Model save
Browse files- README.md +90 -0
- all_results.json +16 -0
- config.json +54 -0
- eval_results.json +11 -0
- model.safetensors +3 -0
- preprocessor_config.json +37 -0
- train_results.json +8 -0
- trainer_state.json +1115 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/resnet-50
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
- f1
|
| 11 |
+
- precision
|
| 12 |
+
- recall
|
| 13 |
+
model-index:
|
| 14 |
+
- name: resnet-50-finetuned-FBark-1k
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Image Classification
|
| 18 |
+
type: image-classification
|
| 19 |
+
dataset:
|
| 20 |
+
name: imagefolder
|
| 21 |
+
type: imagefolder
|
| 22 |
+
config: default
|
| 23 |
+
split: train
|
| 24 |
+
args: default
|
| 25 |
+
metrics:
|
| 26 |
+
- name: Accuracy
|
| 27 |
+
type: accuracy
|
| 28 |
+
value: 0.9791666666666666
|
| 29 |
+
- name: F1
|
| 30 |
+
type: f1
|
| 31 |
+
value: 0.9807711022697999
|
| 32 |
+
- name: Precision
|
| 33 |
+
type: precision
|
| 34 |
+
value: 0.9788043478260869
|
| 35 |
+
- name: Recall
|
| 36 |
+
type: recall
|
| 37 |
+
value: 0.9833043478260869
|
| 38 |
+
---
|
| 39 |
+
|
| 40 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 41 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 42 |
+
|
| 43 |
+
# resnet-50-finetuned-FBark-1k
|
| 44 |
+
|
| 45 |
+
This model is a fine-tuned version of [microsoft/resnet-50](https://huggingface.co/microsoft/resnet-50) on the imagefolder dataset.
|
| 46 |
+
It achieves the following results on the evaluation set:
|
| 47 |
+
- Accuracy: 0.9792
|
| 48 |
+
- F1: 0.9808
|
| 49 |
+
- Loss: 0.0686
|
| 50 |
+
- Precision: 0.9788
|
| 51 |
+
- Recall: 0.9833
|
| 52 |
+
|
| 53 |
+
## Model description
|
| 54 |
+
|
| 55 |
+
More information needed
|
| 56 |
+
|
| 57 |
+
## Intended uses & limitations
|
| 58 |
+
|
| 59 |
+
More information needed
|
| 60 |
+
|
| 61 |
+
## Training and evaluation data
|
| 62 |
+
|
| 63 |
+
More information needed
|
| 64 |
+
|
| 65 |
+
## Training procedure
|
| 66 |
+
|
| 67 |
+
### Training hyperparameters
|
| 68 |
+
|
| 69 |
+
The following hyperparameters were used during training:
|
| 70 |
+
- learning_rate: 0.0001
|
| 71 |
+
- train_batch_size: 8
|
| 72 |
+
- eval_batch_size: 8
|
| 73 |
+
- seed: 42
|
| 74 |
+
- gradient_accumulation_steps: 4
|
| 75 |
+
- total_train_batch_size: 32
|
| 76 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 77 |
+
- lr_scheduler_type: linear
|
| 78 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 79 |
+
- num_epochs: 35
|
| 80 |
+
|
| 81 |
+
### Training results
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.39.3
|
| 88 |
+
- Pytorch 2.3.0
|
| 89 |
+
- Datasets 2.19.1
|
| 90 |
+
- Tokenizers 0.15.1
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_accuracy": 0.9479166666666666,
|
| 4 |
+
"eval_f1": 0.9507936507936507,
|
| 5 |
+
"eval_loss": 0.143270343542099,
|
| 6 |
+
"eval_precision": 0.9516161616161616,
|
| 7 |
+
"eval_recall": 0.9516161616161616,
|
| 8 |
+
"eval_runtime": 41.786,
|
| 9 |
+
"eval_samples_per_second": 2.297,
|
| 10 |
+
"eval_steps_per_second": 0.287,
|
| 11 |
+
"total_flos": 5.702134423852339e+17,
|
| 12 |
+
"train_loss": 0.6366229937190101,
|
| 13 |
+
"train_runtime": 42118.4284,
|
| 14 |
+
"train_samples_per_second": 0.637,
|
| 15 |
+
"train_steps_per_second": 0.02
|
| 16 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/resnet-50",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ResNetForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"depths": [
|
| 7 |
+
3,
|
| 8 |
+
4,
|
| 9 |
+
6,
|
| 10 |
+
3
|
| 11 |
+
],
|
| 12 |
+
"downsample_in_bottleneck": false,
|
| 13 |
+
"downsample_in_first_stage": false,
|
| 14 |
+
"embedding_size": 64,
|
| 15 |
+
"hidden_act": "relu",
|
| 16 |
+
"hidden_sizes": [
|
| 17 |
+
256,
|
| 18 |
+
512,
|
| 19 |
+
1024,
|
| 20 |
+
2048
|
| 21 |
+
],
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "Iinstia bijuga",
|
| 24 |
+
"1": "Mangifera indica",
|
| 25 |
+
"2": "Pterocarpus indicus",
|
| 26 |
+
"3": "Roystonea regia",
|
| 27 |
+
"4": "Tabebuia"
|
| 28 |
+
},
|
| 29 |
+
"label2id": {
|
| 30 |
+
"Iinstia bijuga": 0,
|
| 31 |
+
"Mangifera indica": 1,
|
| 32 |
+
"Pterocarpus indicus": 2,
|
| 33 |
+
"Roystonea regia": 3,
|
| 34 |
+
"Tabebuia": 4
|
| 35 |
+
},
|
| 36 |
+
"layer_type": "bottleneck",
|
| 37 |
+
"model_type": "resnet",
|
| 38 |
+
"num_channels": 3,
|
| 39 |
+
"out_features": [
|
| 40 |
+
"stage4"
|
| 41 |
+
],
|
| 42 |
+
"out_indices": [
|
| 43 |
+
4
|
| 44 |
+
],
|
| 45 |
+
"stage_names": [
|
| 46 |
+
"stem",
|
| 47 |
+
"stage1",
|
| 48 |
+
"stage2",
|
| 49 |
+
"stage3",
|
| 50 |
+
"stage4"
|
| 51 |
+
],
|
| 52 |
+
"torch_dtype": "float32",
|
| 53 |
+
"transformers_version": "4.39.3"
|
| 54 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_accuracy": 0.9479166666666666,
|
| 4 |
+
"eval_f1": 0.9507936507936507,
|
| 5 |
+
"eval_loss": 0.143270343542099,
|
| 6 |
+
"eval_precision": 0.9516161616161616,
|
| 7 |
+
"eval_recall": 0.9516161616161616,
|
| 8 |
+
"eval_runtime": 41.786,
|
| 9 |
+
"eval_samples_per_second": 2.297,
|
| 10 |
+
"eval_steps_per_second": 0.287
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b62125cf7821aa46f94acabbb35def2585b934f7ce94800889278ce2aabb16af
|
| 3 |
+
size 94327540
|
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": 224
|
| 36 |
+
}
|
| 37 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"total_flos": 5.702134423852339e+17,
|
| 4 |
+
"train_loss": 0.6366229937190101,
|
| 5 |
+
"train_runtime": 42118.4284,
|
| 6 |
+
"train_samples_per_second": 0.637,
|
| 7 |
+
"train_steps_per_second": 0.02
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9895833333333334,
