200 |
+
"learning_rate": 0.00015490196078431375,
|
| 201 |
+
"loss": 0.6559,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.35,
|
| 206 |
+
"grad_norm": 3.674975872039795,
|
| 207 |
+
"learning_rate": 0.00015294117647058822,
|
| 208 |
+
"loss": 0.4086,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.45,
|
| 213 |
+
"grad_norm": 3.160930633544922,
|
| 214 |
+
"learning_rate": 0.00015098039215686275,
|
| 215 |
+
"loss": 0.4172,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.55,
|
| 220 |
+
"grad_norm": 5.0961785316467285,
|
| 221 |
+
"learning_rate": 0.00014901960784313728,
|
| 222 |
+
"loss": 0.3948,
|
| 223 |
+
"step": 260
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.65,
|
| 227 |
+
"grad_norm": 3.1396780014038086,
|
| 228 |
+
"learning_rate": 0.00014705882352941178,
|
| 229 |
+
"loss": 0.3086,
|
| 230 |
+
"step": 270
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.75,
|
| 234 |
+
"grad_norm": 8.720426559448242,
|
| 235 |
+
"learning_rate": 0.00014509803921568628,
|
| 236 |
+
"loss": 0.5149,
|
| 237 |
+
"step": 280
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.84,
|
| 241 |
+
"grad_norm": 2.7797322273254395,
|
| 242 |
+
"learning_rate": 0.00014313725490196078,
|
| 243 |
+
"loss": 0.6524,
|
| 244 |
+
"step": 290
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.94,
|
| 248 |
+
"grad_norm": 8.662543296813965,
|
| 249 |
+
"learning_rate": 0.0001411764705882353,
|
| 250 |
+
"loss": 0.5208,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.94,
|
| 255 |
+
"eval_accuracy": 0.7598944591029023,
|
| 256 |
+
"eval_auroc": 0.8058862988428643,
|
| 257 |
+
"eval_f1": 0.7055016181229774,
|
| 258 |
+
"eval_loss": 0.5108699798583984,
|
| 259 |
+
"eval_model_selection": 0.7218122868802057,
|
| 260 |
+
"eval_npv": 0.7217741935483871,
|
| 261 |
+
"eval_ppv": 0.8320610687022901,
|
| 262 |
+
"eval_runtime": 20.396,
|
| 263 |
+
"eval_samples_per_second": 18.582,
|
| 264 |
+
"eval_sensitivity": 0.6123595505617978,
|
| 265 |
+
"eval_specificty": 0.8905472636815921,
|
| 266 |
+
"eval_steps_per_second": 2.353,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.04,
|
| 271 |
+
"grad_norm": 5.801065444946289,
|
| 272 |
+
"learning_rate": 0.0001392156862745098,
|
| 273 |
+
"loss": 0.4872,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.14,
|
| 278 |
+
"grad_norm": 4.54748010635376,
|
| 279 |
+
"learning_rate": 0.0001372549019607843,
|
| 280 |
+
"loss": 0.4804,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.24,
|
| 285 |
+
"grad_norm": 6.328420639038086,
|
| 286 |
+
"learning_rate": 0.00013529411764705884,
|
| 287 |
+
"loss": 0.5523,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.33,
|
| 292 |
+
"grad_norm": 2.860734462738037,
|
| 293 |
+
"learning_rate": 0.00013333333333333334,
|
| 294 |
+
"loss": 0.4061,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.43,
|
| 299 |
+
"grad_norm": 5.824751377105713,
|
| 300 |
+
"learning_rate": 0.00013137254901960784,
|
| 301 |
+
"loss": 0.4895,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.53,
|
| 306 |
+
"grad_norm": 1.802435278892517,
|
| 307 |
+
"learning_rate": 0.00012941176470588237,
|
| 308 |
+
"loss": 0.4011,
|
| 309 |
+
"step": 360
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.63,
|
| 313 |
+
"grad_norm": 2.1423304080963135,
|
| 314 |
+
"learning_rate": 0.00012745098039215687,
|
| 315 |
+
"loss": 0.3881,
|
| 316 |
+
"step": 370
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.73,
|
| 320 |
+
"grad_norm": 2.6464078426361084,
|
| 321 |
+
