Upload folder using huggingface_hub
Browse files- README.md +47 -0
- checkpoint-2047/config.json +43 -0
- checkpoint-2047/model.safetensors +3 -0
- checkpoint-2047/optimizer.pt +3 -0
- checkpoint-2047/preprocessor_config.json +23 -0
- checkpoint-2047/rng_state.pth +3 -0
- checkpoint-2047/scheduler.pt +3 -0
- checkpoint-2047/trainer_state.json +1471 -0
- checkpoint-2047/training_args.bin +3 -0
- config.json +43 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- image-classification
|
| 4 |
+
- pytorch
|
| 5 |
+
- huggingface
|
| 6 |
+
- vit
|
| 7 |
+
- emotion-recognition
|
| 8 |
+
datasets:
|
| 9 |
+
- raf-db
|
| 10 |
+
base_model: trpakov/vit-face-expression
|
| 11 |
+
library_name: transformers
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# ViT Face Expression (Fine-tuned on RAF-DB)
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [trpakov/vit-face-expression](https://huggingface.co/trpakov/vit-face-expression) on the [RAF-DB (Real-world Affective Faces Database)](http://www.whdeng.cn/raf/model1.html).
|
| 17 |
+
|
| 18 |
+
## Model Description
|
| 19 |
+
- **Architecture**: Vision Transformer (ViT)
|
| 20 |
+
- **Task**: Facial Emotion Recognition
|
| 21 |
+
- **Emotions**: Anger, Disgust, Fear, Happiness, Neutral, Sadness, Surprise
|
| 22 |
+
|
| 23 |
+
## Dataset
|
| 24 |
+
RAF-DB is a large-scale facial expression database with around 30,000 facial images downloaded from the Internet. The images cover 7 basic emotions and 12 compound emotions. This model was fine-tuned on the 7 basic emotions subset.
|
| 25 |
+
|
| 26 |
+
## Usage
|
| 27 |
+
|
| 28 |
+
```python
|
| 29 |
+
from transformers import ViTImageProcessor, ViTForImageClassification
|
| 30 |
+
from PIL import Image
|
| 31 |
+
import requests
|
| 32 |
+
|
| 33 |
+
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
|
| 34 |
+
image = Image.open(requests.get(url, stream=True).raw)
|
| 35 |
+
|
| 36 |
+
repo_name = "michaelgathara/vit-face-raf-db"
|
| 37 |
+
|
| 38 |
+
processor = ViTImageProcessor.from_pretrained(repo_name)
|
| 39 |
+
model = ViTForImageClassification.from_pretrained(repo_name)
|
| 40 |
+
|
| 41 |
+
inputs = processor(images=image, return_tensors="pt")
|
| 42 |
+
outputs = model(**inputs)
|
| 43 |
+
logits = outputs.logits
|
| 44 |
+
# model predicts one of the 7 emotions
|
| 45 |
+
predicted_class_idx = logits.argmax(-1).item()
|
| 46 |
+
print("Predicted class:", model.config.id2label[predicted_class_idx])
|
| 47 |
+
```
|
checkpoint-2047/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "anger",
|
| 13 |
+
"1": "disgust",
|
| 14 |
+
"2": "fear",
|
| 15 |
+
"3": "happiness",
|
| 16 |
+
"4": "neutral",
|
| 17 |
+
"5": "sadness",
|
| 18 |
+
"6": "surprise"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"anger": "0",
|
| 25 |
+
"disgust": "1",
|
| 26 |
+
"fear": "2",
|
| 27 |
+
"happiness": "3",
|
| 28 |
+
"neutral": "4",
|
| 29 |
+
"sadness": "5",
|
| 30 |
+
"surprise": "6"
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"pooler_act": "tanh",
|
| 39 |
+
"pooler_output_size": 768,
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"qkv_bias": true,
|
| 42 |
+
"transformers_version": "4.57.6"
|
| 43 |
+
}
|
checkpoint-2047/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0280a8546c3a92190fa43a0b6fb9a34ef22e936b44700f3041bc080f5a2ab0b
|
| 3 |
+
size 343239356
|
checkpoint-2047/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a4c3498856c42d1437bb1ebf4702e8e3d3a812d1b0de1774962dca41a6ef607
|
| 3 |
+
size 686594443
|
checkpoint-2047/preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-2047/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba5ab596857b081dbf5384ce205bf3ca94cda6b4037d3ec9ef7e2781cc9ae4ef
|
| 3 |
+
size 14455
|
checkpoint-2047/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7d750f394a4b6c7f0baf15ac5be235921ab13fb84967e386d29277ec180de81
|
| 3 |
+
size 1465
|
checkpoint-2047/trainer_state.json
ADDED
|
@@ -0,0 +1,1471 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2047,
|
| 3 |
+
"best_metric": 0.8527472527472527,
|
| 4 |
+
"best_model_checkpoint": "models/raf_db_finetuned\\checkpoint-2047",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2047,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004885197850512946,
|
| 14 |
+
"grad_norm": 17.944799423217773,
|
| 15 |
+
"learning_rate": 1.991206643869077e-05,
|
| 16 |
+
"loss": 2.0291,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.009770395701025891,
|
| 21 |
+
"grad_norm": 9.91746711730957,
|
| 22 |
+
"learning_rate": 1.981436248168051e-05,
|
| 23 |
+
"loss": 1.2123,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.014655593551538837,
|
| 28 |
+
"grad_norm": 15.047444343566895,
|
| 29 |
+
"learning_rate": 1.971665852467025e-05,
|
| 30 |
+
"loss": 1.0855,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.019540791402051783,
|
| 35 |
+
"grad_norm": 23.127321243286133,
|
| 36 |
+
"learning_rate": 1.961895456765999e-05,
|
| 37 |
+
"loss": 1.1072,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.024425989252564728,
|
| 42 |
+
"grad_norm": 11.329324722290039,
|
| 43 |
+
"learning_rate": 1.9521250610649734e-05,
|
| 44 |
+
"loss": 0.9336,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.029311187103077674,
|
| 49 |
+
"grad_norm": 5.342128753662109,
|
| 50 |
+
"learning_rate": 1.9423546653639473e-05,
|
| 51 |
+
"loss": 0.7335,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.03419638495359062,
|
| 56 |
+
"grad_norm": 12.106943130493164,
|
| 57 |
+
"learning_rate": 1.9325842696629215e-05,
|
| 58 |
+
"loss": 0.5957,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.039081582804103565,
|
| 63 |
+
"grad_norm": 2.4607601165771484,
|
| 64 |
+
"learning_rate": 1.9228138739618955e-05,
|
| 65 |
+
"loss": 0.5493,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.04396678065461651,
|
| 70 |
+
