Model save
Browse files- README.md +75 -0
- all_results.json +16 -0
- config.json +52 -0
- eval_results.json +12 -0
- model.safetensors +3 -0
- preprocessor_config.json +37 -0
- train_results.json +7 -0
- trainer_state.json +802 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/convnextv2-nano-22k-384
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- f1
|
| 9 |
+
- precision
|
| 10 |
+
- recall
|
| 11 |
+
- matthews_correlation
|
| 12 |
+
model-index:
|
| 13 |
+
- name: convnextv2-nano-22k-384-boulderspot-vN
|
| 14 |
+
results: []
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
+
|
| 20 |
+
# convnextv2-nano-22k-384-boulderspot-vN
|
| 21 |
+
|
| 22 |
+
This model is a fine-tuned version of [facebook/convnextv2-nano-22k-384](https://huggingface.co/facebook/convnextv2-nano-22k-384) on an unknown dataset.
|
| 23 |
+
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.0340
|
| 25 |
+
- Accuracy: 0.9883
|
| 26 |
+
- F1: 0.9883
|
| 27 |
+
- Precision: 0.9883
|
| 28 |
+
- Recall: 0.9883
|
| 29 |
+
- Matthews Correlation: 0.8962
|
| 30 |
+
|
| 31 |
+
## Model description
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Intended uses & limitations
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training and evaluation data
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training procedure
|
| 44 |
+
|
| 45 |
+
### Training hyperparameters
|
| 46 |
+
|
| 47 |
+
The following hyperparameters were used during training:
|
| 48 |
+
- learning_rate: 2e-05
|
| 49 |
+
- train_batch_size: 16
|
| 50 |
+
- eval_batch_size: 16
|
| 51 |
+
- seed: 7890
|
| 52 |
+
- gradient_accumulation_steps: 4
|
| 53 |
+
- total_train_batch_size: 64
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: cosine
|
| 56 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 57 |
+
- num_epochs: 5.0
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Matthews Correlation |
|
| 62 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:--------------------:|
|
| 63 |
+
| 0.1102 | 1.0 | 203 | 0.0431 | 0.9839 | 0.9840 | 0.9841 | 0.9839 | 0.8590 |
|
| 64 |
+
| 0.0559 | 2.0 | 406 | 0.0476 | 0.9839 | 0.9845 | 0.9858 | 0.9839 | 0.8709 |
|
| 65 |
+
| 0.0402 | 3.0 | 609 | 0.0464 | 0.9810 | 0.9817 | 0.9831 | 0.9810 | 0.8468 |
|
| 66 |
+
| 0.0334 | 4.0 | 813 | 0.0348 | 0.9868 | 0.9869 | 0.9870 | 0.9868 | 0.8846 |
|
| 67 |
+
| 0.0445 | 4.99 | 1015 | 0.0340 | 0.9883 | 0.9883 | 0.9883 | 0.9883 | 0.8962 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.39.2
|
| 73 |
+
- Pytorch 2.4.0.dev20240328+cu121
|
| 74 |
+
- Datasets 2.18.0
|
| 75 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_accuracy": 0.9780701754385965,
|
| 4 |
+
"eval_f1": 0.9787695402282305,
|
| 5 |
+
"eval_loss": 0.05532665178179741,
|
| 6 |
+
"eval_matthews_correlation": 0.8420667383515437,
|
| 7 |
+
"eval_precision": 0.9800898852068441,
|
| 8 |
+
"eval_recall": 0.9780701754385965,
|
| 9 |
+
"eval_runtime": 5.9704,
|
| 10 |
+
"eval_samples_per_second": 114.565,
|
| 11 |
+
"eval_steps_per_second": 7.202,
|
| 12 |
+
"train_loss": 0.08238832812591139,
|
| 13 |
+
"train_runtime": 705.5168,
|
| 14 |
+
"train_samples_per_second": 92.096,
|
| 15 |
+
"train_steps_per_second": 1.439
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/convnextv2-nano-22k-384",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ConvNextV2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
2,
|
| 8 |
+
2,
|
| 9 |
+
8,
|
| 10 |
+
2
|
| 11 |
+
],
|
| 12 |
+
"drop_path_rate": 0.0,
|
| 13 |
+
"finetuning_task": "image-classification",
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_sizes": [
|
| 16 |
+
80,
|
| 17 |
+
160,
|
| 18 |
+
320,
|
| 19 |
+
640
|
| 20 |
+
],
|
| 21 |
+
"id2label": {
|
| 22 |
+
"0": "bouldering_area",
|
| 23 |
+
"1": "other"
|
