Upload folder using huggingface_hub
Browse files- README.md +95 -0
- metadata.json +8 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1117 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224
|
| 4 |
+
tags:
|
| 5 |
+
- Image Regression
|
| 6 |
+
datasets:
|
| 7 |
+
- "BrownEnergy/secchi_depth"
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: "sd_depth_regression_v2"
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# sd_depth_regression_v2
|
| 16 |
+
## Image Regression Model
|
| 17 |
+
|
| 18 |
+
This model was trained with [Image Regression Model Trainer](https://github.com/TonyAssi/ImageRegression/tree/main). It takes an image as input and outputs a float value.
|
| 19 |
+
|
| 20 |
+
```python
|
| 21 |
+
from ImageRegression import predict
|
| 22 |
+
predict(repo_id='BrownEnergy/sd_depth_regression_v2',image_path='image.jpg')
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## Dataset
|
| 28 |
+
Dataset: BrownEnergy/secchi_depth\
|
| 29 |
+
Value Column: 'sd_depth'\
|
| 30 |
+
Train Test Split: 0.05
|
| 31 |
+
|
| 32 |
+
---
|
| 33 |
+
|
| 34 |
+
## Training
|
| 35 |
+
Base Model: [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224)\
|
| 36 |
+
Epochs: 10\
|
| 37 |
+
Learning Rate: 0.0001
|
| 38 |
+
|
| 39 |
+
---
|
| 40 |
+
|
| 41 |
+
## Usage
|
| 42 |
+
|
| 43 |
+
### Download
|
| 44 |
+
```bash
|
| 45 |
+
git clone https://github.com/TonyAssi/ImageRegression.git
|
| 46 |
+
cd ImageRegression
|
| 47 |
+
```
|
| 48 |
+
|
| 49 |
+
### Installation
|
| 50 |
+
```bash
|
| 51 |
+
pip install -r requirements.txt
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
### Import
|
| 55 |
+
```python
|
| 56 |
+
from ImageRegression import train_model, upload_model, predict
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
### Inference (Prediction)
|
| 60 |
+
- **repo_id** 🤗 repo id of the model
|
| 61 |
+
- **image_path** path to image
|
| 62 |
+
```python
|
| 63 |
+
predict(repo_id='BrownEnergy/sd_depth_regression_v2',
|
| 64 |
+
image_path='image.jpg')
|
| 65 |
+
```
|
| 66 |
+
The first time this function is called it'll download the safetensor model. Subsequent function calls will run faster.
|
| 67 |
+
|
| 68 |
+
### Train Model
|
| 69 |
+
- **dataset_id** 🤗 dataset id
|
| 70 |
+
- **value_column_name** column name of prediction values in dataset
|
| 71 |
+
- **test_split** test split of the train/test split
|
| 72 |
+
- **output_dir** the directory where the checkpoints will be saved
|
| 73 |
+
- **num_train_epochs** training epochs
|
| 74 |
+
- **learning_rate** learning rate
|
| 75 |
+
```python
|
| 76 |
+
train_model(dataset_id='BrownEnergy/secchi_depth',
|
| 77 |
+
value_column_name='sd_depth',
|
| 78 |
+
test_split=0.05,
|
| 79 |
+
output_dir='./results',
|
| 80 |
+
num_train_epochs=10,
|
| 81 |
+
learning_rate=0.0001)
|
| 82 |
+
|
| 83 |
+
```
|
| 84 |
+
The trainer will save the checkpoints in the output_dir location. The model.safetensors are the trained weights you'll use for inference (predicton).
|
| 85 |
+
|
| 86 |
+
### Upload Model
|
| 87 |
+
This function will upload your model to the 🤗 Hub.