"grad_norm": 8.041631698608398,
|
| 71 |
+
"learning_rate": 1.9130434782608697e-05,
|
| 72 |
+
"loss": 0.9075,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.048851978505129456,
|
| 77 |
+
"grad_norm": 10.222543716430664,
|
| 78 |
+
"learning_rate": 1.9032730825598437e-05,
|
| 79 |
+
"loss": 0.6926,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0537371763556424,
|
| 84 |
+
"grad_norm": 10.51362133026123,
|
| 85 |
+
"learning_rate": 1.893502686858818e-05,
|
| 86 |
+
"loss": 0.8827,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.05862237420615535,
|
| 91 |
+
"grad_norm": 6.351449489593506,
|
| 92 |
+
"learning_rate": 1.883732291157792e-05,
|
| 93 |
+
"loss": 0.6727,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0635075720566683,
|
| 98 |
+
"grad_norm": 13.230606079101562,
|
| 99 |
+
"learning_rate": 1.873961895456766e-05,
|
| 100 |
+
"loss": 0.7156,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.06839276990718124,
|
| 105 |
+
"grad_norm": 10.970815658569336,
|
| 106 |
+
"learning_rate": 1.86419149975574e-05,
|
| 107 |
+
"loss": 0.4933,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.07327796775769418,
|
| 112 |
+
"grad_norm": 0.8731197118759155,
|
| 113 |
+
"learning_rate": 1.8544211040547143e-05,
|
| 114 |
+
"loss": 0.5562,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.07816316560820713,
|
| 119 |
+
"grad_norm": 9.979445457458496,
|
| 120 |
+
"learning_rate": 1.8446507083536886e-05,
|
| 121 |
+
"loss": 0.5514,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.08304836345872008,
|
| 126 |
+
"grad_norm": 10.89950180053711,
|
| 127 |
+
"learning_rate": 1.8348803126526625e-05,
|
| 128 |
+
"loss": 0.6483,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.08793356130923302,
|
| 133 |
+
"grad_norm": 1.3648935556411743,
|
| 134 |
+
"learning_rate": 1.8251099169516368e-05,
|
| 135 |
+
"loss": 0.609,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.09281875915974597,
|
| 140 |
+
"grad_norm": 2.5604639053344727,
|
| 141 |
+
"learning_rate": 1.8153395212506107e-05,
|
| 142 |
+
"loss": 0.8282,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.09770395701025891,
|
| 147 |
+
"grad_norm": 6.0546956062316895,
|
| 148 |
+
"learning_rate": 1.805569125549585e-05,
|
| 149 |
+
"loss": 0.4972,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.10258915486077186,
|
| 154 |
+
"grad_norm": 9.024284362792969,
|
| 155 |
+
"learning_rate": 1.7957987298485592e-05,
|
| 156 |
+
"loss": 0.7344,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.1074743527112848,
|
| 161 |
+
"grad_norm": 15.3169527053833,
|
| 162 |
+
"learning_rate": 1.786028334147533e-05,
|
| 163 |
+
"loss": 0.4587,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.11235955056179775,
|
| 168 |
+
"grad_norm": 6.840464115142822,
|
| 169 |
+
"learning_rate": 1.7762579384465074e-05,
|
| 170 |
+
"loss": 0.3876,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.1172447484123107,
|
| 175 |
+
"grad_norm": 4.563595294952393,
|
| 176 |
+
"learning_rate": 1.7664875427454813e-05,
|
| 177 |
+
"loss": 0.5993,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.12212994626282364,
|
| 182 |
+
"grad_norm": 5.909449100494385,
|
| 183 |
+
"learning_rate": 1.7567171470444556e-05,
|
| 184 |
+
"loss": 0.6124,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.1270151441133366,
|
| 189 |
+
"grad_norm": 10.69510269165039,
|
| 190 |
+
"learning_rate": 1.7469467513434295e-05,
|
| 191 |
+
"loss": 0.5355,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.13190034196384953,
|
| 196 |
+
"grad_norm": 9.001906394958496,
|
| 197 |
+
"learning_rate": 1.7371763556424038e-05,
|
| 198 |
+
"loss": 0.607,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.13678553981436248,
|
| 203 |
+
"grad_norm": 14.748282432556152,
|
| 204 |
+
"learning_rate": 1.7274059599413777e-05,
|
| 205 |
+
"loss": 0.4316,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.14167073766487542,
|
| 210 |
+
"grad_norm": 5.700569152832031,
|
| 211 |
+
"learning_rate": 1.717635564240352e-05,
|
| 212 |
+
"loss": 0.4765,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.14655593551538837,
|
| 217 |
+
"grad_norm": 4.104219913482666,
|
| 218 |
+
"learning_rate": 1.707865168539326e-05,
|
| 219 |
+
"loss": 0.5415,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.15144113336590131,
|
| 224 |
+
"grad_norm": 7.291189670562744,
|
| 225 |
+
"learning_rate": 1.6980947728383002e-05,
|
| 226 |
+
"loss": 0.6046,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.15632633121641426,
|
| 231 |
+
"grad_norm": 6.037685394287109,
|
| 232 |
+
"learning_rate": 1.688324377137274e-05,
|
| 233 |
+
"loss": 0.5612,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.1612115290669272,
|
| 238 |
+
"grad_norm": 13.00805377960205,
|
| 239 |
+
"learning_rate": 1.6785539814362484e-05,
|
| 240 |
+
"loss": 0.5643,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.16609672691744015,
|
| 245 |
+
"grad_norm": 12.02161979675293,
|
| 246 |
+
"learning_rate": 1.6687835857352223e-05,
|
| 247 |
+
"loss": 0.53,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1709819247679531,
|
| 252 |
+
"grad_norm": 9.597453117370605,
|
| 253 |
+
"learning_rate": 1.6590131900341966e-05,
|
| 254 |
+
"loss": 0.5697,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.17586712261846604,
|
| 259 |
+
"grad_norm": 1.7890377044677734,
|
| 260 |
+
"learning_rate": 1.6492427943331705e-05,
|
| 261 |
+
"loss": 0.4628,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.180752320468979,
|
| 266 |
+
"grad_norm": 6.448623180389404,
|
| 267 |
+
"learning_rate": 1.6394723986321448e-05,
|
| 268 |
+
"loss": 0.5923,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.18563751831949193,
|
| 273 |
+
"grad_norm": 10.735410690307617,
|
| 274 |
+
"learning_rate": 1.6297020029311187e-05,
|
| 275 |
+
"loss": 0.4705,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.19052271617000488,
