Commit
•
03ae80e
1
Parent(s):
5bd22bb
Upload folder using huggingface_hub
Browse files- README.md +95 -0
- metadata.json +8 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1514 -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 |
+
- "LucyintheSky/24-5-10_24-5-17-2000"
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: "24-5-10_24-5-17-2000-pred1"
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# 24-5-10_24-5-17-2000-pred1
|
| 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='LucyintheSky/24-5-10_24-5-17-2000-pred1',image_path='image.jpg')
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## Dataset
|
| 28 |
+
Dataset: LucyintheSky/24-5-10_24-5-17-2000\
|
| 29 |
+
Value Column: 'sales_index'\
|
| 30 |
+
Train Test Split: 0.2
|
| 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='LucyintheSky/24-5-10_24-5-17-2000-pred1',
|
| 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='LucyintheSky/24-5-10_24-5-17-2000',
|
| 77 |
+
value_column_name='sales_index',
|
| 78 |
+
test_split=0.2,
|
| 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='24-5-10_24-5-17-2000-pred1',
|
| 93 |
+
token='YOUR_HF_TOKEN',
|
| 94 |
+
checkpoint_dir='./results/checkpoint-940')
|
| 95 |
+
```
|
metadata.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_id": "LucyintheSky/24-5-10_24-5-17-2000",
|
| 3 |
+
"value_column_name": "sales_index",
|
| 4 |
+
"test_split": 0.2,
|
| 5 |
+
"num_train_epochs": 10,
|
| 6 |
+
"learning_rate": 0.0001,
|
| 7 |
+
"max_value": 2000
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e0f910445d999a66a30ca345aedab40494ba7475375297ca92770c2801e0d5e
|
| 3 |
+
size 345583444
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9725d84ce2928bfc8ae737fc16ec219f82ae8811c3d0c866ca06dd85fa7aa73
|
| 3 |
+
size 686557178
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da1db5c227c2000e391e1d225e13a38eda71746be2164bab198c44af9ae0882b
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e301ebd8064bb9799d23981baab716db6ee7302f5ba2efc70a2dd3be85fbcb46
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1514 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05,
|
| 13 |
+
"grad_norm": 7.181795120239258,
|
| 14 |
+
"learning_rate": 9.95e-05,
|
| 15 |
+
"loss": 0.5278,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1,
|
| 20 |
+
"grad_norm": 10.308942794799805,
|
| 21 |
+
"learning_rate": 9.900000000000001e-05,
|
| 22 |
+
"loss": 0.085,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.15,
|
| 27 |
+
"grad_norm": 12.229366302490234,
|
| 28 |
+
"learning_rate": 9.850000000000001e-05,
|
| 29 |
+
"loss": 0.0915,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.2,
|
| 34 |
+
"grad_norm": 2.2935550212860107,
|
| 35 |
+
"learning_rate": 9.8e-05,
|
| 36 |
+
"loss": 0.0936,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.25,
|
| 41 |
+
"grad_norm": 4.0055365562438965,
|
| 42 |
+
"learning_rate": 9.75e-05,
|
| 43 |
+
"loss": 0.0847,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3,
|
| 48 |
+
"grad_norm": 2.5626087188720703,
|
| 49 |
+
"learning_rate": 9.7e-05,
|
| 50 |
+
"loss": 0.104,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.35,
|
| 55 |
+
"grad_norm": 4.1402435302734375,
|
| 56 |
+
"learning_rate": 9.65e-05,
|
| 57 |
+
"loss": 0.0736,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.4,
|
| 62 |
+
"grad_norm": 2.0823185443878174,
|
| 63 |
+
"learning_rate": 9.6e-05,
|
| 64 |
+
"loss": 0.084,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.45,
|
| 69 |
+
"grad_norm": 2.480923891067505,
|
| 70 |
+
"learning_rate": 9.55e-05,
|
| 71 |
+
"loss": 0.0854,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5,
|
| 76 |
+
"grad_norm": 6.268786907196045,
|
| 77 |
+
"learning_rate": 9.5e-05,
|
| 78 |
+
"loss": 0.0662,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.55,
|
| 83 |
+
"grad_norm": 5.55922269821167,
|
| 84 |
+
"learning_rate": 9.449999999999999e-05,
|
| 85 |
+
"loss": 0.0651,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"grad_norm": 6.762533664703369,
|
| 91 |
+
"learning_rate": 9.4e-05,
|
| 92 |
+
"loss": 0.0733,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.65,
|
| 97 |
+
"grad_norm": 4.081423282623291,
|
| 98 |
+
"learning_rate": 9.350000000000001e-05,
|
| 99 |
+
"loss": 0.077,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7,
|
| 104 |
+
"grad_norm": 0.7577868700027466,
|
| 105 |
+
"learning_rate": 9.300000000000001e-05,
|
| 106 |
+
"loss": 0.0683,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.75,
|
| 111 |
+
"grad_norm": 2.6608283519744873,
|
| 112 |
+
"learning_rate": 9.250000000000001e-05,
|
| 113 |
+
"loss": 0.088,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"grad_norm": 1.7237794399261475,
|
| 119 |
+
"learning_rate": 9.200000000000001e-05,
|
| 120 |
+
"loss": 0.1042,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.85,
|
| 125 |
+
"grad_norm": 1.696759819984436,
|
| 126 |
+
"learning_rate": 9.15e-05,
|
| 127 |
+
"loss": 0.0658,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.9,
|
| 132 |
+
"grad_norm": 2.3527326583862305,
|
| 133 |
+
"learning_rate": 9.1e-05,
|
| 134 |
+
"loss": 0.1189,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.95,
|
| 139 |
+
"grad_norm": 8.625548362731934,
|
| 140 |
+
"learning_rate": 9.05e-05,
|
| 141 |
+
"loss": 0.0969,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.0,
|
| 146 |
+
"grad_norm": 12.219880104064941,
|
| 147 |
+
"learning_rate": 9e-05,
|
| 148 |
+
"loss": 0.0886,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.0,
|
| 153 |
+
"eval_loss": 0.05805354192852974,
|
| 154 |
+
"eval_mse": 0.05805354192852974,
|
| 155 |
+
"eval_runtime": 16.5046,
|
| 156 |
+
"eval_samples_per_second": 24.236,
