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 +891 -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 |
+
- "TKayWortmann/shoe-sales-ds"
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: "tamaris-sales-prediction"
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# tamaris-sales-prediction
|
| 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='TKayWortmann/tamaris-sales-prediction',image_path='image.jpg')
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
## Dataset
|
| 28 |
+
Dataset: TKayWortmann/shoe-sales-ds\
|
| 29 |
+
Value Column: 'sales'\
|
| 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='TKayWortmann/tamaris-sales-prediction',
|
| 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='TKayWortmann/shoe-sales-ds',
|
| 77 |
+
value_column_name='sales',
|
| 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='tamaris-sales-prediction',
|
| 93 |
+
token='YOUR_HF_TOKEN',
|
| 94 |
+
checkpoint_dir='./results/checkpoint-940')
|
| 95 |
+
```
|
metadata.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset_id": "TKayWortmann/shoe-sales-ds",
|
| 3 |
+
"value_column_name": "sales",
|
| 4 |
+
"test_split": 0.2,
|
| 5 |
+
"num_train_epochs": 10,
|
| 6 |
+
"learning_rate": 0.0001,
|
| 7 |
+
"max_value": 47926
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74d8c90f1c6c178ee544a2bb2bc565bd03db9d8973bf24ce3372137fee768565
|
| 3 |
+
size 345583444
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5995e955255ab05173a0a3b4977d296dbb04fe41f733ec8be2ad4257b621c63
|
| 3 |
+
size 686562746
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:409f3067cf76c05815b49d5035d10ee15858f68903605e271c88ba195a65ade7
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b088e977ff4fb225dd56384c54b2881f3b9d1421451b5fbc0412d235ab7eaa54
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,891 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1110,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09009009009009009,
|
| 13 |
+
"grad_norm": 16.28987693786621,
|
| 14 |
+
"learning_rate": 9.90990990990991e-05,
|
| 15 |
+
"loss": 0.4883,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.18018018018018017,
|
| 20 |
+
"grad_norm": 3.943525552749634,
|
| 21 |
+
"learning_rate": 9.81981981981982e-05,
|
| 22 |
+
"loss": 0.0823,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2702702702702703,
|
| 27 |
+
"grad_norm": 7.749650955200195,
|
| 28 |
+
"learning_rate": 9.729729729729731e-05,
|
| 29 |
+
"loss": 0.0279,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.36036036036036034,
|
| 34 |
+
"grad_norm": 1.5577881336212158,
|
| 35 |
+
"learning_rate": 9.639639639639641e-05,
|
| 36 |
+
"loss": 0.0247,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.45045045045045046,
|
| 41 |
+
"grad_norm": 1.7881258726119995,
|
| 42 |
+
"learning_rate": 9.54954954954955e-05,
|
| 43 |
+
"loss": 0.0162,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5405405405405406,
|
| 48 |
+
"grad_norm": 1.0929126739501953,
|
| 49 |
+
"learning_rate": 9.45945945945946e-05,
|
| 50 |
+
"loss": 0.0127,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6306306306306306,
|
| 55 |
+
"grad_norm": 2.1130833625793457,
|
| 56 |
+
"learning_rate": 9.36936936936937e-05,
|
| 57 |
+
"loss": 0.0069,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7207207207207207,
|
| 62 |
+
"grad_norm": 3.6001977920532227,
|
| 63 |
+
"learning_rate": 9.279279279279279e-05,
|
| 64 |
+
"loss": 0.0094,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8108108108108109,
|
| 69 |
+
"grad_norm": 0.6843027472496033,
|
| 70 |
+
