Commit
·
043ae68
1
Parent(s):
405a546
Add evaluation results and output files to model card
Browse files- README.md +25 -23
- checkpoint-199/config.json +22 -0
- checkpoint-199/model.safetensors +3 -0
- checkpoint-199/optimizer.pt +3 -0
- checkpoint-199/preprocessor_config.json +22 -0
- checkpoint-199/rng_state.pth +3 -0
- checkpoint-199/scheduler.pt +3 -0
- checkpoint-199/trainer_state.json +1654 -0
- checkpoint-199/training_args.bin +3 -0
- config.json +22 -0
- model.safetensors +3 -0
- pr_curve.png +0 -0
- preprocessor_config.json +22 -0
- roc_curve.png +0 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,31 +1,33 @@
|
|
| 1 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
|
| 3 |
-
|
| 4 |
|
| 5 |
-
|
| 6 |
-
|:---------|------------:|----------------:|---------:|-------------:|-----------:|---------------:|
|
| 7 |
-
| Junction | 58.4 | 24.4 | 41.46 | 26.47 | 0.32 | 0.19 |
|
| 8 |
-
| process | 89.19 | 6.13 | 90.39 | 3.86 | 0.59 | 0.08 |
|
| 9 |
-
| soma | 86.59 | 30.33 | 75.56 | 32.97 | 0.83 | 0.23 |
|
| 10 |
-
| spine | 34.17 | 11.99 | 39.31 | 13.12 | 0.24 | 0.16 |
|
| 11 |
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
|
| 14 |
|
| 15 |
-
|
| 16 |
-
|
| 17 |
-
| Total_area_of_neuronal_process_um^2 | 1.03571e+06 | 1.45047e+06 | 140.05% |
|
| 18 |
-
| Total_Length_of_neuronal_process_um | 81753.7 | 80088.4 | 97.96% |
|
| 19 |
-
| Total_Area_of_soma_um^2 | 170835 | 139919 | 81.90% |
|
| 20 |
-
| Number_of_soma_count | 50 | 34 | 68.00% |
|
| 21 |
-
| Number_of_spine_count | 783 | 432 | 55.17% |
|
| 22 |
-
| junctions_count | 521 | 280 | 53.74% |
|
| 23 |
-
| Total_area_of_spine_um^2 | 41147 | 17780 | 43.21% |
|
| 24 |
|
|
|
|
|
|
|
| 25 |
|
| 26 |
-
|
| 27 |
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: code
|
| 3 |
+
tags:
|
| 4 |
+
- binary-classification
|
| 5 |
+
- model
|
| 6 |
+
- evaluation
|
| 7 |
+
metrics:
|
| 8 |
+
- average_precision: 0.98
|
| 9 |
+
- roc_auc: 0.98
|
| 10 |
+
---
|
| 11 |
|
| 12 |
+
# Binary Classification Model
|
| 13 |
|
| 14 |
+
## Evaluation Results
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
+
**Average Precision:** 0.98
|
| 17 |
+
**ROC AUC:** 0.98
|
| 18 |
|
| 19 |
+
## Visualizations
|
| 20 |
|
| 21 |
+
### Precision-Recall Curve
|
| 22 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
+
### ROC Curve
|
| 25 |
+
|
| 26 |
|
| 27 |
+
## Output Files and Directories
|
| 28 |
|
| 29 |
+
- 📂 `checkpoint-171/`
|
| 30 |
+
- `config.json`
|
| 31 |
+
- `model.safetensors`
|
| 32 |
+
- `preprocessor_config.json`
|
| 33 |
+
- `training_args.bin`
|
checkpoint-199/config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"encoder_stride": 16,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.0,
|
| 9 |
+
"hidden_size": 256,
|
| 10 |
+
"image_size": 32,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 512,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"model_type": "vit",
|
| 15 |
+
"num_attention_heads": 8,
|
| 16 |
+
"num_channels": 3,
|
| 17 |
+
"num_hidden_layers": 4,
|
| 18 |
+
"patch_size": 4,
|
| 19 |
+
"qkv_bias": true,
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.46.1"
|
| 22 |
+
}
|
checkpoint-199/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e038390c61e87b5b67e84acb968d1db02cfc13b82678551adf4c37ef03162405
|
| 3 |
+
size 8563512
|
checkpoint-199/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0a9a60294c69a856395777421eccf556c6cf6c0b1f56cec8584da5831a5ef8e
|
| 3 |
+
size 17153530
|
checkpoint-199/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": false,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 32,
|
| 20 |
+
"width": 32
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-199/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ae1fb4052d4de61fb4cd40977b3e3504e7ae57cbd0696e5c94bde2e90cb6ddc
|
| 3 |
+
size 14244
|
checkpoint-199/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8caed1b9de858a161f32ae36794e9be9167d8eead9a90b52f1f5f9c61b79b73
|
| 3 |
+
size 1000
|
checkpoint-199/trainer_state.json
ADDED
|
@@ -0,0 +1,1654 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9551900170164492,
|
| 3 |
+
"best_model_checkpoint": "/tmp/logs/binary_classification_model_v3.1.3_spines/checkpoint-199",
|
| 4 |
+
"epoch": 18.952380952380953,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 199,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09523809523809523,
|
| 13 |
+
"grad_norm": 7.660887718200684,
|
| 14 |
+
"learning_rate": 2.3638426626323753e-07,
|
| 15 |
+
"loss": 1.3862,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.19047619047619047,
|
| 20 |
+
"grad_norm": 7.8605637550354,
|
| 21 |
+
"learning_rate": 4.7276853252647506e-07,
|
| 22 |
+
"loss": 1.3906,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2857142857142857,
|
| 27 |
+
"grad_norm": 7.425328254699707,
|
| 28 |
+
"learning_rate": 7.091527987897125e-07,
|
| 29 |
+
"loss": 1.3872,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.38095238095238093,
|
| 34 |
+
"grad_norm": 8.001948356628418,
|
| 35 |
+
"learning_rate": 9.455370650529501e-07,
|
| 36 |
+
"loss": 1.3953,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.47619047619047616,
|
| 41 |
+
"grad_norm": 7.028316020965576,
|
| 42 |
+
"learning_rate": 1.1819213313161877e-06,
|
| 43 |
+
"loss": 1.3767,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5714285714285714,
|
| 48 |
+
"grad_norm": 8.270072937011719,
|
| 49 |
+
"learning_rate": 1.418305597579425e-06,
|
| 50 |
+
"loss": 1.3923,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6666666666666666,
|
| 55 |
+
"grad_norm": 6.689312934875488,
|
| 56 |
+
"learning_rate": 1.6546898638426627e-06,
|
| 57 |
+
"loss": 1.3705,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7619047619047619,
|
| 62 |
+
"grad_norm": 6.135200023651123,
|
| 63 |
+
"learning_rate": 1.8910741301059002e-06,
|
| 64 |
+
"loss": 1.3565,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8571428571428571,
|
| 69 |
+
"grad_norm": 8.940109252929688,
|
| 70 |
+
"learning_rate": 2.1274583963691376e-06,
|
| 71 |
+
"loss": 1.3878,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9523809523809523,
|
| 76 |
+
"grad_norm": 6.393802642822266,
|
| 77 |
+
"learning_rate": 2.3638426626323754e-06,
|
| 78 |
+
"loss": 1.3574,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.9523809523809523,
|
| 83 |
+
"eval_accuracy": 0.4685195689166194,
|
| 84 |
+
"eval_f1": 0.06487025948103792,
|
| 85 |
+
"eval_loss": 0.6748560667037964,
|
| 86 |
+
"eval_precision": 0.8441558441558441,
|
| 87 |
+
"eval_recall": 0.033731188375713546,
|
| 88 |
+
"eval_runtime": 1.3169,
|
| 89 |
+
"eval_samples_per_second": 2677.519,
|
| 90 |
+
"eval_steps_per_second": 5.316,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.0476190476190477,
|
| 95 |
+
"grad_norm": 6.996933460235596,
|
| 96 |
+
"learning_rate": 2.6002269288956128e-06,
|
| 97 |
+
"loss": 1.3588,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.1428571428571428,
|
| 102 |
+
"grad_norm": 6.011860370635986,
|
| 103 |
+
"learning_rate": 2.83661119515885e-06,
|
| 104 |
+
"loss": 1.3416,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.2380952380952381,
|
| 109 |
+
"grad_norm": 5.889338970184326,
|
| 110 |
+
"learning_rate": 3.072995461422088e-06,
|
| 111 |
+
"loss": 1.332,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.3333333333333333,
|