| 24 |
+
},
|
| 25 |
+
"image_size": 224,
|
| 26 |
+
"initializer_range": 0.02,
|
| 27 |
+
"label2id": {
|
| 28 |
+
"bouldering_area": "0",
|
| 29 |
+
"other": "1"
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"model_type": "convnextv2",
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"num_stages": 4,
|
| 35 |
+
"out_features": [
|
| 36 |
+
"stage4"
|
| 37 |
+
],
|
| 38 |
+
"out_indices": [
|
| 39 |
+
4
|
| 40 |
+
],
|
| 41 |
+
"patch_size": 4,
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"stage_names": [
|
| 44 |
+
"stem",
|
| 45 |
+
"stage1",
|
| 46 |
+
"stage2",
|
| 47 |
+
"stage3",
|
| 48 |
+
"stage4"
|
| 49 |
+
],
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.39.2"
|
| 52 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"eval_accuracy": 0.9780701754385965,
|
| 4 |
+
"eval_f1": 0.9787695402282305,
|
| 5 |
+
"eval_loss": 0.05532665178179741,
|
| 6 |
+
"eval_matthews_correlation": 0.8420667383515437,
|
| 7 |
+
"eval_precision": 0.9800898852068441,
|
| 8 |
+
"eval_recall": 0.9780701754385965,
|
| 9 |
+
"eval_runtime": 5.9704,
|
| 10 |
+
"eval_samples_per_second": 114.565,
|
| 11 |
+
"eval_steps_per_second": 7.202
|
| 12 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34bf4ee24f0fa6d237ca0b5c89b978010dc6eefd29fe0f497682313d270f0d6
|
| 3 |
+
size 59955208
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"crop_pct",
|
| 7 |
+
"resample",
|
| 8 |
+
"do_rescale",
|
| 9 |
+
"rescale_factor",
|
| 10 |
+
"do_normalize",
|
| 11 |
+
"image_mean",
|
| 12 |
+
"image_std",
|
| 13 |
+
"return_tensors",
|
| 14 |
+
"data_format",
|
| 15 |
+
"input_data_format"
|
| 16 |
+
],
|
| 17 |
+
"crop_pct": 0.875,
|
| 18 |
+
"do_normalize": true,
|
| 19 |
+
"do_rescale": true,
|
| 20 |
+
"do_resize": true,
|
| 21 |
+
"image_mean": [
|
| 22 |
+
0.485,
|
| 23 |
+
0.456,
|
| 24 |
+
0.406
|
| 25 |
+
],
|
| 26 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 27 |
+
"image_std": [
|
| 28 |
+
0.229,
|
| 29 |
+
0.224,
|
| 30 |
+
0.225
|
| 31 |
+
],
|
| 32 |
+
"resample": 3,
|
| 33 |
+
"rescale_factor": 0.00392156862745098,
|
| 34 |
+
"size": {
|
| 35 |
+
"shortest_edge": 384
|
| 36 |
+
}
|
| 37 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.99,
|
| 3 |
+
"train_loss": 0.08238832812591139,
|
| 4 |
+
"train_runtime": 705.5168,
|
| 5 |
+
"train_samples_per_second": 92.096,
|
| 6 |
+
"train_steps_per_second": 1.439
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,802 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9787695402282305,
|
| 3 |
+
"best_model_checkpoint": "./outputs/convnextv2-nano-22k-384-boulderspot-vN/checkpoint-609",
|
| 4 |
+
"epoch": 4.993849938499385,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1015,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 28.485111236572266,
|
| 14 |
+
"learning_rate": 3.92156862745098e-06,
|
| 15 |
+
"loss": 0.8997,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 14.031352043151855,
|
| 21 |
+
"learning_rate": 7.84313725490196e-06,
|
| 22 |
+
"loss": 0.5136,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 5.687072277069092,
|
| 28 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 29 |
+
"loss": 0.2446,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 4.7356672286987305,
|
| 35 |
+
"learning_rate": 1.568627450980392e-05,
|
| 36 |
+
"loss": 0.1611,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 14.7470121383667,
|
| 42 |
+
"learning_rate": 1.9607843137254903e-05,
|
| 43 |
+
"loss": 0.1333,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 9.882979393005371,
|
| 49 |
+
"learning_rate": 1.9995698998770955e-05,
|
| 50 |
+
"loss": 0.1203,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.34,
|
| 55 |
+
"grad_norm": 2.200605869293213,
|
| 56 |
+
"learning_rate": 1.998083609002402e-05,