"learning_rate": 9.18918918918919e-05,
|
| 71 |
+
"loss": 0.0069,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.9009009009009009,
|
| 76 |
+
"grad_norm": 2.2954471111297607,
|
| 77 |
+
"learning_rate": 9.0990990990991e-05,
|
| 78 |
+
"loss": 0.0069,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.990990990990991,
|
| 83 |
+
"grad_norm": 0.22960656881332397,
|
| 84 |
+
"learning_rate": 9.009009009009009e-05,
|
| 85 |
+
"loss": 0.0094,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.0,
|
| 90 |
+
"eval_loss": 0.016822505742311478,
|
| 91 |
+
"eval_mse": 0.016822507604956627,
|
| 92 |
+
"eval_runtime": 26.347,
|
| 93 |
+
"eval_samples_per_second": 8.426,
|
| 94 |
+
"eval_steps_per_second": 1.063,
|
| 95 |
+
"step": 111
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.0810810810810811,
|
| 99 |
+
"grad_norm": 0.10217050462961197,
|
| 100 |
+
"learning_rate": 8.918918918918919e-05,
|
| 101 |
+
"loss": 0.0042,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.1711711711711712,
|
| 106 |
+
"grad_norm": 5.079370498657227,
|
| 107 |
+
"learning_rate": 8.82882882882883e-05,
|
| 108 |
+
"loss": 0.0094,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.2612612612612613,
|
| 113 |
+
"grad_norm": 2.9237141609191895,
|
| 114 |
+
"learning_rate": 8.738738738738738e-05,
|
| 115 |
+
"loss": 0.0099,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.3513513513513513,
|
| 120 |
+
"grad_norm": 3.25941801071167,
|
| 121 |
+
"learning_rate": 8.64864864864865e-05,
|
| 122 |
+
"loss": 0.016,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.4414414414414414,
|
| 127 |
+
"grad_norm": 0.9882258772850037,
|
| 128 |
+
"learning_rate": 8.55855855855856e-05,
|
| 129 |
+
"loss": 0.0061,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.5315315315315314,
|
| 134 |
+
"grad_norm": 4.510200023651123,
|
| 135 |
+
"learning_rate": 8.468468468468469e-05,
|
| 136 |
+
"loss": 0.0143,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.6216216216216215,
|
| 141 |
+
"grad_norm": 0.35400834679603577,
|
| 142 |
+
"learning_rate": 8.378378378378379e-05,
|
| 143 |
+
"loss": 0.0148,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.7117117117117115,
|
| 148 |
+
"grad_norm": 3.6332740783691406,
|
| 149 |
+
"learning_rate": 8.288288288288289e-05,
|
| 150 |
+
"loss": 0.0113,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.8018018018018018,
|
| 155 |
+
"grad_norm": 1.811373233795166,
|
| 156 |
+
"learning_rate": 8.198198198198198e-05,
|
| 157 |
+
"loss": 0.017,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.8918918918918919,
|
| 162 |
+
"grad_norm": 2.500202178955078,
|
| 163 |
+
"learning_rate": 8.108108108108109e-05,
|
| 164 |
+
"loss": 0.0062,
|
| 165 |
+
"step": 210
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.981981981981982,
|
| 169 |
+
"grad_norm": 4.341911792755127,
|
| 170 |
+
"learning_rate": 8.018018018018019e-05,
|
| 171 |
+
"loss": 0.0142,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.0,
|
| 176 |
+
"eval_loss": 0.008252176456153393,
|
| 177 |
+
"eval_mse": 0.008252176456153393,
|
| 178 |
+
"eval_runtime": 25.8199,
|
| 179 |
+
"eval_samples_per_second": 8.598,
|
| 180 |
+
"eval_steps_per_second": 1.084,
|
| 181 |
+
"step": 222
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.0720720720720722,
|
| 185 |
+
"grad_norm": 0.4223078489303589,
|
| 186 |
+
"learning_rate": 7.927927927927928e-05,
|
| 187 |
+
"loss": 0.01,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.1621621621621623,
|
| 192 |
+
"grad_norm": 3.0677056312561035,
|
| 193 |
+
"learning_rate": 7.837837837837838e-05,