"learning_rate": 0.00012549019607843137,
|
| 322 |
+
"loss": 0.4371,
|
| 323 |
+
"step": 380
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.82,
|
| 327 |
+
"grad_norm": 1.5666183233261108,
|
| 328 |
+
"learning_rate": 0.0001235294117647059,
|
| 329 |
+
"loss": 0.4256,
|
| 330 |
+
"step": 390
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.92,
|
| 334 |
+
"grad_norm": 7.859738349914551,
|
| 335 |
+
"learning_rate": 0.00012156862745098039,
|
| 336 |
+
"loss": 0.474,
|
| 337 |
+
"step": 400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.92,
|
| 341 |
+
"eval_accuracy": 0.7994722955145118,
|
| 342 |
+
"eval_auroc": 0.8600536642629548,
|
| 343 |
+
"eval_f1": 0.7432432432432432,
|
| 344 |
+
"eval_loss": 0.5211557149887085,
|
| 345 |
+
"eval_model_selection": 0.6577785231147633,
|
| 346 |
+
"eval_npv": 0.7394636015325671,
|
| 347 |
+
"eval_ppv": 0.9322033898305084,
|
| 348 |
+
"eval_runtime": 20.1111,
|
| 349 |
+
"eval_samples_per_second": 18.845,
|
| 350 |
+
"eval_sensitivity": 0.6179775280898876,
|
| 351 |
+
"eval_specificty": 0.9601990049751243,
|
| 352 |
+
"eval_steps_per_second": 2.387,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.02,
|
| 357 |
+
"grad_norm": 5.231843948364258,
|
| 358 |
+
"learning_rate": 0.0001196078431372549,
|
| 359 |
+
"loss": 0.3969,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.12,
|
| 364 |
+
"grad_norm": 1.5469104051589966,
|
| 365 |
+
"learning_rate": 0.00011764705882352942,
|
| 366 |
+
"loss": 0.4781,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.22,
|
| 371 |
+
"grad_norm": 5.2077765464782715,
|
| 372 |
+
"learning_rate": 0.00011568627450980394,
|
| 373 |
+
"loss": 0.4261,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.31,
|
| 378 |
+
"grad_norm": 0.9990509748458862,
|
| 379 |
+
"learning_rate": 0.00011372549019607843,
|
| 380 |
+
"loss": 0.3773,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.41,
|
| 385 |
+
"grad_norm": 5.277149677276611,
|
| 386 |
+
"learning_rate": 0.00011176470588235294,
|
| 387 |
+
"loss": 0.4551,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.51,
|
| 392 |
+
"grad_norm": 1.3224270343780518,
|
| 393 |
+
"learning_rate": 0.00010980392156862746,
|
| 394 |
+
"loss": 0.3533,
|
| 395 |
+
"step": 460
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.61,
|
| 399 |
+
"grad_norm": 2.360970973968506,
|
| 400 |
+
"learning_rate": 0.00010784313725490196,
|
| 401 |
+
"loss": 0.4317,
|
| 402 |
+
"step": 470
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.71,
|
| 406 |
+
"grad_norm": 2.176283836364746,
|
| 407 |
+
"learning_rate": 0.00010588235294117647,
|
| 408 |
+
"loss": 0.4718,
|
| 409 |
+
"step": 480
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.8,
|
| 413 |
+
"grad_norm": 1.7329970598220825,
|
| 414 |
+
"learning_rate": 0.00010392156862745099,
|
| 415 |
+
"loss": 0.426,
|
| 416 |
+
"step": 490
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.9,
|
| 420 |
+
"grad_norm": 7.07577657699585,
|
| 421 |
+
"learning_rate": 0.00010196078431372549,
|
| 422 |
+
"loss": 0.4285,
|
| 423 |
+
"step": 500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.9,
|
| 427 |
+
"eval_accuracy": 0.7757255936675461,
|
| 428 |
+
"eval_auroc": 0.8728268768516966,
|
| 429 |
+
"eval_f1": 0.7578347578347578,
|
| 430 |
+
"eval_loss": 0.4510786235332489,
|
| 431 |
+
"eval_model_selection": 0.9461959863603332,
|
| 432 |
+
"eval_npv": 0.7815533980582524,
|
| 433 |
+
"eval_ppv": 0.7687861271676301,
|
| 434 |
+
"eval_runtime": 20.6194,
|
| 435 |
+
"eval_samples_per_second": 18.381,
