Upload folder using huggingface_hub
Browse files- README.md +47 -0
- checkpoint-2783/config.json +43 -0
- checkpoint-2783/model.safetensors +3 -0
- checkpoint-2783/optimizer.pt +3 -0
- checkpoint-2783/preprocessor_config.json +23 -0
- checkpoint-2783/rng_state.pth +3 -0
- checkpoint-2783/scheduler.pt +3 -0
- checkpoint-2783/trainer_state.json +1989 -0
- checkpoint-2783/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 |
+
- affectnet
|
| 10 |
+
base_model: trpakov/vit-face-expression
|
| 11 |
+
library_name: transformers
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
# ViT Face Expression (Fine-tuned on AffectNet)
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [trpakov/vit-face-expression](https://huggingface.co/trpakov/vit-face-expression) on the [AffectNet](http://mohammadmahoor.com/affectnet/) dataset.
|
| 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 |
+
AffectNet is a large-scale database of facial expressions in the wild, containing more than 1M facial images from the Internet. This model was fine-tuned on a subset of the manually annotated images covering 7 basic emotions (excluding Contempt to align with the base model's taxonomy).
|
| 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-affectnet"
|
| 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-2783/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-2783/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30b8401bc059b3af5b58485e1e6e3846cf3c6dcb9c069ca543a25406568021e1
|
| 3 |
+
size 343239356
|
checkpoint-2783/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c3c1dad1b4d9bd71620220d4f0cb1cf0ac473d2d45d70612586376929deae2c
|
| 3 |
+
size 686594443
|
checkpoint-2783/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-2783/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e16a2ce8e768900e85f8bbe0050186fece430f07a0e91c713e8911e04e65ca8
|
| 3 |
+
size 14455
|
checkpoint-2783/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9cf1b92f88804438ca3335c6217f2afff4d15904b0b96b30daa3de547452869
|
| 3 |
+
size 1465
|
checkpoint-2783/trainer_state.json
ADDED
|
@@ -0,0 +1,1989 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 2783,
|
| 3 |
+
"best_metric": 0.7164420485175202,
|
| 4 |
+
"best_model_checkpoint": "models/affectnet_finetuned\\checkpoint-2783",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2783,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0035932446999640674,
|
| 14 |
+
"grad_norm": 5.816065311431885,
|
| 15 |
+
"learning_rate": 1.9935321595400647e-05,
|
| 16 |
+
"loss": 1.9356,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.007186489399928135,
|
| 21 |
+
"grad_norm": 16.718177795410156,
|
| 22 |
+
"learning_rate": 1.9863456701401367e-05,
|
| 23 |
+
"loss": 1.7984,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.010779734099892203,
|
| 28 |
+
"grad_norm": 14.972896575927734,
|
| 29 |
+
"learning_rate": 1.9791591807402086e-05,
|
| 30 |
+
"loss": 1.847,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.01437297879985627,
|
| 35 |
+
"grad_norm": 18.699365615844727,
|
| 36 |
+
"learning_rate": 1.9719726913402805e-05,
|
| 37 |
+
"loss": 1.9015,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.017966223499820338,
|
| 42 |
+
"grad_norm": 14.717846870422363,
|
| 43 |
+
"learning_rate": 1.9647862019403524e-05,
|
| 44 |
+
"loss": 1.2742,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.021559468199784406,
|
| 49 |
+
"grad_norm": 13.507522583007812,
|
| 50 |
+
"learning_rate": 1.9575997125404243e-05,
|
| 51 |
+
"loss": 1.0376,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.025152712899748474,
|
| 56 |
+
"grad_norm": 14.181863784790039,
|
| 57 |
+
"learning_rate": 1.950413223140496e-05,
|
| 58 |
+
"loss": 1.6585,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.02874595759971254,
|
| 63 |
+
"grad_norm": 9.426386833190918,
|
| 64 |
+
"learning_rate": 1.9432267337405678e-05,
|
| 65 |
+
"loss": 1.2604,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03233920229967661,
|
| 70 |
+
"grad_norm": 6.423051834106445,
|
| 71 |
+
"learning_rate": 1.93604024434064e-05,
|
| 72 |
+
"loss": 1.2368,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.035932446999640676,
|
| 77 |
+
"grad_norm": 11.146883964538574,
|
| 78 |
+
"learning_rate": 1.9288537549407116e-05,
|
| 79 |
+
"loss": 1.3696,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.039525691699604744,
|
| 84 |
+
"grad_norm": 10.348139762878418,
|
| 85 |
+
"learning_rate": 1.9216672655407835e-05,
|
| 86 |
+
"loss": 1.2237,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04311893639956881,
|
| 91 |
+
"grad_norm": 9.791911125183105,
|
| 92 |
+
"learning_rate": 1.9144807761408554e-05,
|
| 93 |
+
"loss": 1.3294,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.04671218109953288,
|
| 98 |
+
"grad_norm": 6.4929585456848145,
|
| 99 |
+
"learning_rate": 1.9072942867409273e-05,
|
| 100 |
+
"loss": 1.2819,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.05030542579949695,
|
| 105 |
+
"grad_norm": 13.437801361083984,
|
| 106 |
+
"learning_rate": 1.9001077973409992e-05,
|
| 107 |
+
"loss": 1.1734,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.05389867049946101,
|
| 112 |
+
"grad_norm": 9.22572135925293,
|
| 113 |
+
"learning_rate": 1.8929213079410708e-05,
|
| 114 |
+
"loss": 1.0934,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.05749191519942508,
|
| 119 |
+
"grad_norm": 12.908567428588867,
|
| 120 |
+
"learning_rate": 1.8857348185411427e-05,
|
| 121 |
+
"loss": 1.1791,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.061085159899389146,
|
| 126 |
+
"grad_norm": 9.806719779968262,
|
| 127 |
+
"learning_rate": 1.8785483291412146e-05,
|
| 128 |
+
"loss": 1.2094,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06467840459935321,
|
| 133 |
+
"grad_norm": 6.507504463195801,
|
| 134 |
+
"learning_rate": 1.8713618397412865e-05,
|
| 135 |
+
"loss": 1.1484,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.06827164929931728,
|
| 140 |
+
"grad_norm": 13.343854904174805,
|
| 141 |
+
"learning_rate": 1.8641753503413585e-05,
|
| 142 |
+
"loss": 1.0378,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.07186489399928135,
|
| 147 |
+
"grad_norm": 9.213022232055664,
|
| 148 |
+
"learning_rate": 1.85698886094143e-05,
|
| 149 |
+
"loss": 1.149,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.07545813869924542,
|
| 154 |
+
"grad_norm": 6.583609580993652,
|
| 155 |
+