|
| 194 |
+
"loss": 0.0139,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.2522522522522523,
|
| 199 |
+
"grad_norm": 0.3952648639678955,
|
| 200 |
+
"learning_rate": 7.747747747747748e-05,
|
| 201 |
+
"loss": 0.0063,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 2.3423423423423424,
|
| 206 |
+
"grad_norm": 3.6467502117156982,
|
| 207 |
+
"learning_rate": 7.657657657657657e-05,
|
| 208 |
+
"loss": 0.0122,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.4324324324324325,
|
| 213 |
+
"grad_norm": 4.3216352462768555,
|
| 214 |
+
"learning_rate": 7.567567567567568e-05,
|
| 215 |
+
"loss": 0.0106,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.5225225225225225,
|
| 220 |
+
"grad_norm": 3.8619132041931152,
|
| 221 |
+
"learning_rate": 7.477477477477479e-05,
|
| 222 |
+
"loss": 0.0106,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.6126126126126126,
|
| 227 |
+
"grad_norm": 1.1223838329315186,
|
| 228 |
+
"learning_rate": 7.387387387387387e-05,
|
| 229 |
+
"loss": 0.0086,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.7027027027027026,
|
| 234 |
+
"grad_norm": 0.8446173667907715,
|
| 235 |
+
"learning_rate": 7.297297297297297e-05,
|
| 236 |
+
"loss": 0.0202,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.7927927927927927,
|
| 241 |
+
"grad_norm": 0.9771293997764587,
|
| 242 |
+
"learning_rate": 7.207207207207208e-05,
|
| 243 |
+
"loss": 0.0071,
|
| 244 |
+
"step": 310
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 2.8828828828828827,
|
| 248 |
+
"grad_norm": 2.6441454887390137,
|
| 249 |
+
"learning_rate": 7.117117117117116e-05,
|
| 250 |
+
"loss": 0.0093,
|
| 251 |
+
"step": 320
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 2.972972972972973,
|
| 255 |
+
"grad_norm": 3.6695780754089355,
|
| 256 |
+
"learning_rate": 7.027027027027028e-05,
|
| 257 |
+
"loss": 0.0067,
|
| 258 |
+
"step": 330
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.0,
|
| 262 |
+
"eval_loss": 0.012067927978932858,
|
| 263 |
+
"eval_mse": 0.012067928910255432,
|
| 264 |
+
"eval_runtime": 26.2024,
|
| 265 |
+
"eval_samples_per_second": 8.473,
|
| 266 |
+
"eval_steps_per_second": 1.069,
|
| 267 |
+
"step": 333
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 3.063063063063063,
|
| 271 |
+
"grad_norm": 1.334926962852478,
|
| 272 |
+
"learning_rate": 6.936936936936938e-05,
|
| 273 |
+
"loss": 0.0129,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 3.153153153153153,
|
| 278 |
+
"grad_norm": 3.8143014907836914,
|
| 279 |
+
"learning_rate": 6.846846846846847e-05,
|
| 280 |
+
"loss": 0.0084,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.2432432432432434,
|
| 285 |
+
"grad_norm": 0.529600977897644,
|
| 286 |
+
"learning_rate": 6.756756756756757e-05,
|
| 287 |
+
"loss": 0.0059,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.3333333333333335,
|
| 292 |
+
"grad_norm": 6.050387382507324,
|
| 293 |
+
"learning_rate": 6.666666666666667e-05,
|
| 294 |
+
"loss": 0.0184,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.4234234234234235,
|
| 299 |
+
"grad_norm": 0.3079633414745331,
|
| 300 |
+
"learning_rate": 6.576576576576577e-05,
|
| 301 |
+
"loss": 0.0072,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.5135135135135136,
|
| 306 |
+
"grad_norm": 2.165722608566284,
|
| 307 |
+
"learning_rate": 6.486486486486487e-05,
|
| 308 |
+
"loss": 0.0086,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.6036036036036037,
|
| 313 |
+
"grad_norm": 1.4053255319595337,
|
| 314 |
+
"learning_rate": 6.396396396396397e-05,
|
| 315 |
+