|
| 280 |
+
"grad_norm": 6.801768779754639,
|
| 281 |
+
"learning_rate": 1.619931607230093e-05,
|
| 282 |
+
"loss": 0.466,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.19540791402051783,
|
| 287 |
+
"grad_norm": 6.989867687225342,
|
| 288 |
+
"learning_rate": 1.610161211529067e-05,
|
| 289 |
+
"loss": 0.4903,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.20029311187103077,
|
| 294 |
+
"grad_norm": 2.0656211376190186,
|
| 295 |
+
"learning_rate": 1.600390815828041e-05,
|
| 296 |
+
"loss": 0.3788,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.20517830972154372,
|
| 301 |
+
"grad_norm": 4.312288761138916,
|
| 302 |
+
"learning_rate": 1.590620420127015e-05,
|
| 303 |
+
"loss": 0.4398,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.21006350757205666,
|
| 308 |
+
"grad_norm": 11.896406173706055,
|
| 309 |
+
"learning_rate": 1.5808500244259893e-05,
|
| 310 |
+
"loss": 0.503,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.2149487054225696,
|
| 315 |
+
"grad_norm": 8.159215927124023,
|
| 316 |
+
"learning_rate": 1.5710796287249636e-05,
|
| 317 |
+
"loss": 0.3731,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.21983390327308255,
|
| 322 |
+
"grad_norm": 9.295239448547363,
|
| 323 |
+
"learning_rate": 1.5613092330239375e-05,
|
| 324 |
+
"loss": 0.8158,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2247191011235955,
|
| 329 |
+
"grad_norm": 10.293549537658691,
|
| 330 |
+
"learning_rate": 1.5515388373229118e-05,
|
| 331 |
+
"loss": 0.4771,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.22960429897410845,
|
| 336 |
+
"grad_norm": 4.682013988494873,
|
| 337 |
+
"learning_rate": 1.5417684416218857e-05,
|
| 338 |
+
"loss": 0.5787,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.2344894968246214,
|
| 343 |
+
"grad_norm": 7.708519458770752,
|
| 344 |
+
"learning_rate": 1.53199804592086e-05,
|
| 345 |
+
"loss": 0.3852,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.23937469467513434,
|
| 350 |
+
"grad_norm": 8.97301959991455,
|
| 351 |
+
"learning_rate": 1.522227650219834e-05,
|
| 352 |
+
"loss": 0.4236,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.24425989252564728,
|
| 357 |
+
"grad_norm": 4.338143825531006,
|
| 358 |
+
"learning_rate": 1.512457254518808e-05,
|
| 359 |
+
"loss": 0.5029,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.24914509037616023,
|
| 364 |
+
"grad_norm": 6.023448467254639,
|
| 365 |
+
"learning_rate": 1.5026868588177823e-05,
|
| 366 |
+
"loss": 0.3324,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2540302882266732,
|
| 371 |
+
"grad_norm": 18.636865615844727,
|
| 372 |
+
"learning_rate": 1.4929164631167564e-05,
|
| 373 |
+
"loss": 0.5345,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.2589154860771861,
|
| 378 |
+
"grad_norm": 14.49988079071045,
|
| 379 |
+
"learning_rate": 1.4831460674157305e-05,
|
| 380 |
+
"loss": 0.3685,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.26380068392769906,
|
| 385 |
+
"grad_norm": 10.043220520019531,
|
| 386 |
+
"learning_rate": 1.4733756717147046e-05,
|
| 387 |
+
"loss": 0.4565,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.268685881778212,
|
| 392 |
+
"grad_norm": 7.664310932159424,
|
| 393 |
+
"learning_rate": 1.4636052760136787e-05,
|
| 394 |
+
"loss": 0.6481,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.27357107962872496,
|
| 399 |
+
"grad_norm": 10.388060569763184,
|
| 400 |
+
"learning_rate": 1.4538348803126528e-05,
|
| 401 |
+
"loss": 0.6793,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2784562774792379,
|
| 406 |
+
"grad_norm": 16.167070388793945,
|
| 407 |
+
"learning_rate": 1.444064484611627e-05,
|
| 408 |
+
"loss": 0.4101,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.28334147532975085,
|
| 413 |
+
"grad_norm": 11.468669891357422,
|
| 414 |
+
"learning_rate": 1.434294088910601e-05,
|
| 415 |
+
"loss": 0.5556,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.2882266731802638,
|
| 420 |
+
"grad_norm": 10.949549674987793,
|
| 421 |
+
"learning_rate": 1.4245236932095752e-05,
|
| 422 |
+
"loss": 0.4404,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.29311187103077674,
|
| 427 |
+
"grad_norm": 5.8457489013671875,
|
| 428 |
+
"learning_rate": 1.4147532975085491e-05,
|
| 429 |
+
"loss": 0.5041,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.2979970688812897,
|
| 434 |
+
"grad_norm": 7.100272178649902,
|
| 435 |
+
"learning_rate": 1.4049829018075234e-05,
|
| 436 |
+
"loss": 0.4452,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.30288226673180263,
|
| 441 |
+
"grad_norm": 8.908060073852539,
|
| 442 |
+
"learning_rate": 1.3952125061064973e-05,
|
| 443 |
+
"loss": 0.4337,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3077674645823156,
|
| 448 |
+
"grad_norm": 15.235097885131836,
|
| 449 |
+
"learning_rate": 1.3854421104054716e-05,
|
| 450 |
+
"loss": 0.5576,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3126526624328285,
|
| 455 |
+
"grad_norm": 0.3120326101779938,
|
| 456 |
+
"learning_rate": 1.3756717147044455e-05,
|
| 457 |
+
"loss": 0.2936,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.31753786028334147,
|
| 462 |
+
"grad_norm": 9.999382019042969,
|
| 463 |
+
"learning_rate": 1.3659013190034198e-05,
|
| 464 |
+
"loss": 0.4919,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.3224230581338544,
|
| 469 |
+
"grad_norm": 5.313811302185059,
|
| 470 |
+
"learning_rate": 1.3561309233023939e-05,
|
| 471 |
+
"loss": 0.6082,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.32730825598436736,
|
| 476 |
+
"grad_norm": 7.280602931976318,
|
| 477 |
+
"learning_rate": 1.346360527601368e-05,
|
| 478 |
+
"loss": 0.4541,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.3321934538348803,
|
| 483 |
+
"grad_norm": 11.211206436157227,
|
| 484 |
+
"learning_rate": 1.336590131900342e-05,
|
| 485 |