| 116 |
+
"grad_norm": 6.827754497528076,
|
| 117 |
+
"learning_rate": 3.3093797276853253e-06,
|
| 118 |
+
"loss": 1.3126,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.4285714285714286,
|
| 123 |
+
"grad_norm": 5.948705673217773,
|
| 124 |
+
"learning_rate": 3.5457639939485627e-06,
|
| 125 |
+
"loss": 1.3136,
|
| 126 |
+
"step": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.5238095238095237,
|
| 130 |
+
"grad_norm": 6.010759353637695,
|
| 131 |
+
"learning_rate": 3.7821482602118005e-06,
|
| 132 |
+
"loss": 1.3005,
|
| 133 |
+
"step": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.619047619047619,
|
| 137 |
+
"grad_norm": 6.178908348083496,
|
| 138 |
+
"learning_rate": 4.018532526475038e-06,
|
| 139 |
+
"loss": 1.284,
|
| 140 |
+
"step": 17
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.7142857142857144,
|
| 144 |
+
"grad_norm": 6.173403263092041,
|
| 145 |
+
"learning_rate": 4.254916792738275e-06,
|
| 146 |
+
"loss": 1.2685,
|
| 147 |
+
"step": 18
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.8095238095238095,
|
| 151 |
+
"grad_norm": 6.157512187957764,
|
| 152 |
+
"learning_rate": 4.491301059001513e-06,
|
| 153 |
+
"loss": 1.2557,
|
| 154 |
+
"step": 19
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.9047619047619047,
|
| 158 |
+
"grad_norm": 5.948299407958984,
|
| 159 |
+
"learning_rate": 4.727685325264751e-06,
|
| 160 |
+
"loss": 1.2436,
|
| 161 |
+
"step": 20
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.0,
|
| 165 |
+
"grad_norm": 6.165926456451416,
|
| 166 |
+
"learning_rate": 4.964069591527988e-06,
|
| 167 |
+
"loss": 1.23,
|
| 168 |
+
"step": 21
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.0,
|
| 172 |
+
"eval_accuracy": 0.6522972206466251,
|
| 173 |
+
"eval_f1": 0.5411676646706587,
|
| 174 |
+
"eval_loss": 0.6032947301864624,
|
| 175 |
+
"eval_precision": 0.9704697986577181,
|
| 176 |
+
"eval_recall": 0.3751946030098599,
|
| 177 |
+
"eval_runtime": 1.3834,
|
| 178 |
+
"eval_samples_per_second": 2548.746,
|
| 179 |
+
"eval_steps_per_second": 5.06,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.0952380952380953,
|
| 184 |
+
"grad_norm": 5.9527692794799805,
|
| 185 |
+
"learning_rate": 5.2004538577912256e-06,
|
| 186 |
+
"loss": 1.2083,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 2.1904761904761907,
|
| 191 |
+
"grad_norm": 6.154186248779297,
|
| 192 |
+
"learning_rate": 5.436838124054463e-06,
|
| 193 |
+
"loss": 1.1836,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.2857142857142856,
|
| 198 |
+
"grad_norm": 6.162223815917969,
|
| 199 |
+
"learning_rate": 5.6732223903177e-06,
|
| 200 |
+
"loss": 1.1612,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.380952380952381,
|
| 205 |
+
"grad_norm": 7.118120193481445,
|
| 206 |
+
"learning_rate": 5.909606656580938e-06,
|
| 207 |
+
"loss": 1.1487,
|
| 208 |
+
"step": 25
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.4761904761904763,
|
| 212 |
+
"grad_norm": 6.412310600280762,
|
| 213 |
+
"learning_rate": 6.145990922844176e-06,
|
| 214 |
+
"loss": 1.1273,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.571428571428571,
|
| 219 |
+
"grad_norm": 7.129715442657471,
|
| 220 |
+
"learning_rate": 6.382375189107413e-06,
|
| 221 |
+
"loss": 1.0988,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.6666666666666665,
|
| 226 |
+
"grad_norm": 7.162744045257568,
|
| 227 |
+
"learning_rate": 6.618759455370651e-06,
|
| 228 |
+
"loss": 1.0828,
|
| 229 |
+
"step": 28
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.761904761904762,
|
| 233 |
+
"grad_norm": 6.886769771575928,
|
| 234 |
+
"learning_rate": 6.855143721633888e-06,
|
| 235 |
+
"loss": 1.031,
|
| 236 |
+
"step": 29
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.857142857142857,
|
| 240 |
+
"grad_norm": 6.8288116455078125,
|
| 241 |
+
"learning_rate": 7.091527987897125e-06,
|
| 242 |
+
"loss": 1.0444,
|
| 243 |
+
"step": 30
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.9523809523809526,
|
| 247 |
+
"grad_norm": 7.310290813446045,
|
| 248 |
+
"learning_rate": 7.327912254160363e-06,
|
| 249 |
+
"loss": 0.9711,
|
| 250 |
+
"step": 31
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.9523809523809526,
|
| 254 |
+
"eval_accuracy": 0.8352240499149177,
|
| 255 |
+
"eval_f1": 0.8288659793814434,
|
| 256 |
+
"eval_loss": 0.47438114881515503,
|
| 257 |
+
"eval_precision": 0.9584468664850136,
|
| 258 |
+
"eval_recall": 0.7301504929942917,
|
| 259 |
+
"eval_runtime": 1.4139,
|
| 260 |
+
"eval_samples_per_second": 2493.834,
|
| 261 |
+
"eval_steps_per_second": 4.951,
|
| 262 |
+
"step": 31
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.0476190476190474,
|
| 266 |
+
"grad_norm": 7.928469181060791,
|
| 267 |
+
"learning_rate": 7.564296520423601e-06,
|
| 268 |
+
"loss": 0.917,
|
| 269 |
+
"step": 32
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.142857142857143,
|
| 273 |
+
"grad_norm": 7.226131916046143,
|
| 274 |
+
"learning_rate": 7.800680786686839e-06,
|
| 275 |
+
"loss": 0.9208,
|
| 276 |
+
"step": 33
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.238095238095238,
|
| 280 |
+
"grad_norm": 7.905109405517578,
|
| 281 |
+
"learning_rate": 8.037065052950077e-06,
|
| 282 |
+
"loss": 0.8691,
|
| 283 |
+
"step": 34
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 3.3333333333333335,
|
| 287 |
+
"grad_norm": 8.671666145324707,
|
| 288 |
+
"learning_rate": 8.273449319213313e-06,
|
| 289 |
+
"loss": 0.8107,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.4285714285714284,
|
| 294 |
+
"grad_norm": 8.270254135131836,
|
| 295 |
+
"learning_rate": 8.50983358547655e-06,
|
| 296 |
+
"loss": 0.7909,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.5238095238095237,
|
| 301 |
+
"grad_norm": 7.743439197540283,
|
| 302 |
+
"learning_rate": 8.746217851739788e-06,
|
| 303 |
+
"loss": 0.7574,
|
| 304 |
+
"step": 37
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 3.619047619047619,
|
| 308 |
+
"grad_norm": 8.699736595153809,
|
| 309 |
+
"learning_rate": 8.982602118003026e-06,
|
| 310 |
+
"loss": 0.6871,
|
| 311 |
+
"step": 38
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 3.7142857142857144,
|
| 315 |
+
"grad_norm": 8.724274635314941,
|
| 316 |
+
"learning_rate": 9.218986384266264e-06,
|
| 317 |
+
"loss": 0.6753,
|
| 318 |
+
"step": 39
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 3.8095238095238093,
|
| 322 |
+
"grad_norm": 7.583622932434082,
|
| 323 |
+
"learning_rate": 9.455370650529502e-06,
|
| 324 |
+
"loss": 0.5942,
|
| 325 |
+
"step": 40
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.9047619047619047,
|
| 329 |
+
"grad_norm": 7.553926467895508,
|
| 330 |
+
"learning_rate": 9.69175491679274e-06,
|
| 331 |
+
"loss": 0.5591,
|
| 332 |
+
"step": 41
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.0,
|
| 336 |
+
"grad_norm": 9.125824928283691,
|
| 337 |
+
"learning_rate": 9.928139183055976e-06,
|
| 338 |
+
"loss": 0.5089,
|
| 339 |
+
"step": 42
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.0,
|
| 343 |
+
"eval_accuracy": 0.9259784458309699,
|
| 344 |
+
"eval_f1": 0.9310071371927042,
|
| 345 |
+
"eval_loss": 0.24063928425312042,
|
| 346 |
+
"eval_precision": 0.9488146551724138,
|
| 347 |
+
"eval_recall": 0.9138557343020238,
|
| 348 |
+
"eval_runtime": 1.4208,
|
| 349 |
+
"eval_samples_per_second": 2481.618,
|