|
| 157 |
+
"eval_steps_per_second": 3.029,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.05,
|
| 162 |
+
"grad_norm": 11.77884292602539,
|
| 163 |
+
"learning_rate": 8.950000000000001e-05,
|
| 164 |
+
"loss": 0.0646,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.1,
|
| 169 |
+
"grad_norm": 4.1980414390563965,
|
| 170 |
+
"learning_rate": 8.900000000000001e-05,
|
| 171 |
+
"loss": 0.0852,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.15,
|
| 176 |
+
"grad_norm": 0.837498128414154,
|
| 177 |
+
"learning_rate": 8.850000000000001e-05,
|
| 178 |
+
"loss": 0.1304,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.2,
|
| 183 |
+
"grad_norm": 3.922130584716797,
|
| 184 |
+
"learning_rate": 8.800000000000001e-05,
|
| 185 |
+
"loss": 0.0777,
|
| 186 |
+
"step": 240
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.25,
|
| 190 |
+
"grad_norm": 1.215814471244812,
|
| 191 |
+
"learning_rate": 8.75e-05,
|
| 192 |
+
"loss": 0.0479,
|
| 193 |
+
"step": 250
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.3,
|
| 197 |
+
"grad_norm": 6.36415958404541,
|
| 198 |
+
"learning_rate": 8.7e-05,
|
| 199 |
+
"loss": 0.0546,
|
| 200 |
+
"step": 260
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.35,
|
| 204 |
+
"grad_norm": 4.46746826171875,
|
| 205 |
+
"learning_rate": 8.65e-05,
|
| 206 |
+
"loss": 0.0577,
|
| 207 |
+
"step": 270
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.4,
|
| 211 |
+
"grad_norm": 1.044565200805664,
|
| 212 |
+
"learning_rate": 8.6e-05,
|
| 213 |
+
"loss": 0.0759,
|
| 214 |
+
"step": 280
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.45,
|
| 218 |
+
"grad_norm": 7.3412065505981445,
|
| 219 |
+
"learning_rate": 8.55e-05,
|
| 220 |
+
"loss": 0.0662,
|
| 221 |
+
"step": 290
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.5,
|
| 225 |
+
"grad_norm": 2.7329416275024414,
|
| 226 |
+
"learning_rate": 8.5e-05,
|
| 227 |
+
"loss": 0.0531,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.55,
|
| 232 |
+
"grad_norm": 4.7028093338012695,
|
| 233 |
+
"learning_rate": 8.450000000000001e-05,
|
| 234 |
+
"loss": 0.0603,
|
| 235 |
+
"step": 310
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.6,
|
| 239 |
+
"grad_norm": 2.881957530975342,
|
| 240 |
+
"learning_rate": 8.4e-05,
|
| 241 |
+
"loss": 0.0499,
|
| 242 |
+
"step": 320
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.65,
|
| 246 |
+
"grad_norm": 5.929530620574951,
|
| 247 |
+
"learning_rate": 8.35e-05,
|
| 248 |
+
"loss": 0.079,
|
| 249 |
+
"step": 330
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.7,
|
| 253 |
+
"grad_norm": 2.1263890266418457,
|
| 254 |
+
"learning_rate": 8.3e-05,
|
| 255 |
+
"loss": 0.0779,
|
| 256 |
+
"step": 340
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.75,
|
| 260 |
+
"grad_norm": 6.260400772094727,
|
| 261 |
+
"learning_rate": 8.25e-05,
|
| 262 |
+
"loss": 0.0724,
|
| 263 |
+
"step": 350
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.8,
|
| 267 |
+
"grad_norm": 8.152369499206543,
|
| 268 |
+
"learning_rate": 8.2e-05,
|
| 269 |
+
"loss": 0.1059,
|
| 270 |
+
"step": 360
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.85,
|
| 274 |
+
"grad_norm": 2.842404842376709,
|
| 275 |
+
"learning_rate": 8.15e-05,
|
| 276 |
+
"loss": 0.0552,
|
| 277 |
+
"step": 370
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.9,
|
| 281 |
+
"grad_norm": 6.334738254547119,
|
| 282 |
+
"learning_rate": 8.1e-05,
|
| 283 |
+
"loss": 0.0778,
|
| 284 |
+
"step": 380
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.95,
|
| 288 |
+
"grad_norm": 2.1208484172821045,
|
| 289 |
+
"learning_rate": 8.05e-05,
|
| 290 |
+
"loss": 0.063,
|
| 291 |
+
"step": 390
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.0,
|
| 295 |
+
"grad_norm": 3.39943265914917,
|
| 296 |
+
"learning_rate": 8e-05,
|
| 297 |
+
"loss": 0.0632,
|
| 298 |
+
"step": 400
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.0,
|
| 302 |
+
"eval_loss": 0.09050198644399643,
|
| 303 |
+
"eval_mse": 0.09050198644399643,
|
| 304 |
+
"eval_runtime": 16.3832,
|
| 305 |
+
"eval_samples_per_second": 24.415,
|
| 306 |
+
"eval_steps_per_second": 3.052,
|
| 307 |
+
"step": 400
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.05,
|
| 311 |
+
"grad_norm": 0.5936372876167297,
|
| 312 |
+
"learning_rate": 7.950000000000001e-05,
|
| 313 |
+
"loss": 0.0479,
|
| 314 |
+
"step": 410
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.1,
|
| 318 |
+
"grad_norm": 1.255616307258606,
|
| 319 |
+
"learning_rate": 7.900000000000001e-05,
|
| 320 |
+
"loss": 0.0503,
|
| 321 |
+
"step": 420
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.15,
|
| 325 |
+
"grad_norm": 0.4045727252960205,
|
| 326 |
+
"learning_rate": 7.850000000000001e-05,
|
| 327 |
+
"loss": 0.0685,
|
| 328 |
+
"step": 430
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.2,
|
| 332 |
+
"grad_norm": 9.539754867553711,
|
| 333 |
+
"learning_rate": 7.800000000000001e-05,
|
| 334 |
+
"loss": 0.0599,
|
| 335 |
+
"step": 440
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.25,
|
| 339 |
+
"grad_norm": 5.422886848449707,
|
| 340 |
+
"learning_rate": 7.75e-05,
|
| 341 |
+
"loss": 0.0563,
|
| 342 |
+
"step": 450
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.3,
|
| 346 |
+
"grad_norm": 0.7504540085792542,
|
| 347 |
+
"learning_rate": 7.7e-05,
|
| 348 |
+
"loss": 0.0445,
|
| 349 |
+
"step": 460
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.35,
|
| 353 |
+
"grad_norm": 1.4322071075439453,
|
| 354 |
+
"learning_rate": 7.65e-05,
|
| 355 |
+
"loss": 0.048,
|
| 356 |
+
"step": 470
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.4,
|
| 360 |
+
"grad_norm": 3.965813636779785,
