Commit
·
c29ff1a
1
Parent(s):
b5ba7c1
Add evaluation results and output files to model card
Browse files- README.md +36 -0
- checkpoint-171/config.json +23 -0
- checkpoint-171/model.safetensors +3 -0
- checkpoint-171/optimizer.pt +3 -0
- checkpoint-171/preprocessor_config.json +22 -0
- checkpoint-171/rng_state.pth +3 -0
- checkpoint-171/scheduler.pt +3 -0
- checkpoint-171/trainer_state.json +1458 -0
- checkpoint-171/training_args.bin +3 -0
- config.json +23 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: code
|
| 3 |
+
tags:
|
| 4 |
+
- binary-classification
|
| 5 |
+
- model
|
| 6 |
+
- evaluation
|
| 7 |
+
metrics:
|
| 8 |
+
- average_precision: 0.67
|
| 9 |
+
- roc_auc: 0.77
|
| 10 |
+
- best threshold according to F1: 0.42
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Binary Classification Model
|
| 14 |
+
|
| 15 |
+
## Evaluation Results
|
| 16 |
+
|
| 17 |
+
**Average Precision:** 0.67
|
| 18 |
+
**ROC AUC:** 0.77
|
| 19 |
+
**best threshold according to F1: 0.42
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## Visualizations
|
| 23 |
+
|
| 24 |
+
### Precision-Recall Curve
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
### ROC Curve
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
## Output Files and Directories
|
| 31 |
+
|
| 32 |
+
- 📂 `checkpoint-171/`
|
| 33 |
+
- `config.json`
|
| 34 |
+
- `model.safetensors`
|
| 35 |
+
- `preprocessor_config.json`
|
| 36 |
+
- `training_args.bin`
|
checkpoint-171/config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "GenetikaPlus/binary_classification_model_v3.1.3_spines",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 256,
|
| 11 |
+
"image_size": 32,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 512,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"model_type": "vit",
|
| 16 |
+
"num_attention_heads": 8,
|
| 17 |
+
"num_channels": 3,
|
| 18 |
+
"num_hidden_layers": 4,
|
| 19 |
+
"patch_size": 4,
|
| 20 |
+
"qkv_bias": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.46.2"
|
| 23 |
+
}
|
checkpoint-171/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3296337d01ecfc0aabdf11fceb071277d873306c7f611bb786d3aa1bfa53c035
|
| 3 |
+
size 8563512
|
checkpoint-171/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4272504bd3f8fba2f7db1db12081b07ea7d6709ff1a5062eb02c8d0f6b60ef5b
|
| 3 |
+
size 17171514
|
checkpoint-171/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-171/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b835e41d78ca90e7b03e5bb0ab545ee556f7edb32620a808446fe9c2748e593c
|
| 3 |
+
size 14244
|
checkpoint-171/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa8424070a154dd5915b5a32fe02aed2c0823a7e279c136e8b450b0450061e08
|
| 3 |
+
size 1000
|
checkpoint-171/trainer_state.json
ADDED
|
@@ -0,0 +1,1458 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.80322265625,
|
| 3 |
+
"best_model_checkpoint": "/tmp/logs/binary_classification_model_v3.1.5_spines/checkpoint-171",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 171,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1111111111111111,
|
| 13 |
+
"grad_norm": 474895.5625,
|
| 14 |
+
"learning_rate": 2.87092328892972e-10,
|
| 15 |
+
"loss": 0.4027,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2222222222222222,
|
| 20 |
+
"grad_norm": 420552.40625,
|
| 21 |
+
"learning_rate": 5.74184657785944e-10,
|
| 22 |
+
"loss": 0.4218,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.3333333333333333,
|
| 27 |
+
"grad_norm": 373690.21875,
|
| 28 |
+
"learning_rate": 8.612769866789159e-10,
|
| 29 |
+
"loss": 0.4276,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.4444444444444444,
|
| 34 |
+
"grad_norm": 461776.09375,
|
| 35 |
+
"learning_rate": 1.148369315571888e-09,
|
| 36 |
+
"loss": 0.4082,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.5555555555555556,
|
| 41 |
+
"grad_norm": 263371.625,
|
| 42 |
+
"learning_rate": 1.43546164446486e-09,
|
| 43 |
+
"loss": 0.391,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6666666666666666,
|
| 48 |
+
"grad_norm": 285742.5625,
|
| 49 |
+
"learning_rate": 1.7225539733578319e-09,
|
| 50 |
+
"loss": 0.3947,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.7777777777777778,
|
| 55 |
+
"grad_norm": 275876.28125,
|
| 56 |
+
"learning_rate": 2.009646302250804e-09,
|
| 57 |
+
"loss": 0.3982,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.8888888888888888,
|
| 62 |
+
"grad_norm": 254763.890625,
|
| 63 |
+
"learning_rate": 2.296738631143776e-09,
|
| 64 |
+
"loss": 0.3958,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.0,
|
| 69 |
+
"grad_norm": 775464.875,
|
| 70 |
+
"learning_rate": 2.5838309600367482e-09,
|
| 71 |
+
"loss": 0.425,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.0,
|
| 76 |
+
"eval_accuracy": 0.8063849333945797,
|
| 77 |
+
"eval_f1": 0.7877109040543944,
|
| 78 |
+
"eval_loss": 0.40825775265693665,
|
| 79 |
+
"eval_precision": 0.8266384778012685,
|
| 80 |
+
"eval_recall": 0.7522847522847523,
|
| 81 |
+
"eval_runtime": 2.8714,
|
| 82 |
+
"eval_samples_per_second": 1516.327,
|
| 83 |
+
"eval_steps_per_second": 1.045,
|
| 84 |
+
"step": 9
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.1111111111111112,
|
| 88 |
+
"grad_norm": 597081.6875,
|
| 89 |
+
"learning_rate": 2.87092328892972e-09,
|
| 90 |
+
"loss": 0.4126,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.2222222222222223,
|
| 95 |
+
"grad_norm": 260747.1875,
|
| 96 |
+
"learning_rate": 3.158015617822692e-09,
|
| 97 |
+
"loss": 0.4022,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.3333333333333333,
|
| 102 |
+
"grad_norm": 534622.6875,
|
| 103 |
+
"learning_rate": 3.4451079467156637e-09,
|
| 104 |
+
"loss": 0.4173,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.4444444444444444,
|
| 109 |
+
"grad_norm": 448352.53125,
|
| 110 |
+
"learning_rate": 3.732200275608636e-09,
|
| 111 |
+
"loss": 0.3865,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.5555555555555556,
|
| 116 |
+
"grad_norm": 421928.59375,
|
| 117 |
+
"learning_rate": 4.019292604501608e-09,
|
| 118 |
+
"loss": 0.4012,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.6666666666666665,
|
| 123 |
+
"grad_norm": 231615.71875,
|
| 124 |
+
"learning_rate": 4.30638493339458e-09,