|
| 57 |
+
"loss": 0.0866,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.39,
|
| 62 |
+
"grad_norm": 9.529250144958496,
|
| 63 |
+
"learning_rate": 1.995537395500004e-05,
|
| 64 |
+
"loss": 0.0825,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.44,
|
| 69 |
+
"grad_norm": 4.56328010559082,
|
| 70 |
+
"learning_rate": 1.9919339633410737e-05,
|
| 71 |
+
"loss": 0.0757,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.49,
|
| 76 |
+
"grad_norm": 8.917645454406738,
|
| 77 |
+
"learning_rate": 1.9872771392183334e-05,
|
| 78 |
+
"loss": 0.1336,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.54,
|
| 83 |
+
"grad_norm": 4.956594944000244,
|
| 84 |
+
"learning_rate": 1.981571868482269e-05,
|
| 85 |
+
"loss": 0.0986,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.59,
|
| 90 |
+
"grad_norm": 9.08370590209961,
|
| 91 |
+
"learning_rate": 1.974824209889377e-05,
|
| 92 |
+
"loss": 0.0839,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.64,
|
| 97 |
+
"grad_norm": 12.914963722229004,
|
| 98 |
+
"learning_rate": 1.9670413291680223e-05,
|
| 99 |
+
"loss": 0.0909,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.69,
|
| 104 |
+
"grad_norm": 3.6358766555786133,
|
| 105 |
+
"learning_rate": 1.9582314914087344e-05,
|
| 106 |
+
"loss": 0.064,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.74,
|
| 111 |
+
"grad_norm": 7.188825607299805,
|
| 112 |
+
"learning_rate": 1.9484040522870333e-05,
|
| 113 |
+
"loss": 0.0969,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.79,
|
| 118 |
+
"grad_norm": 16.197107315063477,
|
| 119 |
+
"learning_rate": 1.9375694481280965e-05,
|
| 120 |
+
"loss": 0.0871,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.84,
|
| 125 |
+
"grad_norm": 11.690835952758789,
|
| 126 |
+
"learning_rate": 1.9257391848238212e-05,
|
| 127 |
+
"loss": 0.0726,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.89,
|
| 132 |
+
"grad_norm": 3.613584280014038,
|
| 133 |
+
"learning_rate": 1.9129258256140556e-05,
|
| 134 |
+
"loss": 0.0703,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.93,
|
| 139 |
+
"grad_norm": 6.19437313079834,
|
| 140 |
+
"learning_rate": 1.8991429777449674e-05,
|
| 141 |
+
"loss": 0.0939,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.98,
|
| 146 |
+
"grad_norm": 11.514800071716309,
|
| 147 |
+
"learning_rate": 1.884405278018722e-05,
|
| 148 |
+
"loss": 0.068,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_accuracy": 0.9707602339181286,
|
| 154 |
+
"eval_f1": 0.9722762986965865,
|
| 155 |
+
"eval_loss": 0.07348757982254028,
|
| 156 |
+
"eval_matthews_correlation": 0.8017394581463343,
|
| 157 |
+
"eval_precision": 0.9754056100703739,
|
| 158 |
+
"eval_recall": 0.9707602339181286,
|
| 159 |
+
"eval_runtime": 5.7659,
|
| 160 |
+
"eval_samples_per_second": 118.628,
|
| 161 |
+
"eval_steps_per_second": 7.458,
|
| 162 |
+
"step": 203
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.03,
|
| 166 |
+
"grad_norm": 10.175304412841797,
|
| 167 |
+
"learning_rate": 1.8687283772498205e-05,
|
| 168 |
+
"loss": 0.0845,
|
| 169 |
+
"step": 210
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.08,
|
| 173 |
+
"grad_norm": 2.231261968612671,
|
| 174 |
+
"learning_rate": 1.852128923644593e-05,
|
| 175 |
+
"loss": 0.0563,
|
| 176 |
+
"step": 220
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.13,
|
| 180 |
+
"grad_norm": 9.75424861907959,
|
| 181 |
+
"learning_rate": 1.8346245451215068e-05,
|
| 182 |
+
"loss": 0.0791,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.18,
|
| 187 |
+
"grad_norm": 9.436419486999512,
|
| 188 |
+
"learning_rate": 1.8162338305910636e-05,
|
| 189 |
+
"loss": 0.0751,
|
| 190 |
+
"step": 240
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.23,
|
| 194 |
+