|
| 361 |
+
"learning_rate": 7.6e-05,
|
| 362 |
+
"loss": 0.0584,
|
| 363 |
+
"step": 480
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.45,
|
| 367 |
+
"grad_norm": 1.695728063583374,
|
| 368 |
+
"learning_rate": 7.55e-05,
|
| 369 |
+
"loss": 0.0523,
|
| 370 |
+
"step": 490
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.5,
|
| 374 |
+
"grad_norm": 7.276674747467041,
|
| 375 |
+
"learning_rate": 7.500000000000001e-05,
|
| 376 |
+
"loss": 0.0581,
|
| 377 |
+
"step": 500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.55,
|
| 381 |
+
"grad_norm": 1.3874706029891968,
|
| 382 |
+
"learning_rate": 7.450000000000001e-05,
|
| 383 |
+
"loss": 0.0552,
|
| 384 |
+
"step": 510
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.6,
|
| 388 |
+
"grad_norm": 2.3332033157348633,
|
| 389 |
+
"learning_rate": 7.4e-05,
|
| 390 |
+
"loss": 0.0459,
|
| 391 |
+
"step": 520
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.65,
|
| 395 |
+
"grad_norm": 5.276487350463867,
|
| 396 |
+
"learning_rate": 7.35e-05,
|
| 397 |
+
"loss": 0.0552,
|
| 398 |
+
"step": 530
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.7,
|
| 402 |
+
"grad_norm": 1.5198229551315308,
|
| 403 |
+
"learning_rate": 7.3e-05,
|
| 404 |
+
"loss": 0.0437,
|
| 405 |
+
"step": 540
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.75,
|
| 409 |
+
"grad_norm": 2.460489273071289,
|
| 410 |
+
"learning_rate": 7.25e-05,
|
| 411 |
+
"loss": 0.0641,
|
| 412 |
+
"step": 550
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 2.8,
|
| 416 |
+
"grad_norm": 4.7155680656433105,
|
| 417 |
+
"learning_rate": 7.2e-05,
|
| 418 |
+
"loss": 0.0593,
|
| 419 |
+
"step": 560
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.85,
|
| 423 |
+
"grad_norm": 1.9343897104263306,
|
| 424 |
+
"learning_rate": 7.15e-05,
|
| 425 |
+
"loss": 0.0724,
|
| 426 |
+
"step": 570
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.9,
|
| 430 |
+
"grad_norm": 6.80872106552124,
|
| 431 |
+
"learning_rate": 7.1e-05,
|
| 432 |
+
"loss": 0.0641,
|
| 433 |
+
"step": 580
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 2.95,
|
| 437 |
+
"grad_norm": 3.6537954807281494,
|
| 438 |
+
"learning_rate": 7.05e-05,
|
| 439 |
+
"loss": 0.0565,
|
| 440 |
+
"step": 590
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.0,
|
| 444 |
+
"grad_norm": 0.5623217225074768,
|
| 445 |
+
"learning_rate": 7e-05,
|
| 446 |
+
"loss": 0.0706,
|
| 447 |
+
"step": 600
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 3.0,
|
| 451 |
+
"eval_loss": 0.06641849875450134,
|
| 452 |
+
"eval_mse": 0.06641849130392075,
|
| 453 |
+
"eval_runtime": 16.3852,
|
| 454 |
+
"eval_samples_per_second": 24.412,
|
| 455 |
+
"eval_steps_per_second": 3.052,
|
| 456 |
+
"step": 600
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.05,
|
| 460 |
+
"grad_norm": 0.36932703852653503,
|
| 461 |
+
"learning_rate": 6.95e-05,
|
| 462 |
+
"loss": 0.0335,
|
| 463 |
+
"step": 610
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 3.1,
|
| 467 |
+
"grad_norm": 6.078632831573486,
|
| 468 |
+
"learning_rate": 6.9e-05,
|
| 469 |
+
"loss": 0.0263,
|
| 470 |
+
"step": 620
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.15,
|
| 474 |
+
"grad_norm": 1.8647630214691162,
|
| 475 |
+
"learning_rate": 6.850000000000001e-05,
|
| 476 |
+
"loss": 0.0361,
|
| 477 |
+
"step": 630
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.2,
|
| 481 |
+
"grad_norm": 2.3444764614105225,
|
| 482 |
+
"learning_rate": 6.800000000000001e-05,
|
| 483 |
+
"loss": 0.0318,
|
| 484 |
+
"step": 640
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.25,
|
| 488 |
+
"grad_norm": 3.742060899734497,
|
| 489 |
+
"learning_rate": 6.750000000000001e-05,
|
| 490 |
+
"loss": 0.0285,
|
| 491 |
+
"step": 650
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 3.3,
|
| 495 |
+
"grad_norm": 5.139005661010742,
|
| 496 |
+
"learning_rate": 6.7e-05,
|
| 497 |
+
"loss": 0.0282,
|
| 498 |
+
"step": 660
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 3.35,
|
| 502 |
+
"grad_norm": 2.5116076469421387,
|
| 503 |
+
"learning_rate": 6.65e-05,
|
| 504 |
+
"loss": 0.0508,
|
| 505 |
+
"step": 670
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 3.4,
|
| 509 |
+
"grad_norm": 4.835976600646973,
|
| 510 |
+
"learning_rate": 6.6e-05,
|
| 511 |
+
"loss": 0.0603,
|
| 512 |
+
"step": 680
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.45,
|
| 516 |
+
"grad_norm": 0.5137421488761902,
|
| 517 |
+
"learning_rate": 6.55e-05,
|
| 518 |
+
"loss": 0.0327,
|
| 519 |
+
"step": 690
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 3.5,
|
| 523 |
+
"grad_norm": 2.6399364471435547,
|
| 524 |
+
"learning_rate": 6.500000000000001e-05,
|
| 525 |
+
"loss": 0.0365,
|
| 526 |
+
"step": 700
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 3.55,
|
| 530 |
+
"grad_norm": 6.157520294189453,
|
| 531 |
+
"learning_rate": 6.450000000000001e-05,
|
| 532 |
+
"loss": 0.0298,
|
| 533 |
+
"step": 710
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 3.6,
|
| 537 |
+
"grad_norm": 4.332380294799805,
|
| 538 |
+
"learning_rate": 6.400000000000001e-05,
|
| 539 |
+
"loss": 0.0384,
|
| 540 |
+
"step": 720
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 3.65,
|
| 544 |
+
"grad_norm": 0.9350706338882446,
|
| 545 |
+
"learning_rate": 6.35e-05,
|
| 546 |
+
"loss": 0.0701,
|
| 547 |
+
"step": 730
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 3.7,
|
| 551 |
+
"grad_norm": 3.732862710952759,
|
| 552 |
+
"learning_rate": 6.3e-05,
|
| 553 |
+
"loss": 0.0401,
|
| 554 |
+
"step": 740
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.75,
|
| 558 |
+
"grad_norm": 0.5625308752059937,
|
| 559 |
+
"learning_rate": 6.25e-05,