|
| 3 |
+
"best_model_checkpoint": "resnet-50-finetuned-FBark-1k\\checkpoint-504",
|
| 4 |
+
"epoch": 35.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 840,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"step": 24,
|
| 14 |
+
"train_accuracy": 0.2803129074315515,
|
| 15 |
+
"train_f1": 0.15367112828819612,
|
| 16 |
+
"train_loss": 1.604638934135437,
|
| 17 |
+
"train_precision": 0.44938608458390183,
|
| 18 |
+
"train_recall": 0.24397350993377484,
|
| 19 |
+
"train_runtime": 556.5052,
|
| 20 |
+
"train_samples_per_second": 1.378,
|
| 21 |
+
"train_steps_per_second": 0.173
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.0,
|
| 25 |
+
"grad_norm": 0.9430338144302368,
|
| 26 |
+
"learning_rate": 2.857142857142857e-05,
|
| 27 |
+
"loss": 1.6081,
|
| 28 |
+
"step": 24
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 1.0,
|
| 32 |
+
"eval_accuracy": 0.3125,
|
| 33 |
+
"eval_f1": 0.2451058201058201,
|
| 34 |
+
"eval_loss": 1.6051779985427856,
|
| 35 |
+
"eval_precision": 0.45168539325842694,
|
| 36 |
+
"eval_recall": 0.316,
|
| 37 |
+
"eval_runtime": 63.6475,
|
| 38 |
+
"eval_samples_per_second": 1.508,
|
| 39 |
+
"eval_steps_per_second": 0.189,
|
| 40 |
+
"step": 24
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 2.0,
|
| 44 |
+
"step": 48,
|
| 45 |
+
"train_accuracy": 0.3285528031290743,
|
| 46 |
+
"train_f1": 0.20775853398507432,
|
| 47 |
+
"train_loss": 1.5834662914276123,
|
| 48 |
+
"train_precision": 0.24930855315747405,
|
| 49 |
+
"train_recall": 0.29161290322580646,
|
| 50 |
+
"train_runtime": 520.0484,
|
| 51 |
+
"train_samples_per_second": 1.475,
|
| 52 |
+
"train_steps_per_second": 0.185
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 2.0,
|
| 56 |
+
"grad_norm": 1.0157510042190552,
|
| 57 |
+
"learning_rate": 5.714285714285714e-05,
|
| 58 |
+
"loss": 1.5974,
|
| 59 |
+
"step": 48
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"eval_accuracy": 0.3125,
|
| 64 |
+
"eval_f1": 0.24752747252747248,
|
| 65 |
+
"eval_loss": 1.5845800638198853,
|
| 66 |
+
"eval_precision": 0.45168539325842694,
|
| 67 |
+
"eval_recall": 0.328,
|
| 68 |
+
"eval_runtime": 49.9527,
|
| 69 |
+
"eval_samples_per_second": 1.922,
|
| 70 |
+
"eval_steps_per_second": 0.24,
|
| 71 |
+
"step": 48
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0,
|
| 75 |
+
"step": 72,
|
| 76 |
+
"train_accuracy": 0.39765319426336376,
|
| 77 |
+
"train_f1": 0.2643894247741172,
|
| 78 |
+
"train_loss": 1.5244113206863403,
|
| 79 |
+
"train_precision": 0.4317930271167681,
|
| 80 |
+
"train_recall": 0.360322073127407,
|
| 81 |
+
"train_runtime": 240.6873,
|
| 82 |
+
"train_samples_per_second": 3.187,
|
| 83 |
+
"train_steps_per_second": 0.399
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 3.0,
|
| 87 |
+
"grad_norm": 1.2216145992279053,
|
| 88 |
+
"learning_rate": 8.571428571428571e-05,
|
| 89 |
+
"loss": 1.5662,
|
| 90 |
+
"step": 72
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.0,
|
| 94 |
+
"eval_accuracy": 0.3645833333333333,
|
| 95 |
+
"eval_f1": 0.29906685906685904,
|
| 96 |
+
"eval_loss": 1.5273982286453247,
|
| 97 |
+
"eval_precision": 0.4227642276422764,
|
| 98 |
+
"eval_recall": 0.41600000000000004,
|
| 99 |
+
"eval_runtime": 48.8206,
|
| 100 |
+
"eval_samples_per_second": 1.966,
|
| 101 |
+
"eval_steps_per_second": 0.246,
|
| 102 |
+
"step": 72
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.0,
|
| 106 |
+
"step": 96,
|
| 107 |
+
"train_accuracy": 0.560625814863103,
|
| 108 |
+
"train_f1": 0.48350804279434356,
|
| 109 |
+
"train_loss": 1.3708547353744507,
|
| 110 |
+
"train_precision": 0.6093729463212961,
|
| 111 |
+
"train_recall": 0.5236244720884755,
|
| 112 |
+
"train_runtime": 235.7829,
|
| 113 |
+
"train_samples_per_second": 3.253,
|
| 114 |
+
"train_steps_per_second": 0.407
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.0,
|
| 118 |
+
"grad_norm": 2.226966381072998,
|
| 119 |
+
"learning_rate": 9.841269841269841e-05,
|
| 120 |
+
"loss": 1.4744,
|
| 121 |
+
"step": 96
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.0,
|
| 125 |
+
"eval_accuracy": 0.4583333333333333,
|
| 126 |
+
"eval_f1": 0.4015730611897168,
|
| 127 |
+
"eval_loss": 1.3687443733215332,
|
| 128 |
+
"eval_precision": 0.5446969696969697,
|
| 129 |
+
"eval_recall": 0.49866666666666665,
|
| 130 |
+
"eval_runtime": 41.6732,
|
| 131 |
+
"eval_samples_per_second": 2.304,
|
| 132 |
+
"eval_steps_per_second": 0.288,
|
| 133 |
+
"step": 96
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 5.0,
|
| 137 |
+
"step": 120,
|
| 138 |
+
"train_accuracy": 0.7092568448500652,
|
| 139 |
+
"train_f1": 0.6330967191077577,
|
| 140 |
+
"train_loss": 1.2019156217575073,
|
| 141 |
+
"train_precision": 0.8111276153195639,
|
| 142 |
+
"train_recall": 0.674213659345549,
|
| 143 |
+
"train_runtime": 240.5993,
|
| 144 |
+
"train_samples_per_second": 3.188,
|
| 145 |
+
"train_steps_per_second": 0.399
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 5.0,
|
| 149 |
+
"grad_norm": 1.8955597877502441,
|
| 150 |
+
"learning_rate": 9.523809523809524e-05,
|
| 151 |
+
"loss": 1.3433,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 5.0,
|
| 156 |
+
"eval_accuracy": 0.6041666666666666,
|
| 157 |
+
"eval_f1": 0.5857735598991965,
|
| 158 |
+
"eval_loss": 1.2304556369781494,
|
| 159 |
+
"eval_precision": 0.71735347985348,
|
| 160 |
+
"eval_recall": 0.6600579710144927,
|
| 161 |
+
"eval_runtime": 47.1456,
|
| 162 |
+
"eval_samples_per_second": 2.036,
|
| 163 |
+
"eval_steps_per_second": 0.255,
|
| 164 |
+
"step": 120
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 6.0,
|
| 168 |
+
"step": 144,
|
| 169 |
+
"train_accuracy": 0.7848761408083442,