|
| 125 |
+
"loss": 0.4068,
|
| 126 |
+
"step": 15
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.7777777777777777,
|
| 130 |
+
"grad_norm": 299990.625,
|
| 131 |
+
"learning_rate": 4.593477262287552e-09,
|
| 132 |
+
"loss": 0.4235,
|
| 133 |
+
"step": 16
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1.8888888888888888,
|
| 137 |
+
"grad_norm": 399554.59375,
|
| 138 |
+
"learning_rate": 4.8805695911805235e-09,
|
| 139 |
+
"loss": 0.3954,
|
| 140 |
+
"step": 17
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.0,
|
| 144 |
+
"grad_norm": 150956.59375,
|
| 145 |
+
"learning_rate": 5.1676619200734964e-09,
|
| 146 |
+
"loss": 0.4087,
|
| 147 |
+
"step": 18
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.0,
|
| 151 |
+
"eval_accuracy": 0.8063849333945797,
|
| 152 |
+
"eval_f1": 0.7879245283018868,
|
| 153 |
+
"eval_loss": 0.4081619381904602,
|
| 154 |
+
"eval_precision": 0.8259493670886076,
|
| 155 |
+
"eval_recall": 0.7532467532467533,
|
| 156 |
+
"eval_runtime": 3.0185,
|
| 157 |
+
"eval_samples_per_second": 1442.425,
|
| 158 |
+
"eval_steps_per_second": 0.994,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.111111111111111,
|
| 163 |
+
"grad_norm": 578097.9375,
|
| 164 |
+
"learning_rate": 5.454754248966468e-09,
|
| 165 |
+
"loss": 0.41,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.2222222222222223,
|
| 170 |
+
"grad_norm": 241448.453125,
|
| 171 |
+
"learning_rate": 5.74184657785944e-09,
|
| 172 |
+
"loss": 0.4095,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.3333333333333335,
|
| 177 |
+
"grad_norm": 563117.375,
|
| 178 |
+
"learning_rate": 6.028938906752413e-09,
|
| 179 |
+
"loss": 0.4254,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.4444444444444446,
|
| 184 |
+
"grad_norm": 277218.59375,
|
| 185 |
+
"learning_rate": 6.316031235645384e-09,
|
| 186 |
+
"loss": 0.3986,
|
| 187 |
+
"step": 22
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 2.5555555555555554,
|
| 191 |
+
"grad_norm": 253562.546875,
|
| 192 |
+
"learning_rate": 6.603123564538356e-09,
|
| 193 |
+
"loss": 0.4053,
|
| 194 |
+
"step": 23
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.6666666666666665,
|
| 198 |
+
"grad_norm": 386568.96875,
|
| 199 |
+
"learning_rate": 6.8902158934313275e-09,
|
| 200 |
+
"loss": 0.3903,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.7777777777777777,
|
| 205 |
+
"grad_norm": 331298.84375,
|
| 206 |
+
"learning_rate": 7.1773082223243e-09,
|
| 207 |
+
"loss": 0.4037,
|
| 208 |
+
"step": 25
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.888888888888889,
|
| 212 |
+
"grad_norm": 408564.9375,
|
| 213 |
+
"learning_rate": 7.464400551217272e-09,
|
| 214 |
+
"loss": 0.4086,
|
| 215 |
+
"step": 26
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.0,
|
| 219 |
+
"grad_norm": 243629.5625,
|
| 220 |
+
"learning_rate": 7.751492880110245e-09,
|
| 221 |
+
"loss": 0.3882,
|
| 222 |
+
"step": 27
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.0,
|
| 226 |
+
"eval_accuracy": 0.8070739549839229,
|
| 227 |
+
"eval_f1": 0.7888386123680241,
|
| 228 |
+
"eval_loss": 0.40801021456718445,
|
| 229 |
+
"eval_precision": 0.8262243285939969,
|
| 230 |
+
"eval_recall": 0.7546897546897547,
|
| 231 |
+
"eval_runtime": 3.0995,
|
| 232 |
+
"eval_samples_per_second": 1404.727,
|
| 233 |
+
"eval_steps_per_second": 0.968,
|
| 234 |
+
"step": 27
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.111111111111111,
|
| 238 |
+
"grad_norm": 367006.5625,
|
| 239 |
+
"learning_rate": 8.038585209003216e-09,
|
| 240 |
+
"loss": 0.3957,
|
| 241 |
+
"step": 28
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 3.2222222222222223,
|
| 245 |
+
"grad_norm": 460813.4375,
|
| 246 |
+
"learning_rate": 8.325677537896187e-09,
|
| 247 |
+
"loss": 0.3812,
|
| 248 |
+
"step": 29
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.3333333333333335,
|
| 252 |
+
"grad_norm": 207972.6875,
|
| 253 |
+
"learning_rate": 8.61276986678916e-09,
|
| 254 |
+
"loss": 0.4144,
|
| 255 |
+
"step": 30
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 3.4444444444444446,
|
| 259 |
+
"grad_norm": 409202.28125,
|
| 260 |
+
"learning_rate": 8.899862195682133e-09,
|
| 261 |
+
"loss": 0.4003,
|
| 262 |
+
"step": 31
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.5555555555555554,
|
| 266 |
+
"grad_norm": 310814.125,
|
| 267 |
+
"learning_rate": 9.186954524575104e-09,
|
| 268 |
+
"loss": 0.4161,
|
| 269 |
+
"step": 32
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.6666666666666665,
|
| 273 |
+
"grad_norm": 468177.125,
|
| 274 |
+
"learning_rate": 9.474046853468076e-09,
|
| 275 |
+
"loss": 0.4164,
|
| 276 |
+
"step": 33
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.7777777777777777,
|
| 280 |
+
"grad_norm": 565639.8125,
|
| 281 |
+
"learning_rate": 9.761139182361047e-09,
|
| 282 |
+
"loss": 0.3942,
|
| 283 |
+
"step": 34
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 3.888888888888889,
|
| 287 |
+
"grad_norm": 346480.3125,
|
| 288 |
+
"learning_rate": 1.004823151125402e-08,
|
| 289 |
+
"loss": 0.4176,
|
| 290 |
+
"step": 35
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.0,
|
| 294 |
+
"grad_norm": 300739.5625,
|
| 295 |
+
"learning_rate": 1.0335323840146993e-08,
|
| 296 |
+
"loss": 0.3981,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.0,
|
| 301 |
+
"eval_accuracy": 0.807762976573266,
|
| 302 |
+
"eval_f1": 0.789856891790108,
|
| 303 |
+
"eval_loss": 0.40780285000801086,
|
| 304 |
+
"eval_precision": 0.8261554621848739,
|
| 305 |
+
"eval_recall": 0.7566137566137566,
|
| 306 |
+
"eval_runtime": 3.1559,
|
| 307 |
+
"eval_samples_per_second": 1379.616,
|
| 308 |
+
"eval_steps_per_second": 0.951,
|
| 309 |
+
"step": 36
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 4.111111111111111,
|
| 313 |
+
"grad_norm": 283485.25,
|
| 314 |
+
"learning_rate": 1.0622416169039966e-08,
|
| 315 |
+
"loss": 0.4223,
|
| 316 |
+
"step": 37
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 4.222222222222222,
|
| 320 |
+
"grad_norm": 210353.0625,
|
| 321 |
+
"learning_rate": 1.0909508497932935e-08,
|
| 322 |
+
"loss": 0.4203,
|
| 323 |
+
"step": 38
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 4.333333333333333,