|
| 88 |
+
- **model_id** the name of the model id
|
| 89 |
+
- **token** go [here](https://huggingface.co/settings/tokens) to create a new 🤗 token
|
| 90 |
+
- **checkpoint_dir** checkpoint folder that will be uploaded
|
| 91 |
+
```python
|
| 92 |
+
upload_model(model_id='sd_depth_regression_v2',
|
| 93 |
+
token='YOUR_HF_TOKEN',
|
| 94 |
+
checkpoint_dir='./results/checkpoint-940')
|
| 95 |
+
```
|
metadata.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_id": "BrownEnergy/secchi_depth",
|
| 3 |
+
"value_column_name": "sd_depth",
|
| 4 |
+
"test_split": 0.05,
|
| 5 |
+
"num_train_epochs": 10,
|
| 6 |
+
"learning_rate": 0.0001,
|
| 7 |
+
"max_value": 77.0
|
| 8 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:695718a3ab09a6a02652f92086ff3230fce36027dc3302e18a885c42dd6fa230
|
| 3 |
+
size 686507205
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d63672d26affd4e2c44c4ff17d3bf920e43f1f7f8337672d06e9c8ff9d25fa1
|
| 3 |
+
size 345639733
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e69db2ebd3dbe75c8467b788e5787cf93796fa78adc7a0c39fc13316b0348a38
|
| 3 |
+
size 13553
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1f889d3cf32396afaa82d48432f8d317cf7af7fa13660b25c16d00534377fc9
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 1700,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 9.941176470588236e-05,
|
| 13 |
+
"loss": 0.1482,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 9.882352941176471e-05,
|
| 19 |
+
"loss": 0.0992,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 9.823529411764706e-05,
|
| 25 |
+
"loss": 0.0313,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 9.764705882352942e-05,
|
| 31 |
+
"loss": 0.0365,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.29,
|
| 36 |
+
"learning_rate": 9.705882352941177e-05,
|
| 37 |
+
"loss": 0.0326,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.35,
|
| 42 |
+
"learning_rate": 9.647058823529412e-05,
|
| 43 |
+
"loss": 0.0122,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.41,
|
| 48 |
+
"learning_rate": 9.588235294117648e-05,
|
| 49 |
+
"loss": 0.0045,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.47,
|
| 54 |
+
"learning_rate": 9.529411764705883e-05,
|
| 55 |
+
"loss": 0.0044,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.53,
|
| 60 |
+
"learning_rate": 9.470588235294118e-05,
|
| 61 |
+
"loss": 0.0016,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.59,
|
| 66 |
+
"learning_rate": 9.411764705882353e-05,
|
| 67 |
+
"loss": 0.0036,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.65,
|
| 72 |
+
"learning_rate": 9.352941176470589e-05,
|
| 73 |
+
"loss": 0.0158,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.71,
|
| 78 |
+
"learning_rate": 9.294117647058824e-05,
|
| 79 |
+
"loss": 0.0019,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.76,
|
| 84 |
+
"learning_rate": 9.23529411764706e-05,
|
| 85 |
+
"loss": 0.0132,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.82,
|
| 90 |
+
"learning_rate": 9.176470588235295e-05,
|
| 91 |
+
"loss": 0.0025,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.88,
|
| 96 |
+
"learning_rate": 9.11764705882353e-05,
|
| 97 |
+
"loss": 0.0049,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.94,
|
| 102 |
+
"learning_rate": 9.058823529411765e-05,
|
| 103 |
+
"loss": 0.0181,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.0,
|
| 108 |
+
"learning_rate": 9e-05,
|
| 109 |
+
"loss": 0.0153,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.0,
|
| 114 |
+
"eval_loss": 0.005996049847453833,
|
| 115 |
+
"eval_mse": 0.005996049847453833,
|
| 116 |
+
"eval_runtime": 15.3139,
|
| 117 |
+
"eval_samples_per_second": 4.702,
|
| 118 |
+
"eval_steps_per_second": 0.588,
|
| 119 |
+
"step": 170
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.06,
|
| 123 |
+
"learning_rate": 8.941176470588236e-05,
|
| 124 |
+
"loss": 0.0079,
|
| 125 |
+
"step": 180
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.12,
|
| 129 |
+
"learning_rate": 8.882352941176471e-05,
|
| 130 |
+
"loss": 0.0238,
|
| 131 |
+
"step": 190
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.18,
|
| 135 |
+
"learning_rate": 8.823529411764706e-05,
|
| 136 |
+
"loss": 0.0274,
|
| 137 |
+
"step": 200
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.24,
|
| 141 |
+
"learning_rate": 8.764705882352942e-05,
|
| 142 |
+
"loss": 0.0078,
|
| 143 |
+
"step": 210
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.29,
|
| 147 |
+
"learning_rate": 8.705882352941177e-05,
|
| 148 |