"grad_norm": 5.413998126983643,
|
| 195 |
+
"learning_rate": 1.79697631021516e-05,
|
| 196 |
+
"loss": 0.0571,
|
| 197 |
+
"step": 250
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.28,
|
| 201 |
+
"grad_norm": 10.832895278930664,
|
| 202 |
+
"learning_rate": 1.776872434666882e-05,
|
| 203 |
+
"loss": 0.0903,
|
| 204 |
+
"step": 260
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.33,
|
| 208 |
+
"grad_norm": 14.028545379638672,
|
| 209 |
+
"learning_rate": 1.7559435534127534e-05,
|
| 210 |
+
"loss": 0.0924,
|
| 211 |
+
"step": 270
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.38,
|
| 215 |
+
"grad_norm": 6.962947368621826,
|
| 216 |
+
"learning_rate": 1.7342118920405035e-05,
|
| 217 |
+
"loss": 0.1018,
|
| 218 |
+
"step": 280
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.43,
|
| 222 |
+
"grad_norm": 12.277998924255371,
|
| 223 |
+
"learning_rate": 1.7117005286564344e-05,
|
| 224 |
+
"loss": 0.0651,
|
| 225 |
+
"step": 290
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.48,
|
| 229 |
+
"grad_norm": 3.5764994621276855,
|
| 230 |
+
"learning_rate": 1.688433369377444e-05,
|
| 231 |
+
"loss": 0.0811,
|
| 232 |
+
"step": 300
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.53,
|
| 236 |
+
"grad_norm": 6.763672351837158,
|
| 237 |
+
"learning_rate": 1.6644351229437416e-05,
|
| 238 |
+
"loss": 0.0785,
|
| 239 |
+
"step": 310
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.57,
|
| 243 |
+
"grad_norm": 3.3835597038269043,
|
| 244 |
+
"learning_rate": 1.63973127447921e-05,
|
| 245 |
+
"loss": 0.0482,
|
| 246 |
+
"step": 320
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.62,
|
| 250 |
+
"grad_norm": 6.173498153686523,
|
| 251 |
+
"learning_rate": 1.6143480584272794e-05,
|
| 252 |
+
"loss": 0.0593,
|
| 253 |
+
"step": 330
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.67,
|
| 257 |
+
"grad_norm": 7.676692008972168,
|
| 258 |
+
"learning_rate": 1.5883124306910563e-05,
|
| 259 |
+
"loss": 0.0678,
|
| 260 |
+
"step": 340
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.72,
|
| 264 |
+
"grad_norm": 2.495035171508789,
|
| 265 |
+
"learning_rate": 1.5616520400072963e-05,
|
| 266 |
+
"loss": 0.0572,
|
| 267 |
+
"step": 350
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.77,
|
| 271 |
+
"grad_norm": 16.871797561645508,
|
| 272 |
+
"learning_rate": 1.5343951985846096e-05,
|
| 273 |
+
"loss": 0.0756,
|
| 274 |
+
"step": 360
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.82,
|
| 278 |
+
"grad_norm": 2.3725368976593018,
|
| 279 |
+
"learning_rate": 1.5065708520370943e-05,
|
| 280 |
+
"loss": 0.0711,
|
| 281 |
+
"step": 370
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.87,
|
| 285 |
+
"grad_norm": 12.699337005615234,
|
| 286 |
+
"learning_rate": 1.4782085486453155e-05,
|
| 287 |
+
"loss": 0.0769,
|
| 288 |
+
"step": 380
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.92,
|
| 292 |
+
"grad_norm": 0.583565890789032,
|
| 293 |
+
"learning_rate": 1.4493384079772815e-05,
|
| 294 |
+
"loss": 0.0612,
|
| 295 |
+
"step": 390
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.97,
|
| 299 |
+
"grad_norm": 6.7856550216674805,
|
| 300 |
+
"learning_rate": 1.4199910889027335e-05,
|
| 301 |
+
"loss": 0.057,
|
| 302 |
+
"step": 400
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.0,
|
| 306 |
+
"eval_accuracy": 0.9722222222222222,
|
| 307 |
+
"eval_f1": 0.9728689575025272,
|
| 308 |
+
"eval_loss": 0.06863868236541748,
|
| 309 |
+
"eval_matthews_correlation": 0.7943272582319131,
|
| 310 |
+
"eval_precision": 0.9738281672617116,
|
| 311 |
+
"eval_recall": 0.9722222222222222,
|
| 312 |
+
"eval_runtime": 5.5104,
|
| 313 |
+
"eval_samples_per_second": 124.128,
|
| 314 |
+
"eval_steps_per_second": 7.803,
|
| 315 |
+
"step": 406