"loss": 0.0063,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.6936936936936937,
|
| 320 |
+
"grad_norm": 1.4147133827209473,
|
| 321 |
+
"learning_rate": 6.306306306306306e-05,
|
| 322 |
+
"loss": 0.0049,
|
| 323 |
+
"step": 410
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.7837837837837838,
|
| 327 |
+
"grad_norm": 0.1397821009159088,
|
| 328 |
+
"learning_rate": 6.216216216216216e-05,
|
| 329 |
+
"loss": 0.0143,
|
| 330 |
+
"step": 420
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 3.873873873873874,
|
| 334 |
+
"grad_norm": 2.773983955383301,
|
| 335 |
+
"learning_rate": 6.126126126126126e-05,
|
| 336 |
+
"loss": 0.0052,
|
| 337 |
+
"step": 430
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.963963963963964,
|
| 341 |
+
"grad_norm": 2.0396511554718018,
|
| 342 |
+
"learning_rate": 6.0360360360360365e-05,
|
| 343 |
+
"loss": 0.0051,
|
| 344 |
+
"step": 440
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.0,
|
| 348 |
+
"eval_loss": 0.00851067528128624,
|
| 349 |
+
"eval_mse": 0.00851067528128624,
|
| 350 |
+
"eval_runtime": 26.1258,
|
| 351 |
+
"eval_samples_per_second": 8.497,
|
| 352 |
+
"eval_steps_per_second": 1.072,
|
| 353 |
+
"step": 444
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.054054054054054,
|
| 357 |
+
"grad_norm": 1.728843092918396,
|
| 358 |
+
"learning_rate": 5.9459459459459466e-05,
|
| 359 |
+
"loss": 0.0071,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.1441441441441444,
|
| 364 |
+
"grad_norm": 2.8978583812713623,
|
| 365 |
+
"learning_rate": 5.855855855855856e-05,
|
| 366 |
+
"loss": 0.0072,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.2342342342342345,
|
| 371 |
+
"grad_norm": 0.1254826933145523,
|
| 372 |
+
"learning_rate": 5.765765765765766e-05,
|
| 373 |
+
"loss": 0.0045,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 4.324324324324325,
|
| 378 |
+
"grad_norm": 0.3451184034347534,
|
| 379 |
+
"learning_rate": 5.6756756756756757e-05,
|
| 380 |
+
"loss": 0.0034,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.414414414414415,
|
| 385 |
+
"grad_norm": 0.3993205726146698,
|
| 386 |
+
"learning_rate": 5.585585585585585e-05,
|
| 387 |
+
"loss": 0.0062,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4.504504504504505,
|
| 392 |
+
"grad_norm": 1.2357189655303955,
|
| 393 |
+
"learning_rate": 5.4954954954954966e-05,
|
| 394 |
+
"loss": 0.0109,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.594594594594595,
|
| 399 |
+
"grad_norm": 2.587001085281372,
|
| 400 |
+
"learning_rate": 5.405405405405406e-05,
|
| 401 |
+
"loss": 0.0096,
|
| 402 |
+
"step": 510
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 4.684684684684685,
|
| 406 |
+
"grad_norm": 1.4181842803955078,
|
| 407 |
+
"learning_rate": 5.3153153153153155e-05,
|
| 408 |
+
"loss": 0.0053,
|
| 409 |
+
"step": 520
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 4.774774774774775,
|
| 413 |
+
"grad_norm": 0.5997741222381592,
|
| 414 |
+
"learning_rate": 5.2252252252252256e-05,
|
| 415 |
+
"loss": 0.0074,
|
| 416 |
+
"step": 530
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.864864864864865,
|
| 420 |
+
"grad_norm": 0.6971381306648254,
|
| 421 |
+
"learning_rate": 5.135135135135135e-05,
|
| 422 |
+
"loss": 0.0022,
|
| 423 |
+
"step": 540
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.954954954954955,
|
| 427 |
+
"grad_norm": 1.7140687704086304,
|
| 428 |
+
"learning_rate": 5.0450450450450445e-05,
|
| 429 |
+
"loss": 0.0035,
|
| 430 |
+
"step": 550
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 5.0,
|
| 434 |
+
"eval_loss": 0.011971085332334042,
|
| 435 |
+