"learning_rate": 1.849802371541502e-05,
|
| 156 |
+
"loss": 0.9091,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.07905138339920949,
|
| 161 |
+
"grad_norm": 13.28250789642334,
|
| 162 |
+
"learning_rate": 1.8426158821415742e-05,
|
| 163 |
+
"loss": 1.104,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08264462809917356,
|
| 168 |
+
"grad_norm": 9.129759788513184,
|
| 169 |
+
"learning_rate": 1.8354293927416458e-05,
|
| 170 |
+
"loss": 1.175,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08623787279913762,
|
| 175 |
+
"grad_norm": 7.381193161010742,
|
| 176 |
+
"learning_rate": 1.8282429033417177e-05,
|
| 177 |
+
"loss": 0.9531,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.08983111749910169,
|
| 182 |
+
"grad_norm": 8.401652336120605,
|
| 183 |
+
"learning_rate": 1.8210564139417896e-05,
|
| 184 |
+
"loss": 1.0652,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.09342436219906576,
|
| 189 |
+
"grad_norm": 6.572427272796631,
|
| 190 |
+
"learning_rate": 1.8138699245418615e-05,
|
| 191 |
+
"loss": 0.8957,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.09701760689902983,
|
| 196 |
+
"grad_norm": 13.609588623046875,
|
| 197 |
+
"learning_rate": 1.8066834351419334e-05,
|
| 198 |
+
"loss": 1.0328,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1006108515989939,
|
| 203 |
+
"grad_norm": 9.873039245605469,
|
| 204 |
+
"learning_rate": 1.7994969457420053e-05,
|
| 205 |
+
"loss": 0.8974,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.10420409629895797,
|
| 210 |
+
"grad_norm": 6.486234188079834,
|
| 211 |
+
"learning_rate": 1.792310456342077e-05,
|
| 212 |
+
"loss": 0.7499,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.10779734099892202,
|
| 217 |
+
"grad_norm": 8.80713176727295,
|
| 218 |
+
"learning_rate": 1.7851239669421488e-05,
|
| 219 |
+
"loss": 1.0299,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.11139058569888609,
|
| 224 |
+
"grad_norm": 11.095004081726074,
|
| 225 |
+
"learning_rate": 1.7779374775422207e-05,
|
| 226 |
+
"loss": 0.9532,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.11498383039885016,
|
| 231 |
+
"grad_norm": 8.18423843383789,
|
| 232 |
+
"learning_rate": 1.7707509881422926e-05,
|
| 233 |
+
"loss": 0.9966,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.11857707509881422,
|
| 238 |
+
"grad_norm": 7.924959182739258,
|
| 239 |
+
"learning_rate": 1.7635644987423645e-05,
|
| 240 |
+
"loss": 1.0115,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.12217031979877829,
|
| 245 |
+
"grad_norm": 9.02883529663086,
|
| 246 |
+
"learning_rate": 1.7563780093424364e-05,
|
| 247 |
+
"loss": 0.961,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.12576356449874238,
|
| 252 |
+
"grad_norm": 11.199103355407715,
|
| 253 |
+
"learning_rate": 1.7491915199425083e-05,
|
| 254 |
+
"loss": 1.0795,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.12935680919870643,
|
| 259 |
+
"grad_norm": 4.646785259246826,
|
| 260 |
+
"learning_rate": 1.7420050305425803e-05,
|
| 261 |
+
"loss": 0.9701,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.1329500538986705,
|
| 266 |
+
"grad_norm": 8.631613731384277,
|
| 267 |
+
"learning_rate": 1.7348185411426518e-05,
|
| 268 |
+
"loss": 1.0499,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.13654329859863457,
|
| 273 |
+
"grad_norm": 10.40414047241211,
|
| 274 |
+
"learning_rate": 1.7276320517427237e-05,
|
| 275 |
+
"loss": 1.0192,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.14013654329859865,
|
| 280 |
+
"grad_norm": 6.724309921264648,
|
| 281 |
+
"learning_rate": 1.7204455623427956e-05,
|
| 282 |
+
"loss": 0.7622,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.1437297879985627,
|
| 287 |
+
"grad_norm": 10.001465797424316,
|
| 288 |
+
"learning_rate": 1.7132590729428676e-05,
|
| 289 |
+
"loss": 1.0283,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.14732303269852676,
|
| 294 |
+
"grad_norm": 9.960790634155273,
|
| 295 |
+
"learning_rate": 1.7060725835429395e-05,
|
| 296 |
+
"loss": 0.9756,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.15091627739849084,
|
| 301 |
+
"grad_norm": 10.12285041809082,
|
| 302 |
+
"learning_rate": 1.698886094143011e-05,
|
| 303 |
+
"loss": 0.9986,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1545095220984549,
|
| 308 |
+
"grad_norm": 11.869123458862305,
|
| 309 |
+
"learning_rate": 1.6916996047430833e-05,
|
| 310 |
+
"loss": 0.846,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.15810276679841898,
|
| 315 |
+
"grad_norm": 5.06349515914917,
|
| 316 |
+
"learning_rate": 1.6845131153431552e-05,
|
| 317 |
+
"loss": 1.0217,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.16169601149838303,
|
| 322 |
+
"grad_norm": 9.066526412963867,
|
| 323 |
+
"learning_rate": 1.6773266259432268e-05,
|
| 324 |
+
"loss": 0.9221,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.1652892561983471,
|
| 329 |
+
"grad_norm": 9.309064865112305,
|
| 330 |
+
"learning_rate": 1.6701401365432987e-05,
|
| 331 |
+
"loss": 0.7854,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.16888250089831117,
|
| 336 |
+
"grad_norm": 12.74048900604248,
|
| 337 |
+
"learning_rate": 1.6629536471433706e-05,
|
| 338 |
+
"loss": 1.0911,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.17247574559827525,
|
| 343 |
+
"grad_norm": 6.426724433898926,
|
| 344 |
+
"learning_rate": 1.6557671577434425e-05,
|
| 345 |
+
"loss": 0.9062,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.1760689902982393,
|
| 350 |
+
"grad_norm": 10.126945495605469,
|
| 351 |
+
"learning_rate": 1.6485806683435144e-05,
|
| 352 |
+
"loss": 0.9157,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.17966223499820339,
|
| 357 |
+
"grad_norm": 4.212762832641602,
|
| 358 |
+
"learning_rate": 1.641394178943586e-05,
|
| 359 |
+
"loss": 0.8974,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.18325547969816744,
|
| 364 |
+
"grad_norm": 9.264360427856445,
|
| 365 |
+
"learning_rate": 1.634207689543658e-05,
|
| 366 |
+
"loss": 0.9294,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.18684872439813152,
|
| 371 |
+
"grad_norm": 8.043506622314453,
|
| 372 |
+
"learning_rate": 1.62702120014373e-05,
|
| 373 |
+
"loss": 0.8889,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.19044196909809558,
|
| 378 |
+
"grad_norm": 7.407253742218018,
|
| 379 |
+
"learning_rate": 1.6198347107438017e-05,
|
| 380 |
+
"loss": 0.888,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.19403521379805966,
|
| 385 |