|
| 170 |
+
"train_f1": 0.7302362449292985,
|
| 171 |
+
"train_loss": 0.9897820353507996,
|
| 172 |
+
"train_precision": 0.8387314231533833,
|
| 173 |
+
"train_recall": 0.7594057545129057,
|
| 174 |
+
"train_runtime": 255.5505,
|
| 175 |
+
"train_samples_per_second": 3.001,
|
| 176 |
+
"train_steps_per_second": 0.376
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 6.0,
|
| 180 |
+
"grad_norm": 2.129802703857422,
|
| 181 |
+
"learning_rate": 9.206349206349206e-05,
|
| 182 |
+
"loss": 1.1817,
|
| 183 |
+
"step": 144
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.0,
|
| 187 |
+
"eval_accuracy": 0.6770833333333334,
|
| 188 |
+
"eval_f1": 0.6400730340445357,
|
| 189 |
+
"eval_loss": 1.0310033559799194,
|
| 190 |
+
"eval_precision": 0.7296066252587992,
|
| 191 |
+
"eval_recall": 0.7232463768115942,
|
| 192 |
+
"eval_runtime": 42.9425,
|
| 193 |
+
"eval_samples_per_second": 2.236,
|
| 194 |
+
"eval_steps_per_second": 0.279,
|
| 195 |
+
"step": 144
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 7.0,
|
| 199 |
+
"step": 168,
|
| 200 |
+
"train_accuracy": 0.8005215123859192,
|
| 201 |
+
"train_f1": 0.7573090410959133,
|
| 202 |
+
"train_loss": 0.8052171468734741,
|
| 203 |
+
"train_precision": 0.8403513129618181,
|
| 204 |
+
"train_recall": 0.7759091850696327,
|
| 205 |
+
"train_runtime": 229.5863,
|
| 206 |
+
"train_samples_per_second": 3.341,
|
| 207 |
+
"train_steps_per_second": 0.418
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.0,
|
| 211 |
+
"grad_norm": 2.2950687408447266,
|
| 212 |
+
"learning_rate": 8.888888888888889e-05,
|
| 213 |
+
"loss": 1.042,
|
| 214 |
+
"step": 168
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 7.0,
|
| 218 |
+
"eval_accuracy": 0.78125,
|
| 219 |
+
"eval_f1": 0.7573509711419949,
|
| 220 |
+
"eval_loss": 0.8407149910926819,
|
| 221 |
+
"eval_precision": 0.8095754475703325,
|
| 222 |
+
"eval_recall": 0.8141449275362319,
|
| 223 |
+
"eval_runtime": 41.1234,
|
| 224 |
+
"eval_samples_per_second": 2.334,
|
| 225 |
+
"eval_steps_per_second": 0.292,
|
| 226 |
+
"step": 168
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"step": 192,
|
| 231 |
+
"train_accuracy": 0.847457627118644,
|
| 232 |
+
"train_f1": 0.8206811188609147,
|
| 233 |
+
"train_loss": 0.6191346049308777,
|
| 234 |
+
"train_precision": 0.8718831316786277,
|
| 235 |
+
"train_recall": 0.8278987739042905,
|
| 236 |
+
"train_runtime": 238.0376,
|
| 237 |
+
"train_samples_per_second": 3.222,
|
| 238 |
+
"train_steps_per_second": 0.403
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 8.0,
|
| 242 |
+
"grad_norm": 1.7251057624816895,
|
| 243 |
+
"learning_rate": 8.571428571428571e-05,
|
| 244 |
+
"loss": 0.9057,
|
| 245 |
+
"step": 192
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 8.0,
|
| 249 |
+
"eval_accuracy": 0.8125,
|
| 250 |
+
"eval_f1": 0.7954355172644092,
|
| 251 |
+
"eval_loss": 0.6594930291175842,
|
| 252 |
+
"eval_precision": 0.8197173913043478,
|
| 253 |
+
"eval_recall": 0.8348985507246377,
|
| 254 |
+
"eval_runtime": 40.8504,
|
| 255 |
+
"eval_samples_per_second": 2.35,
|
| 256 |
+
"eval_steps_per_second": 0.294,
|
| 257 |
+
"step": 192
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 9.0,
|
| 261 |
+
"step": 216,
|
| 262 |
+
"train_accuracy": 0.8878748370273793,
|
| 263 |
+
"train_f1": 0.8760591514284144,
|
| 264 |
+
"train_loss": 0.5186784267425537,
|
| 265 |
+
"train_precision": 0.9006774019179493,
|
| 266 |
+
"train_recall": 0.8748786062624301,
|
| 267 |
+
"train_runtime": 229.2331,
|
| 268 |
+
"train_samples_per_second": 3.346,
|
| 269 |
+
"train_steps_per_second": 0.419
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 9.0,
|
| 273 |
+
"grad_norm": 2.9402055740356445,
|
| 274 |
+
"learning_rate": 8.253968253968255e-05,
|
| 275 |
+
"loss": 0.827,
|
| 276 |
+
"step": 216
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 9.0,
|
| 280 |
+
"eval_accuracy": 0.8958333333333334,
|
| 281 |
+
"eval_f1": 0.880350631136045,
|
| 282 |
+
"eval_loss": 0.5520768165588379,
|
| 283 |
+
"eval_precision": 0.8784420289855073,
|
| 284 |
+
"eval_recall": 0.903768115942029,
|
| 285 |
+
"eval_runtime": 41.7394,
|
| 286 |
+
"eval_samples_per_second": 2.3,
|
| 287 |
+
"eval_steps_per_second": 0.287,
|
| 288 |
+
"step": 216
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 10.0,
|
| 292 |
+
"step": 240,
|
| 293 |
+
"train_accuracy": 0.9308996088657105,
|
| 294 |
+
"train_f1": 0.9288928506201815,
|
| 295 |
+
"train_loss": 0.44946393370628357,
|
| 296 |
+
"train_precision": 0.9349933314548698,
|
| 297 |
+
"train_recall": 0.926414971755593,
|
| 298 |
+
"train_runtime": 228.8923,
|
| 299 |
+
"train_samples_per_second": 3.351,
|
| 300 |
+
"train_steps_per_second": 0.419
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 10.0,
|
| 304 |
+
"grad_norm": 2.2974233627319336,
|
| 305 |
+
"learning_rate": 7.936507936507937e-05,
|
| 306 |
+
"loss": 0.7259,
|
| 307 |
+
"step": 240
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 10.0,
|
| 311 |
+
"eval_accuracy": 0.8854166666666666,
|
| 312 |
+
"eval_f1": 0.872383707086129,
|
| 313 |
+
"eval_loss": 0.48959246277809143,
|
| 314 |
+
"eval_precision": 0.8708333333333332,
|
| 315 |
+
"eval_recall": 0.895768115942029,
|
| 316 |
+
"eval_runtime": 41.9767,
|
| 317 |
+
"eval_samples_per_second": 2.287,
|
| 318 |
+
"eval_steps_per_second": 0.286,
|
| 319 |
+
"step": 240
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 11.0,
|
| 323 |
+
"step": 264,
|
| 324 |
+
"train_accuracy": 0.9413298565840938,
|
| 325 |
+
"train_f1": 0.9417867419265207,
|
| 326 |
+
"train_loss": 0.3570455312728882,
|
| 327 |
+
"train_precision": 0.9453167745489296,
|
| 328 |