+
"loss": 0.3229,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.33707865168539325,
|
| 490 |
+
"grad_norm": 1.7503819465637207,
|
| 491 |
+
"learning_rate": 1.3268197361993162e-05,
|
| 492 |
+
"loss": 0.3966,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.3419638495359062,
|
| 497 |
+
"grad_norm": 3.4260499477386475,
|
| 498 |
+
"learning_rate": 1.3170493404982903e-05,
|
| 499 |
+
"loss": 0.291,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.34684904738641914,
|
| 504 |
+
"grad_norm": 3.466951370239258,
|
| 505 |
+
"learning_rate": 1.3072789447972645e-05,
|
| 506 |
+
"loss": 0.2094,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.3517342452369321,
|
| 511 |
+
"grad_norm": 10.148577690124512,
|
| 512 |
+
"learning_rate": 1.2975085490962385e-05,
|
| 513 |
+
"loss": 0.4038,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.35661944308744503,
|
| 518 |
+
"grad_norm": 9.461824417114258,
|
| 519 |
+
"learning_rate": 1.2877381533952127e-05,
|
| 520 |
+
"loss": 0.5108,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.361504640937958,
|
| 525 |
+
"grad_norm": 9.039957046508789,
|
| 526 |
+
"learning_rate": 1.2779677576941867e-05,
|
| 527 |
+
"loss": 0.4701,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.3663898387884709,
|
| 532 |
+
"grad_norm": 7.5800065994262695,
|
| 533 |
+
"learning_rate": 1.268197361993161e-05,
|
| 534 |
+
"loss": 0.4359,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.37127503663898387,
|
| 539 |
+
"grad_norm": 4.4555344581604,
|
| 540 |
+
"learning_rate": 1.2584269662921348e-05,
|
| 541 |
+
"loss": 0.2933,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.3761602344894968,
|
| 546 |
+
"grad_norm": 10.27487850189209,
|
| 547 |
+
"learning_rate": 1.2486565705911091e-05,
|
| 548 |
+
"loss": 0.248,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.38104543234000976,
|
| 553 |
+
"grad_norm": 13.357872009277344,
|
| 554 |
+
"learning_rate": 1.238886174890083e-05,
|
| 555 |
+
"loss": 0.3262,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.3859306301905227,
|
| 560 |
+
"grad_norm": 0.9710779190063477,
|
| 561 |
+
"learning_rate": 1.2291157791890573e-05,
|
| 562 |
+
"loss": 0.4878,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.39081582804103565,
|
| 567 |
+
"grad_norm": 8.897228240966797,
|
| 568 |
+
"learning_rate": 1.2193453834880314e-05,
|
| 569 |
+
"loss": 0.3705,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.3957010258915486,
|
| 574 |
+
"grad_norm": 9.922685623168945,
|
| 575 |
+
"learning_rate": 1.2095749877870055e-05,
|
| 576 |
+
"loss": 0.6951,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.40058622374206154,
|
| 581 |
+
"grad_norm": 12.713271141052246,
|
| 582 |
+
"learning_rate": 1.1998045920859796e-05,
|
| 583 |
+
"loss": 0.4512,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.4054714215925745,
|
| 588 |
+
"grad_norm": 7.013885021209717,
|
| 589 |
+
"learning_rate": 1.1900341963849537e-05,
|
| 590 |
+
"loss": 0.4413,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.41035661944308743,
|
| 595 |
+
"grad_norm": 17.14900016784668,
|
| 596 |
+
"learning_rate": 1.1802638006839278e-05,
|
| 597 |
+
"loss": 0.4688,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.4152418172936004,
|
| 602 |
+
"grad_norm": 0.08244088292121887,
|
| 603 |
+
"learning_rate": 1.170493404982902e-05,
|
| 604 |
+
"loss": 0.3977,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.4201270151441133,
|
| 609 |
+
"grad_norm": 6.348947048187256,
|
| 610 |
+
"learning_rate": 1.160723009281876e-05,
|
| 611 |
+
"loss": 0.5694,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.42501221299462627,
|
| 616 |
+
"grad_norm": 0.7870075702667236,
|
| 617 |
+
"learning_rate": 1.1509526135808502e-05,
|
| 618 |
+
"loss": 0.4388,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.4298974108451392,
|
| 623 |
+
"grad_norm": 9.187114715576172,
|
| 624 |
+
"learning_rate": 1.1411822178798242e-05,
|
| 625 |
+
"loss": 0.3909,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.43478260869565216,
|
| 630 |
+
"grad_norm": 1.1734113693237305,
|
| 631 |
+
"learning_rate": 1.1314118221787984e-05,
|
| 632 |
+
"loss": 0.4053,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.4396678065461651,
|
| 637 |
+
"grad_norm": 0.7321255803108215,
|
| 638 |
+
"learning_rate": 1.1216414264777724e-05,
|
| 639 |
+
"loss": 0.4325,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.44455300439667805,
|
| 644 |
+
"grad_norm": 13.496896743774414,
|
| 645 |
+
"learning_rate": 1.1118710307767466e-05,
|
| 646 |
+
"loss": 0.4472,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.449438202247191,
|
| 651 |
+
"grad_norm": 7.10970401763916,
|
| 652 |
+
"learning_rate": 1.1021006350757206e-05,
|
| 653 |
+
"loss": 0.5013,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.45432340009770394,
|
| 658 |
+
"grad_norm": 17.575641632080078,
|
| 659 |
+
"learning_rate": 1.0923302393746948e-05,
|
| 660 |
+
"loss": 0.4886,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.4592085979482169,
|
| 665 |
+
"grad_norm": 10.095125198364258,
|
| 666 |
+
"learning_rate": 1.0825598436736689e-05,
|
| 667 |
+
"loss": 0.4136,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.46409379579872984,
|
| 672 |
+
"grad_norm": 6.8130292892456055,
|
| 673 |
+
"learning_rate": 1.072789447972643e-05,
|
| 674 |
+
"loss": 0.6457,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.4689789936492428,
|
| 679 |
+
"grad_norm": 8.038426399230957,
|
| 680 |
+
"learning_rate": 1.0630190522716171e-05,
|
| 681 |
+
"loss": 0.3581,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.4738641914997557,
|
| 686 |
+
"grad_norm": 3.269139528274536,
|
| 687 |
+
"learning_rate": 1.0532486565705912e-05,
|
| 688 |
+
"loss": 0.4969,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.4787493893502687,
|
| 693 |
+
"grad_norm": 5.605432033538818,