|
| 560 |
+
"loss": 0.0446,
|
| 561 |
+
"step": 750
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.8,
|
| 565 |
+
"grad_norm": 1.4193575382232666,
|
| 566 |
+
"learning_rate": 6.2e-05,
|
| 567 |
+
"loss": 0.0484,
|
| 568 |
+
"step": 760
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 3.85,
|
| 572 |
+
"grad_norm": 3.158599376678467,
|
| 573 |
+
"learning_rate": 6.15e-05,
|
| 574 |
+
"loss": 0.0423,
|
| 575 |
+
"step": 770
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.9,
|
| 579 |
+
"grad_norm": 3.7658185958862305,
|
| 580 |
+
"learning_rate": 6.1e-05,
|
| 581 |
+
"loss": 0.0474,
|
| 582 |
+
"step": 780
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 3.95,
|
| 586 |
+
"grad_norm": 0.5808354616165161,
|
| 587 |
+
"learning_rate": 6.05e-05,
|
| 588 |
+
"loss": 0.0581,
|
| 589 |
+
"step": 790
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 4.0,
|
| 593 |
+
"grad_norm": 3.4763364791870117,
|
| 594 |
+
"learning_rate": 6e-05,
|
| 595 |
+
"loss": 0.0262,
|
| 596 |
+
"step": 800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 4.0,
|
| 600 |
+
"eval_loss": 0.07426866888999939,
|
| 601 |
+
"eval_mse": 0.07426867634057999,
|
| 602 |
+
"eval_runtime": 16.4034,
|
| 603 |
+
"eval_samples_per_second": 24.385,
|
| 604 |
+
"eval_steps_per_second": 3.048,
|
| 605 |
+
"step": 800
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 4.05,
|
| 609 |
+
"grad_norm": 5.053278923034668,
|
| 610 |
+
"learning_rate": 5.95e-05,
|
| 611 |
+
"loss": 0.0417,
|
| 612 |
+
"step": 810
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 4.1,
|
| 616 |
+
"grad_norm": 0.44556859135627747,
|
| 617 |
+
"learning_rate": 5.9e-05,
|
| 618 |
+
"loss": 0.0251,
|
| 619 |
+
"step": 820
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 4.15,
|
| 623 |
+
"grad_norm": 1.782357931137085,
|
| 624 |
+
"learning_rate": 5.85e-05,
|
| 625 |
+
"loss": 0.0241,
|
| 626 |
+
"step": 830
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 4.2,
|
| 630 |
+
"grad_norm": 3.3760969638824463,
|
| 631 |
+
"learning_rate": 5.8e-05,
|
| 632 |
+
"loss": 0.0475,
|
| 633 |
+
"step": 840
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 4.25,
|
| 637 |
+
"grad_norm": 1.7383389472961426,
|
| 638 |
+
"learning_rate": 5.7499999999999995e-05,
|
| 639 |
+
"loss": 0.0322,
|
| 640 |
+
"step": 850
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 4.3,
|
| 644 |
+
"grad_norm": 1.0607361793518066,
|
| 645 |
+
"learning_rate": 5.6999999999999996e-05,
|
| 646 |
+
"loss": 0.0284,
|
| 647 |
+
"step": 860
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 4.35,
|
| 651 |
+
"grad_norm": 2.8519768714904785,
|
| 652 |
+
"learning_rate": 5.65e-05,
|
| 653 |
+
"loss": 0.0242,
|
| 654 |
+
"step": 870
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 4.4,
|
| 658 |
+
"grad_norm": 2.405836582183838,
|
| 659 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 660 |
+
"loss": 0.0188,
|
| 661 |
+
"step": 880
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.45,
|
| 665 |
+
"grad_norm": 0.362431138753891,
|
| 666 |
+
"learning_rate": 5.550000000000001e-05,
|
| 667 |
+
"loss": 0.0239,
|
| 668 |
+
"step": 890
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.5,
|
| 672 |
+
"grad_norm": 3.0968267917633057,
|
| 673 |
+
"learning_rate": 5.500000000000001e-05,
|
| 674 |
+
"loss": 0.0259,
|
| 675 |
+
"step": 900
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 4.55,
|
| 679 |
+
"grad_norm": 1.1966663599014282,
|
| 680 |
+
"learning_rate": 5.45e-05,
|
| 681 |
+
"loss": 0.0253,
|
| 682 |
+
"step": 910
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 4.6,
|
| 686 |
+
"grad_norm": 3.1779186725616455,
|
| 687 |
+
"learning_rate": 5.4000000000000005e-05,
|
| 688 |
+
"loss": 0.0383,
|
| 689 |
+
"step": 920
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 4.65,
|
| 693 |
+
"grad_norm": 9.280014038085938,
|
| 694 |
+
"learning_rate": 5.3500000000000006e-05,
|
| 695 |
+
"loss": 0.046,
|
| 696 |
+
"step": 930
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 4.7,
|
| 700 |
+
"grad_norm": 5.865562915802002,
|
| 701 |
+
"learning_rate": 5.300000000000001e-05,
|
| 702 |
+
"loss": 0.0444,
|
| 703 |
+
"step": 940
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 4.75,
|
| 707 |
+
"grad_norm": 0.8096597790718079,
|
| 708 |
+
"learning_rate": 5.25e-05,
|
| 709 |
+
"loss": 0.0254,
|
| 710 |
+
"step": 950
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 4.8,
|
| 714 |
+
"grad_norm": 2.4865760803222656,
|
| 715 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 716 |
+
"loss": 0.0265,
|
| 717 |
+
"step": 960
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 4.85,
|
| 721 |
+
"grad_norm": 1.709107518196106,
|
| 722 |
+
"learning_rate": 5.1500000000000005e-05,
|
| 723 |
+
"loss": 0.0207,
|
| 724 |
+
"step": 970
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 4.9,
|
| 728 |
+
"grad_norm": 4.747660160064697,
|
| 729 |
+
"learning_rate": 5.1000000000000006e-05,
|
| 730 |
+
"loss": 0.0238,
|
| 731 |
+
"step": 980
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 4.95,
|
| 735 |
+
"grad_norm": 2.693565845489502,
|
| 736 |
+
"learning_rate": 5.05e-05,
|
| 737 |
+
"loss": 0.0273,
|
| 738 |
+
"step": 990
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 5.0,
|
| 742 |
+
"grad_norm": 1.1513164043426514,
|
| 743 |
+
"learning_rate": 5e-05,
|
| 744 |
+
"loss": 0.0254,
|
| 745 |
+
"step": 1000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 5.0,
|
| 749 |
+
"eval_loss": 0.06622488796710968,
|
| 750 |
+
"eval_mse": 0.06622488796710968,
|
| 751 |
+
"eval_runtime": 16.3594,
|
| 752 |
+
"eval_samples_per_second": 24.451,
|
| 753 |
+
"eval_steps_per_second": 3.056,