+
"train_recall": 0.9400834441504553,
|
| 329 |
+
"train_runtime": 248.5818,
|
| 330 |
+
"train_samples_per_second": 3.086,
|
| 331 |
+
"train_steps_per_second": 0.386
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 11.0,
|
| 335 |
+
"grad_norm": 2.431676149368286,
|
| 336 |
+
"learning_rate": 7.619047619047618e-05,
|
| 337 |
+
"loss": 0.6165,
|
| 338 |
+
"step": 264
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 11.0,
|
| 342 |
+
"eval_accuracy": 0.9479166666666666,
|
| 343 |
+
"eval_f1": 0.9415749105966498,
|
| 344 |
+
"eval_loss": 0.3730888366699219,
|
| 345 |
+
"eval_precision": 0.9344416027280478,
|
| 346 |
+
"eval_recall": 0.9565217391304348,
|
| 347 |
+
"eval_runtime": 40.6593,
|
| 348 |
+
"eval_samples_per_second": 2.361,
|
| 349 |
+
"eval_steps_per_second": 0.295,
|
| 350 |
+
"step": 264
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.0,
|
| 354 |
+
"step": 288,
|
| 355 |
+
"train_accuracy": 0.9621903520208605,
|
| 356 |
+
"train_f1": 0.9625360573738101,
|
| 357 |
+
"train_loss": 0.3030441999435425,
|
| 358 |
+
"train_precision": 0.9625629676041886,
|
| 359 |
+
"train_recall": 0.9629287708667498,
|
| 360 |
+
"train_runtime": 230.112,
|
| 361 |
+
"train_samples_per_second": 3.333,
|
| 362 |
+
"train_steps_per_second": 0.417
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 12.0,
|
| 366 |
+
"grad_norm": 4.103673934936523,
|
| 367 |
+
"learning_rate": 7.301587301587302e-05,
|
| 368 |
+
"loss": 0.6012,
|
| 369 |
+
"step": 288
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 12.0,
|
| 373 |
+
"eval_accuracy": 0.9479166666666666,
|
| 374 |
+
"eval_f1": 0.940039100684262,
|
| 375 |
+
"eval_loss": 0.33568963408470154,
|
| 376 |
+
"eval_precision": 0.9325757575757576,
|
| 377 |
+
"eval_recall": 0.9518840579710144,
|
| 378 |
+
"eval_runtime": 40.3994,
|
| 379 |
+
"eval_samples_per_second": 2.376,
|
| 380 |
+
"eval_steps_per_second": 0.297,
|
| 381 |
+
"step": 288
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 13.0,
|
| 385 |
+
"step": 312,
|
| 386 |
+
"train_accuracy": 0.9647979139504563,
|
| 387 |
+
"train_f1": 0.9653626267274655,
|
| 388 |
+
"train_loss": 0.2688322067260742,
|
| 389 |
+
"train_precision": 0.9675790735259078,
|
| 390 |
+
"train_recall": 0.9643315099918202,
|
| 391 |
+
"train_runtime": 232.8569,
|
| 392 |
+
"train_samples_per_second": 3.294,
|
| 393 |
+
"train_steps_per_second": 0.412
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 13.0,
|
| 397 |
+
"grad_norm": 2.537602663040161,
|
| 398 |
+
"learning_rate": 6.984126984126984e-05,
|
| 399 |
+
"loss": 0.5493,
|
| 400 |
+
"step": 312
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 13.0,
|
| 404 |
+
"eval_accuracy": 0.9791666666666666,
|
| 405 |
+
"eval_f1": 0.9779710144927536,
|
| 406 |
+
"eval_loss": 0.2760257124900818,
|
| 407 |
+
"eval_precision": 0.9779710144927536,
|
| 408 |
+
"eval_recall": 0.9779710144927536,
|
| 409 |
+
"eval_runtime": 41.3496,
|
| 410 |
+
"eval_samples_per_second": 2.322,
|
| 411 |
+
"eval_steps_per_second": 0.29,
|
| 412 |
+
"step": 312
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 14.0,
|
| 416 |
+
"step": 336,
|
| 417 |
+
"train_accuracy": 0.9739243807040417,
|
| 418 |
+
"train_f1": 0.9747740494132829,
|
| 419 |
+
"train_loss": 0.2121364027261734,
|
| 420 |
+
"train_precision": 0.9768091844642071,
|
| 421 |
+
"train_recall": 0.9737563601250352,
|
| 422 |
+
"train_runtime": 230.8623,
|
| 423 |
+
"train_samples_per_second": 3.322,
|
| 424 |
+
"train_steps_per_second": 0.416
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 14.0,
|
| 428 |
+
"grad_norm": 3.584627151489258,
|
| 429 |
+
"learning_rate": 6.666666666666667e-05,
|
| 430 |
+
"loss": 0.5346,
|
| 431 |
+
"step": 336
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 14.0,
|
| 435 |
+
"eval_accuracy": 0.9791666666666666,
|
| 436 |
+
"eval_f1": 0.9807711022697999,
|
| 437 |
+
"eval_loss": 0.20107173919677734,
|
| 438 |
+
"eval_precision": 0.9788043478260869,
|
| 439 |
+
"eval_recall": 0.9833043478260869,
|
| 440 |
+
"eval_runtime": 42.0342,
|
| 441 |
+
"eval_samples_per_second": 2.284,
|
| 442 |
+
"eval_steps_per_second": 0.285,
|
| 443 |
+
"step": 336
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 15.0,
|
| 447 |
+
"step": 360,
|
| 448 |
+
"train_accuracy": 0.9713168187744459,
|
| 449 |
+
"train_f1": 0.9713327368360707,
|
| 450 |
+
"train_loss": 0.19078123569488525,
|
| 451 |
+
"train_precision": 0.9721925646339006,
|
| 452 |
+
"train_recall": 0.9707366061842899,
|
| 453 |
+
"train_runtime": 231.7492,
|
| 454 |
+
"train_samples_per_second": 3.31,
|
| 455 |
+
"train_steps_per_second": 0.414
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 15.0,
|
| 459 |
+
"grad_norm": 2.587404251098633,
|
| 460 |
+
"learning_rate": 6.349206349206349e-05,
|
| 461 |
+
"loss": 0.4993,
|
| 462 |
+
"step": 360
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 15.0,
|
| 466 |
+
"eval_accuracy": 0.96875,
|
| 467 |
+
"eval_f1": 0.9668028483015461,
|
| 468 |
+
"eval_loss": 0.19429530203342438,
|
| 469 |
+
"eval_precision": 0.9606225296442688,
|
| 470 |
+
"eval_recall": 0.974608695652174,
|
| 471 |
+
"eval_runtime": 41.4858,
|
| 472 |
+
"eval_samples_per_second": 2.314,
|
| 473 |
+
"eval_steps_per_second": 0.289,
|
| 474 |
+
"step": 360
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 16.0,
|
| 478 |
+
"step": 384,
|
| 479 |
+
"train_accuracy": 0.9739243807040417,
|
| 480 |
+
"train_f1": 0.9741378672001157,
|
| 481 |
+
"train_loss": 0.18284346163272858,
|
| 482 |
+
"train_precision": 0.9753376725337921,
|
| 483 |
+
"train_recall": 0.9732292831146785,
|
| 484 |
+
"train_runtime": 228.9159,
|
| 485 |
+
"train_samples_per_second": 3.351,