| 350 |
+
"eval_steps_per_second": 4.927,
|
| 351 |
+
"step": 42
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.095238095238095,
|
| 355 |
+
"grad_norm": 8.034770965576172,
|
| 356 |
+
"learning_rate": 1.0164523449319213e-05,
|
| 357 |
+
"loss": 0.4586,
|
| 358 |
+
"step": 43
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.190476190476191,
|
| 362 |
+
"grad_norm": 7.927157402038574,
|
| 363 |
+
"learning_rate": 1.0400907715582451e-05,
|
| 364 |
+
"loss": 0.446,
|
| 365 |
+
"step": 44
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 4.285714285714286,
|
| 369 |
+
"grad_norm": 5.977870464324951,
|
| 370 |
+
"learning_rate": 1.0637291981845689e-05,
|
| 371 |
+
"loss": 0.3851,
|
| 372 |
+
"step": 45
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 4.380952380952381,
|
| 376 |
+
"grad_norm": 5.682313919067383,
|
| 377 |
+
"learning_rate": 1.0873676248108927e-05,
|
| 378 |
+
"loss": 0.3767,
|
| 379 |
+
"step": 46
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 4.476190476190476,
|
| 383 |
+
"grad_norm": 8.96394157409668,
|
| 384 |
+
"learning_rate": 1.1110060514372165e-05,
|
| 385 |
+
"loss": 0.3524,
|
| 386 |
+
"step": 47
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 4.571428571428571,
|
| 390 |
+
"grad_norm": 3.3059632778167725,
|
| 391 |
+
"learning_rate": 1.13464447806354e-05,
|
| 392 |
+
"loss": 0.356,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.666666666666667,
|
| 397 |
+
"grad_norm": 3.398942232131958,
|
| 398 |
+
"learning_rate": 1.1582829046898638e-05,
|
| 399 |
+
"loss": 0.3705,
|
| 400 |
+
"step": 49
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 4.761904761904762,
|
| 404 |
+
"grad_norm": 14.366640090942383,
|
| 405 |
+
"learning_rate": 1.1819213313161876e-05,
|
| 406 |
+
"loss": 0.359,
|
| 407 |
+
"step": 50
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.857142857142857,
|
| 411 |
+
"grad_norm": 3.9985570907592773,
|
| 412 |
+
"learning_rate": 1.2055597579425114e-05,
|
| 413 |
+
"loss": 0.3247,
|
| 414 |
+
"step": 51
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 4.9523809523809526,
|
| 418 |
+
"grad_norm": 1.7626423835754395,
|
| 419 |
+
"learning_rate": 1.2291981845688352e-05,
|
| 420 |
+
"loss": 0.3413,
|
| 421 |
+
"step": 52
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 4.9523809523809526,
|
| 425 |
+
"eval_accuracy": 0.9458309699376064,
|
| 426 |
+
"eval_f1": 0.9516333248923778,
|
| 427 |
+
"eval_loss": 0.16178017854690552,
|
| 428 |
+
"eval_precision": 0.9292779426310583,
|
| 429 |
+
"eval_recall": 0.9750908147379346,
|
| 430 |
+
"eval_runtime": 1.4923,
|
| 431 |
+
"eval_samples_per_second": 2362.749,
|
| 432 |
+
"eval_steps_per_second": 4.691,
|
| 433 |
+
"step": 52
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.0476190476190474,
|
| 437 |
+
"grad_norm": 9.635331153869629,
|
| 438 |
+
"learning_rate": 1.252836611195159e-05,
|
| 439 |
+
"loss": 0.3447,
|
| 440 |
+
"step": 53
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.142857142857143,
|
| 444 |
+
"grad_norm": 9.173269271850586,
|
| 445 |
+
"learning_rate": 1.2764750378214826e-05,
|
| 446 |
+
"loss": 0.2926,
|
| 447 |
+
"step": 54
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 5.238095238095238,
|
| 451 |
+
"grad_norm": 4.961584568023682,
|
| 452 |
+
"learning_rate": 1.3001134644478064e-05,
|
| 453 |
+
"loss": 0.3017,
|
| 454 |
+
"step": 55
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 5.333333333333333,
|
| 458 |
+
"grad_norm": 8.47139835357666,
|
| 459 |
+
"learning_rate": 1.3237518910741301e-05,
|
| 460 |
+
"loss": 0.3185,
|
| 461 |
+
"step": 56
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 5.428571428571429,
|
| 465 |
+
"grad_norm": 15.638015747070312,
|
| 466 |
+
"learning_rate": 1.3473903177004537e-05,
|
| 467 |
+
"loss": 0.3635,
|
| 468 |
+
"step": 57
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 5.523809523809524,
|
| 472 |
+
"grad_norm": 19.919715881347656,
|
| 473 |
+
"learning_rate": 1.3710287443267775e-05,
|
| 474 |
+
"loss": 0.3548,
|
| 475 |
+
"step": 58
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 5.619047619047619,
|
| 479 |
+
"grad_norm": 12.047982215881348,
|
| 480 |
+
"learning_rate": 1.3946671709531013e-05,
|
| 481 |
+
"loss": 0.2986,
|
| 482 |
+
"step": 59
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 5.714285714285714,
|
| 486 |
+
"grad_norm": 9.26185417175293,
|
| 487 |
+
"learning_rate": 1.418305597579425e-05,
|
| 488 |
+
"loss": 0.3545,
|
| 489 |
+
"step": 60
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 5.809523809523809,
|
| 493 |
+
"grad_norm": 7.966272354125977,
|
| 494 |
+
"learning_rate": 1.4419440242057489e-05,
|
| 495 |
+
"loss": 0.3448,
|
| 496 |
+
"step": 61
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 5.904761904761905,
|
| 500 |
+
"grad_norm": 4.883288383483887,
|
| 501 |
+
"learning_rate": 1.4655824508320726e-05,
|
| 502 |
+
"loss": 0.3225,
|
| 503 |
+
"step": 62
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 6.0,
|
| 507 |
+
"grad_norm": 3.2868356704711914,
|
| 508 |
+
"learning_rate": 1.4892208774583964e-05,
|
| 509 |
+
"loss": 0.3122,
|
| 510 |
+
"step": 63
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 6.0,
|
| 514 |
+
"eval_accuracy": 0.9480998298355077,
|
| 515 |
+
"eval_f1": 0.9533995416348358,
|
| 516 |
+
"eval_loss": 0.15449711680412292,
|
| 517 |
+
"eval_precision": 0.936,
|
| 518 |
+
"eval_recall": 0.97145822522055,
|
| 519 |
+
"eval_runtime": 1.4533,
|
| 520 |
+
"eval_samples_per_second": 2426.271,
|
| 521 |
+
"eval_steps_per_second": 4.817,
|
| 522 |
+
"step": 63
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 6.095238095238095,
|
| 526 |
+
"grad_norm": 4.3472418785095215,
|
| 527 |
+
"learning_rate": 1.5128593040847202e-05,
|
| 528 |
+
"loss": 0.3173,
|
| 529 |
+
"step": 64
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 6.190476190476191,
|
| 533 |
+
"grad_norm": 7.455476760864258,
|
| 534 |
+
"learning_rate": 1.536497730711044e-05,
|
| 535 |
+
"loss": 0.3193,
|
| 536 |
+
"step": 65
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 6.285714285714286,
|
| 540 |
+
"grad_norm": 2.1543610095977783,
|
| 541 |
+
"learning_rate": 1.5601361573373678e-05,
|
| 542 |
+
"loss": 0.3161,
|
| 543 |
+
"step": 66
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 6.380952380952381,
|
| 547 |
+
"grad_norm": 4.938283443450928,
|
| 548 |
+
"learning_rate": 1.5837745839636915e-05,
|
| 549 |
+
"loss": 0.3123,
|
| 550 |
+
"step": 67
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 6.476190476190476,
|
| 554 |
+
"grad_norm": 20.372398376464844,
|
| 555 |
+
"learning_rate": 1.6074130105900153e-05,
|
| 556 |
+
"loss": 0.3585,
|
| 557 |
+
"step": 68
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 6.571428571428571,
|
| 561 |
+
"grad_norm": 22.94089126586914,
|
| 562 |
+
"learning_rate": 1.631051437216339e-05,
|
| 563 |
+
"loss": 0.3085,
|
| 564 |
+
"step": 69
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 6.666666666666667,
|
| 568 |
+
"grad_norm": 24.728063583374023,
|
| 569 |
+
"learning_rate": 1.6546898638426625e-05,
|
| 570 |
+
"loss": 0.3043,
|
| 571 |
+
"step": 70
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 6.761904761904762,
|
| 575 |
+
"grad_norm": 20.080245971679688,
|
| 576 |
+
"learning_rate": 1.6783282904689863e-05,
|
| 577 |
+
"loss": 0.32,
|
| 578 |