|
| 436 |
+
"eval_sensitivity": 0.7471910112359551,
|
| 437 |
+
"eval_specificty": 0.8009950248756219,
|
| 438 |
+
"eval_steps_per_second": 2.328,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.0,
|
| 443 |
+
"grad_norm": 6.841150760650635,
|
| 444 |
+
"learning_rate": 0.0001,
|
| 445 |
+
"loss": 0.3839,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.1,
|
| 450 |
+
"grad_norm": 2.587709903717041,
|
| 451 |
+
"learning_rate": 9.80392156862745e-05,
|
| 452 |
+
"loss": 0.396,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.2,
|
| 457 |
+
"grad_norm": 2.148972272872925,
|
| 458 |
+
"learning_rate": 9.607843137254903e-05,
|
| 459 |
+
"loss": 0.3475,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.29,
|
| 464 |
+
"grad_norm": 6.0918803215026855,
|
| 465 |
+
"learning_rate": 9.411764705882353e-05,
|
| 466 |
+
"loss": 0.3433,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.39,
|
| 471 |
+
"grad_norm": 1.9835032224655151,
|
| 472 |
+
"learning_rate": 9.215686274509804e-05,
|
| 473 |
+
"loss": 0.3289,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.49,
|
| 478 |
+
"grad_norm": 1.912084698677063,
|
| 479 |
+
"learning_rate": 9.019607843137255e-05,
|
| 480 |
+
"loss": 0.3887,
|
| 481 |
+
"step": 560
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.59,
|
| 485 |
+
"grad_norm": 2.5347495079040527,
|
| 486 |
+
"learning_rate": 8.823529411764706e-05,
|
| 487 |
+
"loss": 0.4516,
|
| 488 |
+
"step": 570
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.69,
|
| 492 |
+
"grad_norm": 3.123342990875244,
|
| 493 |
+
"learning_rate": 8.627450980392158e-05,
|
| 494 |
+
"loss": 0.3973,
|
| 495 |
+
"step": 580
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.78,
|
| 499 |
+
"grad_norm": 6.096330165863037,
|
| 500 |
+
"learning_rate": 8.431372549019608e-05,
|
| 501 |
+
"loss": 0.3895,
|
| 502 |
+
"step": 590
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.88,
|
| 506 |
+
"grad_norm": 1.6143405437469482,
|
| 507 |
+
"learning_rate": 8.23529411764706e-05,
|
| 508 |
+
"loss": 0.3506,
|
| 509 |
+
"step": 600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.88,
|
| 513 |
+
"eval_accuracy": 0.8047493403693932,
|
| 514 |
+
"eval_auroc": 0.8691095086365922,
|
| 515 |
+
"eval_f1": 0.7658227848101267,
|
| 516 |
+
"eval_loss": 0.47164368629455566,
|
| 517 |
+
"eval_model_selection": 0.764352395326737,
|
| 518 |
+
"eval_npv": 0.7634854771784232,
|
| 519 |
+
"eval_ppv": 0.8768115942028986,
|
| 520 |
+
"eval_runtime": 20.5548,
|
| 521 |
+
"eval_samples_per_second": 18.438,
|
| 522 |
+
"eval_sensitivity": 0.6797752808988764,
|
| 523 |
+
"eval_specificty": 0.9154228855721394,
|
| 524 |
+
"eval_steps_per_second": 2.335,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 5.98,
|
| 529 |
+
"grad_norm": 2.3068525791168213,
|
| 530 |
+
"learning_rate": 8.039215686274511e-05,
|
| 531 |
+
"loss": 0.3566,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.08,
|
| 536 |
+
"grad_norm": 3.027449369430542,
|
| 537 |
+
"learning_rate": 7.843137254901961e-05,
|
| 538 |
+
"loss": 0.3662,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.18,
|
| 543 |
+
"grad_norm": 3.0861737728118896,
|
| 544 |
+
"learning_rate": 7.647058823529411e-05,
|
| 545 |
+
"loss": 0.4272,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.27,
|
| 550 |
+
"grad_norm": 2.3498377799987793,
|
| 551 |
+
"learning_rate": 7.450980392156864e-05,
|
| 552 |
+
"loss": 0.2825,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.37,
|
| 557 |
+
"grad_norm": 2.3852789402008057,
|