+
"grad_norm": 3.76177716255188,
|
| 386 |
+
"learning_rate": 1.6126482213438736e-05,
|
| 387 |
+
"loss": 0.7739,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.1976284584980237,
|
| 392 |
+
"grad_norm": 6.74066686630249,
|
| 393 |
+
"learning_rate": 1.6054617319439455e-05,
|
| 394 |
+
"loss": 0.8938,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.2012217031979878,
|
| 399 |
+
"grad_norm": 8.588924407958984,
|
| 400 |
+
"learning_rate": 1.5982752425440174e-05,
|
| 401 |
+
"loss": 1.0615,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.20481494789795185,
|
| 406 |
+
"grad_norm": 7.100722312927246,
|
| 407 |
+
"learning_rate": 1.5910887531440894e-05,
|
| 408 |
+
"loss": 0.788,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.20840819259791593,
|
| 413 |
+
"grad_norm": 8.932958602905273,
|
| 414 |
+
"learning_rate": 1.583902263744161e-05,
|
| 415 |
+
"loss": 0.9478,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.21200143729787999,
|
| 420 |
+
"grad_norm": 5.2799787521362305,
|
| 421 |
+
"learning_rate": 1.576715774344233e-05,
|
| 422 |
+
"loss": 0.9483,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.21559468199784404,
|
| 427 |
+
"grad_norm": 6.58836030960083,
|
| 428 |
+
"learning_rate": 1.5695292849443047e-05,
|
| 429 |
+
"loss": 0.9327,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.21918792669780812,
|
| 434 |
+
"grad_norm": 6.726273059844971,
|
| 435 |
+
"learning_rate": 1.5623427955443767e-05,
|
| 436 |
+
"loss": 0.8143,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.22278117139777218,
|
| 441 |
+
"grad_norm": 13.367673873901367,
|
| 442 |
+
"learning_rate": 1.5551563061444486e-05,
|
| 443 |
+
"loss": 0.7846,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.22637441609773626,
|
| 448 |
+
"grad_norm": 7.093170642852783,
|
| 449 |
+
"learning_rate": 1.5479698167445205e-05,
|
| 450 |
+
"loss": 0.8274,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.2299676607977003,
|
| 455 |
+
"grad_norm": 7.058470726013184,
|
| 456 |
+
"learning_rate": 1.5407833273445924e-05,
|
| 457 |
+
"loss": 0.8349,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.2335609054976644,
|
| 462 |
+
"grad_norm": 7.336752414703369,
|
| 463 |
+
"learning_rate": 1.5335968379446643e-05,
|
| 464 |
+
"loss": 1.0872,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.23715415019762845,
|
| 469 |
+
"grad_norm": 7.090172290802002,
|
| 470 |
+
"learning_rate": 1.5264103485447362e-05,
|
| 471 |
+
"loss": 0.8561,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.24074739489759253,
|
| 476 |
+
"grad_norm": 7.062121391296387,
|
| 477 |
+
"learning_rate": 1.5192238591448078e-05,
|
| 478 |
+
"loss": 0.8298,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.24434063959755659,
|
| 483 |
+
"grad_norm": 4.680623531341553,
|
| 484 |
+
"learning_rate": 1.5120373697448799e-05,
|
| 485 |
+
"loss": 0.7485,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.24793388429752067,
|
| 490 |
+
"grad_norm": 4.166479110717773,
|
| 491 |
+
"learning_rate": 1.5048508803449516e-05,
|
| 492 |
+
"loss": 0.8893,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.25152712899748475,
|
| 497 |
+
"grad_norm": 7.121062278747559,
|
| 498 |
+
"learning_rate": 1.4976643909450235e-05,
|
| 499 |
+
"loss": 0.6611,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.2551203736974488,
|
| 504 |
+
"grad_norm": 5.491664886474609,
|
| 505 |
+
"learning_rate": 1.4904779015450954e-05,
|
| 506 |
+
"loss": 1.0562,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.25871361839741286,
|
| 511 |
+
"grad_norm": 9.273249626159668,
|
| 512 |
+
"learning_rate": 1.4832914121451672e-05,
|
| 513 |
+
"loss": 1.0254,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.26230686309737694,
|
| 518 |
+
"grad_norm": 10.43608570098877,
|
| 519 |
+
"learning_rate": 1.476104922745239e-05,
|
| 520 |
+
"loss": 0.8357,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.265900107797341,
|
| 525 |
+
"grad_norm": 9.218886375427246,
|
| 526 |
+
"learning_rate": 1.468918433345311e-05,
|
| 527 |
+
"loss": 0.8972,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.26949335249730505,
|
| 532 |
+
"grad_norm": 6.967902660369873,
|
| 533 |
+
"learning_rate": 1.4617319439453827e-05,
|
| 534 |
+
"loss": 0.9041,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.27308659719726913,
|
| 539 |
+
"grad_norm": 9.598542213439941,
|
| 540 |
+
"learning_rate": 1.4545454545454546e-05,
|
| 541 |
+
"loss": 0.9741,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.2766798418972332,
|
| 546 |
+
"grad_norm": 7.814625263214111,
|
| 547 |
+
"learning_rate": 1.4473589651455264e-05,
|
| 548 |
+
"loss": 0.9535,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.2802730865971973,
|
| 553 |
+
"grad_norm": 5.9632744789123535,
|
| 554 |
+
"learning_rate": 1.4401724757455985e-05,
|
| 555 |
+
"loss": 0.8045,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.2838663312971613,
|
| 560 |
+
"grad_norm": 8.069158554077148,
|
| 561 |
+
"learning_rate": 1.4329859863456704e-05,
|
| 562 |
+
"loss": 0.8547,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.2874595759971254,
|
| 567 |
+
"grad_norm": 8.814532279968262,
|
| 568 |
+
"learning_rate": 1.4257994969457421e-05,
|
| 569 |
+
"loss": 1.1339,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.2910528206970895,
|
| 574 |
+
"grad_norm": 7.119789123535156,
|
| 575 |
+
"learning_rate": 1.418613007545814e-05,
|
| 576 |
+
"loss": 0.8693,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.2946460653970535,
|
| 581 |
+
"grad_norm": 6.96940279006958,
|
| 582 |
+
"learning_rate": 1.411426518145886e-05,
|
| 583 |
+
"loss": 0.7695,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.2982393100970176,
|
| 588 |
+
"grad_norm": 6.049989223480225,
|
| 589 |
+
"learning_rate": 1.4042400287459577e-05,
|
| 590 |
+
"loss": 0.7869,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3018325547969817,
|
| 595 |
+
"grad_norm": 6.798286437988281,
|
| 596 |
+
"learning_rate": 1.3970535393460296e-05,
|
| 597 |
+
"loss": 0.8735,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.30542579949694576,
|
| 602 |
+
"grad_norm": 7.636628150939941,
|
| 603 |
+
"learning_rate": 1.3898670499461015e-05,
|
| 604 |
+
"loss": 0.5762,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.3090190441969098,
|
| 609 |
+
"grad_norm": 8.8123140335083,
|
| 610 |
+
"learning_rate": 1.3826805605461732e-05,
|
| 611 |
+