"eval_mse": 0.011971085332334042,
|
| 436 |
+
"eval_runtime": 26.2997,
|
| 437 |
+
"eval_samples_per_second": 8.441,
|
| 438 |
+
"eval_steps_per_second": 1.065,
|
| 439 |
+
"step": 555
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5.045045045045045,
|
| 443 |
+
"grad_norm": 1.8608264923095703,
|
| 444 |
+
"learning_rate": 4.954954954954955e-05,
|
| 445 |
+
"loss": 0.0074,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 5.135135135135135,
|
| 450 |
+
"grad_norm": 0.60817551612854,
|
| 451 |
+
"learning_rate": 4.8648648648648654e-05,
|
| 452 |
+
"loss": 0.0068,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 5.225225225225225,
|
| 457 |
+
"grad_norm": 1.958824634552002,
|
| 458 |
+
"learning_rate": 4.774774774774775e-05,
|
| 459 |
+
"loss": 0.006,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 5.315315315315315,
|
| 464 |
+
"grad_norm": 0.3445253372192383,
|
| 465 |
+
"learning_rate": 4.684684684684685e-05,
|
| 466 |
+
"loss": 0.0049,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.405405405405405,
|
| 471 |
+
"grad_norm": 0.22099243104457855,
|
| 472 |
+
"learning_rate": 4.594594594594595e-05,
|
| 473 |
+
"loss": 0.0039,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.495495495495495,
|
| 478 |
+
"grad_norm": 1.4178491830825806,
|
| 479 |
+
"learning_rate": 4.5045045045045046e-05,
|
| 480 |
+
"loss": 0.0131,
|
| 481 |
+
"step": 610
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 5.585585585585585,
|
| 485 |
+
"grad_norm": 0.469068706035614,
|
| 486 |
+
"learning_rate": 4.414414414414415e-05,
|
| 487 |
+
"loss": 0.0025,
|
| 488 |
+
"step": 620
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 5.675675675675675,
|
| 492 |
+
"grad_norm": 0.772139847278595,
|
| 493 |
+
"learning_rate": 4.324324324324325e-05,
|
| 494 |
+
"loss": 0.0032,
|
| 495 |
+
"step": 630
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 5.7657657657657655,
|
| 499 |
+
"grad_norm": 0.21695229411125183,
|
| 500 |
+
"learning_rate": 4.234234234234234e-05,
|
| 501 |
+
"loss": 0.0026,
|
| 502 |
+
"step": 640
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 5.8558558558558556,
|
| 506 |
+
"grad_norm": 1.6817526817321777,
|
| 507 |
+
"learning_rate": 4.1441441441441444e-05,
|
| 508 |
+
"loss": 0.005,
|
| 509 |
+
"step": 650
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.945945945945946,
|
| 513 |
+
"grad_norm": 1.2628576755523682,
|
| 514 |
+
"learning_rate": 4.0540540540540545e-05,
|
| 515 |
+
"loss": 0.0024,
|
| 516 |
+
"step": 660
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 6.0,
|
| 520 |
+
"eval_loss": 0.008206626400351524,
|
| 521 |
+
"eval_mse": 0.008206626400351524,
|
| 522 |
+
"eval_runtime": 26.5886,
|
| 523 |
+
"eval_samples_per_second": 8.349,
|
| 524 |
+
"eval_steps_per_second": 1.053,
|
| 525 |
+
"step": 666
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.036036036036036,
|
| 529 |
+
"grad_norm": 1.1488395929336548,
|
| 530 |
+
"learning_rate": 3.963963963963964e-05,
|
| 531 |
+
"loss": 0.0036,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 6.126126126126126,
|
| 536 |
+
"grad_norm": 1.4983370304107666,
|
| 537 |
+
"learning_rate": 3.873873873873874e-05,
|
| 538 |
+
"loss": 0.0032,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 6.216216216216216,
|
| 543 |
+
"grad_norm": 0.8290634751319885,
|
| 544 |
+
"learning_rate": 3.783783783783784e-05,
|
| 545 |
+
"loss": 0.0091,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 6.306306306306306,
|
| 550 |
+
"grad_norm": 0.4906163811683655,
|
| 551 |
+
"learning_rate": 3.693693693693694e-05,
|
| 552 |
+