| 558 |
+
"learning_rate": 7.254901960784314e-05,
|
| 559 |
+
"loss": 0.361,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.47,
|
| 564 |
+
"grad_norm": 2.655799627304077,
|
| 565 |
+
"learning_rate": 7.058823529411765e-05,
|
| 566 |
+
"loss": 0.291,
|
| 567 |
+
"step": 660
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.57,
|
| 571 |
+
"grad_norm": 4.058769226074219,
|
| 572 |
+
"learning_rate": 6.862745098039216e-05,
|
| 573 |
+
"loss": 0.3045,
|
| 574 |
+
"step": 670
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.67,
|
| 578 |
+
"grad_norm": 4.20621919631958,
|
| 579 |
+
"learning_rate": 6.666666666666667e-05,
|
| 580 |
+
"loss": 0.3931,
|
| 581 |
+
"step": 680
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.76,
|
| 585 |
+
"grad_norm": 4.316690444946289,
|
| 586 |
+
"learning_rate": 6.470588235294118e-05,
|
| 587 |
+
"loss": 0.2858,
|
| 588 |
+
"step": 690
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.86,
|
| 592 |
+
"grad_norm": 3.3390917778015137,
|
| 593 |
+
"learning_rate": 6.274509803921569e-05,
|
| 594 |
+
"loss": 0.4239,
|
| 595 |
+
"step": 700
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 6.86,
|
| 599 |
+
"eval_accuracy": 0.8100263852242744,
|
| 600 |
+
"eval_auroc": 0.8517245234501649,
|
| 601 |
+
"eval_f1": 0.7677419354838709,
|
| 602 |
+
"eval_loss": 0.504310131072998,
|
| 603 |
+
"eval_model_selection": 0.7332159427581195,
|
| 604 |
+
"eval_npv": 0.7611336032388664,
|
| 605 |
+
"eval_ppv": 0.9015151515151515,
|
| 606 |
+
"eval_runtime": 20.9343,
|
| 607 |
+
"eval_samples_per_second": 18.104,
|
| 608 |
+
"eval_sensitivity": 0.6685393258426966,
|
| 609 |
+
"eval_specificty": 0.9353233830845771,
|
| 610 |
+
"eval_steps_per_second": 2.293,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.96,
|
| 615 |
+
"grad_norm": 3.034562587738037,
|
| 616 |
+
"learning_rate": 6.078431372549019e-05,
|
| 617 |
+
"loss": 0.3033,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.06,
|
| 622 |
+
"grad_norm": 0.7752771973609924,
|
| 623 |
+
"learning_rate": 5.882352941176471e-05,
|
| 624 |
+
"loss": 0.2963,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.16,
|
| 629 |
+
"grad_norm": 1.2533752918243408,
|
| 630 |
+
"learning_rate": 5.6862745098039215e-05,
|
| 631 |
+
"loss": 0.2974,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.25,
|
| 636 |
+
"grad_norm": 1.748043179512024,
|
| 637 |
+
"learning_rate": 5.490196078431373e-05,
|
| 638 |
+
"loss": 0.3549,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.35,
|
| 643 |
+
"grad_norm": 2.4874391555786133,
|
| 644 |
+
"learning_rate": 5.294117647058824e-05,
|
| 645 |
+
"loss": 0.413,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.45,
|
| 650 |
+
"grad_norm": 3.017951726913452,
|
| 651 |
+
"learning_rate": 5.0980392156862745e-05,
|
| 652 |
+
"loss": 0.2809,
|
| 653 |
+
"step": 760
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.55,
|
| 657 |
+
"grad_norm": 5.023625373840332,
|
| 658 |
+
"learning_rate": 4.901960784313725e-05,
|
| 659 |
+
"loss": 0.3603,
|
| 660 |
+
"step": 770
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.65,
|
| 664 |
+
"grad_norm": 2.754984140396118,
|
| 665 |
+
"learning_rate": 4.705882352941177e-05,
|
| 666 |
+
"loss": 0.2837,
|
| 667 |
+
"step": 780
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.75,
|
| 671 |
+
"grad_norm": 1.0377743244171143,
|
| 672 |
+
"learning_rate": 4.5098039215686275e-05,
|
| 673 |
+
"loss": 0.3169,
|
| 674 |
+
"step": 790
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.84,
|