"loss": 0.8944,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.31261228889687387,
|
| 616 |
+
"grad_norm": 8.178088188171387,
|
| 617 |
+
"learning_rate": 1.3754940711462453e-05,
|
| 618 |
+
"loss": 0.8161,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.31620553359683795,
|
| 623 |
+
"grad_norm": 5.31364107131958,
|
| 624 |
+
"learning_rate": 1.3683075817463169e-05,
|
| 625 |
+
"loss": 0.7076,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.31979877829680203,
|
| 630 |
+
"grad_norm": 5.974244594573975,
|
| 631 |
+
"learning_rate": 1.361121092346389e-05,
|
| 632 |
+
"loss": 0.7999,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.32339202299676606,
|
| 637 |
+
"grad_norm": 9.109082221984863,
|
| 638 |
+
"learning_rate": 1.3539346029464609e-05,
|
| 639 |
+
"loss": 0.9564,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.32698526769673014,
|
| 644 |
+
"grad_norm": 9.144074440002441,
|
| 645 |
+
"learning_rate": 1.3467481135465326e-05,
|
| 646 |
+
"loss": 0.9651,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.3305785123966942,
|
| 651 |
+
"grad_norm": 11.100114822387695,
|
| 652 |
+
"learning_rate": 1.3395616241466045e-05,
|
| 653 |
+
"loss": 0.9018,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.3341717570966583,
|
| 658 |
+
"grad_norm": 5.25788688659668,
|
| 659 |
+
"learning_rate": 1.3323751347466764e-05,
|
| 660 |
+
"loss": 0.6115,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.33776500179662233,
|
| 665 |
+
"grad_norm": 3.6270971298217773,
|
| 666 |
+
"learning_rate": 1.3251886453467482e-05,
|
| 667 |
+
"loss": 0.6783,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.3413582464965864,
|
| 672 |
+
"grad_norm": 9.1345853805542,
|
| 673 |
+
"learning_rate": 1.31800215594682e-05,
|
| 674 |
+
"loss": 0.9194,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.3449514911965505,
|
| 679 |
+
"grad_norm": 7.9600090980529785,
|
| 680 |
+
"learning_rate": 1.3108156665468918e-05,
|
| 681 |
+
"loss": 0.7061,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.3485447358965146,
|
| 686 |
+
"grad_norm": 11.217706680297852,
|
| 687 |
+
"learning_rate": 1.3036291771469637e-05,
|
| 688 |
+
"loss": 0.8675,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.3521379805964786,
|
| 693 |
+
"grad_norm": 4.390411376953125,
|
| 694 |
+
"learning_rate": 1.2964426877470358e-05,
|
| 695 |
+
"loss": 0.928,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.3557312252964427,
|
| 700 |
+
"grad_norm": 6.773019790649414,
|
| 701 |
+
"learning_rate": 1.2892561983471074e-05,
|
| 702 |
+
"loss": 0.8153,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.35932446999640677,
|
| 707 |
+
"grad_norm": 8.140026092529297,
|
| 708 |
+
"learning_rate": 1.2820697089471795e-05,
|
| 709 |
+
"loss": 0.7,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.3629177146963708,
|
| 714 |
+
"grad_norm": 5.35282039642334,
|
| 715 |
+
"learning_rate": 1.2748832195472514e-05,
|
| 716 |
+
"loss": 0.8485,
|
| 717 |
+
"step": 1010
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.3665109593963349,
|
| 721 |
+
"grad_norm": 8.486083984375,
|
| 722 |
+
"learning_rate": 1.2676967301473231e-05,
|
| 723 |
+
"loss": 0.7128,
|
| 724 |
+
"step": 1020
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.37010420409629896,
|
| 728 |
+
"grad_norm": 8.271173477172852,
|
| 729 |
+
"learning_rate": 1.260510240747395e-05,
|
| 730 |
+
"loss": 0.8304,
|
| 731 |
+
"step": 1030
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.37369744879626304,
|
| 735 |
+
"grad_norm": 7.8794331550598145,
|
| 736 |
+
"learning_rate": 1.2533237513474668e-05,
|
| 737 |
+
"loss": 0.7342,
|
| 738 |
+
"step": 1040
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.37729069349622707,
|
| 742 |
+
"grad_norm": 7.080440044403076,
|
| 743 |
+
"learning_rate": 1.2461372619475387e-05,
|
| 744 |
+
"loss": 0.8883,
|
| 745 |
+
"step": 1050
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.38088393819619115,
|
| 749 |
+
"grad_norm": 7.4731903076171875,
|
| 750 |
+
"learning_rate": 1.2389507725476106e-05,
|
| 751 |
+
"loss": 0.8742,
|
| 752 |
+
"step": 1060
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.38447718289615523,
|
| 756 |
+
"grad_norm": 11.303037643432617,
|
| 757 |
+
"learning_rate": 1.2317642831476823e-05,
|
| 758 |
+
"loss": 0.9059,
|
| 759 |
+
"step": 1070
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.3880704275961193,
|
| 763 |
+
"grad_norm": 3.480085611343384,
|
| 764 |
+
"learning_rate": 1.2245777937477542e-05,
|
| 765 |
+
"loss": 0.7729,
|
| 766 |
+
"step": 1080
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.39166367229608334,
|
| 770 |
+
"grad_norm": 8.819855690002441,
|
| 771 |
+
"learning_rate": 1.2173913043478263e-05,
|
| 772 |
+
"loss": 0.9153,
|
| 773 |
+
"step": 1090
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.3952569169960474,
|
| 777 |
+
"grad_norm": 7.252877235412598,
|
| 778 |
+
"learning_rate": 1.210204814947898e-05,
|
| 779 |
+
"loss": 0.7462,
|
| 780 |
+
"step": 1100
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.3988501616960115,
|
| 784 |
+
"grad_norm": 9.326582908630371,
|
| 785 |
+
"learning_rate": 1.20301832554797e-05,
|
| 786 |
+
"loss": 0.8735,
|
| 787 |
+
"step": 1110
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.4024434063959756,
|
| 791 |
+
"grad_norm": 7.847351551055908,
|
| 792 |
+
"learning_rate": 1.1958318361480419e-05,
|
| 793 |
+
"loss": 0.9442,
|
| 794 |
+
"step": 1120
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.4060366510959396,
|
| 798 |
+
"grad_norm": 9.304997444152832,
|
| 799 |
+
"learning_rate": 1.1886453467481136e-05,
|
| 800 |
+
"loss": 0.7541,
|
| 801 |
+
"step": 1130
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.4096298957959037,
|
| 805 |
+
"grad_norm": 6.713771820068359,
|
| 806 |
+
"learning_rate": 1.1814588573481855e-05,
|
| 807 |
+
"loss": 0.7521,
|
| 808 |
+
"step": 1140
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.4132231404958678,
|
| 812 |
+
"grad_norm": 6.436892986297607,
|
| 813 |
+
"learning_rate": 1.1742723679482573e-05,
|
| 814 |
+
"loss": 0.7816,
|
| 815 |
+
"step": 1150
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.41681638519583186,
|
| 819 |
+
"grad_norm": 1.2891592979431152,
|
| 820 |
+
"learning_rate": 1.1670858785483292e-05,
|
| 821 |
+
"loss": 0.8019,
|
| 822 |
+
"step": 1160
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.4204096298957959,
|
| 826 |
+
"grad_norm": 5.085257530212402,
|
| 827 |
+