+
"step": 71
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 6.857142857142857,
|
| 582 |
+
"grad_norm": 3.566037654876709,
|
| 583 |
+
"learning_rate": 1.70196671709531e-05,
|
| 584 |
+
"loss": 0.299,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 6.9523809523809526,
|
| 589 |
+
"grad_norm": 7.544285774230957,
|
| 590 |
+
"learning_rate": 1.725605143721634e-05,
|
| 591 |
+
"loss": 0.2686,
|
| 592 |
+
"step": 73
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 6.9523809523809526,
|
| 596 |
+
"eval_accuracy": 0.9483834373227453,
|
| 597 |
+
"eval_f1": 0.9540636042402827,
|
| 598 |
+
"eval_loss": 0.15292148292064667,
|
| 599 |
+
"eval_precision": 0.9287469287469288,
|
| 600 |
+
"eval_recall": 0.9807991696938246,
|
| 601 |
+
"eval_runtime": 1.7283,
|
| 602 |
+
"eval_samples_per_second": 2040.192,
|
| 603 |
+
"eval_steps_per_second": 4.05,
|
| 604 |
+
"step": 73
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.0476190476190474,
|
| 608 |
+
"grad_norm": 3.4655869007110596,
|
| 609 |
+
"learning_rate": 1.7492435703479577e-05,
|
| 610 |
+
"loss": 0.3314,
|
| 611 |
+
"step": 74
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.142857142857143,
|
| 615 |
+
"grad_norm": 3.0674173831939697,
|
| 616 |
+
"learning_rate": 1.7728819969742814e-05,
|
| 617 |
+
"loss": 0.3125,
|
| 618 |
+
"step": 75
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.238095238095238,
|
| 622 |
+
"grad_norm": 11.51699447631836,
|
| 623 |
+
"learning_rate": 1.7965204236006052e-05,
|
| 624 |
+
"loss": 0.3565,
|
| 625 |
+
"step": 76
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.333333333333333,
|
| 629 |
+
"grad_norm": 22.48113250732422,
|
| 630 |
+
"learning_rate": 1.820158850226929e-05,
|
| 631 |
+
"loss": 0.3426,
|
| 632 |
+
"step": 77
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.428571428571429,
|
| 636 |
+
"grad_norm": 16.08379364013672,
|
| 637 |
+
"learning_rate": 1.8437972768532528e-05,
|
| 638 |
+
"loss": 0.3174,
|
| 639 |
+
"step": 78
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.523809523809524,
|
| 643 |
+
"grad_norm": 11.77773666381836,
|
| 644 |
+
"learning_rate": 1.8674357034795766e-05,
|
| 645 |
+
"loss": 0.3563,
|
| 646 |
+
"step": 79
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.619047619047619,
|
| 650 |
+
"grad_norm": 3.944478988647461,
|
| 651 |
+
"learning_rate": 1.8910741301059003e-05,
|
| 652 |
+
"loss": 0.3094,
|
| 653 |
+
"step": 80
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.714285714285714,
|
| 657 |
+
"grad_norm": 15.91480827331543,
|
| 658 |
+
"learning_rate": 1.914712556732224e-05,
|
| 659 |
+
"loss": 0.3333,
|
| 660 |
+
"step": 81
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.809523809523809,
|
| 664 |
+
"grad_norm": 23.406877517700195,
|
| 665 |
+
"learning_rate": 1.938350983358548e-05,
|
| 666 |
+
"loss": 0.4276,
|
| 667 |
+
"step": 82
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.904761904761905,
|
| 671 |
+
"grad_norm": 24.73318862915039,
|
| 672 |
+
"learning_rate": 1.9619894099848717e-05,
|
| 673 |
+
"loss": 0.399,
|
| 674 |
+
"step": 83
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 8.0,
|
| 678 |
+
"grad_norm": 15.897306442260742,
|
| 679 |
+
"learning_rate": 1.985627836611195e-05,
|
| 680 |
+
"loss": 0.3178,
|
| 681 |
+
"step": 84
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 8.0,
|
| 685 |
+
"eval_accuracy": 0.9458309699376064,
|
| 686 |
+
"eval_f1": 0.9523809523809523,
|
| 687 |
+
"eval_loss": 0.16457624733448029,
|
| 688 |
+
"eval_precision": 0.9165067178502879,
|
| 689 |
+
"eval_recall": 0.9911779968863519,
|
| 690 |
+
"eval_runtime": 1.5006,
|
| 691 |
+
"eval_samples_per_second": 2349.701,
|
| 692 |
+
"eval_steps_per_second": 4.665,
|
| 693 |
+
"step": 84
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 8.095238095238095,
|
| 697 |
+
"grad_norm": 12.876022338867188,
|
| 698 |
+
"learning_rate": 2.0092662632375192e-05,
|
| 699 |
+
"loss": 0.2793,
|
| 700 |
+
"step": 85
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 8.19047619047619,
|
| 704 |
+
"grad_norm": 2.7764549255371094,
|
| 705 |
+
"learning_rate": 2.0329046898638427e-05,
|
| 706 |
+
"loss": 0.2746,
|
| 707 |
+
"step": 86
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 8.285714285714286,
|
| 711 |
+
"grad_norm": 9.225512504577637,
|
| 712 |
+
"learning_rate": 2.0565431164901664e-05,
|
| 713 |
+
"loss": 0.3127,
|
| 714 |
+
"step": 87
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 8.380952380952381,
|
| 718 |
+
"grad_norm": 20.002197265625,
|
| 719 |
+
"learning_rate": 2.0801815431164902e-05,
|
| 720 |
+
"loss": 0.2829,
|
| 721 |
+
"step": 88
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 8.476190476190476,
|
| 725 |
+
"grad_norm": 12.510419845581055,
|
| 726 |
+
"learning_rate": 2.103819969742814e-05,
|
| 727 |
+
"loss": 0.3139,
|
| 728 |
+
"step": 89
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 8.571428571428571,
|
| 732 |
+
"grad_norm": 2.866379737854004,
|
| 733 |
+
"learning_rate": 2.1274583963691378e-05,
|
| 734 |
+
"loss": 0.3587,
|
| 735 |
+
"step": 90
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 8.666666666666666,
|
| 739 |
+
"grad_norm": 2.67472767829895,
|
| 740 |
+
"learning_rate": 2.1510968229954616e-05,
|
| 741 |
+
"loss": 0.2559,
|
| 742 |
+
"step": 91
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 8.761904761904763,
|
| 746 |
+
"grad_norm": 13.37243366241455,
|
| 747 |
+
"learning_rate": 2.1747352496217853e-05,
|
| 748 |
+
"loss": 0.3146,
|
| 749 |
+
"step": 92
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 8.857142857142858,
|
| 753 |
+
"grad_norm": 8.157402992248535,
|
| 754 |
+
"learning_rate": 2.1983736762481088e-05,
|
| 755 |
+
"loss": 0.3784,
|
| 756 |
+
"step": 93
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 8.952380952380953,
|
| 760 |
+
"grad_norm": 15.986899375915527,
|
| 761 |
+
"learning_rate": 2.222012102874433e-05,
|
| 762 |
+
"loss": 0.3194,
|
| 763 |
+
"step": 94
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 8.952380952380953,
|
| 767 |
+
"eval_accuracy": 0.946965399886557,
|
| 768 |
+
"eval_f1": 0.951940375224878,
|
| 769 |
+
"eval_loss": 0.15091940760612488,
|
| 770 |
+
"eval_precision": 0.9429735234215886,
|
| 771 |
+
"eval_recall": 0.9610793980280228,
|
| 772 |
+
"eval_runtime": 1.5047,
|
| 773 |
+
"eval_samples_per_second": 2343.38,
|
| 774 |
+
"eval_steps_per_second": 4.652,
|
| 775 |
+
"step": 94
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 9.047619047619047,
|
| 779 |
+
"grad_norm": 13.20091438293457,
|
| 780 |
+
"learning_rate": 2.2456505295007563e-05,
|
| 781 |
+
"loss": 0.3433,
|
| 782 |
+
"step": 95
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 9.142857142857142,
|
| 786 |
+
"grad_norm": 2.4314324855804443,
|
| 787 |
+
"learning_rate": 2.26928895612708e-05,
|
| 788 |
+
"loss": 0.3221,
|
| 789 |
+
"step": 96
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 9.238095238095237,
|
| 793 |
+
"grad_norm": 4.801822185516357,
|
| 794 |
+
"learning_rate": 2.292927382753404e-05,
|
| 795 |
+
"loss": 0.3143,
|
| 796 |
+
"step": 97
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 9.333333333333334,
|
| 800 |
+
"grad_norm": 5.851532936096191,
|
| 801 |
+
"learning_rate": 2.3165658093797277e-05,
|
| 802 |
+
"loss": 0.295,
|
| 803 |
+
"step": 98