|
| 327 |
+
"grad_norm": 254267.328125,
|
| 328 |
+
"learning_rate": 1.1196600826825908e-08,
|
| 329 |
+
"loss": 0.3943,
|
| 330 |
+
"step": 39
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 4.444444444444445,
|
| 334 |
+
"grad_norm": 368198.0625,
|
| 335 |
+
"learning_rate": 1.148369315571888e-08,
|
| 336 |
+
"loss": 0.4063,
|
| 337 |
+
"step": 40
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4.555555555555555,
|
| 341 |
+
"grad_norm": 388967.53125,
|
| 342 |
+
"learning_rate": 1.1770785484611853e-08,
|
| 343 |
+
"loss": 0.4066,
|
| 344 |
+
"step": 41
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.666666666666667,
|
| 348 |
+
"grad_norm": 221729.828125,
|
| 349 |
+
"learning_rate": 1.2057877813504826e-08,
|
| 350 |
+
"loss": 0.3929,
|
| 351 |
+
"step": 42
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.777777777777778,
|
| 355 |
+
"grad_norm": 482960.75,
|
| 356 |
+
"learning_rate": 1.2344970142397795e-08,
|
| 357 |
+
"loss": 0.4113,
|
| 358 |
+
"step": 43
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.888888888888889,
|
| 362 |
+
"grad_norm": 252074.890625,
|
| 363 |
+
"learning_rate": 1.2632062471290768e-08,
|
| 364 |
+
"loss": 0.3781,
|
| 365 |
+
"step": 44
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 5.0,
|
| 369 |
+
"grad_norm": 539560.9375,
|
| 370 |
+
"learning_rate": 1.291915480018374e-08,
|
| 371 |
+
"loss": 0.4297,
|
| 372 |
+
"step": 45
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.0,
|
| 376 |
+
"eval_accuracy": 0.808451998162609,
|
| 377 |
+
"eval_f1": 0.7909774436090226,
|
| 378 |
+
"eval_loss": 0.40754494071006775,
|
| 379 |
+
"eval_precision": 0.82574568288854,
|
| 380 |
+
"eval_recall": 0.759018759018759,
|
| 381 |
+
"eval_runtime": 3.477,
|
| 382 |
+
"eval_samples_per_second": 1252.239,
|
| 383 |
+
"eval_steps_per_second": 0.863,
|
| 384 |
+
"step": 45
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 5.111111111111111,
|
| 388 |
+
"grad_norm": 221841.65625,
|
| 389 |
+
"learning_rate": 1.3206247129076712e-08,
|
| 390 |
+
"loss": 0.4104,
|
| 391 |
+
"step": 46
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 5.222222222222222,
|
| 395 |
+
"grad_norm": 389851.0,
|
| 396 |
+
"learning_rate": 1.3493339457969685e-08,
|
| 397 |
+
"loss": 0.376,
|
| 398 |
+
"step": 47
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.333333333333333,
|
| 402 |
+
"grad_norm": 240513.25,
|
| 403 |
+
"learning_rate": 1.3780431786862655e-08,
|
| 404 |
+
"loss": 0.3952,
|
| 405 |
+
"step": 48
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5.444444444444445,
|
| 409 |
+
"grad_norm": 451586.1875,
|
| 410 |
+
"learning_rate": 1.4067524115755628e-08,
|
| 411 |
+
"loss": 0.439,
|
| 412 |
+
"step": 49
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 5.555555555555555,
|
| 416 |
+
"grad_norm": 144918.9375,
|
| 417 |
+
"learning_rate": 1.43546164446486e-08,
|
| 418 |
+
"loss": 0.4047,
|
| 419 |
+
"step": 50
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.666666666666667,
|
| 423 |
+
"grad_norm": 332475.0625,
|
| 424 |
+
"learning_rate": 1.4641708773541572e-08,
|
| 425 |
+
"loss": 0.3976,
|
| 426 |
+
"step": 51
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.777777777777778,
|
| 430 |
+
"grad_norm": 497577.0,
|
| 431 |
+
"learning_rate": 1.4928801102434543e-08,
|
| 432 |
+
"loss": 0.4031,
|
| 433 |
+
"step": 52
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.888888888888889,
|
| 437 |
+
"grad_norm": 291300.15625,
|
| 438 |
+
"learning_rate": 1.5215893431327515e-08,
|
| 439 |
+
"loss": 0.394,
|
| 440 |
+
"step": 53
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 6.0,
|
| 444 |
+
"grad_norm": 505439.625,
|
| 445 |
+
"learning_rate": 1.550298576022049e-08,
|
| 446 |
+
"loss": 0.4158,
|
| 447 |
+
"step": 54
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 6.0,
|
| 451 |
+
"eval_accuracy": 0.808451998162609,
|
| 452 |
+
"eval_f1": 0.7915,
|
| 453 |
+
"eval_loss": 0.407249391078949,
|
| 454 |
+
"eval_precision": 0.8240499739718896,
|
| 455 |
+
"eval_recall": 0.7614237614237614,
|
| 456 |
+
"eval_runtime": 3.2609,
|
| 457 |
+
"eval_samples_per_second": 1335.2,
|
| 458 |
+
"eval_steps_per_second": 0.92,
|
| 459 |
+
"step": 54
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 6.111111111111111,
|
| 463 |
+
"grad_norm": 324893.5,
|
| 464 |
+
"learning_rate": 1.579007808911346e-08,
|
| 465 |
+
"loss": 0.4025,
|
| 466 |
+
"step": 55
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 6.222222222222222,
|
| 470 |
+
"grad_norm": 368678.25,
|
| 471 |
+
"learning_rate": 1.6077170418006432e-08,
|
| 472 |
+
"loss": 0.4055,
|
| 473 |
+
"step": 56
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 6.333333333333333,
|
| 477 |
+
"grad_norm": 255911.453125,
|
| 478 |
+
"learning_rate": 1.6364262746899406e-08,
|
| 479 |
+
"loss": 0.4027,
|
| 480 |
+
"step": 57
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 6.444444444444445,
|
| 484 |
+
"grad_norm": 464521.34375,
|
| 485 |
+
"learning_rate": 1.6651355075792374e-08,
|
| 486 |
+
"loss": 0.3845,
|
| 487 |
+
"step": 58
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 6.555555555555555,
|
| 491 |
+
"grad_norm": 98293.2578125,
|
| 492 |
+
"learning_rate": 1.693844740468535e-08,
|
| 493 |
+
"loss": 0.4181,
|
| 494 |
+
"step": 59
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.666666666666667,
|
| 498 |
+
"grad_norm": 153667.34375,
|
| 499 |
+
"learning_rate": 1.722553973357832e-08,
|
| 500 |
+
"loss": 0.384,
|
| 501 |
+
"step": 60
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 6.777777777777778,
|
| 505 |
+
"grad_norm": 307245.625,
|
| 506 |
+
"learning_rate": 1.751263206247129e-08,
|
| 507 |
+
"loss": 0.4285,
|
| 508 |
+
"step": 61
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 6.888888888888889,
|
| 512 |
+
"grad_norm": 313019.0625,
|
| 513 |
+
"learning_rate": 1.7799724391364266e-08,
|
| 514 |
+
"loss": 0.4083,
|
| 515 |
+
"step": 62
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 7.0,
|
| 519 |
+
"grad_norm": 377737.375,
|
| 520 |
+
"learning_rate": 1.8086816720257234e-08,
|
| 521 |
+
"loss": 0.4009,
|
| 522 |
+
"step": 63
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 7.0,
|
| 526 |
+