|
| 486 |
+
"train_steps_per_second": 0.419
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 16.0,
|
| 490 |
+
"grad_norm": 2.460467576980591,
|
| 491 |
+
"learning_rate": 6.0317460317460316e-05,
|
| 492 |
+
"loss": 0.4662,
|
| 493 |
+
"step": 384
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 16.0,
|
| 497 |
+
"eval_accuracy": 0.9791666666666666,
|
| 498 |
+
"eval_f1": 0.9807711022697999,
|
| 499 |
+
"eval_loss": 0.1412990242242813,
|
| 500 |
+
"eval_precision": 0.9788043478260869,
|
| 501 |
+
"eval_recall": 0.9833043478260869,
|
| 502 |
+
"eval_runtime": 40.0644,
|
| 503 |
+
"eval_samples_per_second": 2.396,
|
| 504 |
+
"eval_steps_per_second": 0.3,
|
| 505 |
+
"step": 384
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 17.0,
|
| 509 |
+
"step": 408,
|
| 510 |
+
"train_accuracy": 0.9778357235984355,
|
| 511 |
+
"train_f1": 0.9776240827714024,
|
| 512 |
+
"train_loss": 0.145884707570076,
|
| 513 |
+
"train_precision": 0.9778175327096849,
|
| 514 |
+
"train_recall": 0.9778137736081629,
|
| 515 |
+
"train_runtime": 230.228,
|
| 516 |
+
"train_samples_per_second": 3.331,
|
| 517 |
+
"train_steps_per_second": 0.417
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 17.0,
|
| 521 |
+
"grad_norm": 2.5160224437713623,
|
| 522 |
+
"learning_rate": 5.714285714285714e-05,
|
| 523 |
+
"loss": 0.4722,
|
| 524 |
+
"step": 408
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 17.0,
|
| 528 |
+
"eval_accuracy": 0.9791666666666666,
|
| 529 |
+
"eval_f1": 0.9807711022697999,
|
| 530 |
+
"eval_loss": 0.1360517293214798,
|
| 531 |
+
"eval_precision": 0.9788043478260869,
|
| 532 |
+
"eval_recall": 0.9833043478260869,
|
| 533 |
+
"eval_runtime": 45.6511,
|
| 534 |
+
"eval_samples_per_second": 2.103,
|
| 535 |
+
"eval_steps_per_second": 0.263,
|
| 536 |
+
"step": 408
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 18.0,
|
| 540 |
+
"step": 432,
|
| 541 |
+
"train_accuracy": 0.9726205997392438,
|
| 542 |
+
"train_f1": 0.973105656865344,
|
| 543 |
+
"train_loss": 0.16023999452590942,
|
| 544 |
+
"train_precision": 0.9736536976180454,
|
| 545 |
+
"train_recall": 0.973107499735422,
|
| 546 |
+
"train_runtime": 232.9746,
|
| 547 |
+
"train_samples_per_second": 3.292,
|
| 548 |
+
"train_steps_per_second": 0.412
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 18.0,
|
| 552 |
+
"grad_norm": 2.056008815765381,
|
| 553 |
+
"learning_rate": 5.396825396825397e-05,
|
| 554 |
+
"loss": 0.4112,
|
| 555 |
+
"step": 432
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 18.0,
|
| 559 |
+
"eval_accuracy": 0.9791666666666666,
|
| 560 |
+
"eval_f1": 0.9807711022697999,
|
| 561 |
+
"eval_loss": 0.14697764813899994,
|
| 562 |
+
"eval_precision": 0.9788043478260869,
|
| 563 |
+
"eval_recall": 0.9833043478260869,
|
| 564 |
+
"eval_runtime": 41.0241,
|
| 565 |
+
"eval_samples_per_second": 2.34,
|
| 566 |
+
"eval_steps_per_second": 0.293,
|
| 567 |
+
"step": 432
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 19.0,
|
| 571 |
+
"step": 456,
|
| 572 |
+
"train_accuracy": 0.9791395045632334,
|
| 573 |
+
"train_f1": 0.9790547334136079,
|
| 574 |
+
"train_loss": 0.12944301962852478,
|
| 575 |
+
"train_precision": 0.9802981933219288,
|
| 576 |
+
"train_recall": 0.9781710425016916,
|
| 577 |
+
"train_runtime": 231.3669,
|
| 578 |
+
"train_samples_per_second": 3.315,
|
| 579 |
+
"train_steps_per_second": 0.415
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 19.0,
|
| 583 |
+
"grad_norm": 2.8184328079223633,
|
| 584 |
+
"learning_rate": 5.0793650793650794e-05,
|
| 585 |
+
"loss": 0.3497,
|
| 586 |
+
"step": 456
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 19.0,
|
| 590 |
+
"eval_accuracy": 0.96875,
|
| 591 |
+
"eval_f1": 0.9724490963166323,
|
| 592 |
+
"eval_loss": 0.11115691810846329,
|
| 593 |
+
"eval_precision": 0.9708333333333332,
|
| 594 |
+
"eval_recall": 0.9753043478260869,
|
| 595 |
+
"eval_runtime": 40.9709,
|
| 596 |
+
"eval_samples_per_second": 2.343,
|
| 597 |
+
"eval_steps_per_second": 0.293,
|
| 598 |
+
"step": 456
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 20.0,
|
| 602 |
+
"step": 480,
|
| 603 |
+
"train_accuracy": 0.9726205997392438,
|
| 604 |
+
"train_f1": 0.974010596954358,
|
| 605 |
+
"train_loss": 0.12856590747833252,
|
| 606 |
+
"train_precision": 0.9757760047994936,
|
| 607 |
+
"train_recall": 0.9727336882447055,
|
| 608 |
+
"train_runtime": 229.914,
|
| 609 |
+
"train_samples_per_second": 3.336,
|
| 610 |
+
"train_steps_per_second": 0.418
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 20.0,
|
| 614 |
+
"grad_norm": 2.9835314750671387,
|
| 615 |
+
"learning_rate": 4.761904761904762e-05,
|
| 616 |
+
"loss": 0.383,
|
| 617 |
+
"step": 480
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 20.0,
|
| 621 |
+
"eval_accuracy": 0.96875,
|
| 622 |
+
"eval_f1": 0.9668028483015461,
|
| 623 |
+
"eval_loss": 0.1326003223657608,
|
| 624 |
+
"eval_precision": 0.9606225296442688,
|
| 625 |
+
"eval_recall": 0.974608695652174,
|
| 626 |
+
"eval_runtime": 41.6077,
|
| 627 |
+
"eval_samples_per_second": 2.307,
|
| 628 |
+
"eval_steps_per_second": 0.288,
|
| 629 |
+
"step": 480
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 21.0,
|
| 633 |
+
"step": 504,
|
| 634 |
+
"train_accuracy": 0.984354628422425,
|
| 635 |
+
"train_f1": 0.985242413654858,
|
| 636 |
+
"train_loss": 0.10190501064062119,
|
| 637 |
+
"train_precision": 0.9852433860091777,
|
| 638 |
+
"train_recall": 0.985650440594714,
|
| 639 |
+
"train_runtime": 232.6041,
|
| 640 |
+
"train_samples_per_second": 3.297,
|
| 641 |
+
"train_steps_per_second": 0.413
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 21.0,
|