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.02,
|
| 319 |
+
"grad_norm": 2.3636648654937744,
|
| 320 |
+
"learning_rate": 1.390197757034721e-05,
|
| 321 |
+
"loss": 0.0745,
|
| 322 |
+
"step": 410
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.07,
|
| 326 |
+
"grad_norm": 21.622703552246094,
|
| 327 |
+
"learning_rate": 1.3599900516330382e-05,
|
| 328 |
+
"loss": 0.0724,
|
| 329 |
+
"step": 420
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.12,
|
| 333 |
+
"grad_norm": 11.821688652038574,
|
| 334 |
+
"learning_rate": 1.3294000520046666e-05,
|
| 335 |
+
"loss": 0.069,
|
| 336 |
+
"step": 430
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.16,
|
| 340 |
+
"grad_norm": 7.000888347625732,
|
| 341 |
+
"learning_rate": 1.2984602434369058e-05,
|
| 342 |
+
"loss": 0.0714,
|
| 343 |
+
"step": 440
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.21,
|
| 347 |
+
"grad_norm": 4.6769256591796875,
|
| 348 |
+
"learning_rate": 1.2672034826993716e-05,
|
| 349 |
+
"loss": 0.0509,
|
| 350 |
+
"step": 450
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.26,
|
| 354 |
+
"grad_norm": 1.7955386638641357,
|
| 355 |
+
"learning_rate": 1.235662963151493e-05,
|
| 356 |
+
"loss": 0.0512,
|
| 357 |
+
"step": 460
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.31,
|
| 361 |
+
"grad_norm": 22.078067779541016,
|
| 362 |
+
"learning_rate": 1.2038721794925689e-05,
|
| 363 |
+
"loss": 0.064,
|
| 364 |
+
"step": 470
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.36,
|
| 368 |
+
"grad_norm": 6.917346000671387,
|
| 369 |
+
"learning_rate": 1.1718648921918112e-05,
|
| 370 |
+
"loss": 0.0701,
|
| 371 |
+
"step": 480
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.41,
|
| 375 |
+
"grad_norm": 8.970315933227539,
|
| 376 |
+
"learning_rate": 1.1396750916361526e-05,
|
| 377 |
+
"loss": 0.0915,
|
| 378 |
+
"step": 490
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.46,
|
| 382 |
+
"grad_norm": 13.326787948608398,
|
| 383 |
+
"learning_rate": 1.1073369620338928e-05,
|
| 384 |
+
"loss": 0.078,
|
| 385 |
+
"step": 500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.51,
|
| 389 |
+
"grad_norm": 5.894493103027344,
|
| 390 |
+
"learning_rate": 1.074884845112512e-05,
|
| 391 |
+
"loss": 0.0636,
|
| 392 |
+
"step": 510
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.56,
|
| 396 |
+
"grad_norm": 5.459946155548096,
|
| 397 |
+
"learning_rate": 1.0423532036492077e-05,
|
| 398 |
+
"loss": 0.0711,
|
| 399 |
+
"step": 520
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.61,
|
| 403 |
+
"grad_norm": 8.83890151977539,
|
| 404 |
+
"learning_rate": 1.0097765848728825e-05,
|
| 405 |
+
"loss": 0.079,
|
| 406 |
+
"step": 530
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.66,
|
| 410 |
+
"grad_norm": 2.340186357498169,
|
| 411 |
+
"learning_rate": 9.771895837764438e-06,
|
| 412 |
+
"loss": 0.0449,
|
| 413 |
+
"step": 540
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.71,
|
| 417 |
+
"grad_norm": 11.93194580078125,
|
| 418 |
+
"learning_rate": 9.446268063783853e-06,
|
| 419 |
+
"loss": 0.0794,
|
| 420 |
+
"step": 550
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.76,
|
| 424 |
+
"grad_norm": 6.638481616973877,
|
| 425 |
+
"learning_rate": 9.121228329726563e-06,
|
| 426 |
+
"loss": 0.0614,
|
| 427 |
+
"step": 560
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.8,
|
| 431 |
+
"grad_norm": 5.963674068450928,
|
| 432 |
+
"learning_rate": 8.797121814058502e-06,
|
| 433 |
+
"loss": 0.0449,
|
| 434 |
+
"step": 570
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.85,
|
| 438 |
+
"grad_norm": 7.2139506340026855,
|
| 439 |
+
"learning_rate": 8.474292704207095e-06,
|
| 440 |
+
"loss": 0.0752,
|
| 441 |
+
"step": 580
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.9,