"eval_accuracy": 0.8079926504363804,
|
| 527 |
+
"eval_f1": 0.7916251246261217,
|
| 528 |
+
"eval_loss": 0.4069373309612274,
|
| 529 |
+
"eval_precision": 0.8215209518882566,
|
| 530 |
+
"eval_recall": 0.7638287638287639,
|
| 531 |
+
"eval_runtime": 3.2888,
|
| 532 |
+
"eval_samples_per_second": 1323.904,
|
| 533 |
+
"eval_steps_per_second": 0.912,
|
| 534 |
+
"step": 63
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.111111111111111,
|
| 538 |
+
"grad_norm": 291745.25,
|
| 539 |
+
"learning_rate": 1.837390904915021e-08,
|
| 540 |
+
"loss": 0.3934,
|
| 541 |
+
"step": 64
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.222222222222222,
|
| 545 |
+
"grad_norm": 371277.96875,
|
| 546 |
+
"learning_rate": 1.866100137804318e-08,
|
| 547 |
+
"loss": 0.3967,
|
| 548 |
+
"step": 65
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.333333333333333,
|
| 552 |
+
"grad_norm": 322570.125,
|
| 553 |
+
"learning_rate": 1.894809370693615e-08,
|
| 554 |
+
"loss": 0.4054,
|
| 555 |
+
"step": 66
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.444444444444445,
|
| 559 |
+
"grad_norm": 214398.75,
|
| 560 |
+
"learning_rate": 1.9235186035829126e-08,
|
| 561 |
+
"loss": 0.4069,
|
| 562 |
+
"step": 67
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.555555555555555,
|
| 566 |
+
"grad_norm": 213520.4375,
|
| 567 |
+
"learning_rate": 1.9522278364722094e-08,
|
| 568 |
+
"loss": 0.4127,
|
| 569 |
+
"step": 68
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.666666666666667,
|
| 573 |
+
"grad_norm": 303630.6875,
|
| 574 |
+
"learning_rate": 1.9809370693615065e-08,
|
| 575 |
+
"loss": 0.4015,
|
| 576 |
+
"step": 69
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.777777777777778,
|
| 580 |
+
"grad_norm": 307784.3125,
|
| 581 |
+
"learning_rate": 2.009646302250804e-08,
|
| 582 |
+
"loss": 0.4286,
|
| 583 |
+
"step": 70
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 7.888888888888889,
|
| 587 |
+
"grad_norm": 276592.65625,
|
| 588 |
+
"learning_rate": 2.038355535140101e-08,
|
| 589 |
+
"loss": 0.4014,
|
| 590 |
+
"step": 71
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 8.0,
|
| 594 |
+
"grad_norm": 183215.234375,
|
| 595 |
+
"learning_rate": 2.0670647680293986e-08,
|
| 596 |
+
"loss": 0.3701,
|
| 597 |
+
"step": 72
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.0,
|
| 601 |
+
"eval_accuracy": 0.8091410197519522,
|
| 602 |
+
"eval_f1": 0.7934377330350485,
|
| 603 |
+
"eval_loss": 0.4066150188446045,
|
| 604 |
+
"eval_precision": 0.8209876543209876,
|
| 605 |
+
"eval_recall": 0.7676767676767676,
|
| 606 |
+
"eval_runtime": 3.374,
|
| 607 |
+
"eval_samples_per_second": 1290.473,
|
| 608 |
+
"eval_steps_per_second": 0.889,
|
| 609 |
+
"step": 72
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 8.11111111111111,
|
| 613 |
+
"grad_norm": 368879.1875,
|
| 614 |
+
"learning_rate": 2.0957740009186957e-08,
|
| 615 |
+
"loss": 0.3844,
|
| 616 |
+
"step": 73
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 8.222222222222221,
|
| 620 |
+
"grad_norm": 375783.4375,
|
| 621 |
+
"learning_rate": 2.124483233807993e-08,
|
| 622 |
+
"loss": 0.4067,
|
| 623 |
+
"step": 74
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 8.333333333333334,
|
| 627 |
+
"grad_norm": 295647.8125,
|
| 628 |
+
"learning_rate": 2.15319246669729e-08,
|
| 629 |
+
"loss": 0.4126,
|
| 630 |
+
"step": 75
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 8.444444444444445,
|
| 634 |
+
"grad_norm": 396154.8125,
|
| 635 |
+
"learning_rate": 2.181901699586587e-08,
|
| 636 |
+
"loss": 0.4184,
|
| 637 |
+
"step": 76
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 8.555555555555555,
|
| 641 |
+
"grad_norm": 323196.53125,
|
| 642 |
+
"learning_rate": 2.2106109324758845e-08,
|
| 643 |
+
"loss": 0.4218,
|
| 644 |
+
"step": 77
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 8.666666666666666,
|
| 648 |
+
"grad_norm": 180532.421875,
|
| 649 |
+
"learning_rate": 2.2393201653651817e-08,
|
| 650 |
+
"loss": 0.4102,
|
| 651 |
+
"step": 78
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 8.777777777777779,
|
| 655 |
+
"grad_norm": 160135.71875,
|
| 656 |
+
"learning_rate": 2.268029398254479e-08,
|
| 657 |
+
"loss": 0.3813,
|
| 658 |
+
"step": 79
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 8.88888888888889,
|
| 662 |
+
"grad_norm": 90108.5390625,
|
| 663 |
+
"learning_rate": 2.296738631143776e-08,
|
| 664 |
+
"loss": 0.3771,
|
| 665 |
+
"step": 80
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 9.0,
|
| 669 |
+
"grad_norm": 148206.140625,
|
| 670 |
+
"learning_rate": 2.325447864033073e-08,
|
| 671 |
+
"loss": 0.3913,
|
| 672 |
+
"step": 81
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 9.0,
|
| 676 |
+
"eval_accuracy": 0.8089113458888378,
|
| 677 |
+
"eval_f1": 0.7938553022794846,
|
| 678 |
+
"eval_loss": 0.4063035249710083,
|
| 679 |
+
"eval_precision": 0.8185998978027593,
|
| 680 |
+
"eval_recall": 0.7705627705627706,
|
| 681 |
+
"eval_runtime": 3.4033,
|
| 682 |
+
"eval_samples_per_second": 1279.333,
|
| 683 |
+
"eval_steps_per_second": 0.881,
|
| 684 |
+
"step": 81
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 9.11111111111111,
|
| 688 |
+
"grad_norm": 368934.125,
|
| 689 |
+
"learning_rate": 2.3541570969223705e-08,
|
| 690 |
+
"loss": 0.3934,
|
| 691 |
+
"step": 82
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 9.222222222222221,
|
| 695 |
+
"grad_norm": 121018.4921875,
|
| 696 |
+
"learning_rate": 2.3828663298116677e-08,
|
| 697 |
+
"loss": 0.39,
|
| 698 |
+
"step": 83
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 9.333333333333334,
|
| 702 |
+
"grad_norm": 145493.53125,
|
| 703 |
+
"learning_rate": 2.411575562700965e-08,
|
| 704 |
+
"loss": 0.4076,
|
| 705 |
+
"step": 84
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 9.444444444444445,
|
| 709 |
+
"grad_norm": 255409.46875,
|
| 710 |
+
"learning_rate": 2.440284795590262e-08,
|
| 711 |
+
"loss": 0.4162,
|
| 712 |
+
"step": 85
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 9.555555555555555,
|
| 716 |
+
"grad_norm": 283049.0625,
|
| 717 |
+
"learning_rate": 2.468994028479559e-08,
|
| 718 |
+
"loss": 0.4,
|
| 719 |
+
"step": 86