| 645 |
+
"grad_norm": 3.4986414909362793,
|
| 646 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 647 |
+
"loss": 0.3835,
|
| 648 |
+
"step": 504
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 21.0,
|
| 652 |
+
"eval_accuracy": 0.9895833333333334,
|
| 653 |
+
"eval_f1": 0.9891039426523298,
|
| 654 |
+
"eval_loss": 0.09684587270021439,
|
| 655 |
+
"eval_precision": 0.9875,
|
| 656 |
+
"eval_recall": 0.9913043478260869,
|
| 657 |
+
"eval_runtime": 42.0198,
|
| 658 |
+
"eval_samples_per_second": 2.285,
|
| 659 |
+
"eval_steps_per_second": 0.286,
|
| 660 |
+
"step": 504
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 22.0,
|
| 664 |
+
"step": 528,
|
| 665 |
+
"train_accuracy": 0.9856584093872229,
|
| 666 |
+
"train_f1": 0.9857542719271224,
|
| 667 |
+
"train_loss": 0.10507090389728546,
|
| 668 |
+
"train_precision": 0.9866456571269954,
|
| 669 |
+
"train_recall": 0.9850819589725311,
|
| 670 |
+
"train_runtime": 231.3064,
|
| 671 |
+
"train_samples_per_second": 3.316,
|
| 672 |
+
"train_steps_per_second": 0.415
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 22.0,
|
| 676 |
+
"grad_norm": 3.1002776622772217,
|
| 677 |
+
"learning_rate": 4.126984126984127e-05,
|
| 678 |
+
"loss": 0.37,
|
| 679 |
+
"step": 528
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 22.0,
|
| 683 |
+
"eval_accuracy": 0.9791666666666666,
|
| 684 |
+
"eval_f1": 0.9807711022697999,
|
| 685 |
+
"eval_loss": 0.10016053915023804,
|
| 686 |
+
"eval_precision": 0.9788043478260869,
|
| 687 |
+
"eval_recall": 0.9833043478260869,
|
| 688 |
+
"eval_runtime": 41.4299,
|
| 689 |
+
"eval_samples_per_second": 2.317,
|
| 690 |
+
"eval_steps_per_second": 0.29,
|
| 691 |
+
"step": 528
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 23.0,
|
| 695 |
+
"step": 552,
|
| 696 |
+
"train_accuracy": 0.9908735332464146,
|
| 697 |
+
"train_f1": 0.9908835885486533,
|
| 698 |
+
"train_loss": 0.09519027173519135,
|
| 699 |
+
"train_precision": 0.9915443252399774,
|
| 700 |
+
"train_recall": 0.9903473945409429,
|
| 701 |
+
"train_runtime": 230.8399,
|
| 702 |
+
"train_samples_per_second": 3.323,
|
| 703 |
+
"train_steps_per_second": 0.416
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 23.0,
|
| 707 |
+
"grad_norm": 1.822899341583252,
|
| 708 |
+
"learning_rate": 3.809523809523809e-05,
|
| 709 |
+
"loss": 0.4095,
|
| 710 |
+
"step": 552
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 23.0,
|
| 714 |
+
"eval_accuracy": 0.9895833333333334,
|
| 715 |
+
"eval_f1": 0.9891039426523298,
|
| 716 |
+
"eval_loss": 0.08792722970247269,
|
| 717 |
+
"eval_precision": 0.9875,
|
| 718 |
+
"eval_recall": 0.9913043478260869,
|
| 719 |
+
"eval_runtime": 42.0359,
|
| 720 |
+
"eval_samples_per_second": 2.284,
|
| 721 |
+
"eval_steps_per_second": 0.285,
|
| 722 |
+
"step": 552
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 24.0,
|
| 726 |
+
"step": 576,
|
| 727 |
+
"train_accuracy": 0.9869621903520208,
|
| 728 |
+
"train_f1": 0.987107806070091,
|
| 729 |
+
"train_loss": 0.10206671804189682,
|
| 730 |
+
"train_precision": 0.9869968656131645,
|
| 731 |
+
"train_recall": 0.9872260989174195,
|
| 732 |
+
"train_runtime": 232.0205,
|
| 733 |
+
"train_samples_per_second": 3.306,
|
| 734 |
+
"train_steps_per_second": 0.414
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 24.0,
|
| 738 |
+
"grad_norm": 1.2630761861801147,
|
| 739 |
+
"learning_rate": 3.492063492063492e-05,
|
| 740 |
+
"loss": 0.3128,
|
| 741 |
+
"step": 576
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 24.0,
|
| 745 |
+
"eval_accuracy": 0.9791666666666666,
|
| 746 |
+
"eval_f1": 0.9807711022697999,
|
| 747 |
+
"eval_loss": 0.09869974106550217,
|
| 748 |
+
"eval_precision": 0.9788043478260869,
|
| 749 |
+
"eval_recall": 0.9833043478260869,
|
| 750 |
+
"eval_runtime": 41.2033,
|
| 751 |
+
"eval_samples_per_second": 2.33,
|
| 752 |
+
"eval_steps_per_second": 0.291,
|
| 753 |
+
"step": 576
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 25.0,
|
| 757 |
+
"step": 600,
|
| 758 |
+
"train_accuracy": 0.9817470664928292,
|
| 759 |
+
"train_f1": 0.982066284449598,
|
| 760 |
+
"train_loss": 0.0919913500547409,
|
| 761 |
+
"train_precision": 0.9819293180262086,
|
| 762 |
+
"train_recall": 0.9825659761731764,
|
| 763 |
+
"train_runtime": 230.888,
|
| 764 |
+
"train_samples_per_second": 3.322,
|
| 765 |
+
"train_steps_per_second": 0.416
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 25.0,
|
| 769 |
+
"grad_norm": 4.3139190673828125,
|
| 770 |
+
"learning_rate": 3.1746031746031745e-05,
|
| 771 |
+
"loss": 0.3509,
|
| 772 |
+
"step": 600
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 25.0,
|
| 776 |
+
"eval_accuracy": 0.9895833333333334,
|
| 777 |
+
"eval_f1": 0.9891039426523298,
|
| 778 |
+
"eval_loss": 0.06910046190023422,
|
| 779 |
+
"eval_precision": 0.9875,
|
| 780 |
+
"eval_recall": 0.9913043478260869,
|
| 781 |
+
"eval_runtime": 40.8366,
|
| 782 |
+
"eval_samples_per_second": 2.351,
|
| 783 |
+
"eval_steps_per_second": 0.294,
|
| 784 |
+
"step": 600
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 26.0,
|
| 788 |
+
"step": 624,
|
| 789 |
+
"train_accuracy": 0.9817470664928292,
|
| 790 |
+
"train_f1": 0.9813015231469322,
|
| 791 |
+
"train_loss": 0.09761997312307358,
|
| 792 |
+
"train_precision": 0.9806165023306634,
|
| 793 |
+
"train_recall": 0.9825411622773947,
|
| 794 |
+
"train_runtime": 231.5274,
|
| 795 |
+
"train_samples_per_second": 3.313,
|
| 796 |
+
"train_steps_per_second": 0.415
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 26.0,
|
| 800 |
+
"grad_norm": 3.532228708267212,
|
| 801 |
+
"learning_rate": 2.857142857142857e-05,
|
| 802 |
+
"loss": 0.3437,