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 9.428571428571429,
|
| 807 |
+
"grad_norm": 3.861736536026001,
|
| 808 |
+
"learning_rate": 2.3402042360060515e-05,
|
| 809 |
+
"loss": 0.3003,
|
| 810 |
+
"step": 99
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 9.523809523809524,
|
| 814 |
+
"grad_norm": 3.4719653129577637,
|
| 815 |
+
"learning_rate": 2.3638426626323752e-05,
|
| 816 |
+
"loss": 0.2526,
|
| 817 |
+
"step": 100
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 9.619047619047619,
|
| 821 |
+
"grad_norm": 5.870892524719238,
|
| 822 |
+
"learning_rate": 2.387481089258699e-05,
|
| 823 |
+
"loss": 0.2879,
|
| 824 |
+
"step": 101
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 9.714285714285714,
|
| 828 |
+
"grad_norm": 5.269529342651367,
|
| 829 |
+
"learning_rate": 2.4111195158850228e-05,
|
| 830 |
+
"loss": 0.3111,
|
| 831 |
+
"step": 102
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 9.80952380952381,
|
| 835 |
+
"grad_norm": 3.9850101470947266,
|
| 836 |
+
"learning_rate": 2.4347579425113466e-05,
|
| 837 |
+
"loss": 0.333,
|
| 838 |
+
"step": 103
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 9.904761904761905,
|
| 842 |
+
"grad_norm": 16.48617172241211,
|
| 843 |
+
"learning_rate": 2.4583963691376704e-05,
|
| 844 |
+
"loss": 0.347,
|
| 845 |
+
"step": 104
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 10.0,
|
| 849 |
+
"grad_norm": 20.063276290893555,
|
| 850 |
+
"learning_rate": 2.4820347957639938e-05,
|
| 851 |
+
"loss": 0.3186,
|
| 852 |
+
"step": 105
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 10.0,
|
| 856 |
+
"eval_accuracy": 0.9429948950652297,
|
| 857 |
+
"eval_f1": 0.9478057647364321,
|
| 858 |
+
"eval_loss": 0.15304207801818848,
|
| 859 |
+
"eval_precision": 0.9485446985446986,
|
| 860 |
+
"eval_recall": 0.9470679813181111,
|
| 861 |
+
"eval_runtime": 1.5347,
|
| 862 |
+
"eval_samples_per_second": 2297.479,
|
| 863 |
+
"eval_steps_per_second": 4.561,
|
| 864 |
+
"step": 105
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 10.095238095238095,
|
| 868 |
+
"grad_norm": 14.030604362487793,
|
| 869 |
+
"learning_rate": 2.505673222390318e-05,
|
| 870 |
+
"loss": 0.3345,
|
| 871 |
+
"step": 106
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 10.19047619047619,
|
| 875 |
+
"grad_norm": 8.608407020568848,
|
| 876 |
+
"learning_rate": 2.5293116490166414e-05,
|
| 877 |
+
"loss": 0.2998,
|
| 878 |
+
"step": 107
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 10.285714285714286,
|
| 882 |
+
"grad_norm": 13.165003776550293,
|
| 883 |
+
"learning_rate": 2.552950075642965e-05,
|
| 884 |
+
"loss": 0.2687,
|
| 885 |
+
"step": 108
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 10.380952380952381,
|
| 889 |
+
"grad_norm": 14.150562286376953,
|
| 890 |
+
"learning_rate": 2.576588502269289e-05,
|
| 891 |
+
"loss": 0.2553,
|
| 892 |
+
"step": 109
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 10.476190476190476,
|
| 896 |
+
"grad_norm": 21.196813583374023,
|
| 897 |
+
"learning_rate": 2.6002269288956127e-05,
|
| 898 |
+
"loss": 0.3232,
|
| 899 |
+
"step": 110
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 10.571428571428571,
|
| 903 |
+
"grad_norm": 6.832909107208252,
|
| 904 |
+
"learning_rate": 2.6238653555219365e-05,
|
| 905 |
+
"loss": 0.2842,
|
| 906 |
+
"step": 111
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 10.666666666666666,
|
| 910 |
+
"grad_norm": 1.0033546686172485,
|
| 911 |
+
"learning_rate": 2.6475037821482603e-05,
|
| 912 |
+
"loss": 0.2871,
|
| 913 |
+
"step": 112
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 10.761904761904763,
|
| 917 |
+
"grad_norm": 33.71710205078125,
|
| 918 |
+
"learning_rate": 2.671142208774584e-05,
|
| 919 |
+
"loss": 0.3478,
|
| 920 |
+
"step": 113
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 10.857142857142858,
|
| 924 |
+
"grad_norm": 50.65483474731445,
|
| 925 |
+
"learning_rate": 2.6947806354009075e-05,
|
| 926 |
+
"loss": 0.4764,
|
| 927 |
+
"step": 114
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 10.952380952380953,
|
| 931 |
+
"grad_norm": 54.59239196777344,
|
| 932 |
+
"learning_rate": 2.7184190620272316e-05,
|
| 933 |
+
"loss": 0.518,
|
| 934 |
+
"step": 115
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 10.952380952380953,
|
| 938 |
+
"eval_accuracy": 0.9194554736245036,
|
| 939 |
+
"eval_f1": 0.9237379162191193,
|
| 940 |
+
"eval_loss": 0.18742962181568146,
|
| 941 |
+
"eval_precision": 0.9571508069003896,
|
| 942 |
+
"eval_recall": 0.892579138557343,
|
| 943 |
+
"eval_runtime": 1.5556,
|
| 944 |
+
"eval_samples_per_second": 2266.683,
|
| 945 |
+
"eval_steps_per_second": 4.5,
|
| 946 |
+
"step": 115
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 11.047619047619047,
|
| 950 |
+
"grad_norm": 36.66478729248047,
|
| 951 |
+
"learning_rate": 2.742057488653555e-05,
|
| 952 |
+
"loss": 0.3506,
|
| 953 |
+
"step": 116
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 11.142857142857142,
|
| 957 |
+
"grad_norm": 15.977128982543945,
|
| 958 |
+
"learning_rate": 2.765695915279879e-05,
|
| 959 |
+
"loss": 0.3211,
|
| 960 |
+
"step": 117
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 11.238095238095237,
|
| 964 |
+
"grad_norm": 6.046239852905273,
|
| 965 |
+
"learning_rate": 2.7893343419062026e-05,
|
| 966 |
+
"loss": 0.3184,
|
| 967 |
+
"step": 118
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 11.333333333333334,
|
| 971 |
+
"grad_norm": 4.22792387008667,
|
| 972 |
+
"learning_rate": 2.8129727685325267e-05,
|
| 973 |
+
"loss": 0.2998,
|
| 974 |
+
"step": 119
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 11.428571428571429,
|
| 978 |
+
"grad_norm": 10.150542259216309,
|
| 979 |
+
"learning_rate": 2.83661119515885e-05,
|
| 980 |
+
"loss": 0.3248,
|
| 981 |
+
"step": 120
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 11.523809523809524,
|
| 985 |
+
"grad_norm": 6.277641773223877,
|
| 986 |
+
"learning_rate": 2.8602496217851743e-05,
|
| 987 |
+
"loss": 0.3321,
|
| 988 |
+
"step": 121
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 11.619047619047619,
|
| 992 |
+
"grad_norm": 5.486034393310547,
|
| 993 |
+
"learning_rate": 2.8838880484114977e-05,
|
| 994 |
+
"loss": 0.2872,
|
| 995 |
+
"step": 122
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 11.714285714285714,
|
| 999 |
+
"grad_norm": 14.875836372375488,
|
| 1000 |
+
"learning_rate": 2.907526475037821e-05,
|
| 1001 |
+
"loss": 0.2694,
|
| 1002 |
+
"step": 123
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 11.80952380952381,
|
| 1006 |
+
"grad_norm": 11.530607223510742,
|
| 1007 |
+
"learning_rate": 2.9311649016641453e-05,
|
| 1008 |
+
"loss": 0.261,
|
| 1009 |
+
"step": 124
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 11.904761904761905,
|
| 1013 |
+
"grad_norm": 1.041492223739624,
|
| 1014 |
+
"learning_rate": 2.9548033282904687e-05,
|
| 1015 |
+
"loss": 0.2602,
|
| 1016 |
+
"step": 125
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 12.0,
|
| 1020 |
+
"grad_norm": 7.879367828369141,
|
| 1021 |
+
"learning_rate": 2.978441754916793e-05,
|
| 1022 |
+
"loss": 0.3075,
|
| 1023 |
+
"step": 126
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 12.0,
|
| 1027 |
+
"eval_accuracy": 0.9512195121951219,
|
| 1028 |
+
"eval_f1": 0.9563894523326572,
|
| 1029 |
+
"eval_loss": 0.14357148110866547,
|