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 9.666666666666666,
|
| 723 |
+
"grad_norm": 291149.34375,
|
| 724 |
+
"learning_rate": 2.4977032613688565e-08,
|
| 725 |
+
"loss": 0.4227,
|
| 726 |
+
"step": 87
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 9.777777777777779,
|
| 730 |
+
"grad_norm": 190105.96875,
|
| 731 |
+
"learning_rate": 2.5264124942581536e-08,
|
| 732 |
+
"loss": 0.3963,
|
| 733 |
+
"step": 88
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 9.88888888888889,
|
| 737 |
+
"grad_norm": 155022.09375,
|
| 738 |
+
"learning_rate": 2.555121727147451e-08,
|
| 739 |
+
"loss": 0.3905,
|
| 740 |
+
"step": 89
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 10.0,
|
| 744 |
+
"grad_norm": 194663.59375,
|
| 745 |
+
"learning_rate": 2.583830960036748e-08,
|
| 746 |
+
"loss": 0.3815,
|
| 747 |
+
"step": 90
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 10.0,
|
| 751 |
+
"eval_accuracy": 0.809600367478181,
|
| 752 |
+
"eval_f1": 0.7948527592180153,
|
| 753 |
+
"eval_loss": 0.4060344994068146,
|
| 754 |
+
"eval_precision": 0.81855249745158,
|
| 755 |
+
"eval_recall": 0.7724867724867724,
|
| 756 |
+
"eval_runtime": 3.7122,
|
| 757 |
+
"eval_samples_per_second": 1172.903,
|
| 758 |
+
"eval_steps_per_second": 0.808,
|
| 759 |
+
"step": 90
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 10.11111111111111,
|
| 763 |
+
"grad_norm": 176111.203125,
|
| 764 |
+
"learning_rate": 2.612540192926045e-08,
|
| 765 |
+
"loss": 0.4231,
|
| 766 |
+
"step": 91
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 10.222222222222221,
|
| 770 |
+
"grad_norm": 206408.578125,
|
| 771 |
+
"learning_rate": 2.6412494258153425e-08,
|
| 772 |
+
"loss": 0.3939,
|
| 773 |
+
"step": 92
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 10.333333333333334,
|
| 777 |
+
"grad_norm": 266319.78125,
|
| 778 |
+
"learning_rate": 2.6699586587046396e-08,
|
| 779 |
+
"loss": 0.4014,
|
| 780 |
+
"step": 93
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 10.444444444444445,
|
| 784 |
+
"grad_norm": 153663.359375,
|
| 785 |
+
"learning_rate": 2.698667891593937e-08,
|
| 786 |
+
"loss": 0.3855,
|
| 787 |
+
"step": 94
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 10.555555555555555,
|
| 791 |
+
"grad_norm": 122127.5390625,
|
| 792 |
+
"learning_rate": 2.727377124483234e-08,
|
| 793 |
+
"loss": 0.3873,
|
| 794 |
+
"step": 95
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 10.666666666666666,
|
| 798 |
+
"grad_norm": 314791.78125,
|
| 799 |
+
"learning_rate": 2.756086357372531e-08,
|
| 800 |
+
"loss": 0.4327,
|
| 801 |
+
"step": 96
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 10.777777777777779,
|
| 805 |
+
"grad_norm": 127333.1171875,
|
| 806 |
+
"learning_rate": 2.7847955902618285e-08,
|
| 807 |
+
"loss": 0.4,
|
| 808 |
+
"step": 97
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 10.88888888888889,
|
| 812 |
+
"grad_norm": 317753.1875,
|
| 813 |
+
"learning_rate": 2.8135048231511256e-08,
|
| 814 |
+
"loss": 0.4006,
|
| 815 |
+
"step": 98
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 11.0,
|
| 819 |
+
"grad_norm": 146177.5625,
|
| 820 |
+
"learning_rate": 2.842214056040423e-08,
|
| 821 |
+
"loss": 0.4056,
|
| 822 |
+
"step": 99
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 11.0,
|
| 826 |
+
"eval_accuracy": 0.8105190629306385,
|
| 827 |
+
"eval_f1": 0.7963465810910886,
|
| 828 |
+
"eval_loss": 0.4058038294315338,
|
| 829 |
+
"eval_precision": 0.8179513184584178,
|
| 830 |
+
"eval_recall": 0.7758537758537759,
|
| 831 |
+
"eval_runtime": 3.481,
|
| 832 |
+
"eval_samples_per_second": 1250.793,
|
| 833 |
+
"eval_steps_per_second": 0.862,
|
| 834 |
+
"step": 99
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 11.11111111111111,
|
| 838 |
+
"grad_norm": 197264.453125,
|
| 839 |
+
"learning_rate": 2.87092328892972e-08,
|
| 840 |
+
"loss": 0.3961,
|
| 841 |
+
"step": 100
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 11.222222222222221,
|
| 845 |
+
"grad_norm": 119001.2421875,
|
| 846 |
+
"learning_rate": 2.899632521819017e-08,
|
| 847 |
+
"loss": 0.4046,
|
| 848 |
+
"step": 101
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 11.333333333333334,
|
| 852 |
+
"grad_norm": 190082.234375,
|
| 853 |
+
"learning_rate": 2.9283417547083144e-08,
|
| 854 |
+
"loss": 0.416,
|
| 855 |
+
"step": 102
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 11.444444444444445,
|
| 859 |
+
"grad_norm": 123708.5625,
|
| 860 |
+
"learning_rate": 2.9570509875976116e-08,
|
| 861 |
+
"loss": 0.391,
|
| 862 |
+
"step": 103
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 11.555555555555555,
|
| 866 |
+
"grad_norm": 172807.75,
|
| 867 |
+
"learning_rate": 2.985760220486909e-08,
|
| 868 |
+
"loss": 0.3847,
|
| 869 |
+
"step": 104
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 11.666666666666666,
|
| 873 |
+
"grad_norm": 118848.234375,
|
| 874 |
+
"learning_rate": 3.014469453376206e-08,
|
| 875 |
+
"loss": 0.3968,
|
| 876 |
+
"step": 105
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 11.777777777777779,
|
| 880 |
+
"grad_norm": 337085.53125,
|
| 881 |
+
"learning_rate": 3.043178686265503e-08,
|
| 882 |
+
"loss": 0.4127,
|
| 883 |
+
"step": 106
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 11.88888888888889,
|
| 887 |
+
"grad_norm": 254728.96875,
|
| 888 |
+
"learning_rate": 3.071887919154801e-08,
|
| 889 |
+
"loss": 0.4058,
|
| 890 |
+
"step": 107
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 12.0,
|
| 894 |
+
"grad_norm": 179838.640625,
|
| 895 |
+
"learning_rate": 3.100597152044098e-08,
|
| 896 |
+
"loss": 0.4056,
|
| 897 |
+
"step": 108
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 12.0,
|
| 901 |
+
"eval_accuracy": 0.8118971061093248,
|
| 902 |
+
"eval_f1": 0.7984248092542456,
|
| 903 |
+
"eval_loss": 0.40560415387153625,
|
| 904 |
+
"eval_precision": 0.8175403225806451,
|
| 905 |
+
"eval_recall": 0.7801827801827802,
|
| 906 |
+
"eval_runtime": 3.5421,
|
| 907 |
+
"eval_samples_per_second": 1229.227,
|
| 908 |
+
"eval_steps_per_second": 0.847,
|
| 909 |
+
"step": 108
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 12.11111111111111,
|
| 913 |
+
"grad_norm": 152279.546875,
|
| 914 |
+
"learning_rate": 3.129306384933395e-08,