"learning_rate": 1.1598993891484011e-05,
|
| 828 |
+
"loss": 0.7397,
|
| 829 |
+
"step": 1170
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.42400287459575997,
|
| 833 |
+
"grad_norm": 3.4146158695220947,
|
| 834 |
+
"learning_rate": 1.1527128997484728e-05,
|
| 835 |
+
"loss": 0.857,
|
| 836 |
+
"step": 1180
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.42759611929572405,
|
| 840 |
+
"grad_norm": 3.6032421588897705,
|
| 841 |
+
"learning_rate": 1.1455264103485449e-05,
|
| 842 |
+
"loss": 0.7684,
|
| 843 |
+
"step": 1190
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.4311893639956881,
|
| 847 |
+
"grad_norm": 5.2717390060424805,
|
| 848 |
+
"learning_rate": 1.1383399209486168e-05,
|
| 849 |
+
"loss": 0.7619,
|
| 850 |
+
"step": 1200
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.43478260869565216,
|
| 854 |
+
"grad_norm": 6.56957483291626,
|
| 855 |
+
"learning_rate": 1.1311534315486886e-05,
|
| 856 |
+
"loss": 0.7833,
|
| 857 |
+
"step": 1210
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.43837585339561624,
|
| 861 |
+
"grad_norm": 3.006985664367676,
|
| 862 |
+
"learning_rate": 1.1239669421487605e-05,
|
| 863 |
+
"loss": 0.6434,
|
| 864 |
+
"step": 1220
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.4419690980955803,
|
| 868 |
+
"grad_norm": 7.374829292297363,
|
| 869 |
+
"learning_rate": 1.1167804527488322e-05,
|
| 870 |
+
"loss": 0.6415,
|
| 871 |
+
"step": 1230
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.44556234279554435,
|
| 875 |
+
"grad_norm": 5.94835901260376,
|
| 876 |
+
"learning_rate": 1.1095939633489041e-05,
|
| 877 |
+
"loss": 0.771,
|
| 878 |
+
"step": 1240
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.44915558749550843,
|
| 882 |
+
"grad_norm": 8.715871810913086,
|
| 883 |
+
"learning_rate": 1.102407473948976e-05,
|
| 884 |
+
"loss": 0.9368,
|
| 885 |
+
"step": 1250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.4527488321954725,
|
| 889 |
+
"grad_norm": 3.8362183570861816,
|
| 890 |
+
"learning_rate": 1.0952209845490478e-05,
|
| 891 |
+
"loss": 0.5955,
|
| 892 |
+
"step": 1260
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.4563420768954366,
|
| 896 |
+
"grad_norm": 8.438674926757812,
|
| 897 |
+
"learning_rate": 1.0880344951491197e-05,
|
| 898 |
+
"loss": 0.9797,
|
| 899 |
+
"step": 1270
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.4599353215954006,
|
| 903 |
+
"grad_norm": 7.920464515686035,
|
| 904 |
+
"learning_rate": 1.0808480057491918e-05,
|
| 905 |
+
"loss": 0.9476,
|
| 906 |
+
"step": 1280
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.4635285662953647,
|
| 910 |
+
"grad_norm": 5.010650157928467,
|
| 911 |
+
"learning_rate": 1.0736615163492633e-05,
|
| 912 |
+
"loss": 0.8197,
|
| 913 |
+
"step": 1290
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.4671218109953288,
|
| 917 |
+
"grad_norm": 9.06809139251709,
|
| 918 |
+
"learning_rate": 1.0664750269493354e-05,
|
| 919 |
+
"loss": 0.7204,
|
| 920 |
+
"step": 1300
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.47071505569529287,
|
| 924 |
+
"grad_norm": 8.399813652038574,
|
| 925 |
+
"learning_rate": 1.0592885375494073e-05,
|
| 926 |
+
"loss": 0.9134,
|
| 927 |
+
"step": 1310
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.4743083003952569,
|
| 931 |
+
"grad_norm": 8.060338020324707,
|
| 932 |
+
"learning_rate": 1.052102048149479e-05,
|
| 933 |
+
"loss": 0.8562,
|
| 934 |
+
"step": 1320
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.477901545095221,
|
| 938 |
+
"grad_norm": 4.944212436676025,
|
| 939 |
+
"learning_rate": 1.044915558749551e-05,
|
| 940 |
+
"loss": 0.7243,
|
| 941 |
+
"step": 1330
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.48149478979518506,
|
| 945 |
+
"grad_norm": 8.986311912536621,
|
| 946 |
+
"learning_rate": 1.0377290693496227e-05,
|
| 947 |
+
"loss": 0.7713,
|
| 948 |
+
"step": 1340
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.48508803449514915,
|
| 952 |
+
"grad_norm": 7.62788200378418,
|
| 953 |
+
"learning_rate": 1.0305425799496946e-05,
|
| 954 |
+
"loss": 0.788,
|
| 955 |
+
"step": 1350
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.48868127919511317,
|
| 959 |
+
"grad_norm": 4.31091833114624,
|
| 960 |
+
"learning_rate": 1.0233560905497665e-05,
|
| 961 |
+
"loss": 0.7138,
|
| 962 |
+
"step": 1360
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.49227452389507725,
|
| 966 |
+
"grad_norm": 4.296084880828857,
|
| 967 |
+
"learning_rate": 1.0161696011498383e-05,
|
| 968 |
+
"loss": 0.8723,
|
| 969 |
+
"step": 1370
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.49586776859504134,
|
| 973 |
+
"grad_norm": 7.611781597137451,
|
| 974 |
+
"learning_rate": 1.0089831117499102e-05,
|
| 975 |
+
"loss": 0.8424,
|
| 976 |
+
"step": 1380
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.49946101329500536,
|
| 980 |
+
"grad_norm": 5.098887920379639,
|
| 981 |
+
"learning_rate": 1.0017966223499823e-05,
|
| 982 |
+
"loss": 0.5966,
|
| 983 |
+
"step": 1390
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.5030542579949695,
|
| 987 |
+
"grad_norm": 7.735159873962402,
|
| 988 |
+
"learning_rate": 9.94610132950054e-06,
|
| 989 |
+
"loss": 0.8796,
|
| 990 |
+
"step": 1400
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.5066475026949335,
|
| 994 |
+
"grad_norm": 12.891678810119629,
|
| 995 |
+
"learning_rate": 9.87423643550126e-06,
|
| 996 |
+
"loss": 0.9252,
|
| 997 |
+
"step": 1410
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.5102407473948976,
|
| 1001 |
+
"grad_norm": 4.764705181121826,
|
| 1002 |
+
"learning_rate": 9.802371541501977e-06,
|
| 1003 |
+
"loss": 0.7076,
|
| 1004 |
+
"step": 1420
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.5138339920948617,
|
| 1008 |
+
"grad_norm": 8.446547508239746,
|
| 1009 |
+
"learning_rate": 9.730506647502696e-06,
|
| 1010 |
+
"loss": 0.6827,
|
| 1011 |
+
"step": 1430
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.5174272367948257,
|
| 1015 |
+
"grad_norm": 7.600401878356934,
|
| 1016 |
+
"learning_rate": 9.658641753503413e-06,
|
| 1017 |
+
"loss": 0.7225,
|
| 1018 |
+
"step": 1440
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.5210204814947897,
|
| 1022 |
+
"grad_norm": 5.719719409942627,
|
| 1023 |
+
"learning_rate": 9.586776859504134e-06,
|
| 1024 |
+
"loss": 0.6234,
|
| 1025 |
+
"step": 1450
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.5246137261947539,
|
| 1029 |
+