|
| 754 |
+
"step": 1000
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 5.05,
|
| 758 |
+
"grad_norm": 1.512947678565979,
|
| 759 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 760 |
+
"loss": 0.0165,
|
| 761 |
+
"step": 1010
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 5.1,
|
| 765 |
+
"grad_norm": 2.5008397102355957,
|
| 766 |
+
"learning_rate": 4.9e-05,
|
| 767 |
+
"loss": 0.0133,
|
| 768 |
+
"step": 1020
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 5.15,
|
| 772 |
+
"grad_norm": 2.0179872512817383,
|
| 773 |
+
"learning_rate": 4.85e-05,
|
| 774 |
+
"loss": 0.0202,
|
| 775 |
+
"step": 1030
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 5.2,
|
| 779 |
+
"grad_norm": 3.1750917434692383,
|
| 780 |
+
"learning_rate": 4.8e-05,
|
| 781 |
+
"loss": 0.0154,
|
| 782 |
+
"step": 1040
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 5.25,
|
| 786 |
+
"grad_norm": 2.2271130084991455,
|
| 787 |
+
"learning_rate": 4.75e-05,
|
| 788 |
+
"loss": 0.0247,
|
| 789 |
+
"step": 1050
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 5.3,
|
| 793 |
+
"grad_norm": 3.316953182220459,
|
| 794 |
+
"learning_rate": 4.7e-05,
|
| 795 |
+
"loss": 0.0185,
|
| 796 |
+
"step": 1060
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 5.35,
|
| 800 |
+
"grad_norm": 0.9691615104675293,
|
| 801 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 802 |
+
"loss": 0.0183,
|
| 803 |
+
"step": 1070
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 5.4,
|
| 807 |
+
"grad_norm": 2.1814730167388916,
|
| 808 |
+
"learning_rate": 4.600000000000001e-05,
|
| 809 |
+
"loss": 0.0127,
|
| 810 |
+
"step": 1080
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 5.45,
|
| 814 |
+
"grad_norm": 0.5520786643028259,
|
| 815 |
+
"learning_rate": 4.55e-05,
|
| 816 |
+
"loss": 0.0134,
|
| 817 |
+
"step": 1090
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 5.5,
|
| 821 |
+
"grad_norm": 1.098179578781128,
|
| 822 |
+
"learning_rate": 4.5e-05,
|
| 823 |
+
"loss": 0.0136,
|
| 824 |
+
"step": 1100
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 5.55,
|
| 828 |
+
"grad_norm": 2.0275049209594727,
|
| 829 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 830 |
+
"loss": 0.0186,
|
| 831 |
+
"step": 1110
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 5.6,
|
| 835 |
+
"grad_norm": 0.6353259086608887,
|
| 836 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 837 |
+
"loss": 0.0105,
|
| 838 |
+
"step": 1120
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 5.65,
|
| 842 |
+
"grad_norm": 0.8149334192276001,
|
| 843 |
+
"learning_rate": 4.35e-05,
|
| 844 |
+
"loss": 0.0124,
|
| 845 |
+
"step": 1130
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 5.7,
|
| 849 |
+
"grad_norm": 0.48699653148651123,
|
| 850 |
+
"learning_rate": 4.3e-05,
|
| 851 |
+
"loss": 0.0165,
|
| 852 |
+
"step": 1140
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 5.75,
|
| 856 |
+
"grad_norm": 1.4988057613372803,
|
| 857 |
+
"learning_rate": 4.25e-05,
|
| 858 |
+
"loss": 0.0131,
|
| 859 |
+
"step": 1150
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 5.8,
|
| 863 |
+
"grad_norm": 1.8789329528808594,
|
| 864 |
+
"learning_rate": 4.2e-05,
|
| 865 |
+
"loss": 0.0139,
|
| 866 |
+
"step": 1160
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 5.85,
|
| 870 |
+
"grad_norm": 0.5368540287017822,
|
| 871 |
+
"learning_rate": 4.15e-05,
|
| 872 |
+
"loss": 0.0127,
|
| 873 |
+
"step": 1170
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 5.9,
|
| 877 |
+
"grad_norm": 1.9691675901412964,
|
| 878 |
+
"learning_rate": 4.1e-05,
|
| 879 |
+
"loss": 0.0154,
|
| 880 |
+
"step": 1180
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 5.95,
|
| 884 |
+
"grad_norm": 1.972278356552124,
|
| 885 |
+
"learning_rate": 4.05e-05,
|
| 886 |
+
"loss": 0.0134,
|
| 887 |
+
"step": 1190
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 6.0,
|
| 891 |
+
"grad_norm": 0.720190167427063,
|
| 892 |
+
"learning_rate": 4e-05,
|
| 893 |
+
"loss": 0.0158,
|
| 894 |
+
"step": 1200
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 6.0,
|
| 898 |
+
"eval_loss": 0.061197929084300995,
|
| 899 |
+
"eval_mse": 0.061197929084300995,
|
| 900 |
+
"eval_runtime": 16.3287,
|
| 901 |
+
"eval_samples_per_second": 24.497,
|
| 902 |
+
"eval_steps_per_second": 3.062,
|
| 903 |
+
"step": 1200
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 6.05,
|
| 907 |
+
"grad_norm": 0.4566974937915802,
|
| 908 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 909 |
+
"loss": 0.0069,
|
| 910 |
+
"step": 1210
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 6.1,
|
| 914 |
+
"grad_norm": 3.2127201557159424,
|
| 915 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 916 |
+
"loss": 0.0113,
|
| 917 |
+
"step": 1220
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 6.15,
|
| 921 |
+
"grad_norm": 3.4719629287719727,
|
| 922 |
+
"learning_rate": 3.85e-05,
|
| 923 |
+
"loss": 0.0125,
|
| 924 |
+
"step": 1230
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 6.2,
|
| 928 |
+
"grad_norm": 0.5567223429679871,
|
| 929 |
+
"learning_rate": 3.8e-05,
|
| 930 |
+
"loss": 0.011,
|
| 931 |
+
"step": 1240
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 6.25,
|
| 935 |
+
"grad_norm": 1.591753363609314,
|
| 936 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 937 |
+
"loss": 0.0099,
|
| 938 |
+
"step": 1250
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 6.3,
|
| 942 |
+
"grad_norm": 2.333648681640625,
|
| 943 |
+
"learning_rate": 3.7e-05,
|
| 944 |
+
"loss": 0.0106,
|
| 945 |
+
"step": 1260
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 6.35,
|
| 949 |
+
"grad_norm": 0.5757361650466919,