|
| 694 |
+
"learning_rate": 1.0434782608695653e-05,
|
| 695 |
+
"loss": 0.3964,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.4836345872007816,
|
| 700 |
+
"grad_norm": 6.879159927368164,
|
| 701 |
+
"learning_rate": 1.0337078651685396e-05,
|
| 702 |
+
"loss": 0.3005,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.48851978505129456,
|
| 707 |
+
"grad_norm": 0.27517643570899963,
|
| 708 |
+
"learning_rate": 1.0239374694675135e-05,
|
| 709 |
+
"loss": 0.4044,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.4934049829018075,
|
| 714 |
+
"grad_norm": 18.99689483642578,
|
| 715 |
+
"learning_rate": 1.0141670737664878e-05,
|
| 716 |
+
"loss": 0.5072,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.49829018075232046,
|
| 721 |
+
"grad_norm": 6.253431797027588,
|
| 722 |
+
"learning_rate": 1.0043966780654617e-05,
|
| 723 |
+
"loss": 0.4955,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.5031753786028335,
|
| 728 |
+
"grad_norm": 5.144866466522217,
|
| 729 |
+
"learning_rate": 9.946262823644358e-06,
|
| 730 |
+
"loss": 0.2145,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.5080605764533463,
|
| 735 |
+
"grad_norm": 4.817426681518555,
|
| 736 |
+
"learning_rate": 9.848558866634099e-06,
|
| 737 |
+
"loss": 0.4397,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.5129457743038593,
|
| 742 |
+
"grad_norm": 11.465901374816895,
|
| 743 |
+
"learning_rate": 9.75085490962384e-06,
|
| 744 |
+
"loss": 0.3449,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.5178309721543722,
|
| 749 |
+
"grad_norm": 9.008246421813965,
|
| 750 |
+
"learning_rate": 9.65315095261358e-06,
|
| 751 |
+
"loss": 0.2979,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.5227161700048852,
|
| 756 |
+
"grad_norm": 4.4735636711120605,
|
| 757 |
+
"learning_rate": 9.555446995603323e-06,
|
| 758 |
+
"loss": 0.4377,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.5276013678553981,
|
| 763 |
+
"grad_norm": 2.9690377712249756,
|
| 764 |
+
"learning_rate": 9.457743038593064e-06,
|
| 765 |
+
"loss": 0.4898,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.5324865657059111,
|
| 770 |
+
"grad_norm": 4.649147033691406,
|
| 771 |
+
"learning_rate": 9.360039081582805e-06,
|
| 772 |
+
"loss": 0.5745,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.537371763556424,
|
| 777 |
+
"grad_norm": 1.9182021617889404,
|
| 778 |
+
"learning_rate": 9.262335124572546e-06,
|
| 779 |
+
"loss": 0.4778,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.542256961406937,
|
| 784 |
+
"grad_norm": 5.130582809448242,
|
| 785 |
+
"learning_rate": 9.164631167562287e-06,
|
| 786 |
+
"loss": 0.3995,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.5471421592574499,
|
| 791 |
+
"grad_norm": 1.418589472770691,
|
| 792 |
+
"learning_rate": 9.066927210552028e-06,
|
| 793 |
+
"loss": 0.3468,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5520273571079629,
|
| 798 |
+
"grad_norm": 5.989200115203857,
|
| 799 |
+
"learning_rate": 8.969223253541769e-06,
|
| 800 |
+
"loss": 0.2423,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.5569125549584758,
|
| 805 |
+
"grad_norm": 12.977813720703125,
|
| 806 |
+
"learning_rate": 8.87151929653151e-06,
|
| 807 |
+
"loss": 0.4263,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.5617977528089888,
|
| 812 |
+
"grad_norm": 5.596517562866211,
|
| 813 |
+
"learning_rate": 8.773815339521251e-06,
|
| 814 |
+
"loss": 0.5422,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.5666829506595017,
|
| 819 |
+
"grad_norm": 9.800990104675293,
|
| 820 |
+
"learning_rate": 8.676111382510992e-06,
|
| 821 |
+
"loss": 0.4936,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.5715681485100147,
|
| 826 |
+
"grad_norm": 6.063791275024414,
|
| 827 |
+
"learning_rate": 8.578407425500733e-06,
|
| 828 |
+
"loss": 0.2772,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.5764533463605276,
|
| 833 |
+
"grad_norm": 6.097079753875732,
|
| 834 |
+
"learning_rate": 8.480703468490474e-06,
|
| 835 |
+
"loss": 0.2633,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.5813385442110406,
|
| 840 |
+
"grad_norm": 7.569230556488037,
|
| 841 |
+
"learning_rate": 8.382999511480215e-06,
|
| 842 |
+
"loss": 0.6212,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.5862237420615535,
|
| 847 |
+
"grad_norm": 1.887565016746521,
|
| 848 |
+
"learning_rate": 8.285295554469956e-06,
|
| 849 |
+
"loss": 0.4124,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.5911089399120665,
|
| 854 |
+
"grad_norm": 2.559924840927124,
|
| 855 |
+
"learning_rate": 8.187591597459697e-06,
|
| 856 |
+
"loss": 0.4965,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.5959941377625794,
|
| 861 |
+
"grad_norm": 1.9086635112762451,
|
| 862 |
+
"learning_rate": 8.08988764044944e-06,
|
| 863 |
+
"loss": 0.3139,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.6008793356130924,
|
| 868 |
+
"grad_norm": 2.0462982654571533,
|
| 869 |
+
"learning_rate": 7.99218368343918e-06,
|
| 870 |
+
"loss": 0.3031,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.6057645334636053,
|
| 875 |
+
"grad_norm": 3.3513333797454834,
|
| 876 |
+
"learning_rate": 7.894479726428921e-06,
|
| 877 |
+
"loss": 0.3425,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.6106497313141183,
|
| 882 |
+
"grad_norm": 9.786959648132324,
|
| 883 |
+
"learning_rate": 7.796775769418662e-06,
|
| 884 |
+
"loss": 0.5955,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.6155349291646312,
|
| 889 |
+
"grad_norm": 6.594499588012695,
|
| 890 |
+
"learning_rate": 7.699071812408403e-06,
|
| 891 |
+
"loss": 0.3468,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.6204201270151442,
|
| 896 |
+
"grad_norm": 14.10224437713623,
|
| 897 |
+
"learning_rate": 7.601367855398144e-06,
|
| 898 |
+
"loss": 0.5912,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.625305324865657,