"grad_norm": 6.583295822143555,
|
| 1030 |
+
"learning_rate": 9.514911965504851e-06,
|
| 1031 |
+
"loss": 0.7279,
|
| 1032 |
+
"step": 1460
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.5282069708947179,
|
| 1036 |
+
"grad_norm": 6.228325843811035,
|
| 1037 |
+
"learning_rate": 9.44304707150557e-06,
|
| 1038 |
+
"loss": 0.7585,
|
| 1039 |
+
"step": 1470
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.531800215594682,
|
| 1043 |
+
"grad_norm": 7.8453688621521,
|
| 1044 |
+
"learning_rate": 9.37118217750629e-06,
|
| 1045 |
+
"loss": 0.8482,
|
| 1046 |
+
"step": 1480
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.5353934602946461,
|
| 1050 |
+
"grad_norm": 7.193871974945068,
|
| 1051 |
+
"learning_rate": 9.299317283507007e-06,
|
| 1052 |
+
"loss": 1.026,
|
| 1053 |
+
"step": 1490
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.5389867049946101,
|
| 1057 |
+
"grad_norm": 4.170319080352783,
|
| 1058 |
+
"learning_rate": 9.227452389507726e-06,
|
| 1059 |
+
"loss": 0.9686,
|
| 1060 |
+
"step": 1500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.5425799496945742,
|
| 1064 |
+
"grad_norm": 4.138383388519287,
|
| 1065 |
+
"learning_rate": 9.155587495508445e-06,
|
| 1066 |
+
"loss": 0.7255,
|
| 1067 |
+
"step": 1510
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.5461731943945383,
|
| 1071 |
+
"grad_norm": 3.0961215496063232,
|
| 1072 |
+
"learning_rate": 9.083722601509164e-06,
|
| 1073 |
+
"loss": 0.8167,
|
| 1074 |
+
"step": 1520
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.5497664390945023,
|
| 1078 |
+
"grad_norm": 4.225940704345703,
|
| 1079 |
+
"learning_rate": 9.011857707509882e-06,
|
| 1080 |
+
"loss": 0.9055,
|
| 1081 |
+
"step": 1530
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.5533596837944664,
|
| 1085 |
+
"grad_norm": 3.334969997406006,
|
| 1086 |
+
"learning_rate": 8.9399928135106e-06,
|
| 1087 |
+
"loss": 0.6123,
|
| 1088 |
+
"step": 1540
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.5569529284944305,
|
| 1092 |
+
"grad_norm": 6.848125457763672,
|
| 1093 |
+
"learning_rate": 8.868127919511318e-06,
|
| 1094 |
+
"loss": 0.814,
|
| 1095 |
+
"step": 1550
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.5605461731943946,
|
| 1099 |
+
"grad_norm": 6.627513408660889,
|
| 1100 |
+
"learning_rate": 8.796263025512039e-06,
|
| 1101 |
+
"loss": 0.668,
|
| 1102 |
+
"step": 1560
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.5641394178943586,
|
| 1106 |
+
"grad_norm": 4.6623382568359375,
|
| 1107 |
+
"learning_rate": 8.724398131512756e-06,
|
| 1108 |
+
"loss": 0.5911,
|
| 1109 |
+
"step": 1570
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.5677326625943226,
|
| 1113 |
+
"grad_norm": 6.965736389160156,
|
| 1114 |
+
"learning_rate": 8.652533237513476e-06,
|
| 1115 |
+
"loss": 0.8645,
|
| 1116 |
+
"step": 1580
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.5713259072942868,
|
| 1120 |
+
"grad_norm": 5.471493244171143,
|
| 1121 |
+
"learning_rate": 8.580668343514193e-06,
|
| 1122 |
+
"loss": 0.7217,
|
| 1123 |
+
"step": 1590
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.5749191519942508,
|
| 1127 |
+
"grad_norm": 10.030547142028809,
|
| 1128 |
+
"learning_rate": 8.508803449514914e-06,
|
| 1129 |
+
"loss": 0.8575,
|
| 1130 |
+
"step": 1600
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.5785123966942148,
|
| 1134 |
+
"grad_norm": 6.807426452636719,
|
| 1135 |
+
"learning_rate": 8.436938555515631e-06,
|
| 1136 |
+
"loss": 0.913,
|
| 1137 |
+
"step": 1610
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.582105641394179,
|
| 1141 |
+
"grad_norm": 6.466938018798828,
|
| 1142 |
+
"learning_rate": 8.36507366151635e-06,
|
| 1143 |
+
"loss": 0.9222,
|
| 1144 |
+
"step": 1620
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.585698886094143,
|
| 1148 |
+
"grad_norm": 4.761947154998779,
|
| 1149 |
+
"learning_rate": 8.293208767517068e-06,
|
| 1150 |
+
"loss": 0.8348,
|
| 1151 |
+
"step": 1630
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.589292130794107,
|
| 1155 |
+
"grad_norm": 6.450058460235596,
|
| 1156 |
+
"learning_rate": 8.221343873517787e-06,
|
| 1157 |
+
"loss": 0.6135,
|
| 1158 |
+
"step": 1640
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.5928853754940712,
|
| 1162 |
+
"grad_norm": 6.998159885406494,
|
| 1163 |
+
"learning_rate": 8.149478979518506e-06,
|
| 1164 |
+
"loss": 0.694,
|
| 1165 |
+
"step": 1650
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.5964786201940352,
|
| 1169 |
+
"grad_norm": 6.691666126251221,
|
| 1170 |
+
"learning_rate": 8.077614085519225e-06,
|
| 1171 |
+
"loss": 0.7971,
|
| 1172 |
+
"step": 1660
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.6000718648939993,
|
| 1176 |
+
"grad_norm": 7.232285976409912,
|
| 1177 |
+
"learning_rate": 8.005749191519944e-06,
|
| 1178 |
+
"loss": 0.7618,
|
| 1179 |
+
"step": 1670
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.6036651095939634,
|
| 1183 |
+
"grad_norm": 6.530168056488037,
|
| 1184 |
+
"learning_rate": 7.933884297520661e-06,
|
| 1185 |
+
"loss": 0.6388,
|
| 1186 |
+
"step": 1680
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.6072583542939274,
|
| 1190 |
+
"grad_norm": 3.380647659301758,
|
| 1191 |
+
"learning_rate": 7.86201940352138e-06,
|
| 1192 |
+
"loss": 0.6414,
|
| 1193 |
+
"step": 1690
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.6108515989938915,
|
| 1197 |
+
"grad_norm": 7.021971225738525,
|
| 1198 |
+
"learning_rate": 7.790154509522098e-06,
|
| 1199 |
+
"loss": 0.8261,
|
| 1200 |
+
"step": 1700
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.6144448436938555,
|
| 1204 |
+
"grad_norm": 8.17015552520752,
|
| 1205 |
+
"learning_rate": 7.718289615522819e-06,
|
| 1206 |
+
"loss": 0.722,
|
| 1207 |
+
"step": 1710
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.6180380883938196,
|
| 1211 |
+
"grad_norm": 11.588608741760254,
|
| 1212 |
+
"learning_rate": 7.646424721523536e-06,
|
| 1213 |
+
"loss": 0.8205,
|
| 1214 |
+
"step": 1720
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.6216313330937837,
|
| 1218 |
+
"grad_norm": 5.765032768249512,
|
| 1219 |
+
"learning_rate": 7.574559827524255e-06,
|
| 1220 |
+
"loss": 0.6734,
|
| 1221 |
+
"step": 1730
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.6252245777937477,
|
| 1225 |
+
"grad_norm": 8.35347843170166,
|
| 1226 |
+
"learning_rate": 7.5026949335249736e-06,
|
| 1227 |
+
"loss": 0.8921,
|
| 1228 |
+
"step": 1740