+
"loss": 0.0144,
|
| 149 |
+
"step": 220
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.35,
|
| 153 |
+
"learning_rate": 8.647058823529412e-05,
|
| 154 |
+
"loss": 0.0046,
|
| 155 |
+
"step": 230
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.41,
|
| 159 |
+
"learning_rate": 8.588235294117646e-05,
|
| 160 |
+
"loss": 0.0078,
|
| 161 |
+
"step": 240
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.47,
|
| 165 |
+
"learning_rate": 8.529411764705883e-05,
|
| 166 |
+
"loss": 0.0012,
|
| 167 |
+
"step": 250
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.53,
|
| 171 |
+
"learning_rate": 8.470588235294118e-05,
|
| 172 |
+
"loss": 0.0124,
|
| 173 |
+
"step": 260
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.59,
|
| 177 |
+
"learning_rate": 8.411764705882354e-05,
|
| 178 |
+
"loss": 0.0105,
|
| 179 |
+
"step": 270
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.65,
|
| 183 |
+
"learning_rate": 8.352941176470589e-05,
|
| 184 |
+
"loss": 0.0089,
|
| 185 |
+
"step": 280
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.71,
|
| 189 |
+
"learning_rate": 8.294117647058824e-05,
|
| 190 |
+
"loss": 0.0017,
|
| 191 |
+
"step": 290
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.76,
|
| 195 |
+
"learning_rate": 8.23529411764706e-05,
|
| 196 |
+
"loss": 0.0095,
|
| 197 |
+
"step": 300
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.82,
|
| 201 |
+
"learning_rate": 8.176470588235295e-05,
|
| 202 |
+
"loss": 0.0016,
|
| 203 |
+
"step": 310
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.88,
|
| 207 |
+
"learning_rate": 8.11764705882353e-05,
|
| 208 |
+
"loss": 0.0128,
|
| 209 |
+
"step": 320
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.94,
|
| 213 |
+
"learning_rate": 8.058823529411765e-05,
|
| 214 |
+
"loss": 0.008,
|
| 215 |
+
"step": 330
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.0,
|
| 219 |
+
"learning_rate": 8e-05,
|
| 220 |
+
"loss": 0.001,
|
| 221 |
+
"step": 340
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.0,
|
| 225 |
+
"eval_loss": 0.0011689820094034076,
|
| 226 |
+
"eval_mse": 0.0011689820094034076,
|
| 227 |
+
"eval_runtime": 15.7171,
|
| 228 |
+
"eval_samples_per_second": 4.581,
|
| 229 |
+
"eval_steps_per_second": 0.573,
|
| 230 |
+
"step": 340
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.06,
|
| 234 |
+
"learning_rate": 7.941176470588235e-05,
|
| 235 |
+
"loss": 0.0005,
|
| 236 |
+
"step": 350
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.12,
|
| 240 |
+
"learning_rate": 7.882352941176471e-05,
|
| 241 |
+
"loss": 0.0007,
|
| 242 |
+
"step": 360
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.18,
|
| 246 |
+
"learning_rate": 7.823529411764707e-05,
|
| 247 |
+
"loss": 0.0183,
|
| 248 |
+
"step": 370
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.24,
|
| 252 |
+
"learning_rate": 7.764705882352942e-05,
|
| 253 |
+
"loss": 0.0021,
|
| 254 |
+
"step": 380
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.29,
|
| 258 |
+
"learning_rate": 7.705882352941177e-05,
|
| 259 |
+
"loss": 0.008,
|
| 260 |
+
"step": 390
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.35,
|
| 264 |
+
"learning_rate": 7.647058823529411e-05,
|
| 265 |
+
"loss": 0.0047,
|
| 266 |
+
"step": 400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.41,
|
| 270 |
+
"learning_rate": 7.588235294117648e-05,
|
| 271 |
+
"loss": 0.011,
|
| 272 |
+
"step": 410
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.47,
|
| 276 |
+
"learning_rate": 7.529411764705883e-05,
|
| 277 |
+
"loss": 0.0024,
|
| 278 |
+
"step": 420
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.53,
|
| 282 |
+
"learning_rate": 7.470588235294118e-05,
|
| 283 |
+
"loss": 0.0019,
|
| 284 |
+
"step": 430
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.59,
|
| 288 |
+
"learning_rate": 7.411764705882354e-05,
|
| 289 |
+
"loss": 0.0074,
|
| 290 |
+
"step": 440
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.65,
|
| 294 |
+
"learning_rate": 7.352941176470589e-05,
|
| 295 |
+
"loss": 0.0017,
|
| 296 |
+
"step": 450
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.71,
|
| 300 |
+
"learning_rate": 7.294117647058823e-05,
|
| 301 |
+
"loss": 0.0081,
|
| 302 |
+
"step": 460
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.76,
|
| 306 |
+
"learning_rate": 7.23529411764706e-05,
|
| 307 |
+
"loss": 0.0195,
|
| 308 |
+
"step": 470
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.82,
|
| 312 |
+
"learning_rate": 7.176470588235295e-05,
|
| 313 |
+