|
| 803 |
+
"step": 624
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 26.0,
|
| 807 |
+
"eval_accuracy": 0.9895833333333334,
|
| 808 |
+
"eval_f1": 0.9891039426523298,
|
| 809 |
+
"eval_loss": 0.07000591605901718,
|
| 810 |
+
"eval_precision": 0.9875,
|
| 811 |
+
"eval_recall": 0.9913043478260869,
|
| 812 |
+
"eval_runtime": 41.7728,
|
| 813 |
+
"eval_samples_per_second": 2.298,
|
| 814 |
+
"eval_steps_per_second": 0.287,
|
| 815 |
+
"step": 624
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 27.0,
|
| 819 |
+
"step": 648,
|
| 820 |
+
"train_accuracy": 0.984354628422425,
|
| 821 |
+
"train_f1": 0.984768710004493,
|
| 822 |
+
"train_loss": 0.09194578230381012,
|
| 823 |
+
"train_precision": 0.9846057628135428,
|
| 824 |
+
"train_recall": 0.9850342998172179,
|
| 825 |
+
"train_runtime": 230.2394,
|
| 826 |
+
"train_samples_per_second": 3.331,
|
| 827 |
+
"train_steps_per_second": 0.417
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 27.0,
|
| 831 |
+
"grad_norm": 2.549860954284668,
|
| 832 |
+
"learning_rate": 2.5396825396825397e-05,
|
| 833 |
+
"loss": 0.3199,
|
| 834 |
+
"step": 648
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 27.0,
|
| 838 |
+
"eval_accuracy": 0.9791666666666666,
|
| 839 |
+
"eval_f1": 0.9807711022697999,
|
| 840 |
+
"eval_loss": 0.09211982041597366,
|
| 841 |
+
"eval_precision": 0.9788043478260869,
|
| 842 |
+
"eval_recall": 0.9833043478260869,
|
| 843 |
+
"eval_runtime": 40.9626,
|
| 844 |
+
"eval_samples_per_second": 2.344,
|
| 845 |
+
"eval_steps_per_second": 0.293,
|
| 846 |
+
"step": 648
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 28.0,
|
| 850 |
+
"step": 672,
|
| 851 |
+
"train_accuracy": 0.9895697522816167,
|
| 852 |
+
"train_f1": 0.9894324540918479,
|
| 853 |
+
"train_loss": 0.07698369771242142,
|
| 854 |
+
"train_precision": 0.9899059425153529,
|
| 855 |
+
"train_recall": 0.9890969204264518,
|
| 856 |
+
"train_runtime": 229.7842,
|
| 857 |
+
"train_samples_per_second": 3.338,
|
| 858 |
+
"train_steps_per_second": 0.418
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 28.0,
|
| 862 |
+
"grad_norm": 3.8666512966156006,
|
| 863 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 864 |
+
"loss": 0.3209,
|
| 865 |
+
"step": 672
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 28.0,
|
| 869 |
+
"eval_accuracy": 0.9895833333333334,
|
| 870 |
+
"eval_f1": 0.9891039426523298,
|
| 871 |
+
"eval_loss": 0.09196734428405762,
|
| 872 |
+
"eval_precision": 0.9875,
|
| 873 |
+
"eval_recall": 0.9913043478260869,
|
| 874 |
+
"eval_runtime": 41.6269,
|
| 875 |
+
"eval_samples_per_second": 2.306,
|
| 876 |
+
"eval_steps_per_second": 0.288,
|
| 877 |
+
"step": 672
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 29.0,
|
| 881 |
+
"step": 696,
|
| 882 |
+
"train_accuracy": 0.9817470664928292,
|
| 883 |
+
"train_f1": 0.98251652272311,
|
| 884 |
+
"train_loss": 0.0892641544342041,
|
| 885 |
+
"train_precision": 0.9842240801851391,
|
| 886 |
+
"train_recall": 0.9815242050409255,
|
| 887 |
+
"train_runtime": 17904.397,
|
| 888 |
+
"train_samples_per_second": 0.043,
|
| 889 |
+
"train_steps_per_second": 0.005
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 29.0,
|
| 893 |
+
"grad_norm": 1.3375637531280518,
|
| 894 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 895 |
+
"loss": 0.3183,
|
| 896 |
+
"step": 696
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 29.0,
|
| 900 |
+
"eval_accuracy": 0.9895833333333334,
|
| 901 |
+
"eval_f1": 0.9891039426523298,
|
| 902 |
+
"eval_loss": 0.06283224374055862,
|
| 903 |
+
"eval_precision": 0.9875,
|
| 904 |
+
"eval_recall": 0.9913043478260869,
|
| 905 |
+
"eval_runtime": 45.9691,
|
| 906 |
+
"eval_samples_per_second": 2.088,
|
| 907 |
+
"eval_steps_per_second": 0.261,
|
| 908 |
+
"step": 696
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 30.0,
|
| 912 |
+
"step": 720,
|
| 913 |
+
"train_accuracy": 0.9830508474576272,
|
| 914 |
+
"train_f1": 0.9832111511301278,
|
| 915 |
+
"train_loss": 0.08690536767244339,
|
| 916 |
+
"train_precision": 0.9836087367732624,
|
| 917 |
+
"train_recall": 0.9828637429225561,
|
| 918 |
+
"train_runtime": 229.6055,
|
| 919 |
+
"train_samples_per_second": 3.341,
|
| 920 |
+
"train_steps_per_second": 0.418
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 30.0,
|
| 924 |
+
"grad_norm": 2.389967203140259,
|
| 925 |
+
"learning_rate": 1.5873015873015872e-05,
|
| 926 |
+
"loss": 0.299,
|
| 927 |
+
"step": 720
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 30.0,
|
| 931 |
+
"eval_accuracy": 0.9791666666666666,
|
| 932 |
+
"eval_f1": 0.9807711022697999,
|
| 933 |
+
"eval_loss": 0.09559374302625656,
|
| 934 |
+
"eval_precision": 0.9788043478260869,
|
| 935 |
+
"eval_recall": 0.9833043478260869,
|
| 936 |
+
"eval_runtime": 41.6431,
|
| 937 |
+
"eval_samples_per_second": 2.305,
|
| 938 |
+
"eval_steps_per_second": 0.288,
|
| 939 |
+
"step": 720
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 31.0,
|
| 943 |
+
"step": 744,
|
| 944 |
+
"train_accuracy": 0.9869621903520208,
|
| 945 |
+
"train_f1": 0.9867448459593989,
|
| 946 |
+
"train_loss": 0.08398473262786865,
|
| 947 |
+
"train_precision": 0.9860696436282815,
|
| 948 |
+
"train_recall": 0.9876175485415614,
|
| 949 |
+
"train_runtime": 229.4597,
|
| 950 |
+
"train_samples_per_second": 3.343,
|
| 951 |
+
"train_steps_per_second": 0.418
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 31.0,
|
| 955 |
+
"grad_norm": 3.2682044506073,
|
| 956 |
+
"learning_rate": 1.2698412698412699e-05,
|
| 957 |
+
"loss": 0.3617,
|
| 958 |
+
"step": 744
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 31.0,
|
| 962 |
+