|
| 445 |
+
"grad_norm": 2.9632108211517334,
|
| 446 |
+
"learning_rate": 8.153083831048772e-06,
|
| 447 |
+
"loss": 0.0575,
|
| 448 |
+
"step": 590
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.95,
|
| 452 |
+
"grad_norm": 3.8059580326080322,
|
| 453 |
+
"learning_rate": 7.833836304837022e-06,
|
| 454 |
+
"loss": 0.046,
|
| 455 |
+
"step": 600
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.0,
|
| 459 |
+
"eval_accuracy": 0.9780701754385965,
|
| 460 |
+
"eval_f1": 0.9787695402282305,
|
| 461 |
+
"eval_loss": 0.05532665178179741,
|
| 462 |
+
"eval_matthews_correlation": 0.8420667383515437,
|
| 463 |
+
"eval_precision": 0.9800898852068441,
|
| 464 |
+
"eval_recall": 0.9780701754385965,
|
| 465 |
+
"eval_runtime": 5.6675,
|
| 466 |
+
"eval_samples_per_second": 120.688,
|
| 467 |
+
"eval_steps_per_second": 7.587,
|
| 468 |
+
"step": 609
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 3.0,
|
| 472 |
+
"grad_norm": 6.808079719543457,
|
| 473 |
+
"learning_rate": 7.516889152957744e-06,
|
| 474 |
+
"loss": 0.074,
|
| 475 |
+
"step": 610
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 3.05,
|
| 479 |
+
"grad_norm": 2.9367547035217285,
|
| 480 |
+
"learning_rate": 7.202578959896491e-06,
|
| 481 |
+
"loss": 0.0646,
|
| 482 |
+
"step": 620
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.1,
|
| 486 |
+
"grad_norm": 15.483344078063965,
|
| 487 |
+
"learning_rate": 6.891239509799932e-06,
|
| 488 |
+
"loss": 0.0835,
|
| 489 |
+
"step": 630
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.15,
|
| 493 |
+
"grad_norm": 8.343765258789062,
|
| 494 |
+
"learning_rate": 6.583201432011217e-06,
|
| 495 |
+
"loss": 0.0609,
|
| 496 |
+
"step": 640
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 3.2,
|
| 500 |
+
"grad_norm": 2.9499011039733887,
|
| 501 |
+
"learning_rate": 6.278791849955583e-06,
|
| 502 |
+
"loss": 0.0669,
|
| 503 |
+
"step": 650
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 3.25,
|
| 507 |
+
"grad_norm": 4.759853363037109,
|
| 508 |
+
"learning_rate": 5.978334033749076e-06,
|
| 509 |
+
"loss": 0.0434,
|
| 510 |
+
"step": 660
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 3.3,
|
| 514 |
+
"grad_norm": 3.5021698474884033,
|
| 515 |
+
"learning_rate": 5.682147056899361e-06,
|
| 516 |
+
"loss": 0.0389,
|
| 517 |
+
"step": 670
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 3.35,
|
| 521 |
+
"grad_norm": 8.20483112335205,
|
| 522 |
+
"learning_rate": 5.390545457463134e-06,
|
| 523 |
+
"loss": 0.0512,
|
| 524 |
+
"step": 680
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.39,
|
| 528 |
+
"grad_norm": 15.760091781616211,
|
| 529 |
+
"learning_rate": 5.103838904019993e-06,
|
| 530 |
+
"loss": 0.082,
|
| 531 |
+
"step": 690
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 3.44,
|
| 535 |
+
"grad_norm": 5.340324878692627,
|
| 536 |
+
"learning_rate": 4.822331866817478e-06,
|
| 537 |
+
"loss": 0.0412,
|
| 538 |
+
"step": 700
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.49,
|
| 542 |
+
"grad_norm": 2.386610507965088,
|
| 543 |
+
"learning_rate": 4.546323294436556e-06,
|
| 544 |
+
"loss": 0.0764,
|
| 545 |
+
"step": 710
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 3.54,
|
| 549 |
+
"grad_norm": 2.604590892791748,
|
| 550 |
+
"learning_rate": 4.276106296320828e-06,
|
| 551 |
+
"loss": 0.0322,
|
| 552 |
+
"step": 720
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 3.59,
|
| 556 |
+
"grad_norm": 2.6730122566223145,
|
| 557 |
+
"learning_rate": 4.0119678315067025e-06,
|
| 558 |
+
"loss": 0.0532,
|
| 559 |
+
"step": 730
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 3.64,
|
| 563 |
+
"grad_norm": 11.014791488647461,
|
| 564 |
+
"learning_rate": 3.754188403885013e-06,
|
| 565 |