"loss": 0.0013,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 6.396396396396397,
|
| 557 |
+
"grad_norm": 0.5014496445655823,
|
| 558 |
+
"learning_rate": 3.603603603603604e-05,
|
| 559 |
+
"loss": 0.0019,
|
| 560 |
+
"step": 710
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 6.486486486486487,
|
| 564 |
+
"grad_norm": 0.38546356558799744,
|
| 565 |
+
"learning_rate": 3.513513513513514e-05,
|
| 566 |
+
"loss": 0.0013,
|
| 567 |
+
"step": 720
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 6.576576576576577,
|
| 571 |
+
"grad_norm": 2.099214553833008,
|
| 572 |
+
"learning_rate": 3.4234234234234234e-05,
|
| 573 |
+
"loss": 0.0018,
|
| 574 |
+
"step": 730
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 6.666666666666667,
|
| 578 |
+
"grad_norm": 0.1836785525083542,
|
| 579 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 580 |
+
"loss": 0.0013,
|
| 581 |
+
"step": 740
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 6.756756756756757,
|
| 585 |
+
"grad_norm": 0.2982404828071594,
|
| 586 |
+
"learning_rate": 3.2432432432432436e-05,
|
| 587 |
+
"loss": 0.0015,
|
| 588 |
+
"step": 750
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 6.846846846846847,
|
| 592 |
+
"grad_norm": 2.1191866397857666,
|
| 593 |
+
"learning_rate": 3.153153153153153e-05,
|
| 594 |
+
"loss": 0.0037,
|
| 595 |
+
"step": 760
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 6.936936936936937,
|
| 599 |
+
"grad_norm": 1.7569901943206787,
|
| 600 |
+
"learning_rate": 3.063063063063063e-05,
|
| 601 |
+
"loss": 0.0079,
|
| 602 |
+
"step": 770
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 7.0,
|
| 606 |
+
"eval_loss": 0.007293929811567068,
|
| 607 |
+
"eval_mse": 0.0072939288802444935,
|
| 608 |
+
"eval_runtime": 23.2827,
|
| 609 |
+
"eval_samples_per_second": 9.535,
|
| 610 |
+
"eval_steps_per_second": 1.203,
|
| 611 |
+
"step": 777
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 7.027027027027027,
|
| 615 |
+
"grad_norm": 0.3839648365974426,
|
| 616 |
+
"learning_rate": 2.9729729729729733e-05,
|
| 617 |
+
"loss": 0.0013,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 7.117117117117117,
|
| 622 |
+
"grad_norm": 0.09070757776498795,
|
| 623 |
+
"learning_rate": 2.882882882882883e-05,
|
| 624 |
+
"loss": 0.0009,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 7.207207207207207,
|
| 629 |
+
"grad_norm": 0.15580403804779053,
|
| 630 |
+
"learning_rate": 2.7927927927927926e-05,
|
| 631 |
+
"loss": 0.0006,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 7.297297297297297,
|
| 636 |
+
"grad_norm": 0.6153419017791748,
|
| 637 |
+
"learning_rate": 2.702702702702703e-05,
|
| 638 |
+
"loss": 0.0015,
|
| 639 |
+
"step": 810
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 7.387387387387387,
|
| 643 |
+
"grad_norm": 0.3068805932998657,
|
| 644 |
+
"learning_rate": 2.6126126126126128e-05,
|
| 645 |
+
"loss": 0.0009,
|
| 646 |
+
"step": 820
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 7.4774774774774775,
|
| 650 |
+
"grad_norm": 0.38947150111198425,
|
| 651 |
+
"learning_rate": 2.5225225225225222e-05,
|
| 652 |
+
"loss": 0.0018,
|
| 653 |
+
"step": 830
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 7.5675675675675675,
|
| 657 |
+
"grad_norm": 0.3517474830150604,
|
| 658 |
+
"learning_rate": 2.4324324324324327e-05,
|
| 659 |
+
"loss": 0.0006,
|
| 660 |
+
"step": 840
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 7.657657657657658,
|
| 664 |
+
"grad_norm": 0.26397421956062317,
|
| 665 |
+
"learning_rate": 2.3423423423423425e-05,
|
| 666 |
+
"loss": 0.0044,
|
| 667 |