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.6288178224937119,
|
| 1232 |
+
"grad_norm": 5.127620220184326,
|
| 1233 |
+
"learning_rate": 7.430830039525693e-06,
|
| 1234 |
+
"loss": 0.6934,
|
| 1235 |
+
"step": 1750
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.6324110671936759,
|
| 1239 |
+
"grad_norm": 4.722314834594727,
|
| 1240 |
+
"learning_rate": 7.358965145526411e-06,
|
| 1241 |
+
"loss": 0.6978,
|
| 1242 |
+
"step": 1760
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.6360043118936399,
|
| 1246 |
+
"grad_norm": 7.5209455490112305,
|
| 1247 |
+
"learning_rate": 7.287100251527129e-06,
|
| 1248 |
+
"loss": 0.7246,
|
| 1249 |
+
"step": 1770
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.6395975565936041,
|
| 1253 |
+
"grad_norm": 7.9390435218811035,
|
| 1254 |
+
"learning_rate": 7.2152353575278474e-06,
|
| 1255 |
+
"loss": 0.7407,
|
| 1256 |
+
"step": 1780
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.6431908012935681,
|
| 1260 |
+
"grad_norm": 4.685247898101807,
|
| 1261 |
+
"learning_rate": 7.143370463528567e-06,
|
| 1262 |
+
"loss": 0.8586,
|
| 1263 |
+
"step": 1790
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.6467840459935321,
|
| 1267 |
+
"grad_norm": 6.8963623046875,
|
| 1268 |
+
"learning_rate": 7.071505569529286e-06,
|
| 1269 |
+
"loss": 0.7048,
|
| 1270 |
+
"step": 1800
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.6503772906934963,
|
| 1274 |
+
"grad_norm": 7.452021598815918,
|
| 1275 |
+
"learning_rate": 6.999640675530004e-06,
|
| 1276 |
+
"loss": 0.7082,
|
| 1277 |
+
"step": 1810
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.6539705353934603,
|
| 1281 |
+
"grad_norm": 7.505745887756348,
|
| 1282 |
+
"learning_rate": 6.927775781530722e-06,
|
| 1283 |
+
"loss": 0.683,
|
| 1284 |
+
"step": 1820
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.6575637800934243,
|
| 1288 |
+
"grad_norm": 7.095577716827393,
|
| 1289 |
+
"learning_rate": 6.855910887531442e-06,
|
| 1290 |
+
"loss": 0.7954,
|
| 1291 |
+
"step": 1830
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.6611570247933884,
|
| 1295 |
+
"grad_norm": 5.106074333190918,
|
| 1296 |
+
"learning_rate": 6.78404599353216e-06,
|
| 1297 |
+
"loss": 0.7707,
|
| 1298 |
+
"step": 1840
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.6647502694933525,
|
| 1302 |
+
"grad_norm": 4.525816917419434,
|
| 1303 |
+
"learning_rate": 6.712181099532879e-06,
|
| 1304 |
+
"loss": 0.7274,
|
| 1305 |
+
"step": 1850
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.6683435141933166,
|
| 1309 |
+
"grad_norm": 9.403148651123047,
|
| 1310 |
+
"learning_rate": 6.640316205533598e-06,
|
| 1311 |
+
"loss": 0.7981,
|
| 1312 |
+
"step": 1860
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.6719367588932806,
|
| 1316 |
+
"grad_norm": 2.272888422012329,
|
| 1317 |
+
"learning_rate": 6.568451311534316e-06,
|
| 1318 |
+
"loss": 0.6679,
|
| 1319 |
+
"step": 1870
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.6755300035932447,
|
| 1323 |
+
"grad_norm": 3.779609203338623,
|
| 1324 |
+
"learning_rate": 6.496586417535034e-06,
|
| 1325 |
+
"loss": 0.6771,
|
| 1326 |
+
"step": 1880
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.6791232482932088,
|
| 1330 |
+
"grad_norm": 6.928153038024902,
|
| 1331 |
+
"learning_rate": 6.424721523535753e-06,
|
| 1332 |
+
"loss": 0.8161,
|
| 1333 |
+
"step": 1890
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.6827164929931728,
|
| 1337 |
+
"grad_norm": 9.023139953613281,
|
| 1338 |
+
"learning_rate": 6.3528566295364724e-06,
|
| 1339 |
+
"loss": 0.7828,
|
| 1340 |
+
"step": 1900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.6863097376931369,
|
| 1344 |
+
"grad_norm": 6.370776653289795,
|
| 1345 |
+
"learning_rate": 6.280991735537191e-06,
|
| 1346 |
+
"loss": 0.7397,
|
| 1347 |
+
"step": 1910
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.689902982393101,
|
| 1351 |
+
"grad_norm": 4.26768159866333,
|
| 1352 |
+
"learning_rate": 6.209126841537909e-06,
|
| 1353 |
+
"loss": 0.671,
|
| 1354 |
+
"step": 1920
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.693496227093065,
|
| 1358 |
+
"grad_norm": 11.181378364562988,
|
| 1359 |
+
"learning_rate": 6.137261947538627e-06,
|
| 1360 |
+
"loss": 0.8204,
|
| 1361 |
+
"step": 1930
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.6970894717930292,
|
| 1365 |
+
"grad_norm": 11.705507278442383,
|
| 1366 |
+
"learning_rate": 6.065397053539347e-06,
|
| 1367 |
+
"loss": 0.6734,
|
| 1368 |
+
"step": 1940
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.7006827164929932,
|
| 1372 |
+
"grad_norm": 8.077978134155273,
|
| 1373 |
+
"learning_rate": 5.993532159540065e-06,
|
| 1374 |
+
"loss": 0.9679,
|
| 1375 |
+
"step": 1950
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.7042759611929572,
|
| 1379 |
+
"grad_norm": 3.5401253700256348,
|
| 1380 |
+
"learning_rate": 5.921667265540784e-06,
|
| 1381 |
+
"loss": 0.7084,
|
| 1382 |
+
"step": 1960
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.7078692058929213,
|
| 1386 |
+
"grad_norm": 7.2463555335998535,
|
| 1387 |
+
"learning_rate": 5.849802371541502e-06,
|
| 1388 |
+
"loss": 0.7845,
|
| 1389 |
+
"step": 1970
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.7114624505928854,
|
| 1393 |
+
"grad_norm": 3.2862935066223145,
|
| 1394 |
+
"learning_rate": 5.777937477542221e-06,
|
| 1395 |
+
"loss": 0.5628,
|
| 1396 |
+
"step": 1980
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.7150556952928494,
|
| 1400 |
+
"grad_norm": 11.543691635131836,
|
| 1401 |
+
"learning_rate": 5.70607258354294e-06,
|
| 1402 |
+
"loss": 0.7221,
|
| 1403 |
+
"step": 1990
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.7186489399928135,
|
| 1407 |
+
"grad_norm": 8.188749313354492,
|
| 1408 |
+
"learning_rate": 5.634207689543658e-06,
|
| 1409 |
+
"loss": 0.7816,
|
| 1410 |
+
"step": 2000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.7222421846927776,
|
| 1414 |
+
"grad_norm": 5.3175740242004395,
|
| 1415 |
+
"learning_rate": 5.562342795544377e-06,
|
| 1416 |
+
"loss": 0.6603,
|
| 1417 |
+
"step": 2010
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.7258354293927416,
|
| 1421 |
+
"grad_norm": 6.805153846740723,
|
| 1422 |
+
"learning_rate": 5.490477901545096e-06,
|
| 1423 |
+
"loss": 0.8621,
|
| 1424 |
+
"step": 2020
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.7294286740927057,
|
| 1428 |
+
"grad_norm": 11.035388946533203,