| 1030 |
+
"eval_precision": 0.9350520575111552,
|
| 1031 |
+
"eval_recall": 0.9787234042553191,
|
| 1032 |
+
"eval_runtime": 1.569,
|
| 1033 |
+
"eval_samples_per_second": 2247.276,
|
| 1034 |
+
"eval_steps_per_second": 4.461,
|
| 1035 |
+
"step": 126
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 12.095238095238095,
|
| 1039 |
+
"grad_norm": 2.177398443222046,
|
| 1040 |
+
"learning_rate": 3.0020801815431163e-05,
|
| 1041 |
+
"loss": 0.2702,
|
| 1042 |
+
"step": 127
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 12.19047619047619,
|
| 1046 |
+
"grad_norm": 14.060430526733398,
|
| 1047 |
+
"learning_rate": 3.0257186081694404e-05,
|
| 1048 |
+
"loss": 0.3227,
|
| 1049 |
+
"step": 128
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 12.285714285714286,
|
| 1053 |
+
"grad_norm": 9.275856018066406,
|
| 1054 |
+
"learning_rate": 3.049357034795764e-05,
|
| 1055 |
+
"loss": 0.2946,
|
| 1056 |
+
"step": 129
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 12.380952380952381,
|
| 1060 |
+
"grad_norm": 7.879756450653076,
|
| 1061 |
+
"learning_rate": 3.072995461422088e-05,
|
| 1062 |
+
"loss": 0.3323,
|
| 1063 |
+
"step": 130
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 12.476190476190476,
|
| 1067 |
+
"grad_norm": 9.934654235839844,
|
| 1068 |
+
"learning_rate": 3.0966338880484114e-05,
|
| 1069 |
+
"loss": 0.2998,
|
| 1070 |
+
"step": 131
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 12.571428571428571,
|
| 1074 |
+
"grad_norm": 17.82680892944336,
|
| 1075 |
+
"learning_rate": 3.1202723146747355e-05,
|
| 1076 |
+
"loss": 0.3211,
|
| 1077 |
+
"step": 132
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 12.666666666666666,
|
| 1081 |
+
"grad_norm": 12.753545761108398,
|
| 1082 |
+
"learning_rate": 3.143910741301059e-05,
|
| 1083 |
+
"loss": 0.289,
|
| 1084 |
+
"step": 133
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 12.761904761904763,
|
| 1088 |
+
"grad_norm": 5.311514377593994,
|
| 1089 |
+
"learning_rate": 3.167549167927383e-05,
|
| 1090 |
+
"loss": 0.298,
|
| 1091 |
+
"step": 134
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 12.857142857142858,
|
| 1095 |
+
"grad_norm": 12.639371871948242,
|
| 1096 |
+
"learning_rate": 3.1911875945537065e-05,
|
| 1097 |
+
"loss": 0.3605,
|
| 1098 |
+
"step": 135
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 12.952380952380953,
|
| 1102 |
+
"grad_norm": 2.637108564376831,
|
| 1103 |
+
"learning_rate": 3.2148260211800306e-05,
|
| 1104 |
+
"loss": 0.283,
|
| 1105 |
+
"step": 136
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 12.952380952380953,
|
| 1109 |
+
"eval_accuracy": 0.9509359047078842,
|
| 1110 |
+
"eval_f1": 0.9564121945074326,
|
| 1111 |
+
"eval_loss": 0.14562606811523438,
|
| 1112 |
+
"eval_precision": 0.9294809010773751,
|
| 1113 |
+
"eval_recall": 0.9849507005708354,
|
| 1114 |
+
"eval_runtime": 1.5912,
|
| 1115 |
+
"eval_samples_per_second": 2215.912,
|
| 1116 |
+
"eval_steps_per_second": 4.399,
|
| 1117 |
+
"step": 136
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 13.047619047619047,
|
| 1121 |
+
"grad_norm": 7.62993049621582,
|
| 1122 |
+
"learning_rate": 3.238464447806354e-05,
|
| 1123 |
+
"loss": 0.3216,
|
| 1124 |
+
"step": 137
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 13.142857142857142,
|
| 1128 |
+
"grad_norm": 10.03891658782959,
|
| 1129 |
+
"learning_rate": 3.262102874432678e-05,
|
| 1130 |
+
"loss": 0.2947,
|
| 1131 |
+
"step": 138
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 13.238095238095237,
|
| 1135 |
+
"grad_norm": 5.97321081161499,
|
| 1136 |
+
"learning_rate": 3.2857413010590016e-05,
|
| 1137 |
+
"loss": 0.2612,
|
| 1138 |
+
"step": 139
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 13.333333333333334,
|
| 1142 |
+
"grad_norm": 8.86699104309082,
|
| 1143 |
+
"learning_rate": 3.309379727685325e-05,
|
| 1144 |
+
"loss": 0.3227,
|
| 1145 |
+
"step": 140
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 13.428571428571429,
|
| 1149 |
+
"grad_norm": 15.790081977844238,
|
| 1150 |
+
"learning_rate": 3.333018154311649e-05,
|
| 1151 |
+
"loss": 0.2995,
|
| 1152 |
+
"step": 141
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 13.523809523809524,
|
| 1156 |
+
"grad_norm": 5.853909492492676,
|
| 1157 |
+
"learning_rate": 3.3566565809379726e-05,
|
| 1158 |
+
"loss": 0.2933,
|
| 1159 |
+
"step": 142
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 13.619047619047619,
|
| 1163 |
+
"grad_norm": 5.831888198852539,
|
| 1164 |
+
"learning_rate": 3.380295007564297e-05,
|
| 1165 |
+
"loss": 0.2468,
|
| 1166 |
+
"step": 143
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 13.714285714285714,
|
| 1170 |
+
"grad_norm": 10.357230186462402,
|
| 1171 |
+
"learning_rate": 3.40393343419062e-05,
|
| 1172 |
+
"loss": 0.2623,
|
| 1173 |
+
"step": 144
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 13.80952380952381,
|
| 1177 |
+
"grad_norm": 5.2562031745910645,
|
| 1178 |
+
"learning_rate": 3.427571860816944e-05,
|
| 1179 |
+
"loss": 0.3479,
|
| 1180 |
+
"step": 145
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 13.904761904761905,
|
| 1184 |
+
"grad_norm": 15.13800048828125,
|
| 1185 |
+
"learning_rate": 3.451210287443268e-05,
|
| 1186 |
+
"loss": 0.3319,
|
| 1187 |
+
"step": 146
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 14.0,
|
| 1191 |
+
"grad_norm": 12.705235481262207,
|
| 1192 |
+
"learning_rate": 3.474848714069592e-05,
|
| 1193 |
+
"loss": 0.259,
|
| 1194 |
+
"step": 147
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 14.0,
|
| 1198 |
+
"eval_accuracy": 0.9506522972206466,
|
| 1199 |
+
"eval_f1": 0.9553388090349076,
|
| 1200 |
+
"eval_loss": 0.1397620439529419,
|
| 1201 |
+
"eval_precision": 0.9451498222447943,
|
| 1202 |
+
"eval_recall": 0.9657498702646601,
|
| 1203 |
+
"eval_runtime": 1.619,
|
| 1204 |
+
"eval_samples_per_second": 2177.916,
|
| 1205 |
+
"eval_steps_per_second": 4.324,
|
| 1206 |
+
"step": 147
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 14.095238095238095,
|
| 1210 |
+
"grad_norm": 8.386173248291016,
|
| 1211 |
+
"learning_rate": 3.498487140695915e-05,
|
| 1212 |
+
"loss": 0.307,
|
| 1213 |
+
"step": 148
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 14.19047619047619,
|
| 1217 |
+
"grad_norm": 13.692023277282715,
|
| 1218 |
+
"learning_rate": 3.5221255673222394e-05,
|
| 1219 |
+
"loss": 0.2774,
|
| 1220 |
+
"step": 149
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 14.285714285714286,
|
| 1224 |
+
"grad_norm": 14.223930358886719,
|
| 1225 |
+
"learning_rate": 3.545763993948563e-05,
|
| 1226 |
+
"loss": 0.2818,
|
| 1227 |
+
"step": 150
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 14.380952380952381,
|
| 1231 |
+
"grad_norm": 10.126199722290039,
|
| 1232 |
+
"learning_rate": 3.569402420574887e-05,
|
| 1233 |
+
"loss": 0.291,
|
| 1234 |
+
"step": 151
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 14.476190476190476,
|
| 1238 |
+
"grad_norm": 1.373759388923645,
|
| 1239 |
+
"learning_rate": 3.5930408472012104e-05,
|
| 1240 |
+
"loss": 0.2705,
|
| 1241 |
+
"step": 152
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 14.571428571428571,
|
| 1245 |
+
"grad_norm": 9.481996536254883,
|
| 1246 |
+
"learning_rate": 3.6166792738275345e-05,
|
| 1247 |
+
"loss": 0.2586,
|
| 1248 |
+
"step": 153