|
| 915 |
+
"loss": 0.401,
|
| 916 |
+
"step": 109
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 12.222222222222221,
|
| 920 |
+
"grad_norm": 145296.5,
|
| 921 |
+
"learning_rate": 3.158015617822692e-08,
|
| 922 |
+
"loss": 0.4145,
|
| 923 |
+
"step": 110
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 12.333333333333334,
|
| 927 |
+
"grad_norm": 162064.296875,
|
| 928 |
+
"learning_rate": 3.186724850711989e-08,
|
| 929 |
+
"loss": 0.4096,
|
| 930 |
+
"step": 111
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 12.444444444444445,
|
| 934 |
+
"grad_norm": 142840.90625,
|
| 935 |
+
"learning_rate": 3.2154340836012864e-08,
|
| 936 |
+
"loss": 0.3996,
|
| 937 |
+
"step": 112
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 12.555555555555555,
|
| 941 |
+
"grad_norm": 121552.7421875,
|
| 942 |
+
"learning_rate": 3.2441433164905835e-08,
|
| 943 |
+
"loss": 0.3979,
|
| 944 |
+
"step": 113
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 12.666666666666666,
|
| 948 |
+
"grad_norm": 124694.5546875,
|
| 949 |
+
"learning_rate": 3.272852549379881e-08,
|
| 950 |
+
"loss": 0.4006,
|
| 951 |
+
"step": 114
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 12.777777777777779,
|
| 955 |
+
"grad_norm": 375322.09375,
|
| 956 |
+
"learning_rate": 3.301561782269178e-08,
|
| 957 |
+
"loss": 0.4088,
|
| 958 |
+
"step": 115
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 12.88888888888889,
|
| 962 |
+
"grad_norm": 157402.0625,
|
| 963 |
+
"learning_rate": 3.330271015158475e-08,
|
| 964 |
+
"loss": 0.4087,
|
| 965 |
+
"step": 116
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 13.0,
|
| 969 |
+
"grad_norm": 202887.8125,
|
| 970 |
+
"learning_rate": 3.358980248047773e-08,
|
| 971 |
+
"loss": 0.3654,
|
| 972 |
+
"step": 117
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 13.0,
|
| 976 |
+
"eval_accuracy": 0.8121267799724391,
|
| 977 |
+
"eval_f1": 0.799017199017199,
|
| 978 |
+
"eval_loss": 0.40542593598365784,
|
| 979 |
+
"eval_precision": 0.8166750376695128,
|
| 980 |
+
"eval_recall": 0.7821067821067821,
|
| 981 |
+
"eval_runtime": 3.5933,
|
| 982 |
+
"eval_samples_per_second": 1211.695,
|
| 983 |
+
"eval_steps_per_second": 0.835,
|
| 984 |
+
"step": 117
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 13.11111111111111,
|
| 988 |
+
"grad_norm": 103942.6640625,
|
| 989 |
+
"learning_rate": 3.38768948093707e-08,
|
| 990 |
+
"loss": 0.4133,
|
| 991 |
+
"step": 118
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 13.222222222222221,
|
| 995 |
+
"grad_norm": 73012.1328125,
|
| 996 |
+
"learning_rate": 3.416398713826367e-08,
|
| 997 |
+
"loss": 0.3909,
|
| 998 |
+
"step": 119
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 13.333333333333334,
|
| 1002 |
+
"grad_norm": 94441.5625,
|
| 1003 |
+
"learning_rate": 3.445107946715664e-08,
|
| 1004 |
+
"loss": 0.4166,
|
| 1005 |
+
"step": 120
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 13.444444444444445,
|
| 1009 |
+
"grad_norm": 150568.984375,
|
| 1010 |
+
"learning_rate": 3.473817179604961e-08,
|
| 1011 |
+
"loss": 0.3918,
|
| 1012 |
+
"step": 121
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 13.555555555555555,
|
| 1016 |
+
"grad_norm": 132181.59375,
|
| 1017 |
+
"learning_rate": 3.502526412494258e-08,
|
| 1018 |
+
"loss": 0.3995,
|
| 1019 |
+
"step": 122
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 13.666666666666666,
|
| 1023 |
+
"grad_norm": 112690.1171875,
|
| 1024 |
+
"learning_rate": 3.5312356453835555e-08,
|
| 1025 |
+
"loss": 0.4005,
|
| 1026 |
+
"step": 123
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 13.777777777777779,
|
| 1030 |
+
"grad_norm": 309373.25,
|
| 1031 |
+
"learning_rate": 3.559944878272853e-08,
|
| 1032 |
+
"loss": 0.3928,
|
| 1033 |
+
"step": 124
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 13.88888888888889,
|
| 1037 |
+
"grad_norm": 123288.84375,
|
| 1038 |
+
"learning_rate": 3.5886541111621504e-08,
|
| 1039 |
+
"loss": 0.3923,
|
| 1040 |
+
"step": 125
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 14.0,
|
| 1044 |
+
"grad_norm": 179755.625,
|
| 1045 |
+
"learning_rate": 3.617363344051447e-08,
|
| 1046 |
+
"loss": 0.3993,
|
| 1047 |
+
"step": 126
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 14.0,
|
| 1051 |
+
"eval_accuracy": 0.8130454754248967,
|
| 1052 |
+
"eval_f1": 0.8003923491907798,
|
| 1053 |
+
"eval_loss": 0.4052511155605316,
|
| 1054 |
+
"eval_precision": 0.8164082041020511,
|
| 1055 |
+
"eval_recall": 0.784992784992785,
|
| 1056 |
+
"eval_runtime": 3.6375,
|
| 1057 |
+
"eval_samples_per_second": 1196.967,
|
| 1058 |
+
"eval_steps_per_second": 0.825,
|
| 1059 |
+
"step": 126
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 14.11111111111111,
|
| 1063 |
+
"grad_norm": 89736.4609375,
|
| 1064 |
+
"learning_rate": 3.6460725769407446e-08,
|
| 1065 |
+
"loss": 0.4223,
|
| 1066 |
+
"step": 127
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 14.222222222222221,
|
| 1070 |
+
"grad_norm": 118175.4921875,
|
| 1071 |
+
"learning_rate": 3.674781809830042e-08,
|
| 1072 |
+
"loss": 0.4071,
|
| 1073 |
+
"step": 128
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 14.333333333333334,
|
| 1077 |
+
"grad_norm": 128466.0625,
|
| 1078 |
+
"learning_rate": 3.703491042719339e-08,
|
| 1079 |
+
"loss": 0.3898,
|
| 1080 |
+
"step": 129
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 14.444444444444445,
|
| 1084 |
+
"grad_norm": 76387.4296875,
|
| 1085 |
+
"learning_rate": 3.732200275608636e-08,
|
| 1086 |
+
"loss": 0.4033,
|
| 1087 |
+
"step": 130
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 14.555555555555555,
|
| 1091 |
+
"grad_norm": 117603.078125,
|
| 1092 |
+
"learning_rate": 3.760909508497933e-08,
|
| 1093 |
+
"loss": 0.3862,
|
| 1094 |
+
"step": 131
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 14.666666666666666,
|
| 1098 |
+
"grad_norm": 112156.703125,
|
| 1099 |
+
"learning_rate": 3.78961874138723e-08,
|
| 1100 |
+
"loss": 0.3988,
|
| 1101 |
+
"step": 132
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 14.777777777777779,
|
| 1105 |
+
"grad_norm": 116138.1171875,
|
| 1106 |
+
"learning_rate": 3.8183279742765274e-08,
|
| 1107 |
+
"loss": 0.3811,