|
| 903 |
+
"grad_norm": 9.290619850158691,
|
| 904 |
+
"learning_rate": 7.503663898387885e-06,
|
| 905 |
+
"loss": 0.6282,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.63019052271617,
|
| 910 |
+
"grad_norm": 11.20014762878418,
|
| 911 |
+
"learning_rate": 7.405959941377626e-06,
|
| 912 |
+
"loss": 0.2973,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.6350757205666829,
|
| 917 |
+
"grad_norm": 7.336958408355713,
|
| 918 |
+
"learning_rate": 7.308255984367367e-06,
|
| 919 |
+
"loss": 0.4738,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.6399609184171959,
|
| 924 |
+
"grad_norm": 0.04702078178524971,
|
| 925 |
+
"learning_rate": 7.210552027357108e-06,
|
| 926 |
+
"loss": 0.5161,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.6448461162677088,
|
| 931 |
+
"grad_norm": 7.214766502380371,
|
| 932 |
+
"learning_rate": 7.11284807034685e-06,
|
| 933 |
+
"loss": 0.4346,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.6497313141182218,
|
| 938 |
+
"grad_norm": 9.381763458251953,
|
| 939 |
+
"learning_rate": 7.015144113336591e-06,
|
| 940 |
+
"loss": 0.3613,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.6546165119687347,
|
| 945 |
+
"grad_norm": 6.74038028717041,
|
| 946 |
+
"learning_rate": 6.917440156326332e-06,
|
| 947 |
+
"loss": 0.4634,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.6595017098192477,
|
| 952 |
+
"grad_norm": 8.606428146362305,
|
| 953 |
+
"learning_rate": 6.819736199316073e-06,
|
| 954 |
+
"loss": 0.6249,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.6643869076697606,
|
| 959 |
+
"grad_norm": 14.990072250366211,
|
| 960 |
+
"learning_rate": 6.722032242305814e-06,
|
| 961 |
+
"loss": 0.517,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.6692721055202736,
|
| 966 |
+
"grad_norm": 5.394313335418701,
|
| 967 |
+
"learning_rate": 6.624328285295555e-06,
|
| 968 |
+
"loss": 0.3539,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.6741573033707865,
|
| 973 |
+
"grad_norm": 4.493410587310791,
|
| 974 |
+
"learning_rate": 6.526624328285296e-06,
|
| 975 |
+
"loss": 0.3574,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.6790425012212995,
|
| 980 |
+
"grad_norm": 12.217620849609375,
|
| 981 |
+
"learning_rate": 6.428920371275037e-06,
|
| 982 |
+
"loss": 0.5452,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.6839276990718124,
|
| 987 |
+
"grad_norm": 0.7943627834320068,
|
| 988 |
+
"learning_rate": 6.331216414264778e-06,
|
| 989 |
+
"loss": 0.2409,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.6888128969223254,
|
| 994 |
+
"grad_norm": 10.535755157470703,
|
| 995 |
+
"learning_rate": 6.233512457254519e-06,
|
| 996 |
+
"loss": 0.5708,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.6936980947728383,
|
| 1001 |
+
"grad_norm": 7.569476127624512,
|
| 1002 |
+
"learning_rate": 6.13580850024426e-06,
|
| 1003 |
+
"loss": 0.2425,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.6985832926233513,
|
| 1008 |
+
"grad_norm": 7.93254280090332,
|
| 1009 |
+
"learning_rate": 6.038104543234001e-06,
|
| 1010 |
+
"loss": 0.3463,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.7034684904738642,
|
| 1015 |
+
"grad_norm": 2.2692394256591797,
|
| 1016 |
+
"learning_rate": 5.940400586223742e-06,
|
| 1017 |
+
"loss": 0.4627,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.7083536883243772,
|
| 1022 |
+
"grad_norm": 2.044731616973877,
|
| 1023 |
+
"learning_rate": 5.842696629213483e-06,
|
| 1024 |
+
"loss": 0.2857,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.7132388861748901,
|
| 1029 |
+
"grad_norm": 9.001659393310547,
|
| 1030 |
+
"learning_rate": 5.744992672203225e-06,
|
| 1031 |
+
"loss": 0.3712,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.7181240840254031,
|
| 1036 |
+
"grad_norm": 8.663535118103027,
|
| 1037 |
+
"learning_rate": 5.647288715192966e-06,
|
| 1038 |
+
"loss": 0.4056,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.723009281875916,
|
| 1043 |
+
"grad_norm": 2.3330843448638916,
|
| 1044 |
+
"learning_rate": 5.549584758182707e-06,
|
| 1045 |
+
"loss": 0.328,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.727894479726429,
|
| 1050 |
+
"grad_norm": 5.642626762390137,
|
| 1051 |
+
"learning_rate": 5.451880801172448e-06,
|
| 1052 |
+
"loss": 0.5109,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.7327796775769418,
|
| 1057 |
+
"grad_norm": 15.361739158630371,
|
| 1058 |
+
"learning_rate": 5.354176844162189e-06,
|
| 1059 |
+
"loss": 0.4808,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.7376648754274548,
|
| 1064 |
+
"grad_norm": 10.109480857849121,
|
| 1065 |
+
"learning_rate": 5.25647288715193e-06,
|
| 1066 |
+
"loss": 0.5841,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.7425500732779677,
|
| 1071 |
+
"grad_norm": 3.49552845954895,
|
| 1072 |
+
"learning_rate": 5.158768930141671e-06,
|
| 1073 |
+
"loss": 0.4657,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7474352711284807,
|
| 1078 |
+
"grad_norm": 2.950178861618042,
|
| 1079 |
+
"learning_rate": 5.061064973131412e-06,
|
| 1080 |
+
"loss": 0.3558,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.7523204689789936,
|
| 1085 |
+
"grad_norm": 2.48479962348938,
|
| 1086 |
+
"learning_rate": 4.9633610161211535e-06,
|
| 1087 |
+
"loss": 0.5736,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.7572056668295066,
|
| 1092 |
+
"grad_norm": 2.948216676712036,
|
| 1093 |
+
"learning_rate": 4.8656570591108944e-06,
|
| 1094 |
+
"loss": 0.5026,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.7620908646800195,
|
| 1099 |
+
"grad_norm": 10.953573226928711,
|
| 1100 |
+
"learning_rate": 4.767953102100635e-06,
|
| 1101 |
+
"loss": 0.3647,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.7669760625305325,
|
| 1106 |
+
"grad_norm": 0.7188931703567505,
|
| 1107 |
+
"learning_rate": 4.670249145090376e-06,
|
| 1108 |
+