"eval_accuracy": 0.9895833333333334,
|
| 963 |
+
"eval_f1": 0.9891039426523298,
|
| 964 |
+
"eval_loss": 0.06870979815721512,
|
| 965 |
+
"eval_precision": 0.9875,
|
| 966 |
+
"eval_recall": 0.9913043478260869,
|
| 967 |
+
"eval_runtime": 41.3418,
|
| 968 |
+
"eval_samples_per_second": 2.322,
|
| 969 |
+
"eval_steps_per_second": 0.29,
|
| 970 |
+
"step": 744
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 32.0,
|
| 974 |
+
"step": 768,
|
| 975 |
+
"train_accuracy": 0.9830508474576272,
|
| 976 |
+
"train_f1": 0.9825972137742822,
|
| 977 |
+
"train_loss": 0.0890418067574501,
|
| 978 |
+
"train_precision": 0.9833445096300124,
|
| 979 |
+
"train_recall": 0.9819400560702711,
|
| 980 |
+
"train_runtime": 230.1795,
|
| 981 |
+
"train_samples_per_second": 3.332,
|
| 982 |
+
"train_steps_per_second": 0.417
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 32.0,
|
| 986 |
+
"grad_norm": 3.531033754348755,
|
| 987 |
+
"learning_rate": 9.523809523809523e-06,
|
| 988 |
+
"loss": 0.3753,
|
| 989 |
+
"step": 768
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 32.0,
|
| 993 |
+
"eval_accuracy": 0.9791666666666666,
|
| 994 |
+
"eval_f1": 0.9807711022697999,
|
| 995 |
+
"eval_loss": 0.09568967670202255,
|
| 996 |
+
"eval_precision": 0.9788043478260869,
|
| 997 |
+
"eval_recall": 0.9833043478260869,
|
| 998 |
+
"eval_runtime": 42.1426,
|
| 999 |
+
"eval_samples_per_second": 2.278,
|
| 1000 |
+
"eval_steps_per_second": 0.285,
|
| 1001 |
+
"step": 768
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 33.0,
|
| 1005 |
+
"step": 792,
|
| 1006 |
+
"train_accuracy": 0.9791395045632334,
|
| 1007 |
+
"train_f1": 0.9795263690474447,
|
| 1008 |
+
"train_loss": 0.08663059771060944,
|
| 1009 |
+
"train_precision": 0.9798244808980103,
|
| 1010 |
+
"train_recall": 0.9797057099136859,
|
| 1011 |
+
"train_runtime": 235.7792,
|
| 1012 |
+
"train_samples_per_second": 3.253,
|
| 1013 |
+
"train_steps_per_second": 0.407
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 33.0,
|
| 1017 |
+
"grad_norm": 3.389780044555664,
|
| 1018 |
+
"learning_rate": 6.349206349206349e-06,
|
| 1019 |
+
"loss": 0.3168,
|
| 1020 |
+
"step": 792
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 33.0,
|
| 1024 |
+
"eval_accuracy": 0.9895833333333334,
|
| 1025 |
+
"eval_f1": 0.9891039426523298,
|
| 1026 |
+
"eval_loss": 0.048726532608270645,
|
| 1027 |
+
"eval_precision": 0.9875,
|
| 1028 |
+
"eval_recall": 0.9913043478260869,
|
| 1029 |
+
"eval_runtime": 44.3738,
|
| 1030 |
+
"eval_samples_per_second": 2.163,
|
| 1031 |
+
"eval_steps_per_second": 0.27,
|
| 1032 |
+
"step": 792
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 34.0,
|
| 1036 |
+
"step": 816,
|
| 1037 |
+
"train_accuracy": 0.9869621903520208,
|
| 1038 |
+
"train_f1": 0.9866353664936988,
|
| 1039 |
+
"train_loss": 0.0734185054898262,
|
| 1040 |
+
"train_precision": 0.9862292242559578,
|
| 1041 |
+
"train_recall": 0.9871329235604117,
|
| 1042 |
+
"train_runtime": 233.6307,
|
| 1043 |
+
"train_samples_per_second": 3.283,
|
| 1044 |
+
"train_steps_per_second": 0.411
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 34.0,
|
| 1048 |
+
"grad_norm": 3.781233787536621,
|
| 1049 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 1050 |
+
"loss": 0.3371,
|
| 1051 |
+
"step": 816
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 34.0,
|
| 1055 |
+
"eval_accuracy": 0.9895833333333334,
|
| 1056 |
+
"eval_f1": 0.9891039426523298,
|
| 1057 |
+
"eval_loss": 0.06520267575979233,
|
| 1058 |
+
"eval_precision": 0.9875,
|
| 1059 |
+
"eval_recall": 0.9913043478260869,
|
| 1060 |
+
"eval_runtime": 48.9682,
|
| 1061 |
+
"eval_samples_per_second": 1.96,
|
| 1062 |
+
"eval_steps_per_second": 0.245,
|
| 1063 |
+
"step": 816
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 35.0,
|
| 1067 |
+
"step": 840,
|
| 1068 |
+
"train_accuracy": 0.9856584093872229,
|
| 1069 |
+
"train_f1": 0.9861427492811959,
|
| 1070 |
+
"train_loss": 0.07886829227209091,
|
| 1071 |
+
"train_precision": 0.9863290451212052,
|
| 1072 |
+
"train_recall": 0.9859963740171611,
|
| 1073 |
+
"train_runtime": 233.2854,
|
| 1074 |
+
"train_samples_per_second": 3.288,
|
| 1075 |
+
"train_steps_per_second": 0.412
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 35.0,
|
| 1079 |
+
"grad_norm": 3.668701648712158,
|
| 1080 |
+
"learning_rate": 0.0,
|
| 1081 |
+
"loss": 0.3076,
|
| 1082 |
+
"step": 840
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 35.0,
|
| 1086 |
+
"eval_accuracy": 0.9791666666666666,
|
| 1087 |
+
"eval_f1": 0.9807711022697999,
|
| 1088 |
+
"eval_loss": 0.06859644502401352,
|
| 1089 |
+
"eval_precision": 0.9788043478260869,
|
| 1090 |
+
"eval_recall": 0.9833043478260869,
|
| 1091 |
+
"eval_runtime": 47.1013,
|
| 1092 |
+
"eval_samples_per_second": 2.038,
|
| 1093 |
+
"eval_steps_per_second": 0.255,
|
| 1094 |
+
"step": 840
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 35.0,
|
| 1098 |
+
"step": 840,
|
| 1099 |
+
"total_flos": 5.702134423852339e+17,
|
| 1100 |
+
"train_loss": 0.6366229937190101,
|
| 1101 |
+
"train_runtime": 42118.4284,
|
| 1102 |
+
"train_samples_per_second": 0.637,
|
| 1103 |
+
"train_steps_per_second": 0.02
|
| 1104 |
+
}
|
| 1105 |
+
],
|
| 1106 |
+
"logging_steps": 50,
|
| 1107 |
+
"max_steps": 840,
|
| 1108 |
+
"num_input_tokens_seen": 0,
|
| 1109 |
+
"num_train_epochs": 35,
|
| 1110 |
+
"save_steps": 500,
|
| 1111 |
+
"total_flos": 5.702134423852339e+17,
|
| 1112 |
+
"train_batch_size": 8,
|
| 1113 |
+
"trial_name": null,
|
| 1114 |
+
"trial_params": null
|
| 1115 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5db3e7fba7d0eb675f1459563b568ff47851c35815e37bf626f9a764e0740c13
|
| 3 |
+
size 4856
|