+
"step": 850
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 7.747747747747748,
|
| 671 |
+
"grad_norm": 0.5078900456428528,
|
| 672 |
+
"learning_rate": 2.2522522522522523e-05,
|
| 673 |
+
"loss": 0.0018,
|
| 674 |
+
"step": 860
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 7.837837837837838,
|
| 678 |
+
"grad_norm": 0.13668565452098846,
|
| 679 |
+
"learning_rate": 2.1621621621621624e-05,
|
| 680 |
+
"loss": 0.0006,
|
| 681 |
+
"step": 870
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 7.927927927927928,
|
| 685 |
+
"grad_norm": 0.2840743660926819,
|
| 686 |
+
"learning_rate": 2.0720720720720722e-05,
|
| 687 |
+
"loss": 0.0005,
|
| 688 |
+
"step": 880
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 8.0,
|
| 692 |
+
"eval_loss": 0.006760227959603071,
|
| 693 |
+
"eval_mse": 0.0067602284252643585,
|
| 694 |
+
"eval_runtime": 25.9835,
|
| 695 |
+
"eval_samples_per_second": 8.544,
|
| 696 |
+
"eval_steps_per_second": 1.078,
|
| 697 |
+
"step": 888
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 8.018018018018019,
|
| 701 |
+
"grad_norm": 0.12077564746141434,
|
| 702 |
+
"learning_rate": 1.981981981981982e-05,
|
| 703 |
+
"loss": 0.0005,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 8.108108108108109,
|
| 708 |
+
"grad_norm": 0.14313092827796936,
|
| 709 |
+
"learning_rate": 1.891891891891892e-05,
|
| 710 |
+
"loss": 0.0007,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8.198198198198199,
|
| 715 |
+
"grad_norm": 0.04330454021692276,
|
| 716 |
+
"learning_rate": 1.801801801801802e-05,
|
| 717 |
+
"loss": 0.0002,
|
| 718 |
+
"step": 910
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 8.288288288288289,
|
| 722 |
+
"grad_norm": 0.09245187044143677,
|
| 723 |
+
"learning_rate": 1.7117117117117117e-05,
|
| 724 |
+
"loss": 0.0003,
|
| 725 |
+
"step": 920
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 8.378378378378379,
|
| 729 |
+
"grad_norm": 1.145082950592041,
|
| 730 |
+
"learning_rate": 1.6216216216216218e-05,
|
| 731 |
+
"loss": 0.0005,
|
| 732 |
+
"step": 930
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 8.468468468468469,
|
| 736 |
+
"grad_norm": 0.16518352925777435,
|
| 737 |
+
"learning_rate": 1.5315315315315316e-05,
|
| 738 |
+
"loss": 0.0028,
|
| 739 |
+
"step": 940
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 8.558558558558559,
|
| 743 |
+
"grad_norm": 0.21115215122699738,
|
| 744 |
+
"learning_rate": 1.4414414414414416e-05,
|
| 745 |
+
"loss": 0.0004,
|
| 746 |
+
"step": 950
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 8.64864864864865,
|
| 750 |
+
"grad_norm": 0.5826627612113953,
|
| 751 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 752 |
+
"loss": 0.0004,
|
| 753 |
+
"step": 960
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 8.73873873873874,
|
| 757 |
+
"grad_norm": 0.5220029354095459,
|
| 758 |
+
"learning_rate": 1.2612612612612611e-05,
|
| 759 |
+
"loss": 0.0003,
|
| 760 |
+
"step": 970
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 8.82882882882883,
|
| 764 |
+
"grad_norm": 0.10058625787496567,
|
| 765 |
+
"learning_rate": 1.1711711711711713e-05,
|
| 766 |
+
"loss": 0.0005,
|
| 767 |
+
"step": 980
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 8.91891891891892,
|
| 771 |
+
"grad_norm": 0.5194815993309021,
|
| 772 |
+
"learning_rate": 1.0810810810810812e-05,
|
| 773 |
+
"loss": 0.0004,
|
| 774 |
+
"step": 990
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 9.0,
|
| 778 |
+
"eval_loss": 0.006972064264118671,
|
| 779 |
+
"eval_mse": 0.006972064264118671,
|
| 780 |
+