"loss": 0.4338,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.7718612603810454,
|
| 1113 |
+
"grad_norm": 5.085393905639648,
|
| 1114 |
+
"learning_rate": 4.572545188080117e-06,
|
| 1115 |
+
"loss": 0.3118,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.7767464582315584,
|
| 1120 |
+
"grad_norm": 0.31807640194892883,
|
| 1121 |
+
"learning_rate": 4.474841231069858e-06,
|
| 1122 |
+
"loss": 0.4693,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.7816316560820713,
|
| 1127 |
+
"grad_norm": 4.8351287841796875,
|
| 1128 |
+
"learning_rate": 4.377137274059599e-06,
|
| 1129 |
+
"loss": 0.5351,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7865168539325843,
|
| 1134 |
+
"grad_norm": 4.054388999938965,
|
| 1135 |
+
"learning_rate": 4.279433317049341e-06,
|
| 1136 |
+
"loss": 0.4113,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.7914020517830972,
|
| 1141 |
+
"grad_norm": 9.017539024353027,
|
| 1142 |
+
"learning_rate": 4.181729360039082e-06,
|
| 1143 |
+
"loss": 0.3507,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.7962872496336102,
|
| 1148 |
+
"grad_norm": 0.9139829874038696,
|
| 1149 |
+
"learning_rate": 4.084025403028823e-06,
|
| 1150 |
+
"loss": 0.5123,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.8011724474841231,
|
| 1155 |
+
"grad_norm": 5.668177127838135,
|
| 1156 |
+
"learning_rate": 3.986321446018564e-06,
|
| 1157 |
+
"loss": 0.4119,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.8060576453346361,
|
| 1162 |
+
"grad_norm": 3.6785178184509277,
|
| 1163 |
+
"learning_rate": 3.888617489008305e-06,
|
| 1164 |
+
"loss": 0.3159,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.810942843185149,
|
| 1169 |
+
"grad_norm": 1.998555302619934,
|
| 1170 |
+
"learning_rate": 3.7909135319980463e-06,
|
| 1171 |
+
"loss": 0.3291,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.815828041035662,
|
| 1176 |
+
"grad_norm": 1.5727540254592896,
|
| 1177 |
+
"learning_rate": 3.6932095749877872e-06,
|
| 1178 |
+
"loss": 0.3416,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.8207132388861749,
|
| 1183 |
+
"grad_norm": 11.895509719848633,
|
| 1184 |
+
"learning_rate": 3.595505617977528e-06,
|
| 1185 |
+
"loss": 0.3537,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8255984367366879,
|
| 1190 |
+
"grad_norm": 5.824265480041504,
|
| 1191 |
+
"learning_rate": 3.4978016609672696e-06,
|
| 1192 |
+
"loss": 0.2603,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.8304836345872008,
|
| 1197 |
+
"grad_norm": 12.911538124084473,
|
| 1198 |
+
"learning_rate": 3.4000977039570105e-06,
|
| 1199 |
+
"loss": 0.5172,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.8353688324377138,
|
| 1204 |
+
"grad_norm": 6.1299614906311035,
|
| 1205 |
+
"learning_rate": 3.3023937469467515e-06,
|
| 1206 |
+
"loss": 0.3283,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.8402540302882266,
|
| 1211 |
+
"grad_norm": 8.103076934814453,
|
| 1212 |
+
"learning_rate": 3.2046897899364925e-06,
|
| 1213 |
+
"loss": 0.2746,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.8451392281387397,
|
| 1218 |
+
"grad_norm": 10.692161560058594,
|
| 1219 |
+
"learning_rate": 3.106985832926234e-06,
|
| 1220 |
+
"loss": 0.6933,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.8500244259892525,
|
| 1225 |
+
"grad_norm": 5.779560089111328,
|
| 1226 |
+
"learning_rate": 3.009281875915975e-06,
|
| 1227 |
+
"loss": 0.3408,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.8549096238397655,
|
| 1232 |
+
"grad_norm": 6.992332935333252,
|
| 1233 |
+
"learning_rate": 2.9115779189057158e-06,
|
| 1234 |
+
"loss": 0.4603,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.8597948216902784,
|
| 1239 |
+
"grad_norm": 7.0532121658325195,
|
| 1240 |
+
"learning_rate": 2.8138739618954567e-06,
|
| 1241 |
+
"loss": 0.304,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.8646800195407914,
|
| 1246 |
+
"grad_norm": 14.865501403808594,
|
| 1247 |
+
"learning_rate": 2.716170004885198e-06,
|
| 1248 |
+
"loss": 0.6035,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.8695652173913043,
|
| 1253 |
+
"grad_norm": 8.351088523864746,
|
| 1254 |
+
"learning_rate": 2.618466047874939e-06,
|
| 1255 |
+
"loss": 0.4957,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.8744504152418173,
|
| 1260 |
+
"grad_norm": 8.012289047241211,
|
| 1261 |
+
"learning_rate": 2.52076209086468e-06,
|
| 1262 |
+
"loss": 0.4995,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.8793356130923302,
|
| 1267 |
+
"grad_norm": 10.582439422607422,
|
| 1268 |
+
"learning_rate": 2.4230581338544214e-06,
|
| 1269 |
+
"loss": 0.3412,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.8842208109428432,
|
| 1274 |
+
"grad_norm": 7.599929332733154,
|
| 1275 |
+
"learning_rate": 2.3253541768441624e-06,
|
| 1276 |
+
"loss": 0.2842,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.8891060087933561,
|
| 1281 |
+
"grad_norm": 9.53080940246582,
|
| 1282 |
+
"learning_rate": 2.2276502198339033e-06,
|
| 1283 |
+
"loss": 0.4446,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.8939912066438691,
|
| 1288 |
+
"grad_norm": 6.277515888214111,
|
| 1289 |
+
"learning_rate": 2.1299462628236443e-06,
|
| 1290 |
+
"loss": 0.5967,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.898876404494382,
|
| 1295 |
+
"grad_norm": 0.5566537380218506,
|
| 1296 |
+
"learning_rate": 2.0322423058133857e-06,
|
| 1297 |
+
"loss": 0.3504,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.903761602344895,
|
| 1302 |
+
"grad_norm": 8.149109840393066,
|
| 1303 |
+
"learning_rate": 1.9345383488031266e-06,
|
| 1304 |
+
"loss": 0.4962,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.9086468001954079,
|
| 1309 |
+
"grad_norm": 16.717893600463867,
|
| 1310 |
+
"learning_rate": 1.8368343917928678e-06,
|
| 1311 |
+
"loss": 0.543,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.9135319980459209,