| 678 |
+
"grad_norm": 4.163206100463867,
|
| 679 |
+
"learning_rate": 4.313725490196079e-05,
|
| 680 |
+
"loss": 0.2447,
|
| 681 |
+
"step": 800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 7.84,
|
| 685 |
+
"eval_accuracy": 0.8073878627968337,
|
| 686 |
+
"eval_auroc": 0.8591872100173291,
|
| 687 |
+
"eval_f1": 0.7711598746081505,
|
| 688 |
+
"eval_loss": 0.580413818359375,
|
| 689 |
+
"eval_model_selection": 0.7805634747610264,
|
| 690 |
+
"eval_npv": 0.7689075630252101,
|
| 691 |
+
"eval_ppv": 0.8723404255319149,
|
| 692 |
+
"eval_runtime": 20.1671,
|
| 693 |
+
"eval_samples_per_second": 18.793,
|
| 694 |
+
"eval_sensitivity": 0.6910112359550562,
|
| 695 |
+
"eval_specificty": 0.9104477611940298,
|
| 696 |
+
"eval_steps_per_second": 2.38,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 7.94,
|
| 701 |
+
"grad_norm": 3.30311918258667,
|
| 702 |
+
"learning_rate": 4.11764705882353e-05,
|
| 703 |
+
"loss": 0.3555,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.04,
|
| 708 |
+
"grad_norm": 4.967993259429932,
|
| 709 |
+
"learning_rate": 3.9215686274509805e-05,
|
| 710 |
+
"loss": 0.2679,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8.14,
|
| 715 |
+
"grad_norm": 4.838258266448975,
|
| 716 |
+
"learning_rate": 3.725490196078432e-05,
|
| 717 |
+
"loss": 0.2416,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 8.24,
|
| 722 |
+
"grad_norm": 4.202385425567627,
|
| 723 |
+
"learning_rate": 3.529411764705883e-05,
|
| 724 |
+
"loss": 0.1758,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 8.33,
|
| 729 |
+
"grad_norm": 3.0037460327148438,
|
| 730 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 731 |
+
"loss": 0.3192,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 8.43,
|
| 736 |
+
"grad_norm": 4.337649822235107,
|
| 737 |
+
"learning_rate": 3.137254901960784e-05,
|
| 738 |
+
"loss": 0.2669,
|
| 739 |
+
"step": 860
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 8.53,
|
| 743 |
+
"grad_norm": 6.011264801025391,
|
| 744 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 745 |
+
"loss": 0.228,
|
| 746 |
+
"step": 870
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.63,
|
| 750 |
+
"grad_norm": 0.5027784109115601,
|
| 751 |
+
"learning_rate": 2.7450980392156865e-05,
|
| 752 |
+
"loss": 0.3023,
|
| 753 |
+
"step": 880
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.73,
|
| 757 |
+
"grad_norm": 1.8822238445281982,
|
| 758 |
+
"learning_rate": 2.5490196078431373e-05,
|
| 759 |
+
"loss": 0.3109,
|
| 760 |
+
"step": 890
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 8.82,
|
| 764 |
+
"grad_norm": 3.6861536502838135,
|
| 765 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 766 |
+
"loss": 0.1739,
|
| 767 |
+
"step": 900
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 8.82,
|
| 771 |
+
"eval_accuracy": 0.8073878627968337,
|
| 772 |
+
"eval_auroc": 0.856224495500028,
|
| 773 |
+
"eval_f1": 0.7767584097859327,
|
| 774 |
+
"eval_loss": 0.6224877238273621,
|
| 775 |
+
"eval_model_selection": 0.8229358823858236,
|
| 776 |
+
"eval_npv": 0.7782608695652173,
|
| 777 |
+
"eval_ppv": 0.8523489932885906,
|
| 778 |
+
"eval_runtime": 20.4294,
|
| 779 |
+
"eval_samples_per_second": 18.552,
|
| 780 |
+
"eval_sensitivity": 0.7134831460674157,
|
| 781 |
+
"eval_specificty": 0.8905472636815921,
|
| 782 |
+
"eval_steps_per_second": 2.35,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 8.92,
|
| 787 |
+
"grad_norm": 5.0469770431518555,
|
| 788 |
+
"learning_rate": 2.1568627450980395e-05,
|
| 789 |
+