+
"loss": 0.0788,
|
| 566 |
+
"step": 740
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.69,
|
| 570 |
+
"grad_norm": 2.279393196105957,
|
| 571 |
+
"learning_rate": 3.5030417643177416e-06,
|
| 572 |
+
"loss": 0.0465,
|
| 573 |
+
"step": 750
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 3.74,
|
| 577 |
+
"grad_norm": 7.80838680267334,
|
| 578 |
+
"learning_rate": 3.258794619926159e-06,
|
| 579 |
+
"loss": 0.0441,
|
| 580 |
+
"step": 760
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 3.79,
|
| 584 |
+
"grad_norm": 5.728611946105957,
|
| 585 |
+
"learning_rate": 3.021706350859147e-06,
|
| 586 |
+
"loss": 0.0476,
|
| 587 |
+
"step": 770
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.84,
|
| 591 |
+
"grad_norm": 2.4311773777008057,
|
| 592 |
+
"learning_rate": 2.792028734842418e-06,
|
| 593 |
+
"loss": 0.0421,
|
| 594 |
+
"step": 780
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 3.89,
|
| 598 |
+
"grad_norm": 19.25046730041504,
|
| 599 |
+
"learning_rate": 2.5700056798012164e-06,
|
| 600 |
+
"loss": 0.0829,
|
| 601 |
+
"step": 790
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 3.94,
|
| 605 |
+
"grad_norm": 16.992164611816406,
|
| 606 |
+
"learning_rate": 2.3558729648404065e-06,
|
| 607 |
+
"loss": 0.0694,
|
| 608 |
+
"step": 800
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.99,
|
| 612 |
+
"grad_norm": 1.1272871494293213,
|
| 613 |
+
"learning_rate": 2.1498579898570228e-06,
|
| 614 |
+
"loss": 0.0571,
|
| 615 |
+
"step": 810
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 4.0,
|
| 619 |
+
"eval_accuracy": 0.9780701754385965,
|
| 620 |
+
"eval_f1": 0.9777344542006784,
|
| 621 |
+
"eval_loss": 0.05015131086111069,
|
| 622 |
+
"eval_matthews_correlation": 0.8239461397313993,
|
| 623 |
+
"eval_precision": 0.9775337669457737,
|
| 624 |
+
"eval_recall": 0.9780701754385965,
|
| 625 |
+
"eval_runtime": 5.516,
|
| 626 |
+
"eval_samples_per_second": 124.003,
|
| 627 |
+
"eval_steps_per_second": 7.796,
|
| 628 |
+
"step": 813
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 4.03,
|
| 632 |
+
"grad_norm": 20.361764907836914,
|
| 633 |
+
"learning_rate": 1.952179534051183e-06,
|
| 634 |
+
"loss": 0.0545,
|
| 635 |
+
"step": 820
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 4.08,
|
| 639 |
+
"grad_norm": 12.892123222351074,
|
| 640 |
+
"learning_rate": 1.763047523591831e-06,
|
| 641 |
+
"loss": 0.0507,
|
| 642 |
+
"step": 830
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 4.13,
|
| 646 |
+
"grad_norm": 4.696685791015625,
|
| 647 |
+
"learning_rate": 1.5826628086839968e-06,
|
| 648 |
+
"loss": 0.0635,
|
| 649 |
+
"step": 840
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 4.18,
|
| 653 |
+
"grad_norm": 10.167694091796875,
|
| 654 |
+
"learning_rate": 1.41121695027438e-06,
|
| 655 |
+
"loss": 0.0547,
|
| 656 |
+
"step": 850
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 4.23,
|
| 660 |
+
"grad_norm": 4.277148723602295,
|
| 661 |
+
"learning_rate": 1.2488920166217034e-06,
|
| 662 |
+
"loss": 0.059,
|
| 663 |
+
"step": 860
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 4.28,
|
| 667 |
+
"grad_norm": 15.234513282775879,
|
| 668 |
+
"learning_rate": 1.095860389947928e-06,
|
| 669 |
+
"loss": 0.068,
|
| 670 |
+
"step": 870
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 4.33,
|
| 674 |
+
"grad_norm": 5.693934440612793,
|
| 675 |
+
"learning_rate": 9.522845833756001e-07,
|
| 676 |
+
"loss": 0.0451,
|
| 677 |
+
"step": 880
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 4.38,
|
| 681 |
+
"grad_norm": 10.728283882141113,
|
| 682 |
+
"learning_rate": 8.183170683457986e-07,
|
| 683 |
+
"loss": 0.0468,
|
| 684 |
+
"step": 890
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.43,
|
| 688 |
+