|
| 1316 |
+
"grad_norm": 6.368210315704346,
|
| 1317 |
+
"learning_rate": 1.7391304347826088e-06,
|
| 1318 |
+
"loss": 0.3421,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.9184171958964338,
|
| 1323 |
+
"grad_norm": 7.611034393310547,
|
| 1324 |
+
"learning_rate": 1.64142647777235e-06,
|
| 1325 |
+
"loss": 0.2211,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.9233023937469468,
|
| 1330 |
+
"grad_norm": 6.015079498291016,
|
| 1331 |
+
"learning_rate": 1.5437225207620909e-06,
|
| 1332 |
+
"loss": 0.4114,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.9281875915974597,
|
| 1337 |
+
"grad_norm": 5.758971214294434,
|
| 1338 |
+
"learning_rate": 1.446018563751832e-06,
|
| 1339 |
+
"loss": 0.2586,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.9330727894479727,
|
| 1344 |
+
"grad_norm": 10.397595405578613,
|
| 1345 |
+
"learning_rate": 1.348314606741573e-06,
|
| 1346 |
+
"loss": 0.3601,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.9379579872984856,
|
| 1351 |
+
"grad_norm": 6.008655548095703,
|
| 1352 |
+
"learning_rate": 1.2506106497313142e-06,
|
| 1353 |
+
"loss": 0.3286,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.9428431851489986,
|
| 1358 |
+
"grad_norm": 10.383055686950684,
|
| 1359 |
+
"learning_rate": 1.1529066927210554e-06,
|
| 1360 |
+
"loss": 0.3969,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.9477283829995115,
|
| 1365 |
+
"grad_norm": 5.051438331604004,
|
| 1366 |
+
"learning_rate": 1.0552027357107963e-06,
|
| 1367 |
+
"loss": 0.2447,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.9526135808500245,
|
| 1372 |
+
"grad_norm": 9.03067684173584,
|
| 1373 |
+
"learning_rate": 9.574987787005375e-07,
|
| 1374 |
+
"loss": 0.2699,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.9574987787005373,
|
| 1379 |
+
"grad_norm": 5.482412338256836,
|
| 1380 |
+
"learning_rate": 8.597948216902785e-07,
|
| 1381 |
+
"loss": 0.4556,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.9623839765510503,
|
| 1386 |
+
"grad_norm": 9.010185241699219,
|
| 1387 |
+
"learning_rate": 7.620908646800196e-07,
|
| 1388 |
+
"loss": 0.3432,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9672691744015632,
|
| 1393 |
+
"grad_norm": 7.145694255828857,
|
| 1394 |
+
"learning_rate": 6.643869076697607e-07,
|
| 1395 |
+
"loss": 0.2654,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.9721543722520762,
|
| 1400 |
+
"grad_norm": 6.059538841247559,
|
| 1401 |
+
"learning_rate": 5.666829506595018e-07,
|
| 1402 |
+
"loss": 0.2687,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.9770395701025891,
|
| 1407 |
+
"grad_norm": 3.838576555252075,
|
| 1408 |
+
"learning_rate": 4.689789936492428e-07,
|
| 1409 |
+
"loss": 0.3676,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.9819247679531021,
|
| 1414 |
+
"grad_norm": 6.402182102203369,
|
| 1415 |
+
"learning_rate": 3.712750366389839e-07,
|
| 1416 |
+
"loss": 0.415,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.986809965803615,
|
| 1421 |
+
"grad_norm": 1.021118402481079,
|
| 1422 |
+
"learning_rate": 2.7357107962872495e-07,
|
| 1423 |
+
"loss": 0.307,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.991695163654128,
|
| 1428 |
+
"grad_norm": 8.60698413848877,
|
| 1429 |
+
"learning_rate": 1.7586712261846604e-07,
|
| 1430 |
+
"loss": 0.5131,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.9965803615046409,
|
| 1435 |
+
"grad_norm": 7.274533271789551,
|
| 1436 |
+
"learning_rate": 7.816316560820714e-08,
|
| 1437 |
+
"loss": 0.3784,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.0,
|
| 1442 |
+
"eval_accuracy": 0.8527472527472527,
|
| 1443 |
+
"eval_loss": 0.4573296904563904,
|
| 1444 |
+
"eval_runtime": 505.9062,
|
| 1445 |
+
"eval_samples_per_second": 8.094,
|
| 1446 |
+
"eval_steps_per_second": 1.012,
|
| 1447 |
+
"step": 2047
|
| 1448 |
+
}
|
| 1449 |
+
],
|
| 1450 |
+
"logging_steps": 10,
|
| 1451 |
+
"max_steps": 2047,
|
| 1452 |
+
"num_input_tokens_seen": 0,
|
| 1453 |
+
"num_train_epochs": 1,
|
| 1454 |
+
"save_steps": 500,
|
| 1455 |
+
"stateful_callbacks": {
|
| 1456 |
+
"TrainerControl": {
|
| 1457 |
+
"args": {
|
| 1458 |
+
"should_epoch_stop": false,
|
| 1459 |
+
"should_evaluate": false,
|
| 1460 |
+
"should_log": false,
|
| 1461 |
+
"should_save": true,
|
| 1462 |
+
"should_training_stop": true
|
| 1463 |
+
},
|
| 1464 |
+
"attributes": {}
|
| 1465 |
+
}
|
| 1466 |
+
},
|
| 1467 |
+
"total_flos": 1.2690656905519596e+18,
|
| 1468 |
+
"train_batch_size": 8,
|
| 1469 |
+
"trial_name": null,
|
| 1470 |
+
"trial_params": null
|
| 1471 |
+
}
|
checkpoint-2047/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66708c48cae981cf94bc4aeb4bfd5275154c3f88e241dffc030d8fd493a80290
|
| 3 |
+
size 5777
|
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ViTForImageClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.0,
|
| 6 |
+
"dtype": "float32",
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "anger",
|
| 13 |
+
"1": "disgust",
|
| 14 |
+
"2": "fear",
|
| 15 |
+
"3": "happiness",
|
| 16 |
+
"4": "neutral",
|
| 17 |
+
"5": "sadness",
|
| 18 |
+
"6": "surprise"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"anger": "0",
|
| 25 |
+
"disgust": "1",
|
| 26 |
+
"fear": "2",
|
| 27 |
+
"happiness": "3",
|
| 28 |
+
"neutral": "4",
|
| 29 |
+
"sadness": "5",
|
| 30 |
+
"surprise": "6"
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"pooler_act": "tanh",
|
| 39 |
+
"pooler_output_size": 768,
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"qkv_bias": true,
|
| 42 |
+
"transformers_version": "4.57.6"
|
| 43 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0280a8546c3a92190fa43a0b6fb9a34ef22e936b44700f3041bc080f5a2ab0b
|
| 3 |
+
size 343239356
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66708c48cae981cf94bc4aeb4bfd5275154c3f88e241dffc030d8fd493a80290
|
| 3 |
+
size 5777
|