|
| 950 |
+
"learning_rate": 3.65e-05,
|
| 951 |
+
"loss": 0.0066,
|
| 952 |
+
"step": 1270
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 6.4,
|
| 956 |
+
"grad_norm": 0.1848592758178711,
|
| 957 |
+
"learning_rate": 3.6e-05,
|
| 958 |
+
"loss": 0.0075,
|
| 959 |
+
"step": 1280
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 6.45,
|
| 963 |
+
"grad_norm": 2.7622129917144775,
|
| 964 |
+
"learning_rate": 3.55e-05,
|
| 965 |
+
"loss": 0.0064,
|
| 966 |
+
"step": 1290
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 6.5,
|
| 970 |
+
"grad_norm": 2.2141900062561035,
|
| 971 |
+
"learning_rate": 3.5e-05,
|
| 972 |
+
"loss": 0.0058,
|
| 973 |
+
"step": 1300
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 6.55,
|
| 977 |
+
"grad_norm": 2.2228360176086426,
|
| 978 |
+
"learning_rate": 3.45e-05,
|
| 979 |
+
"loss": 0.0075,
|
| 980 |
+
"step": 1310
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 6.6,
|
| 984 |
+
"grad_norm": 1.4335148334503174,
|
| 985 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 986 |
+
"loss": 0.0049,
|
| 987 |
+
"step": 1320
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 6.65,
|
| 991 |
+
"grad_norm": 5.4220781326293945,
|
| 992 |
+
"learning_rate": 3.35e-05,
|
| 993 |
+
"loss": 0.0097,
|
| 994 |
+
"step": 1330
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 6.7,
|
| 998 |
+
"grad_norm": 3.363415479660034,
|
| 999 |
+
"learning_rate": 3.3e-05,
|
| 1000 |
+
"loss": 0.011,
|
| 1001 |
+
"step": 1340
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 6.75,
|
| 1005 |
+
"grad_norm": 0.620877742767334,
|
| 1006 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 1007 |
+
"loss": 0.0085,
|
| 1008 |
+
"step": 1350
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 6.8,
|
| 1012 |
+
"grad_norm": 0.262657105922699,
|
| 1013 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 1014 |
+
"loss": 0.0063,
|
| 1015 |
+
"step": 1360
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 6.85,
|
| 1019 |
+
"grad_norm": 0.18443162739276886,
|
| 1020 |
+
"learning_rate": 3.15e-05,
|
| 1021 |
+
"loss": 0.0056,
|
| 1022 |
+
"step": 1370
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 6.9,
|
| 1026 |
+
"grad_norm": 1.5864096879959106,
|
| 1027 |
+
"learning_rate": 3.1e-05,
|
| 1028 |
+
"loss": 0.0078,
|
| 1029 |
+
"step": 1380
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 6.95,
|
| 1033 |
+
"grad_norm": 0.2312205284833908,
|
| 1034 |
+
"learning_rate": 3.05e-05,
|
| 1035 |
+
"loss": 0.0078,
|
| 1036 |
+
"step": 1390
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 7.0,
|
| 1040 |
+
"grad_norm": 1.5744479894638062,
|
| 1041 |
+
"learning_rate": 3e-05,
|
| 1042 |
+
"loss": 0.0082,
|
| 1043 |
+
"step": 1400
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 7.0,
|
| 1047 |
+
"eval_loss": 0.05860908329486847,
|
| 1048 |
+
"eval_mse": 0.058609090745449066,
|
| 1049 |
+
"eval_runtime": 16.3726,
|
| 1050 |
+
"eval_samples_per_second": 24.431,
|
| 1051 |
+
"eval_steps_per_second": 3.054,
|
| 1052 |
+
"step": 1400
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 7.05,
|
| 1056 |
+
"grad_norm": 0.41979604959487915,
|
| 1057 |
+
"learning_rate": 2.95e-05,
|
| 1058 |
+
"loss": 0.0029,
|
| 1059 |
+
"step": 1410
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 7.1,
|
| 1063 |
+
"grad_norm": 1.5260108709335327,
|
| 1064 |
+
"learning_rate": 2.9e-05,
|
| 1065 |
+
"loss": 0.0048,
|
| 1066 |
+
"step": 1420
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 7.15,
|
| 1070 |
+
"grad_norm": 1.438675880432129,
|
| 1071 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 1072 |
+
"loss": 0.0051,
|
| 1073 |
+
"step": 1430
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 7.2,
|
| 1077 |
+
"grad_norm": 1.684127688407898,
|
| 1078 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 1079 |
+
"loss": 0.0041,
|
| 1080 |
+
"step": 1440
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 7.25,
|
| 1084 |
+
"grad_norm": 0.2706861197948456,
|
| 1085 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 1086 |
+
"loss": 0.0035,
|
| 1087 |
+
"step": 1450
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 7.3,
|
| 1091 |
+
"grad_norm": 2.0461597442626953,
|
| 1092 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 1093 |
+
"loss": 0.0052,
|
| 1094 |
+
"step": 1460
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 7.35,
|
| 1098 |
+
"grad_norm": 0.6794195771217346,
|
| 1099 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 1100 |
+
"loss": 0.003,
|
| 1101 |
+
"step": 1470
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 7.4,
|
| 1105 |
+
"grad_norm": 2.5439083576202393,
|
| 1106 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 1107 |
+
"loss": 0.0041,
|
| 1108 |
+
"step": 1480
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 7.45,
|
| 1112 |
+
"grad_norm": 0.684155285358429,
|
| 1113 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 1114 |
+
"loss": 0.0043,
|
| 1115 |
+
"step": 1490
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 7.5,
|
| 1119 |
+
"grad_norm": 0.2224631905555725,
|
| 1120 |
+
"learning_rate": 2.5e-05,
|
| 1121 |
+
"loss": 0.0047,
|
| 1122 |
+
"step": 1500
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 7.55,
|
| 1126 |
+
"grad_norm": 0.820940375328064,
|
| 1127 |
+
"learning_rate": 2.45e-05,
|
| 1128 |
+
"loss": 0.0028,
|
| 1129 |
+
"step": 1510
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 7.6,
|
| 1133 |
+
"grad_norm": 0.22735460102558136,
|
| 1134 |
+
"learning_rate": 2.4e-05,
|
| 1135 |
+
"loss": 0.0043,
|
| 1136 |
+
"step": 1520
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 7.65,
|
| 1140 |
+