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 14.666666666666666,
|
| 1252 |
+
"grad_norm": 10.558037757873535,
|
| 1253 |
+
"learning_rate": 3.640317700453858e-05,
|
| 1254 |
+
"loss": 0.2298,
|
| 1255 |
+
"step": 154
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 14.761904761904763,
|
| 1259 |
+
"grad_norm": 15.332423210144043,
|
| 1260 |
+
"learning_rate": 3.6639561270801814e-05,
|
| 1261 |
+
"loss": 0.294,
|
| 1262 |
+
"step": 155
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 14.857142857142858,
|
| 1266 |
+
"grad_norm": 21.822694778442383,
|
| 1267 |
+
"learning_rate": 3.6875945537065055e-05,
|
| 1268 |
+
"loss": 0.3159,
|
| 1269 |
+
"step": 156
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 14.952380952380953,
|
| 1273 |
+
"grad_norm": 14.891203880310059,
|
| 1274 |
+
"learning_rate": 3.711232980332829e-05,
|
| 1275 |
+
"loss": 0.2775,
|
| 1276 |
+
"step": 157
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 14.952380952380953,
|
| 1280 |
+
"eval_accuracy": 0.9534883720930233,
|
| 1281 |
+
"eval_f1": 0.9579702716555613,
|
| 1282 |
+
"eval_loss": 0.1380477398633957,
|
| 1283 |
+
"eval_precision": 0.9463291139240506,
|
| 1284 |
+
"eval_recall": 0.969901401141671,
|
| 1285 |
+
"eval_runtime": 1.6414,
|
| 1286 |
+
"eval_samples_per_second": 2148.137,
|
| 1287 |
+
"eval_steps_per_second": 4.265,
|
| 1288 |
+
"step": 157
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 15.047619047619047,
|
| 1292 |
+
"grad_norm": 2.741567611694336,
|
| 1293 |
+
"learning_rate": 3.734871406959153e-05,
|
| 1294 |
+
"loss": 0.327,
|
| 1295 |
+
"step": 158
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 15.142857142857142,
|
| 1299 |
+
"grad_norm": 26.54619789123535,
|
| 1300 |
+
"learning_rate": 3.7585098335854765e-05,
|
| 1301 |
+
"loss": 0.2935,
|
| 1302 |
+
"step": 159
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 15.238095238095237,
|
| 1306 |
+
"grad_norm": 34.790714263916016,
|
| 1307 |
+
"learning_rate": 3.782148260211801e-05,
|
| 1308 |
+
"loss": 0.3899,
|
| 1309 |
+
"step": 160
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 15.333333333333334,
|
| 1313 |
+
"grad_norm": 19.43800163269043,
|
| 1314 |
+
"learning_rate": 3.805786686838124e-05,
|
| 1315 |
+
"loss": 0.2958,
|
| 1316 |
+
"step": 161
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 15.428571428571429,
|
| 1320 |
+
"grad_norm": 6.42747163772583,
|
| 1321 |
+
"learning_rate": 3.829425113464448e-05,
|
| 1322 |
+
"loss": 0.3268,
|
| 1323 |
+
"step": 162
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 15.523809523809524,
|
| 1327 |
+
"grad_norm": 9.489509582519531,
|
| 1328 |
+
"learning_rate": 3.853063540090772e-05,
|
| 1329 |
+
"loss": 0.2973,
|
| 1330 |
+
"step": 163
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 15.619047619047619,
|
| 1334 |
+
"grad_norm": 2.128261089324951,
|
| 1335 |
+
"learning_rate": 3.876701966717096e-05,
|
| 1336 |
+
"loss": 0.2732,
|
| 1337 |
+
"step": 164
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 15.714285714285714,
|
| 1341 |
+
"grad_norm": 4.82932710647583,
|
| 1342 |
+
"learning_rate": 3.900340393343419e-05,
|
| 1343 |
+
"loss": 0.2954,
|
| 1344 |
+
"step": 165
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 15.80952380952381,
|
| 1348 |
+
"grad_norm": 6.700158596038818,
|
| 1349 |
+
"learning_rate": 3.9239788199697433e-05,
|
| 1350 |
+
"loss": 0.2775,
|
| 1351 |
+
"step": 166
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 15.904761904761905,
|
| 1355 |
+
"grad_norm": 7.611496925354004,
|
| 1356 |
+
"learning_rate": 3.947617246596067e-05,
|
| 1357 |
+
"loss": 0.2412,
|
| 1358 |
+
"step": 167
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 16.0,
|
| 1362 |
+
"grad_norm": 10.439764976501465,
|
| 1363 |
+
"learning_rate": 3.97125567322239e-05,
|
| 1364 |
+
"loss": 0.2441,
|
| 1365 |
+
"step": 168
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 16.0,
|
| 1369 |
+
"eval_accuracy": 0.9463981849120817,
|
| 1370 |
+
"eval_f1": 0.950896336710834,
|
| 1371 |
+
"eval_loss": 0.14303936064243317,
|
| 1372 |
+
"eval_precision": 0.9521331945889698,
|
| 1373 |
+
"eval_recall": 0.9496626881162429,
|
| 1374 |
+
"eval_runtime": 1.6304,
|
| 1375 |
+
"eval_samples_per_second": 2162.648,
|
| 1376 |
+
"eval_steps_per_second": 4.293,
|
| 1377 |
+
"step": 168
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 16.095238095238095,
|
| 1381 |
+
"grad_norm": 16.28002166748047,
|
| 1382 |
+
"learning_rate": 3.9948940998487143e-05,
|
| 1383 |
+
"loss": 0.245,
|
| 1384 |
+
"step": 169
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 16.19047619047619,
|
| 1388 |
+
"grad_norm": 2.897649049758911,
|
| 1389 |
+
"learning_rate": 4.0185325264750385e-05,
|
| 1390 |
+
"loss": 0.3018,
|
| 1391 |
+
"step": 170
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 16.285714285714285,
|
| 1395 |
+
"grad_norm": 17.607654571533203,
|
| 1396 |
+
"learning_rate": 4.042170953101361e-05,
|
| 1397 |
+
"loss": 0.2769,
|
| 1398 |
+
"step": 171
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 16.38095238095238,
|
| 1402 |
+
"grad_norm": 16.687471389770508,
|
| 1403 |
+
"learning_rate": 4.0658093797276853e-05,
|
| 1404 |
+
"loss": 0.2907,
|
| 1405 |
+
"step": 172
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 16.476190476190474,
|
| 1409 |
+
"grad_norm": 16.236730575561523,
|
| 1410 |
+
"learning_rate": 4.0894478063540095e-05,
|
| 1411 |
+
"loss": 0.3441,
|
| 1412 |
+
"step": 173
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 16.571428571428573,
|
| 1416 |
+
"grad_norm": 9.936101913452148,
|
| 1417 |
+
"learning_rate": 4.113086232980333e-05,
|
| 1418 |
+
"loss": 0.2438,
|
| 1419 |
+
"step": 174
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 16.666666666666668,
|
| 1423 |
+
"grad_norm": 11.340507507324219,
|
| 1424 |
+
"learning_rate": 4.1367246596066563e-05,
|
| 1425 |
+
"loss": 0.2779,
|
| 1426 |
+
"step": 175
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 16.761904761904763,
|
| 1430 |
+
"grad_norm": 12.564432144165039,
|
| 1431 |
+
"learning_rate": 4.1603630862329805e-05,
|
| 1432 |
+
"loss": 0.2693,
|
| 1433 |
+
"step": 176
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 16.857142857142858,
|
| 1437 |
+
"grad_norm": 10.584827423095703,
|
| 1438 |
+
"learning_rate": 4.1840015128593046e-05,
|
| 1439 |
+
"loss": 0.2824,
|
| 1440 |
+
"step": 177
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 16.952380952380953,
|
| 1444 |
+
"grad_norm": 17.218711853027344,
|
| 1445 |
+
"learning_rate": 4.207639939485628e-05,
|
| 1446 |
+
"loss": 0.2491,
|
| 1447 |
+
"step": 178
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 16.952380952380953,
|
| 1451 |
+
"eval_accuracy": 0.9546228020419739,
|
| 1452 |
+
"eval_f1": 0.9594526102382159,
|
| 1453 |
+
"eval_loss": 0.1373429149389267,
|
| 1454 |
+
"eval_precision": 0.937592867756315,
|
| 1455 |
+
"eval_recall": 0.9823559937727037,
|
| 1456 |
+
"eval_runtime": 1.6556,
|
| 1457 |
+
"eval_samples_per_second": 2129.758,
|
| 1458 |
+
"eval_steps_per_second": 4.228,
|
| 1459 |
+
"step": 178
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 17.047619047619047,
|
| 1463 |
+
"grad_norm": 5.5430474281311035,
|
| 1464 |
+
"learning_rate": 4.2312783661119515e-05,
|
| 1465 |
+
"loss": 0.2252,
|
| 1466 |
+
"step": 179
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 17.142857142857142,