"loss": 0.0072,
|
| 314 |
+
"step": 480
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.88,
|
| 318 |
+
"learning_rate": 7.11764705882353e-05,
|
| 319 |
+
"loss": 0.0048,
|
| 320 |
+
"step": 490
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.94,
|
| 324 |
+
"learning_rate": 7.058823529411765e-05,
|
| 325 |
+
"loss": 0.0012,
|
| 326 |
+
"step": 500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.0,
|
| 330 |
+
"learning_rate": 7e-05,
|
| 331 |
+
"loss": 0.0036,
|
| 332 |
+
"step": 510
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.0,
|
| 336 |
+
"eval_loss": 0.0050306557677686214,
|
| 337 |
+
"eval_mse": 0.0050306557677686214,
|
| 338 |
+
"eval_runtime": 16.8544,
|
| 339 |
+
"eval_samples_per_second": 4.272,
|
| 340 |
+
"eval_steps_per_second": 0.534,
|
| 341 |
+
"step": 510
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.06,
|
| 345 |
+
"learning_rate": 6.941176470588236e-05,
|
| 346 |
+
"loss": 0.0055,
|
| 347 |
+
"step": 520
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.12,
|
| 351 |
+
"learning_rate": 6.882352941176471e-05,
|
| 352 |
+
"loss": 0.0112,
|
| 353 |
+
"step": 530
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.18,
|
| 357 |
+
"learning_rate": 6.823529411764707e-05,
|
| 358 |
+
"loss": 0.0038,
|
| 359 |
+
"step": 540
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.24,
|
| 363 |
+
"learning_rate": 6.764705882352942e-05,
|
| 364 |
+
"loss": 0.0017,
|
| 365 |
+
"step": 550
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.29,
|
| 369 |
+
"learning_rate": 6.705882352941176e-05,
|
| 370 |
+
"loss": 0.0015,
|
| 371 |
+
"step": 560
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.35,
|
| 375 |
+
"learning_rate": 6.647058823529411e-05,
|
| 376 |
+
"loss": 0.001,
|
| 377 |
+
"step": 570
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.41,
|
| 381 |
+
"learning_rate": 6.588235294117648e-05,
|
| 382 |
+
"loss": 0.0115,
|
| 383 |
+
"step": 580
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.47,
|
| 387 |
+
"learning_rate": 6.529411764705883e-05,
|
| 388 |
+
"loss": 0.0024,
|
| 389 |
+
"step": 590
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.53,
|
| 393 |
+
"learning_rate": 6.470588235294118e-05,
|
| 394 |
+
"loss": 0.0021,
|
| 395 |
+
"step": 600
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.59,
|
| 399 |
+
"learning_rate": 6.411764705882354e-05,
|
| 400 |
+
"loss": 0.0015,
|
| 401 |
+
"step": 610
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.65,
|
| 405 |
+
"learning_rate": 6.352941176470588e-05,
|
| 406 |
+
"loss": 0.0016,
|
| 407 |
+
"step": 620
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.71,
|
| 411 |
+
"learning_rate": 6.294117647058824e-05,
|
| 412 |
+
"loss": 0.0103,
|
| 413 |
+
"step": 630
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.76,
|
| 417 |
+
"learning_rate": 6.23529411764706e-05,
|
| 418 |
+
"loss": 0.0108,
|
| 419 |
+
"step": 640
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.82,
|
| 423 |
+
"learning_rate": 6.176470588235295e-05,
|
| 424 |
+
"loss": 0.0071,
|
| 425 |
+
"step": 650
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 3.88,
|
| 429 |
+
"learning_rate": 6.11764705882353e-05,
|
| 430 |
+
"loss": 0.0078,
|
| 431 |
+
"step": 660
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 3.94,
|
| 435 |
+
"learning_rate": 6.058823529411765e-05,
|
| 436 |
+
"loss": 0.0043,
|
| 437 |
+
"step": 670
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.0,
|
| 441 |
+
"learning_rate": 6e-05,
|
| 442 |
+
"loss": 0.0017,
|
| 443 |
+
"step": 680
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.0,
|
| 447 |
+
"eval_loss": 0.0019855075515806675,
|
| 448 |
+
"eval_mse": 0.001985507318750024,
|
| 449 |
+
"eval_runtime": 15.5377,
|
| 450 |
+
"eval_samples_per_second": 4.634,
|
| 451 |
+
"eval_steps_per_second": 0.579,
|
| 452 |
+
"step": 680
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.06,
|
| 456 |
+
"learning_rate": 5.9411764705882355e-05,
|
| 457 |
+
"loss": 0.0022,
|
| 458 |
+
"step": 690
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.12,
|
| 462 |
+
"learning_rate": 5.882352941176471e-05,
|
| 463 |
+
"loss": 0.0092,
|
| 464 |
+
"step": 700
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.18,
|
| 468 |
+
"learning_rate": 5.823529411764707e-05,
|
| 469 |
+
"loss": 0.0024,
|
| 470 |
+
"step": 710
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.24,
|
| 474 |
+
"learning_rate": 5.764705882352941e-05,
|
| 475 |
+
"loss": 0.002,
|
| 476 |
+
"step": 720