"grad_norm": 0.598775327205658,
|
| 1141 |
+
"learning_rate": 2.35e-05,
|
| 1142 |
+
"loss": 0.0035,
|
| 1143 |
+
"step": 1530
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 7.7,
|
| 1147 |
+
"grad_norm": 0.42806899547576904,
|
| 1148 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 1149 |
+
"loss": 0.0038,
|
| 1150 |
+
"step": 1540
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 7.75,
|
| 1154 |
+
"grad_norm": 0.46802547574043274,
|
| 1155 |
+
"learning_rate": 2.25e-05,
|
| 1156 |
+
"loss": 0.003,
|
| 1157 |
+
"step": 1550
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 7.8,
|
| 1161 |
+
"grad_norm": 1.4230495691299438,
|
| 1162 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 1163 |
+
"loss": 0.0043,
|
| 1164 |
+
"step": 1560
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 7.85,
|
| 1168 |
+
"grad_norm": 1.492274522781372,
|
| 1169 |
+
"learning_rate": 2.15e-05,
|
| 1170 |
+
"loss": 0.004,
|
| 1171 |
+
"step": 1570
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 7.9,
|
| 1175 |
+
"grad_norm": 0.22267311811447144,
|
| 1176 |
+
"learning_rate": 2.1e-05,
|
| 1177 |
+
"loss": 0.0034,
|
| 1178 |
+
"step": 1580
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 7.95,
|
| 1182 |
+
"grad_norm": 1.372755527496338,
|
| 1183 |
+
"learning_rate": 2.05e-05,
|
| 1184 |
+
"loss": 0.0041,
|
| 1185 |
+
"step": 1590
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 8.0,
|
| 1189 |
+
"grad_norm": 0.3921973407268524,
|
| 1190 |
+
"learning_rate": 2e-05,
|
| 1191 |
+
"loss": 0.004,
|
| 1192 |
+
"step": 1600
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 8.0,
|
| 1196 |
+
"eval_loss": 0.058916158974170685,
|
| 1197 |
+
"eval_mse": 0.058916158974170685,
|
| 1198 |
+
"eval_runtime": 16.4617,
|
| 1199 |
+
"eval_samples_per_second": 24.299,
|
| 1200 |
+
"eval_steps_per_second": 3.037,
|
| 1201 |
+
"step": 1600
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 8.05,
|
| 1205 |
+
"grad_norm": 0.9684560298919678,
|
| 1206 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 1207 |
+
"loss": 0.0015,
|
| 1208 |
+
"step": 1610
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 8.1,
|
| 1212 |
+
"grad_norm": 0.6896412372589111,
|
| 1213 |
+
"learning_rate": 1.9e-05,
|
| 1214 |
+
"loss": 0.0012,
|
| 1215 |
+
"step": 1620
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 8.15,
|
| 1219 |
+
"grad_norm": 0.0872649997472763,
|
| 1220 |
+
"learning_rate": 1.85e-05,
|
| 1221 |
+
"loss": 0.0013,
|
| 1222 |
+
"step": 1630
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 8.2,
|
| 1226 |
+
"grad_norm": 0.639758288860321,
|
| 1227 |
+
"learning_rate": 1.8e-05,
|
| 1228 |
+
"loss": 0.0023,
|
| 1229 |
+
"step": 1640
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 8.25,
|
| 1233 |
+
"grad_norm": 0.17185546457767487,
|
| 1234 |
+
"learning_rate": 1.75e-05,
|
| 1235 |
+
"loss": 0.0013,
|
| 1236 |
+
"step": 1650
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 8.3,
|
| 1240 |
+
"grad_norm": 1.2242165803909302,
|
| 1241 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 1242 |
+
"loss": 0.0016,
|
| 1243 |
+
"step": 1660
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 8.35,
|
| 1247 |
+
"grad_norm": 0.9778568148612976,
|
| 1248 |
+
"learning_rate": 1.65e-05,
|
| 1249 |
+
"loss": 0.0014,
|
| 1250 |
+
"step": 1670
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 8.4,
|
| 1254 |
+
"grad_norm": 0.3234766721725464,
|
| 1255 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 1256 |
+
"loss": 0.001,
|
| 1257 |
+
"step": 1680
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 8.45,
|
| 1261 |
+
"grad_norm": 1.149452805519104,
|
| 1262 |
+
"learning_rate": 1.55e-05,
|
| 1263 |
+
"loss": 0.0014,
|
| 1264 |
+
"step": 1690
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 8.5,
|
| 1268 |
+
"grad_norm": 0.6951824426651001,
|
| 1269 |
+
"learning_rate": 1.5e-05,
|
| 1270 |
+
"loss": 0.0013,
|
| 1271 |
+
"step": 1700
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 8.55,
|
| 1275 |
+
"grad_norm": 0.7042409181594849,
|
| 1276 |
+
"learning_rate": 1.45e-05,
|
| 1277 |
+
"loss": 0.0016,
|
| 1278 |
+
"step": 1710
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 8.6,
|
| 1282 |
+
"grad_norm": 0.1889318823814392,
|
| 1283 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 1284 |
+
"loss": 0.0014,
|
| 1285 |
+
"step": 1720
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 8.65,
|
| 1289 |
+
"grad_norm": 0.9096256494522095,
|
| 1290 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 1291 |
+
"loss": 0.0016,
|
| 1292 |
+
"step": 1730
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 8.7,
|
| 1296 |
+
"grad_norm": 0.3144957721233368,
|
| 1297 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 1298 |
+
"loss": 0.001,
|
| 1299 |
+
"step": 1740
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 8.75,
|
| 1303 |
+
"grad_norm": 0.6703792810440063,
|
| 1304 |
+
"learning_rate": 1.25e-05,
|
| 1305 |
+
"loss": 0.0017,
|
| 1306 |
+
"step": 1750
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 8.8,
|
| 1310 |
+
"grad_norm": 0.6046918034553528,
|
| 1311 |
+
"learning_rate": 1.2e-05,
|
| 1312 |
+
"loss": 0.0015,
|
| 1313 |
+
"step": 1760
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 8.85,
|
| 1317 |
+
"grad_norm": 0.3708367645740509,
|
| 1318 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 1319 |
+
"loss": 0.0012,
|
| 1320 |
+
"step": 1770
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 8.9,
|
| 1324 |
+
"grad_norm": 1.035162329673767,
|
| 1325 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 1326 |
+
"loss": 0.0013,
|
| 1327 |
+
"step": 1780
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 8.95,