|
| 1108 |
+
"step": 133
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 14.88888888888889,
|
| 1112 |
+
"grad_norm": 169944.3125,
|
| 1113 |
+
"learning_rate": 3.847037207165825e-08,
|
| 1114 |
+
"loss": 0.3836,
|
| 1115 |
+
"step": 134
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 15.0,
|
| 1119 |
+
"grad_norm": 162322.875,
|
| 1120 |
+
"learning_rate": 3.875746440055122e-08,
|
| 1121 |
+
"loss": 0.4048,
|
| 1122 |
+
"step": 135
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 15.0,
|
| 1126 |
+
"eval_accuracy": 0.8141938447404685,
|
| 1127 |
+
"eval_f1": 0.801861376438893,
|
| 1128 |
+
"eval_loss": 0.4050845801830292,
|
| 1129 |
+
"eval_precision": 0.8168662674650699,
|
| 1130 |
+
"eval_recall": 0.7873977873977874,
|
| 1131 |
+
"eval_runtime": 3.6466,
|
| 1132 |
+
"eval_samples_per_second": 1194.003,
|
| 1133 |
+
"eval_steps_per_second": 0.823,
|
| 1134 |
+
"step": 135
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 15.11111111111111,
|
| 1138 |
+
"grad_norm": 113360.9453125,
|
| 1139 |
+
"learning_rate": 3.904455672944419e-08,
|
| 1140 |
+
"loss": 0.3972,
|
| 1141 |
+
"step": 136
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 15.222222222222221,
|
| 1145 |
+
"grad_norm": 92233.84375,
|
| 1146 |
+
"learning_rate": 3.9331649058337166e-08,
|
| 1147 |
+
"loss": 0.4229,
|
| 1148 |
+
"step": 137
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 15.333333333333334,
|
| 1152 |
+
"grad_norm": 334741.0,
|
| 1153 |
+
"learning_rate": 3.961874138723013e-08,
|
| 1154 |
+
"loss": 0.3986,
|
| 1155 |
+
"step": 138
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 15.444444444444445,
|
| 1159 |
+
"grad_norm": 207920.78125,
|
| 1160 |
+
"learning_rate": 3.99058337161231e-08,
|
| 1161 |
+
"loss": 0.3979,
|
| 1162 |
+
"step": 139
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 15.555555555555555,
|
| 1166 |
+
"grad_norm": 78730.8671875,
|
| 1167 |
+
"learning_rate": 4.019292604501608e-08,
|
| 1168 |
+
"loss": 0.4066,
|
| 1169 |
+
"step": 140
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 15.666666666666666,
|
| 1173 |
+
"grad_norm": 272575.46875,
|
| 1174 |
+
"learning_rate": 4.048001837390905e-08,
|
| 1175 |
+
"loss": 0.4215,
|
| 1176 |
+
"step": 141
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 15.777777777777779,
|
| 1180 |
+
"grad_norm": 121701.4921875,
|
| 1181 |
+
"learning_rate": 4.076711070280202e-08,
|
| 1182 |
+
"loss": 0.4133,
|
| 1183 |
+
"step": 142
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 15.88888888888889,
|
| 1187 |
+
"grad_norm": 224911.0,
|
| 1188 |
+
"learning_rate": 4.1054203031694994e-08,
|
| 1189 |
+
"loss": 0.3784,
|
| 1190 |
+
"step": 143
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 16.0,
|
| 1194 |
+
"grad_norm": 88522.6171875,
|
| 1195 |
+
"learning_rate": 4.134129536058797e-08,
|
| 1196 |
+
"loss": 0.4024,
|
| 1197 |
+
"step": 144
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 16.0,
|
| 1201 |
+
"eval_accuracy": 0.8148828663298117,
|
| 1202 |
+
"eval_f1": 0.8029339853300733,
|
| 1203 |
+
"eval_loss": 0.40494343638420105,
|
| 1204 |
+
"eval_precision": 0.8165091994032819,
|
| 1205 |
+
"eval_recall": 0.7898027898027898,
|
| 1206 |
+
"eval_runtime": 4.3334,
|
| 1207 |
+
"eval_samples_per_second": 1004.752,
|
| 1208 |
+
"eval_steps_per_second": 0.692,
|
| 1209 |
+
"step": 144
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 16.11111111111111,
|
| 1213 |
+
"grad_norm": 111251.046875,
|
| 1214 |
+
"learning_rate": 4.162838768948094e-08,
|
| 1215 |
+
"loss": 0.382,
|
| 1216 |
+
"step": 145
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 16.22222222222222,
|
| 1220 |
+
"grad_norm": 103675.90625,
|
| 1221 |
+
"learning_rate": 4.1915480018373914e-08,
|
| 1222 |
+
"loss": 0.4145,
|
| 1223 |
+
"step": 146
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 16.333333333333332,
|
| 1227 |
+
"grad_norm": 58449.1328125,
|
| 1228 |
+
"learning_rate": 4.2202572347266885e-08,
|
| 1229 |
+
"loss": 0.3989,
|
| 1230 |
+
"step": 147
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 16.444444444444443,
|
| 1234 |
+
"grad_norm": 321891.53125,
|
| 1235 |
+
"learning_rate": 4.248966467615986e-08,
|
| 1236 |
+
"loss": 0.4029,
|
| 1237 |
+
"step": 148
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 16.555555555555557,
|
| 1241 |
+
"grad_norm": 203043.90625,
|
| 1242 |
+
"learning_rate": 4.277675700505283e-08,
|
| 1243 |
+
"loss": 0.4039,
|
| 1244 |
+
"step": 149
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 16.666666666666668,
|
| 1248 |
+
"grad_norm": 162260.46875,
|
| 1249 |
+
"learning_rate": 4.30638493339458e-08,
|
| 1250 |
+
"loss": 0.3799,
|
| 1251 |
+
"step": 150
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 16.77777777777778,
|
| 1255 |
+
"grad_norm": 75518.8359375,
|
| 1256 |
+
"learning_rate": 4.335094166283877e-08,
|
| 1257 |
+
"loss": 0.415,
|
| 1258 |
+
"step": 151
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 16.88888888888889,
|
| 1262 |
+
"grad_norm": 377702.125,
|
| 1263 |
+
"learning_rate": 4.363803399173174e-08,
|
| 1264 |
+
"loss": 0.4015,
|
| 1265 |
+
"step": 152
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 17.0,
|
| 1269 |
+
"grad_norm": 183517.390625,
|
| 1270 |
+
"learning_rate": 4.392512632062471e-08,
|
| 1271 |
+
"loss": 0.4073,
|
| 1272 |
+
"step": 153
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 17.0,
|
| 1276 |
+
"eval_accuracy": 0.8146531924666973,
|
| 1277 |
+
"eval_f1": 0.802544653780279,
|
| 1278 |
+
"eval_loss": 0.40483081340789795,
|
| 1279 |
+
"eval_precision": 0.8167330677290837,
|
| 1280 |
+
"eval_recall": 0.7888407888407888,
|
| 1281 |
+
"eval_runtime": 3.7671,
|
| 1282 |
+
"eval_samples_per_second": 1155.81,
|
| 1283 |
+
"eval_steps_per_second": 0.796,
|
| 1284 |
+
"step": 153
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 17.11111111111111,
|
| 1288 |
+
"grad_norm": 58819.46484375,
|
| 1289 |
+
"learning_rate": 4.421221864951769e-08,
|
| 1290 |
+
"loss": 0.3848,
|
| 1291 |
+
"step": 154
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 17.22222222222222,
|
| 1295 |
+
"grad_norm": 139786.34375,
|
| 1296 |
+
"learning_rate": 4.449931097841066e-08,
|
| 1297 |
+
"loss": 0.403,
|