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.29,
|
| 480 |
+
"learning_rate": 5.7058823529411766e-05,
|
| 481 |
+
"loss": 0.0042,
|
| 482 |
+
"step": 730
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.35,
|
| 486 |
+
"learning_rate": 5.647058823529412e-05,
|
| 487 |
+
"loss": 0.0602,
|
| 488 |
+
"step": 740
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.41,
|
| 492 |
+
"learning_rate": 5.588235294117647e-05,
|
| 493 |
+
"loss": 0.0062,
|
| 494 |
+
"step": 750
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.47,
|
| 498 |
+
"learning_rate": 5.529411764705883e-05,
|
| 499 |
+
"loss": 0.003,
|
| 500 |
+
"step": 760
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.53,
|
| 504 |
+
"learning_rate": 5.4705882352941185e-05,
|
| 505 |
+
"loss": 0.0088,
|
| 506 |
+
"step": 770
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 4.59,
|
| 510 |
+
"learning_rate": 5.411764705882353e-05,
|
| 511 |
+
"loss": 0.0025,
|
| 512 |
+
"step": 780
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.65,
|
| 516 |
+
"learning_rate": 5.3529411764705884e-05,
|
| 517 |
+
"loss": 0.0109,
|
| 518 |
+
"step": 790
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.71,
|
| 522 |
+
"learning_rate": 5.294117647058824e-05,
|
| 523 |
+
"loss": 0.0015,
|
| 524 |
+
"step": 800
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.76,
|
| 528 |
+
"learning_rate": 5.235294117647059e-05,
|
| 529 |
+
"loss": 0.0011,
|
| 530 |
+
"step": 810
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.82,
|
| 534 |
+
"learning_rate": 5.176470588235295e-05,
|
| 535 |
+
"loss": 0.0101,
|
| 536 |
+
"step": 820
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.88,
|
| 540 |
+
"learning_rate": 5.117647058823529e-05,
|
| 541 |
+
"loss": 0.0011,
|
| 542 |
+
"step": 830
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 4.94,
|
| 546 |
+
"learning_rate": 5.058823529411765e-05,
|
| 547 |
+
"loss": 0.0017,
|
| 548 |
+
"step": 840
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 5.0,
|
| 552 |
+
"learning_rate": 5e-05,
|
| 553 |
+
"loss": 0.0014,
|
| 554 |
+
"step": 850
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 5.0,
|
| 558 |
+
"eval_loss": 0.001027416903525591,
|
| 559 |
+
"eval_mse": 0.001027416903525591,
|
| 560 |
+
"eval_runtime": 17.3556,
|
| 561 |
+
"eval_samples_per_second": 4.149,
|
| 562 |
+
"eval_steps_per_second": 0.519,
|
| 563 |
+
"step": 850
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 5.06,
|
| 567 |
+
"learning_rate": 4.9411764705882355e-05,
|
| 568 |
+
"loss": 0.0023,
|
| 569 |
+
"step": 860
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.12,
|
| 573 |
+
"learning_rate": 4.882352941176471e-05,
|
| 574 |
+
"loss": 0.0005,
|
| 575 |
+
"step": 870
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.18,
|
| 579 |
+
"learning_rate": 4.823529411764706e-05,
|
| 580 |
+
"loss": 0.0053,
|
| 581 |
+
"step": 880
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 5.24,
|
| 585 |
+
"learning_rate": 4.7647058823529414e-05,
|
| 586 |
+
"loss": 0.0026,
|
| 587 |
+
"step": 890
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 5.29,
|
| 591 |
+
"learning_rate": 4.705882352941177e-05,
|
| 592 |
+
"loss": 0.0045,
|
| 593 |
+
"step": 900
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 5.35,
|
| 597 |
+
"learning_rate": 4.647058823529412e-05,
|
| 598 |
+
"loss": 0.0017,
|
| 599 |
+
"step": 910
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 5.41,
|
| 603 |
+
"learning_rate": 4.588235294117647e-05,
|
| 604 |
+
"loss": 0.0012,
|
| 605 |
+
"step": 920
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.47,
|
| 609 |
+
"learning_rate": 4.5294117647058826e-05,
|
| 610 |
+
"loss": 0.0098,
|
| 611 |
+
"step": 930
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.53,
|
| 615 |
+
"learning_rate": 4.470588235294118e-05,
|
| 616 |
+
"loss": 0.0016,
|
| 617 |
+
"step": 940
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.59,
|
| 621 |
+
"learning_rate": 4.411764705882353e-05,
|
| 622 |
+
"loss": 0.0011,
|
| 623 |
+
"step": 950
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 5.65,
|
| 627 |
+
"learning_rate": 4.3529411764705885e-05,
|
| 628 |
+
"loss": 0.001,
|
| 629 |
+
"step": 960
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 5.71,
|
| 633 |
+
"learning_rate": 4.294117647058823e-05,
|
| 634 |
+
"loss": 0.0005,
|
| 635 |
+
"step": 970
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 5.76,
|
| 639 |
+
"learning_rate": 4.235294117647059e-05,
|
| 640 |
+
"loss": 0.0021,