"eval_runtime": 25.2631,
|
| 781 |
+
"eval_samples_per_second": 8.788,
|
| 782 |
+
"eval_steps_per_second": 1.108,
|
| 783 |
+
"step": 999
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 9.00900900900901,
|
| 787 |
+
"grad_norm": 0.20283883810043335,
|
| 788 |
+
"learning_rate": 9.90990990990991e-06,
|
| 789 |
+
"loss": 0.0003,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9.0990990990991,
|
| 794 |
+
"grad_norm": 0.34447431564331055,
|
| 795 |
+
"learning_rate": 9.00900900900901e-06,
|
| 796 |
+
"loss": 0.0002,
|
| 797 |
+
"step": 1010
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 9.18918918918919,
|
| 801 |
+
"grad_norm": 0.08173416554927826,
|
| 802 |
+
"learning_rate": 8.108108108108109e-06,
|
| 803 |
+
"loss": 0.0002,
|
| 804 |
+
"step": 1020
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 9.27927927927928,
|
| 808 |
+
"grad_norm": 0.10527441650629044,
|
| 809 |
+
"learning_rate": 7.207207207207208e-06,
|
| 810 |
+
"loss": 0.0002,
|
| 811 |
+
"step": 1030
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 9.36936936936937,
|
| 815 |
+
"grad_norm": 0.0803741067647934,
|
| 816 |
+
"learning_rate": 6.306306306306306e-06,
|
| 817 |
+
"loss": 0.0001,
|
| 818 |
+
"step": 1040
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 9.45945945945946,
|
| 822 |
+
"grad_norm": 0.10471061617136002,
|
| 823 |
+
"learning_rate": 5.405405405405406e-06,
|
| 824 |
+
"loss": 0.0002,
|
| 825 |
+
"step": 1050
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 9.54954954954955,
|
| 829 |
+
"grad_norm": 0.05206935107707977,
|
| 830 |
+
"learning_rate": 4.504504504504505e-06,
|
| 831 |
+
"loss": 0.0002,
|
| 832 |
+
"step": 1060
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 9.63963963963964,
|
| 836 |
+
"grad_norm": 0.022533565759658813,
|
| 837 |
+
"learning_rate": 3.603603603603604e-06,
|
| 838 |
+
"loss": 0.0001,
|
| 839 |
+
"step": 1070
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 9.72972972972973,
|
| 843 |
+
"grad_norm": 0.08269208669662476,
|
| 844 |
+
"learning_rate": 2.702702702702703e-06,
|
| 845 |
+
"loss": 0.0002,
|
| 846 |
+
"step": 1080
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 9.81981981981982,
|
| 850 |
+
"grad_norm": 0.05740358307957649,
|
| 851 |
+
"learning_rate": 1.801801801801802e-06,
|
| 852 |
+
"loss": 0.0002,
|
| 853 |
+
"step": 1090
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 9.90990990990991,
|
| 857 |
+
"grad_norm": 0.2768089771270752,
|
| 858 |
+
"learning_rate": 9.00900900900901e-07,
|
| 859 |
+
"loss": 0.001,
|
| 860 |
+
"step": 1100
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 10.0,
|
| 864 |
+
"grad_norm": 0.1483727991580963,
|
| 865 |
+
"learning_rate": 0.0,
|
| 866 |
+
"loss": 0.0001,
|
| 867 |
+
"step": 1110
|
| 868 |
+
}
|
| 869 |
+
],
|
| 870 |
+
"logging_steps": 10,
|
| 871 |
+
"max_steps": 1110,
|
| 872 |
+
"num_input_tokens_seen": 0,
|
| 873 |
+
"num_train_epochs": 10,
|
| 874 |
+
"save_steps": 10,
|
| 875 |
+
"stateful_callbacks": {
|
| 876 |
+
"TrainerControl": {
|
| 877 |
+
"args": {
|
| 878 |
+
"should_epoch_stop": false,
|
| 879 |
+
"should_evaluate": false,
|
| 880 |
+
"should_log": false,
|
| 881 |
+
"should_save": true,
|
| 882 |
+
"should_training_stop": true
|
| 883 |
+
},
|
| 884 |
+
"attributes": {}
|
| 885 |
+
}
|
| 886 |
+
},
|
| 887 |
+
"total_flos": 0.0,
|
| 888 |
+
"train_batch_size": 8,
|
| 889 |
+
"trial_name": null,
|
| 890 |
+
"trial_params": null
|
| 891 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64a884ffc91dd8fd2488e6d5443c733ab51847a6117598c54531f734425ce0d0
|
| 3 |
+
size 5240
|