"loss": 0.4354,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9.02,
|
| 794 |
+
"grad_norm": 4.443832874298096,
|
| 795 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 796 |
+
"loss": 0.334,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 9.12,
|
| 801 |
+
"grad_norm": 2.0471107959747314,
|
| 802 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 803 |
+
"loss": 0.2051,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 9.22,
|
| 808 |
+
"grad_norm": 3.442962169647217,
|
| 809 |
+
"learning_rate": 1.568627450980392e-05,
|
| 810 |
+
"loss": 0.2112,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 9.31,
|
| 815 |
+
"grad_norm": 2.31436824798584,
|
| 816 |
+
"learning_rate": 1.3725490196078432e-05,
|
| 817 |
+
"loss": 0.3268,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.41,
|
| 822 |
+
"grad_norm": 2.2342071533203125,
|
| 823 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 824 |
+
"loss": 0.3107,
|
| 825 |
+
"step": 960
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 9.51,
|
| 829 |
+
"grad_norm": 3.2926645278930664,
|
| 830 |
+
"learning_rate": 9.803921568627451e-06,
|
| 831 |
+
"loss": 0.2284,
|
| 832 |
+
"step": 970
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 9.61,
|
| 836 |
+
"grad_norm": 2.639843702316284,
|
| 837 |
+
"learning_rate": 7.84313725490196e-06,
|
| 838 |
+
"loss": 0.2269,
|
| 839 |
+
"step": 980
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 9.71,
|
| 843 |
+
"grad_norm": 2.7015938758850098,
|
| 844 |
+
"learning_rate": 5.882352941176471e-06,
|
| 845 |
+
"loss": 0.1987,
|
| 846 |
+
"step": 990
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 9.8,
|
| 850 |
+
"grad_norm": 8.358205795288086,
|
| 851 |
+
"learning_rate": 3.92156862745098e-06,
|
| 852 |
+
"loss": 0.2888,
|
| 853 |
+
"step": 1000
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 9.8,
|
| 857 |
+
"eval_accuracy": 0.8047493403693932,
|
| 858 |
+
"eval_auroc": 0.856979149197831,
|
| 859 |
+
"eval_f1": 0.783625730994152,
|
| 860 |
+
"eval_loss": 0.5807113647460938,
|
| 861 |
+
"eval_model_selection": 0.9020627201073285,
|
| 862 |
+
"eval_npv": 0.7953488372093023,
|
| 863 |
+
"eval_ppv": 0.8170731707317073,
|
| 864 |
+
"eval_runtime": 20.5189,
|
| 865 |
+
"eval_samples_per_second": 18.471,
|
| 866 |
+
"eval_sensitivity": 0.7528089887640449,
|
| 867 |
+
"eval_specificty": 0.8507462686567164,
|
| 868 |
+
"eval_steps_per_second": 2.339,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 9.9,
|
| 873 |
+
"grad_norm": 3.527721881866455,
|
| 874 |
+
"learning_rate": 1.96078431372549e-06,
|
| 875 |
+
"loss": 0.3236,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 10.0,
|
| 880 |
+
"grad_norm": 6.274048805236816,
|
| 881 |
+
"learning_rate": 0.0,
|
| 882 |
+
"loss": 0.26,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 10.0,
|
| 887 |
+
"step": 1020,
|
| 888 |
+
"total_flos": 1.25924483123712e+18,
|
| 889 |
+
"train_loss": 0.40091259911948557,
|
| 890 |
+
"train_runtime": 1906.0636,
|
| 891 |
+
"train_samples_per_second": 8.525,
|
| 892 |
+
"train_steps_per_second": 0.535
|
| 893 |
}
|
| 894 |
],
|
| 895 |
"logging_steps": 10,
|
| 896 |
+
"max_steps": 1020,
|
| 897 |
"num_input_tokens_seen": 0,
|
| 898 |
+
"num_train_epochs": 10,
|
| 899 |
"save_steps": 100,
|
| 900 |
+
"total_flos": 1.25924483123712e+18,
|
| 901 |
"train_batch_size": 16,
|
| 902 |
"trial_name": null,
|
| 903 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9b8681ac14df074d86effc7d88c047f14205bc1279b55ae26aecff241216142
|
| 3 |
+
size 4475
|