|
| 641 |
+
"step": 980
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 5.82,
|
| 645 |
+
"learning_rate": 4.1764705882352944e-05,
|
| 646 |
+
"loss": 0.0107,
|
| 647 |
+
"step": 990
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 5.88,
|
| 651 |
+
"learning_rate": 4.11764705882353e-05,
|
| 652 |
+
"loss": 0.0086,
|
| 653 |
+
"step": 1000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 5.94,
|
| 657 |
+
"learning_rate": 4.058823529411765e-05,
|
| 658 |
+
"loss": 0.0014,
|
| 659 |
+
"step": 1010
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 6.0,
|
| 663 |
+
"learning_rate": 4e-05,
|
| 664 |
+
"loss": 0.0008,
|
| 665 |
+
"step": 1020
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 6.0,
|
| 669 |
+
"eval_loss": 0.001083881827071309,
|
| 670 |
+
"eval_mse": 0.001083881827071309,
|
| 671 |
+
"eval_runtime": 15.3262,
|
| 672 |
+
"eval_samples_per_second": 4.698,
|
| 673 |
+
"eval_steps_per_second": 0.587,
|
| 674 |
+
"step": 1020
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.06,
|
| 678 |
+
"learning_rate": 3.9411764705882356e-05,
|
| 679 |
+
"loss": 0.0012,
|
| 680 |
+
"step": 1030
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 6.12,
|
| 684 |
+
"learning_rate": 3.882352941176471e-05,
|
| 685 |
+
"loss": 0.002,
|
| 686 |
+
"step": 1040
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 6.18,
|
| 690 |
+
"learning_rate": 3.8235294117647055e-05,
|
| 691 |
+
"loss": 0.0062,
|
| 692 |
+
"step": 1050
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 6.24,
|
| 696 |
+
"learning_rate": 3.7647058823529415e-05,
|
| 697 |
+
"loss": 0.0017,
|
| 698 |
+
"step": 1060
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 6.29,
|
| 702 |
+
"learning_rate": 3.705882352941177e-05,
|
| 703 |
+
"loss": 0.0008,
|
| 704 |
+
"step": 1070
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.35,
|
| 708 |
+
"learning_rate": 3.6470588235294114e-05,
|
| 709 |
+
"loss": 0.0013,
|
| 710 |
+
"step": 1080
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 6.41,
|
| 714 |
+
"learning_rate": 3.5882352941176474e-05,
|
| 715 |
+
"loss": 0.0078,
|
| 716 |
+
"step": 1090
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 6.47,
|
| 720 |
+
"learning_rate": 3.529411764705883e-05,
|
| 721 |
+
"loss": 0.0026,
|
| 722 |
+
"step": 1100
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 6.53,
|
| 726 |
+
"learning_rate": 3.470588235294118e-05,
|
| 727 |
+
"loss": 0.0084,
|
| 728 |
+
"step": 1110
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 6.59,
|
| 732 |
+
"learning_rate": 3.411764705882353e-05,
|
| 733 |
+
"loss": 0.0016,
|
| 734 |
+
"step": 1120
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 6.65,
|
| 738 |
+
"learning_rate": 3.352941176470588e-05,
|
| 739 |
+
"loss": 0.0026,
|
| 740 |
+
"step": 1130
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 6.71,
|
| 744 |
+
"learning_rate": 3.294117647058824e-05,
|
| 745 |
+
"loss": 0.0053,
|
| 746 |
+
"step": 1140
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 6.76,
|
| 750 |
+
"learning_rate": 3.235294117647059e-05,
|
| 751 |
+
"loss": 0.0058,
|
| 752 |
+
"step": 1150
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 6.82,
|
| 756 |
+
"learning_rate": 3.176470588235294e-05,
|
| 757 |
+
"loss": 0.001,
|
| 758 |
+
"step": 1160
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 6.88,
|
| 762 |
+
"learning_rate": 3.11764705882353e-05,
|
| 763 |
+
"loss": 0.0011,
|
| 764 |
+
"step": 1170
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 6.94,
|
| 768 |
+
"learning_rate": 3.058823529411765e-05,
|
| 769 |
+
"loss": 0.001,
|
| 770 |
+
"step": 1180
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 7.0,
|
| 774 |
+
"learning_rate": 3e-05,
|
| 775 |
+
"loss": 0.0008,
|
| 776 |
+
"step": 1190
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 7.0,
|
| 780 |
+
"eval_loss": 0.000933311355765909,
|
| 781 |
+
"eval_mse": 0.000933311355765909,
|
| 782 |
+
"eval_runtime": 15.2402,
|
| 783 |
+
"eval_samples_per_second": 4.724,
|
| 784 |
+
"eval_steps_per_second": 0.591,
|
| 785 |
+
"step": 1190
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 7.06,
|
| 789 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 790 |
+
"loss": 0.0152,
|
| 791 |
+
"step": 1200
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 7.12,
|
| 795 |
+
"learning_rate": 2.8823529411764703e-05,
|
| 796 |
+
"loss": 0.0025,
|
| 797 |
+
"step": 1210
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 7.18,
|
| 801 |
+
"learning_rate": 2.823529411764706e-05,