"grad_norm": 8.146360397338867,
|
| 689 |
+
"learning_rate": 6.941001126998892e-07,
|
| 690 |
+
"loss": 0.0378,
|
| 691 |
+
"step": 900
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 4.48,
|
| 695 |
+
"grad_norm": 3.4322080612182617,
|
| 696 |
+
"learning_rate": 5.797656295970955e-07,
|
| 697 |
+
"loss": 0.0418,
|
| 698 |
+
"step": 910
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 4.53,
|
| 702 |
+
"grad_norm": 3.0174903869628906,
|
| 703 |
+
"learning_rate": 4.754350374283001e-07,
|
| 704 |
+
"loss": 0.0441,
|
| 705 |
+
"step": 920
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 4.58,
|
| 709 |
+
"grad_norm": 16.416744232177734,
|
| 710 |
+
"learning_rate": 3.8121913087483033e-07,
|
| 711 |
+
"loss": 0.0495,
|
| 712 |
+
"step": 930
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 4.62,
|
| 716 |
+
"grad_norm": 12.529999732971191,
|
| 717 |
+
"learning_rate": 2.972179632491989e-07,
|
| 718 |
+
"loss": 0.0747,
|
| 719 |
+
"step": 940
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 4.67,
|
| 723 |
+
"grad_norm": 1.2379523515701294,
|
| 724 |
+
"learning_rate": 2.23520740242712e-07,
|
| 725 |
+
"loss": 0.0583,
|
| 726 |
+
"step": 950
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 4.72,
|
| 730 |
+
"grad_norm": 5.813112735748291,
|
| 731 |
+
"learning_rate": 1.602057251927891e-07,
|
| 732 |
+
"loss": 0.0612,
|
| 733 |
+
"step": 960
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 4.77,
|
| 737 |
+
"grad_norm": 9.207404136657715,
|
| 738 |
+
"learning_rate": 1.0734015597060222e-07,
|
| 739 |
+
"loss": 0.0462,
|
| 740 |
+
"step": 970
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 4.82,
|
| 744 |
+
"grad_norm": 10.823348999023438,
|
| 745 |
+
"learning_rate": 6.498017357731035e-08,
|
| 746 |
+
"loss": 0.0653,
|
| 747 |
+
"step": 980
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 4.87,
|
| 751 |
+
"grad_norm": 1.9045536518096924,
|
| 752 |
+
"learning_rate": 3.317076252467133e-08,
|
| 753 |
+
"loss": 0.0487,
|
| 754 |
+
"step": 990
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 4.92,
|
| 758 |
+
"grad_norm": 10.43856430053711,
|
| 759 |
+
"learning_rate": 1.1945703063402925e-08,
|
| 760 |
+
"loss": 0.0449,
|
| 761 |
+
"step": 1000
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 4.97,
|
| 765 |
+
"grad_norm": 4.215317249298096,
|
| 766 |
+
"learning_rate": 1.327535309979533e-09,
|
| 767 |
+
"loss": 0.0491,
|
| 768 |
+
"step": 1010
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.99,
|
| 772 |
+
"eval_accuracy": 0.9766081871345029,
|
| 773 |
+
"eval_f1": 0.9755931812139886,
|
| 774 |
+
"eval_loss": 0.04963676258921623,
|
| 775 |
+
"eval_matthews_correlation": 0.8055620626992487,
|
| 776 |
+
"eval_precision": 0.9756262052467682,
|
| 777 |
+
"eval_recall": 0.9766081871345029,
|
| 778 |
+
"eval_runtime": 5.7281,
|
| 779 |
+
"eval_samples_per_second": 119.41,
|
| 780 |
+
"eval_steps_per_second": 7.507,
|
| 781 |
+
"step": 1015
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 4.99,
|
| 785 |
+
"step": 1015,
|
| 786 |
+
"total_flos": 2.581447650539471e+18,
|
| 787 |
+
"train_loss": 0.08238832812591139,
|
| 788 |
+
"train_runtime": 705.5168,
|
| 789 |
+
"train_samples_per_second": 92.096,
|
| 790 |
+
"train_steps_per_second": 1.439
|
| 791 |
+
}
|
| 792 |
+
],
|
| 793 |
+
"logging_steps": 10,
|
| 794 |
+
"max_steps": 1015,
|
| 795 |
+
"num_input_tokens_seen": 0,
|
| 796 |
+
"num_train_epochs": 5,
|
| 797 |
+
"save_steps": 500,
|
| 798 |
+
"total_flos": 2.581447650539471e+18,
|
| 799 |
+
"train_batch_size": 16,
|
| 800 |
+
"trial_name": null,
|
| 801 |
+
"trial_params": null
|
| 802 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1b014cf88e1cf23f6b3fb34f9bc088d449783fed87357bd88dc05f4b020a200
|
| 3 |
+
size 5112
|