|
| 1331 |
+
"grad_norm": 0.273884117603302,
|
| 1332 |
+
"learning_rate": 1.05e-05,
|
| 1333 |
+
"loss": 0.0013,
|
| 1334 |
+
"step": 1790
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 9.0,
|
| 1338 |
+
"grad_norm": 0.5523194074630737,
|
| 1339 |
+
"learning_rate": 1e-05,
|
| 1340 |
+
"loss": 0.0017,
|
| 1341 |
+
"step": 1800
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 9.0,
|
| 1345 |
+
"eval_loss": 0.05794011056423187,
|
| 1346 |
+
"eval_mse": 0.05794011056423187,
|
| 1347 |
+
"eval_runtime": 16.743,
|
| 1348 |
+
"eval_samples_per_second": 23.891,
|
| 1349 |
+
"eval_steps_per_second": 2.986,
|
| 1350 |
+
"step": 1800
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 9.05,
|
| 1354 |
+
"grad_norm": 0.26945334672927856,
|
| 1355 |
+
"learning_rate": 9.5e-06,
|
| 1356 |
+
"loss": 0.0009,
|
| 1357 |
+
"step": 1810
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 9.1,
|
| 1361 |
+
"grad_norm": 0.4931265711784363,
|
| 1362 |
+
"learning_rate": 9e-06,
|
| 1363 |
+
"loss": 0.0005,
|
| 1364 |
+
"step": 1820
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 9.15,
|
| 1368 |
+
"grad_norm": 0.17124253511428833,
|
| 1369 |
+
"learning_rate": 8.500000000000002e-06,
|
| 1370 |
+
"loss": 0.0005,
|
| 1371 |
+
"step": 1830
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 9.2,
|
| 1375 |
+
"grad_norm": 0.5681818723678589,
|
| 1376 |
+
"learning_rate": 8.000000000000001e-06,
|
| 1377 |
+
"loss": 0.0005,
|
| 1378 |
+
"step": 1840
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 9.25,
|
| 1382 |
+
"grad_norm": 0.5338633060455322,
|
| 1383 |
+
"learning_rate": 7.5e-06,
|
| 1384 |
+
"loss": 0.0004,
|
| 1385 |
+
"step": 1850
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 9.3,
|
| 1389 |
+
"grad_norm": 0.28590112924575806,
|
| 1390 |
+
"learning_rate": 7.000000000000001e-06,
|
| 1391 |
+
"loss": 0.0004,
|
| 1392 |
+
"step": 1860
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 9.35,
|
| 1396 |
+
"grad_norm": 0.047065772116184235,
|
| 1397 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 1398 |
+
"loss": 0.0003,
|
| 1399 |
+
"step": 1870
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 9.4,
|
| 1403 |
+
"grad_norm": 0.1954226791858673,
|
| 1404 |
+
"learning_rate": 6e-06,
|
| 1405 |
+
"loss": 0.0003,
|
| 1406 |
+
"step": 1880
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 9.45,
|
| 1410 |
+
"grad_norm": 0.20763620734214783,
|
| 1411 |
+
"learning_rate": 5.500000000000001e-06,
|
| 1412 |
+
"loss": 0.0005,
|
| 1413 |
+
"step": 1890
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 9.5,
|
| 1417 |
+
"grad_norm": 0.10486303269863129,
|
| 1418 |
+
"learning_rate": 5e-06,
|
| 1419 |
+
"loss": 0.0004,
|
| 1420 |
+
"step": 1900
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 9.55,
|
| 1424 |
+
"grad_norm": 0.09675983339548111,
|
| 1425 |
+
"learning_rate": 4.5e-06,
|
| 1426 |
+
"loss": 0.0007,
|
| 1427 |
+
"step": 1910
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 9.6,
|
| 1431 |
+
"grad_norm": 0.12553900480270386,
|
| 1432 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1433 |
+
"loss": 0.0004,
|
| 1434 |
+
"step": 1920
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 9.65,
|
| 1438 |
+
"grad_norm": 0.300682008266449,
|
| 1439 |
+
"learning_rate": 3.5000000000000004e-06,
|
| 1440 |
+
"loss": 0.0004,
|
| 1441 |
+
"step": 1930
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 9.7,
|
| 1445 |
+
"grad_norm": 0.2784073054790497,
|
| 1446 |
+
"learning_rate": 3e-06,
|
| 1447 |
+
"loss": 0.0004,
|
| 1448 |
+
"step": 1940
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 9.75,
|
| 1452 |
+
"grad_norm": 0.21158581972122192,
|
| 1453 |
+
"learning_rate": 2.5e-06,
|
| 1454 |
+
"loss": 0.0004,
|
| 1455 |
+
"step": 1950
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 9.8,
|
| 1459 |
+
"grad_norm": 0.36177006363868713,
|
| 1460 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 1461 |
+
"loss": 0.0004,
|
| 1462 |
+
"step": 1960
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 9.85,
|
| 1466 |
+
"grad_norm": 0.07186894863843918,
|
| 1467 |
+
"learning_rate": 1.5e-06,
|
| 1468 |
+
"loss": 0.0004,
|
| 1469 |
+
"step": 1970
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 9.9,
|
| 1473 |
+
"grad_norm": 0.07330793887376785,
|
| 1474 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 1475 |
+
"loss": 0.0005,
|
| 1476 |
+
"step": 1980
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 9.95,
|
| 1480 |
+
"grad_norm": 0.1601114273071289,
|
| 1481 |
+
"learning_rate": 5.000000000000001e-07,
|
| 1482 |
+
"loss": 0.0005,
|
| 1483 |
+
"step": 1990
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 10.0,
|
| 1487 |
+
"grad_norm": 0.520894467830658,
|
| 1488 |
+
"learning_rate": 0.0,
|
| 1489 |
+
"loss": 0.0005,
|
| 1490 |
+
"step": 2000
|
| 1491 |
+
}
|
| 1492 |
+
],
|
| 1493 |
+
"logging_steps": 10,
|
| 1494 |
+
"max_steps": 2000,
|
| 1495 |
+
"num_input_tokens_seen": 0,
|
| 1496 |
+
"num_train_epochs": 10,
|
| 1497 |
+
"save_steps": 10,
|
| 1498 |
+
"stateful_callbacks": {
|
| 1499 |
+
"TrainerControl": {
|
| 1500 |
+
"args": {
|
| 1501 |
+
"should_epoch_stop": false,
|
| 1502 |
+
"should_evaluate": false,
|
| 1503 |
+
"should_log": false,
|
| 1504 |
+
"should_save": true,
|
| 1505 |
+
"should_training_stop": true
|
| 1506 |
+
},
|
| 1507 |
+
"attributes": {}
|
| 1508 |
+
}
|
| 1509 |
+
},
|
| 1510 |
+
"total_flos": 0.0,
|
| 1511 |
+
"train_batch_size": 8,
|
| 1512 |
+
"trial_name": null,
|
| 1513 |
+
"trial_params": null
|
| 1514 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b480aac25c4b78f1cc3dabceb4e63961ccbdce5223bd2dfa17bcab947ac96b9e
|
| 3 |
+
size 5048
|