|
| 802 |
+
"loss": 0.0018,
|
| 803 |
+
"step": 1220
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 7.24,
|
| 807 |
+
"learning_rate": 2.7647058823529416e-05,
|
| 808 |
+
"loss": 0.0011,
|
| 809 |
+
"step": 1230
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 7.29,
|
| 813 |
+
"learning_rate": 2.7058823529411766e-05,
|
| 814 |
+
"loss": 0.0076,
|
| 815 |
+
"step": 1240
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 7.35,
|
| 819 |
+
"learning_rate": 2.647058823529412e-05,
|
| 820 |
+
"loss": 0.0009,
|
| 821 |
+
"step": 1250
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 7.41,
|
| 825 |
+
"learning_rate": 2.5882352941176475e-05,
|
| 826 |
+
"loss": 0.0054,
|
| 827 |
+
"step": 1260
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 7.47,
|
| 831 |
+
"learning_rate": 2.5294117647058825e-05,
|
| 832 |
+
"loss": 0.0012,
|
| 833 |
+
"step": 1270
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 7.53,
|
| 837 |
+
"learning_rate": 2.4705882352941178e-05,
|
| 838 |
+
"loss": 0.0012,
|
| 839 |
+
"step": 1280
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 7.59,
|
| 843 |
+
"learning_rate": 2.411764705882353e-05,
|
| 844 |
+
"loss": 0.0005,
|
| 845 |
+
"step": 1290
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 7.65,
|
| 849 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 850 |
+
"loss": 0.0011,
|
| 851 |
+
"step": 1300
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 7.71,
|
| 855 |
+
"learning_rate": 2.2941176470588237e-05,
|
| 856 |
+
"loss": 0.0022,
|
| 857 |
+
"step": 1310
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 7.76,
|
| 861 |
+
"learning_rate": 2.235294117647059e-05,
|
| 862 |
+
"loss": 0.0009,
|
| 863 |
+
"step": 1320
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 7.82,
|
| 867 |
+
"learning_rate": 2.1764705882352943e-05,
|
| 868 |
+
"loss": 0.0007,
|
| 869 |
+
"step": 1330
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 7.88,
|
| 873 |
+
"learning_rate": 2.1176470588235296e-05,
|
| 874 |
+
"loss": 0.0007,
|
| 875 |
+
"step": 1340
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 7.94,
|
| 879 |
+
"learning_rate": 2.058823529411765e-05,
|
| 880 |
+
"loss": 0.0007,
|
| 881 |
+
"step": 1350
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 8.0,
|
| 885 |
+
"learning_rate": 2e-05,
|
| 886 |
+
"loss": 0.0008,
|
| 887 |
+
"step": 1360
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 8.0,
|
| 891 |
+
"eval_loss": 0.001160233630798757,
|
| 892 |
+
"eval_mse": 0.001160233747214079,
|
| 893 |
+
"eval_runtime": 18.2978,
|
| 894 |
+
"eval_samples_per_second": 3.935,
|
| 895 |
+
"eval_steps_per_second": 0.492,
|
| 896 |
+
"step": 1360
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 8.06,
|
| 900 |
+
"learning_rate": 1.9411764705882355e-05,
|
| 901 |
+
"loss": 0.0072,
|
| 902 |
+
"step": 1370
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 8.12,
|
| 906 |
+
"learning_rate": 1.8823529411764708e-05,
|
| 907 |
+
"loss": 0.001,
|
| 908 |
+
"step": 1380
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 8.18,
|
| 912 |
+
"learning_rate": 1.8235294117647057e-05,
|
| 913 |
+
"loss": 0.0008,
|
| 914 |
+
"step": 1390
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 8.24,
|
| 918 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 919 |
+
"loss": 0.0025,
|
| 920 |
+
"step": 1400
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 8.29,
|
| 924 |
+
"learning_rate": 1.7058823529411767e-05,
|
| 925 |
+
"loss": 0.001,
|
| 926 |
+
"step": 1410
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 8.35,
|
| 930 |
+
"learning_rate": 1.647058823529412e-05,
|
| 931 |
+
"loss": 0.0014,
|
| 932 |
+
"step": 1420
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 8.41,
|
| 936 |
+
"learning_rate": 1.588235294117647e-05,
|
| 937 |
+
"loss": 0.0015,
|
| 938 |
+
"step": 1430
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 8.47,
|
| 942 |
+
"learning_rate": 1.5294117647058826e-05,
|
| 943 |
+
"loss": 0.0041,
|
| 944 |
+
"step": 1440
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 8.53,
|
| 948 |
+
"learning_rate": 1.4705882352941177e-05,
|
| 949 |
+
"loss": 0.0012,
|
| 950 |
+
"step": 1450
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 8.59,
|
| 954 |
+
"learning_rate": 1.411764705882353e-05,
|
| 955 |
+
"loss": 0.0009,
|
| 956 |
+
"step": 1460
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 8.65,
|
| 960 |
+
"learning_rate": 1.3529411764705883e-05,
|
| 961 |
+
"loss": 0.0012,
|
| 962 |
+