|
| 1470 |
+
"grad_norm": 14.669001579284668,
|
| 1471 |
+
"learning_rate": 4.2549167927382756e-05,
|
| 1472 |
+
"loss": 0.2431,
|
| 1473 |
+
"step": 180
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 17.238095238095237,
|
| 1477 |
+
"grad_norm": 22.088754653930664,
|
| 1478 |
+
"learning_rate": 4.278555219364599e-05,
|
| 1479 |
+
"loss": 0.3157,
|
| 1480 |
+
"step": 181
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 17.333333333333332,
|
| 1484 |
+
"grad_norm": 12.44052791595459,
|
| 1485 |
+
"learning_rate": 4.302193645990923e-05,
|
| 1486 |
+
"loss": 0.2802,
|
| 1487 |
+
"step": 182
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 17.428571428571427,
|
| 1491 |
+
"grad_norm": 8.848921775817871,
|
| 1492 |
+
"learning_rate": 4.3258320726172466e-05,
|
| 1493 |
+
"loss": 0.2946,
|
| 1494 |
+
"step": 183
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 17.523809523809526,
|
| 1498 |
+
"grad_norm": 18.54819679260254,
|
| 1499 |
+
"learning_rate": 4.349470499243571e-05,
|
| 1500 |
+
"loss": 0.3171,
|
| 1501 |
+
"step": 184
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 17.61904761904762,
|
| 1505 |
+
"grad_norm": 9.934106826782227,
|
| 1506 |
+
"learning_rate": 4.373108925869894e-05,
|
| 1507 |
+
"loss": 0.2718,
|
| 1508 |
+
"step": 185
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 17.714285714285715,
|
| 1512 |
+
"grad_norm": 10.600541114807129,
|
| 1513 |
+
"learning_rate": 4.3967473524962176e-05,
|
| 1514 |
+
"loss": 0.2508,
|
| 1515 |
+
"step": 186
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 17.80952380952381,
|
| 1519 |
+
"grad_norm": 14.236543655395508,
|
| 1520 |
+
"learning_rate": 4.420385779122542e-05,
|
| 1521 |
+
"loss": 0.33,
|
| 1522 |
+
"step": 187
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 17.904761904761905,
|
| 1526 |
+
"grad_norm": 9.139389991760254,
|
| 1527 |
+
"learning_rate": 4.444024205748866e-05,
|
| 1528 |
+
"loss": 0.2513,
|
| 1529 |
+
"step": 188
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 18.0,
|
| 1533 |
+
"grad_norm": 7.131582260131836,
|
| 1534 |
+
"learning_rate": 4.467662632375189e-05,
|
| 1535 |
+
"loss": 0.2243,
|
| 1536 |
+
"step": 189
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 18.0,
|
| 1540 |
+
"eval_accuracy": 0.9534883720930233,
|
| 1541 |
+
"eval_f1": 0.958876629889669,
|
| 1542 |
+
"eval_loss": 0.14191094040870667,
|
| 1543 |
+
"eval_precision": 0.9277049975739932,
|
| 1544 |
+
"eval_recall": 0.9922158796056045,
|
| 1545 |
+
"eval_runtime": 1.6789,
|
| 1546 |
+
"eval_samples_per_second": 2100.147,
|
| 1547 |
+
"eval_steps_per_second": 4.169,
|
| 1548 |
+
"step": 189
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 18.095238095238095,
|
| 1552 |
+
"grad_norm": 18.005144119262695,
|
| 1553 |
+
"learning_rate": 4.491301059001513e-05,
|
| 1554 |
+
"loss": 0.3256,
|
| 1555 |
+
"step": 190
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 18.19047619047619,
|
| 1559 |
+
"grad_norm": 5.411448955535889,
|
| 1560 |
+
"learning_rate": 4.514939485627837e-05,
|
| 1561 |
+
"loss": 0.2466,
|
| 1562 |
+
"step": 191
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 18.285714285714285,
|
| 1566 |
+
"grad_norm": 13.415284156799316,
|
| 1567 |
+
"learning_rate": 4.53857791225416e-05,
|
| 1568 |
+
"loss": 0.3122,
|
| 1569 |
+
"step": 192
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 18.38095238095238,
|
| 1573 |
+
"grad_norm": 18.9256534576416,
|
| 1574 |
+
"learning_rate": 4.5622163388804844e-05,
|
| 1575 |
+
"loss": 0.2766,
|
| 1576 |
+
"step": 193
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 18.476190476190474,
|
| 1580 |
+
"grad_norm": 11.247349739074707,
|
| 1581 |
+
"learning_rate": 4.585854765506808e-05,
|
| 1582 |
+
"loss": 0.2936,
|
| 1583 |
+
"step": 194
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 18.571428571428573,
|
| 1587 |
+
"grad_norm": 10.798985481262207,
|
| 1588 |
+
"learning_rate": 4.609493192133132e-05,
|
| 1589 |
+
"loss": 0.261,
|
| 1590 |
+
"step": 195
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 18.666666666666668,
|
| 1594 |
+
"grad_norm": 10.872228622436523,
|
| 1595 |
+
"learning_rate": 4.6331316187594554e-05,
|
| 1596 |
+
"loss": 0.2491,
|
| 1597 |
+
"step": 196
|
| 1598 |
+
},
|
| 1599 |
+
{
|
| 1600 |
+
"epoch": 18.761904761904763,
|
| 1601 |
+
"grad_norm": 11.194981575012207,
|
| 1602 |
+
"learning_rate": 4.6567700453857795e-05,
|
| 1603 |
+
"loss": 0.2419,
|
| 1604 |
+
"step": 197
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 18.857142857142858,
|
| 1608 |
+
"grad_norm": 19.81293296813965,
|
| 1609 |
+
"learning_rate": 4.680408472012103e-05,
|
| 1610 |
+
"loss": 0.2847,
|
| 1611 |
+
"step": 198
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 18.952380952380953,
|
| 1615 |
+
"grad_norm": 18.402585983276367,
|
| 1616 |
+
"learning_rate": 4.704046898638427e-05,
|
| 1617 |
+
"loss": 0.2236,
|
| 1618 |
+
"step": 199
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 18.952380952380953,
|
| 1622 |
+
"eval_accuracy": 0.9551900170164492,
|
| 1623 |
+
"eval_f1": 0.9594039054470709,
|
| 1624 |
+
"eval_loss": 0.13194940984249115,
|
| 1625 |
+
"eval_precision": 0.9501272264631043,
|
| 1626 |
+
"eval_recall": 0.9688635184224182,
|
| 1627 |
+
"eval_runtime": 1.6849,
|
| 1628 |
+
"eval_samples_per_second": 2092.67,
|
| 1629 |
+
"eval_steps_per_second": 4.154,
|
| 1630 |
+
"step": 199
|
| 1631 |
+
}
|
| 1632 |
+
],
|
| 1633 |
+
"logging_steps": 1,
|
| 1634 |
+
"max_steps": 200,
|
| 1635 |
+
"num_input_tokens_seen": 0,
|
| 1636 |
+
"num_train_epochs": 20,
|
| 1637 |
+
"save_steps": 500,
|
| 1638 |
+
"stateful_callbacks": {
|
| 1639 |
+
"TrainerControl": {
|
| 1640 |
+
"args": {
|
| 1641 |
+
"should_epoch_stop": false,
|
| 1642 |
+
"should_evaluate": false,
|
| 1643 |
+
"should_log": false,
|
| 1644 |
+
"should_save": true,
|
| 1645 |
+
"should_training_stop": false
|
| 1646 |
+
},
|
| 1647 |
+
"attributes": {}
|
| 1648 |
+
}
|
| 1649 |
+
},
|
| 1650 |
+
"total_flos": 7921990740934656.0,
|
| 1651 |
+
"train_batch_size": 512,
|
| 1652 |
+
"trial_name": null,
|
| 1653 |
+
"trial_params": null
|
| 1654 |
+
}
|
checkpoint-199/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df1535d56f69b10dec594d0116a6d77d9220713be79d301e5d938e5c3d7f1940
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"encoder_stride": 16,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.0,
|
| 9 |
+
"hidden_size": 256,
|
| 10 |
+
"image_size": 32,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 512,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"model_type": "vit",
|
| 15 |
+
"num_attention_heads": 8,
|
| 16 |
+
"num_channels": 3,
|
| 17 |
+
"num_hidden_layers": 4,
|
| 18 |
+
"patch_size": 4,
|
| 19 |
+
"qkv_bias": true,
|
| 20 |
+
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.46.1"
|
| 22 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3763285e8dd082d9840123bbe4a55f1faaefe6dabaa87bbe48938bee65866d2
|
| 3 |
+
size 8563512
|
pr_curve.png
ADDED
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": false,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 32,
|
| 20 |
+
"width": 32
|
| 21 |
+
}
|
| 22 |
+
}
|
roc_curve.png
ADDED
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df1535d56f69b10dec594d0116a6d77d9220713be79d301e5d938e5c3d7f1940
|
| 3 |
+
size 5368
|