| 1298 |
+
"step": 155
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 17.333333333333332,
|
| 1302 |
+
"grad_norm": 247516.828125,
|
| 1303 |
+
"learning_rate": 4.4786403307303634e-08,
|
| 1304 |
+
"loss": 0.4033,
|
| 1305 |
+
"step": 156
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 17.444444444444443,
|
| 1309 |
+
"grad_norm": 97322.15625,
|
| 1310 |
+
"learning_rate": 4.5073495636196605e-08,
|
| 1311 |
+
"loss": 0.3917,
|
| 1312 |
+
"step": 157
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 17.555555555555557,
|
| 1316 |
+
"grad_norm": 123633.953125,
|
| 1317 |
+
"learning_rate": 4.536058796508958e-08,
|
| 1318 |
+
"loss": 0.4085,
|
| 1319 |
+
"step": 158
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 17.666666666666668,
|
| 1323 |
+
"grad_norm": 226355.78125,
|
| 1324 |
+
"learning_rate": 4.564768029398255e-08,
|
| 1325 |
+
"loss": 0.4028,
|
| 1326 |
+
"step": 159
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 17.77777777777778,
|
| 1330 |
+
"grad_norm": 55226.03515625,
|
| 1331 |
+
"learning_rate": 4.593477262287552e-08,
|
| 1332 |
+
"loss": 0.408,
|
| 1333 |
+
"step": 160
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 17.88888888888889,
|
| 1337 |
+
"grad_norm": 114759.9296875,
|
| 1338 |
+
"learning_rate": 4.622186495176849e-08,
|
| 1339 |
+
"loss": 0.3813,
|
| 1340 |
+
"step": 161
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 18.0,
|
| 1344 |
+
"grad_norm": 157256.296875,
|
| 1345 |
+
"learning_rate": 4.650895728066146e-08,
|
| 1346 |
+
"loss": 0.3884,
|
| 1347 |
+
"step": 162
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 18.0,
|
| 1351 |
+
"eval_accuracy": 0.8146531924666973,
|
| 1352 |
+
"eval_f1": 0.8027377169396236,
|
| 1353 |
+
"eval_loss": 0.40473371744155884,
|
| 1354 |
+
"eval_precision": 0.81610337972167,
|
| 1355 |
+
"eval_recall": 0.7898027898027898,
|
| 1356 |
+
"eval_runtime": 3.8201,
|
| 1357 |
+
"eval_samples_per_second": 1139.77,
|
| 1358 |
+
"eval_steps_per_second": 0.785,
|
| 1359 |
+
"step": 162
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 18.11111111111111,
|
| 1363 |
+
"grad_norm": 103914.2421875,
|
| 1364 |
+
"learning_rate": 4.679604960955444e-08,
|
| 1365 |
+
"loss": 0.3989,
|
| 1366 |
+
"step": 163
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 18.22222222222222,
|
| 1370 |
+
"grad_norm": 101009.2421875,
|
| 1371 |
+
"learning_rate": 4.708314193844741e-08,
|
| 1372 |
+
"loss": 0.3977,
|
| 1373 |
+
"step": 164
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 18.333333333333332,
|
| 1377 |
+
"grad_norm": 161130.59375,
|
| 1378 |
+
"learning_rate": 4.737023426734038e-08,
|
| 1379 |
+
"loss": 0.4009,
|
| 1380 |
+
"step": 165
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 18.444444444444443,
|
| 1384 |
+
"grad_norm": 137444.46875,
|
| 1385 |
+
"learning_rate": 4.765732659623335e-08,
|
| 1386 |
+
"loss": 0.3911,
|
| 1387 |
+
"step": 166
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 18.555555555555557,
|
| 1391 |
+
"grad_norm": 178129.796875,
|
| 1392 |
+
"learning_rate": 4.7944418925126324e-08,
|
| 1393 |
+
"loss": 0.4103,
|
| 1394 |
+
"step": 167
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 18.666666666666668,
|
| 1398 |
+
"grad_norm": 150367.984375,
|
| 1399 |
+
"learning_rate": 4.82315112540193e-08,
|
| 1400 |
+
"loss": 0.428,
|
| 1401 |
+
"step": 168
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 18.77777777777778,
|
| 1405 |
+
"grad_norm": 108212.7265625,
|
| 1406 |
+
"learning_rate": 4.851860358291227e-08,
|
| 1407 |
+
"loss": 0.4053,
|
| 1408 |
+
"step": 169
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 18.88888888888889,
|
| 1412 |
+
"grad_norm": 92431.296875,
|
| 1413 |
+
"learning_rate": 4.880569591180524e-08,
|
| 1414 |
+
"loss": 0.3938,
|
| 1415 |
+
"step": 170
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 19.0,
|
| 1419 |
+
"grad_norm": 98930.1328125,
|
| 1420 |
+
"learning_rate": 4.909278824069821e-08,
|
| 1421 |
+
"loss": 0.3901,
|
| 1422 |
+
"step": 171
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 19.0,
|
| 1426 |
+
"eval_accuracy": 0.8148828663298117,
|
| 1427 |
+
"eval_f1": 0.80322265625,
|
| 1428 |
+
"eval_loss": 0.404643177986145,
|
| 1429 |
+
"eval_precision": 0.8155676747645018,
|
| 1430 |
+
"eval_recall": 0.7912457912457912,
|
| 1431 |
+
"eval_runtime": 3.8213,
|
| 1432 |
+
"eval_samples_per_second": 1139.417,
|
| 1433 |
+
"eval_steps_per_second": 0.785,
|
| 1434 |
+
"step": 171
|
| 1435 |
+
}
|
| 1436 |
+
],
|
| 1437 |
+
"logging_steps": 1,
|
| 1438 |
+
"max_steps": 180,
|
| 1439 |
+
"num_input_tokens_seen": 0,
|
| 1440 |
+
"num_train_epochs": 20,
|
| 1441 |
+
"save_steps": 500,
|
| 1442 |
+
"stateful_callbacks": {
|
| 1443 |
+
"TrainerControl": {
|
| 1444 |
+
"args": {
|
| 1445 |
+
"should_epoch_stop": false,
|
| 1446 |
+
"should_evaluate": false,
|
| 1447 |
+
"should_log": false,
|
| 1448 |
+
"should_save": true,
|
| 1449 |
+
"should_training_stop": false
|
| 1450 |
+
},
|
| 1451 |
+
"attributes": {}
|
| 1452 |
+
}
|
| 1453 |
+
},
|
| 1454 |
+
"total_flos": 1.3045517279133696e+16,
|
| 1455 |
+
"train_batch_size": 2048,
|
| 1456 |
+
"trial_name": null,
|
| 1457 |
+
"trial_params": null
|
| 1458 |
+
}
|
checkpoint-171/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db7a6e522bc59163d2b15697b64887320385f6e05bcc931836ff29f5693f7d4f
|
| 3 |
+
size 5368
|
config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "GenetikaPlus/binary_classification_model_v3.1.3_spines",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 256,
|
| 11 |
+
"image_size": 32,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 512,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"model_type": "vit",
|
| 16 |
+
"num_attention_heads": 8,
|
| 17 |
+
"num_channels": 3,
|
| 18 |
+
"num_hidden_layers": 4,
|
| 19 |
+
"patch_size": 4,
|
| 20 |
+
"qkv_bias": true,
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.46.2"
|
| 23 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aebf6830fe10538fdd5841cfa8bc3a7de059c6edd64c4cbbbbe6f2bd94c9fc23
|
| 3 |
+
size 8563512
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db7a6e522bc59163d2b15697b64887320385f6e05bcc931836ff29f5693f7d4f
|
| 3 |
+
size 5368
|