"step": 1470
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 8.71,
|
| 966 |
+
"learning_rate": 1.2941176470588238e-05,
|
| 967 |
+
"loss": 0.0022,
|
| 968 |
+
"step": 1480
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 8.76,
|
| 972 |
+
"learning_rate": 1.2352941176470589e-05,
|
| 973 |
+
"loss": 0.0007,
|
| 974 |
+
"step": 1490
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 8.82,
|
| 978 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 979 |
+
"loss": 0.0064,
|
| 980 |
+
"step": 1500
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 8.88,
|
| 984 |
+
"learning_rate": 1.1176470588235295e-05,
|
| 985 |
+
"loss": 0.0014,
|
| 986 |
+
"step": 1510
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 8.94,
|
| 990 |
+
"learning_rate": 1.0588235294117648e-05,
|
| 991 |
+
"loss": 0.0006,
|
| 992 |
+
"step": 1520
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 9.0,
|
| 996 |
+
"learning_rate": 1e-05,
|
| 997 |
+
"loss": 0.001,
|
| 998 |
+
"step": 1530
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 9.0,
|
| 1002 |
+
"eval_loss": 0.0007979701040312648,
|
| 1003 |
+
"eval_mse": 0.0007979701040312648,
|
| 1004 |
+
"eval_runtime": 17.0378,
|
| 1005 |
+
"eval_samples_per_second": 4.226,
|
| 1006 |
+
"eval_steps_per_second": 0.528,
|
| 1007 |
+
"step": 1530
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 9.06,
|
| 1011 |
+
"learning_rate": 9.411764705882354e-06,
|
| 1012 |
+
"loss": 0.0009,
|
| 1013 |
+
"step": 1540
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 9.12,
|
| 1017 |
+
"learning_rate": 8.823529411764707e-06,
|
| 1018 |
+
"loss": 0.0008,
|
| 1019 |
+
"step": 1550
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 9.18,
|
| 1023 |
+
"learning_rate": 8.23529411764706e-06,
|
| 1024 |
+
"loss": 0.0021,
|
| 1025 |
+
"step": 1560
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 9.24,
|
| 1029 |
+
"learning_rate": 7.647058823529413e-06,
|
| 1030 |
+
"loss": 0.0009,
|
| 1031 |
+
"step": 1570
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 9.29,
|
| 1035 |
+
"learning_rate": 7.058823529411765e-06,
|
| 1036 |
+
"loss": 0.0006,
|
| 1037 |
+
"step": 1580
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 9.35,
|
| 1041 |
+
"learning_rate": 6.470588235294119e-06,
|
| 1042 |
+
"loss": 0.0005,
|
| 1043 |
+
"step": 1590
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 9.41,
|
| 1047 |
+
"learning_rate": 5.882352941176471e-06,
|
| 1048 |
+
"loss": 0.0005,
|
| 1049 |
+
"step": 1600
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 9.47,
|
| 1053 |
+
"learning_rate": 5.294117647058824e-06,
|
| 1054 |
+
"loss": 0.0007,
|
| 1055 |
+
"step": 1610
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 9.53,
|
| 1059 |
+
"learning_rate": 4.705882352941177e-06,
|
| 1060 |
+
"loss": 0.0033,
|
| 1061 |
+
"step": 1620
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 9.59,
|
| 1065 |
+
"learning_rate": 4.11764705882353e-06,
|
| 1066 |
+
"loss": 0.0009,
|
| 1067 |
+
"step": 1630
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 9.65,
|
| 1071 |
+
"learning_rate": 3.5294117647058825e-06,
|
| 1072 |
+
"loss": 0.0008,
|
| 1073 |
+
"step": 1640
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 9.71,
|
| 1077 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 1078 |
+
"loss": 0.0007,
|
| 1079 |
+
"step": 1650
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 9.76,
|
| 1083 |
+
"learning_rate": 2.3529411764705885e-06,
|
| 1084 |
+
"loss": 0.002,
|
| 1085 |
+
"step": 1660
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 9.82,
|
| 1089 |
+
"learning_rate": 1.7647058823529412e-06,
|
| 1090 |
+
"loss": 0.0009,
|
| 1091 |
+
"step": 1670
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 9.88,
|
| 1095 |
+
"learning_rate": 1.1764705882352942e-06,
|
| 1096 |
+
"loss": 0.0008,
|
| 1097 |
+
"step": 1680
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 9.94,
|
| 1101 |
+
"learning_rate": 5.882352941176471e-07,
|
| 1102 |
+
"loss": 0.0063,
|
| 1103 |
+
"step": 1690
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 10.0,
|
| 1107 |
+
"learning_rate": 0.0,
|
| 1108 |
+
"loss": 0.0004,
|
| 1109 |
+
"step": 1700
|
| 1110 |
+
}
|
| 1111 |
+
],
|
| 1112 |
+
"max_steps": 1700,
|
| 1113 |
+
"num_train_epochs": 10,
|
| 1114 |
+
"total_flos": 0.0,
|
| 1115 |
+
"trial_name": null,
|
| 1116 |
+
"trial_params": null
|
| 1117 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9129b253c4797bfda8d87a2ac803edfd36087b3175c2d38ef40e84ae3f06f6e
|
| 3 |
+
size 3899
|