|
| 1429 |
+
"learning_rate": 5.418613007545814e-06,
|
| 1430 |
+
"loss": 0.8959,
|
| 1431 |
+
"step": 2030
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.7330219187926698,
|
| 1435 |
+
"grad_norm": 6.663356304168701,
|
| 1436 |
+
"learning_rate": 5.346748113546532e-06,
|
| 1437 |
+
"loss": 0.7328,
|
| 1438 |
+
"step": 2040
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.7366151634926339,
|
| 1442 |
+
"grad_norm": 8.319828987121582,
|
| 1443 |
+
"learning_rate": 5.274883219547252e-06,
|
| 1444 |
+
"loss": 0.8377,
|
| 1445 |
+
"step": 2050
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.7402084081925979,
|
| 1449 |
+
"grad_norm": 12.84389591217041,
|
| 1450 |
+
"learning_rate": 5.2030183255479705e-06,
|
| 1451 |
+
"loss": 0.8101,
|
| 1452 |
+
"step": 2060
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.743801652892562,
|
| 1456 |
+
"grad_norm": 9.387964248657227,
|
| 1457 |
+
"learning_rate": 5.131153431548689e-06,
|
| 1458 |
+
"loss": 0.819,
|
| 1459 |
+
"step": 2070
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.7473948975925261,
|
| 1463 |
+
"grad_norm": 13.591238021850586,
|
| 1464 |
+
"learning_rate": 5.059288537549407e-06,
|
| 1465 |
+
"loss": 0.5644,
|
| 1466 |
+
"step": 2080
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.7509881422924901,
|
| 1470 |
+
"grad_norm": 7.670563697814941,
|
| 1471 |
+
"learning_rate": 4.987423643550126e-06,
|
| 1472 |
+
"loss": 0.8611,
|
| 1473 |
+
"step": 2090
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.7545813869924541,
|
| 1477 |
+
"grad_norm": 7.460164546966553,
|
| 1478 |
+
"learning_rate": 4.915558749550845e-06,
|
| 1479 |
+
"loss": 0.5785,
|
| 1480 |
+
"step": 2100
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.7581746316924183,
|
| 1484 |
+
"grad_norm": 10.167394638061523,
|
| 1485 |
+
"learning_rate": 4.8436938555515634e-06,
|
| 1486 |
+
"loss": 0.8433,
|
| 1487 |
+
"step": 2110
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.7617678763923823,
|
| 1491 |
+
"grad_norm": 5.6100945472717285,
|
| 1492 |
+
"learning_rate": 4.7718289615522825e-06,
|
| 1493 |
+
"loss": 0.6128,
|
| 1494 |
+
"step": 2120
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.7653611210923464,
|
| 1498 |
+
"grad_norm": 7.009652614593506,
|
| 1499 |
+
"learning_rate": 4.699964067553001e-06,
|
| 1500 |
+
"loss": 0.6752,
|
| 1501 |
+
"step": 2130
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.7689543657923105,
|
| 1505 |
+
"grad_norm": 6.665421485900879,
|
| 1506 |
+
"learning_rate": 4.62809917355372e-06,
|
| 1507 |
+
"loss": 0.551,
|
| 1508 |
+
"step": 2140
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.7725476104922745,
|
| 1512 |
+
"grad_norm": 7.132537364959717,
|
| 1513 |
+
"learning_rate": 4.556234279554438e-06,
|
| 1514 |
+
"loss": 0.7817,
|
| 1515 |
+
"step": 2150
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.7761408551922386,
|
| 1519 |
+
"grad_norm": 7.3072943687438965,
|
| 1520 |
+
"learning_rate": 4.484369385555156e-06,
|
| 1521 |
+
"loss": 0.7506,
|
| 1522 |
+
"step": 2160
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.7797340998922027,
|
| 1526 |
+
"grad_norm": 6.452977657318115,
|
| 1527 |
+
"learning_rate": 4.4125044915558755e-06,
|
| 1528 |
+
"loss": 0.7703,
|
| 1529 |
+
"step": 2170
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.7833273445921667,
|
| 1533 |
+
"grad_norm": 9.874847412109375,
|
| 1534 |
+
"learning_rate": 4.340639597556594e-06,
|
| 1535 |
+
"loss": 0.8214,
|
| 1536 |
+
"step": 2180
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.7869205892921308,
|
| 1540 |
+
"grad_norm": 4.646761417388916,
|
| 1541 |
+
"learning_rate": 4.268774703557312e-06,
|
| 1542 |
+
"loss": 0.8222,
|
| 1543 |
+
"step": 2190
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.7905138339920948,
|
| 1547 |
+
"grad_norm": 4.57820463180542,
|
| 1548 |
+
"learning_rate": 4.196909809558031e-06,
|
| 1549 |
+
"loss": 0.6275,
|
| 1550 |
+
"step": 2200
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.7941070786920589,
|
| 1554 |
+
"grad_norm": 6.416154861450195,
|
| 1555 |
+
"learning_rate": 4.125044915558749e-06,
|
| 1556 |
+
"loss": 0.6548,
|
| 1557 |
+
"step": 2210
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.797700323392023,
|
| 1561 |
+
"grad_norm": 6.637320041656494,
|
| 1562 |
+
"learning_rate": 4.0531800215594685e-06,
|
| 1563 |
+
"loss": 0.8877,
|
| 1564 |
+
"step": 2220
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.801293568091987,
|
| 1568 |
+
"grad_norm": 5.396492004394531,
|
| 1569 |
+
"learning_rate": 3.981315127560187e-06,
|
| 1570 |
+
"loss": 0.8622,
|
| 1571 |
+
"step": 2230
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.8048868127919512,
|
| 1575 |
+
"grad_norm": 7.009629726409912,
|
| 1576 |
+
"learning_rate": 3.909450233560906e-06,
|
| 1577 |
+
"loss": 0.7937,
|
| 1578 |
+
"step": 2240
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.8084800574919152,
|
| 1582 |
+
"grad_norm": 6.630249977111816,
|
| 1583 |
+
"learning_rate": 3.837585339561625e-06,
|
| 1584 |
+
"loss": 0.8945,
|
| 1585 |
+
"step": 2250
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.8120733021918792,
|
| 1589 |
+
"grad_norm": 7.130268096923828,
|
| 1590 |
+
"learning_rate": 3.7657204455623432e-06,
|
| 1591 |
+
"loss": 0.8868,
|
| 1592 |
+
"step": 2260
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.8156665468918434,
|
| 1596 |
+
"grad_norm": 5.933340072631836,
|
| 1597 |
+
"learning_rate": 3.693855551563062e-06,
|
| 1598 |
+
"loss": 0.8686,
|
| 1599 |
+
"step": 2270
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.8192597915918074,
|
| 1603 |
+
"grad_norm": 3.7892746925354004,
|
| 1604 |
+
"learning_rate": 3.62199065756378e-06,
|
| 1605 |
+
"loss": 0.6425,
|
| 1606 |
+
"step": 2280
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.8228530362917714,
|
| 1610 |
+
"grad_norm": 11.255279541015625,
|
| 1611 |
+
"learning_rate": 3.5501257635644993e-06,
|
| 1612 |
+
"loss": 0.7639,
|
| 1613 |
+
"step": 2290
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.8264462809917356,
|
| 1617 |
+
"grad_norm": 6.262332916259766,
|
| 1618 |
+
"learning_rate": 3.4782608695652175e-06,
|
| 1619 |
+
"loss": 0.6272,
|
| 1620 |
+
"step": 2300
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.8300395256916996,
|
| 1624 |
+
"grad_norm": 4.936995506286621,
|
| 1625 |
+
"learning_rate": 3.4063959755659366e-06,
|
| 1626 |
+
"loss": 0.635,
|
| 1627 |
+
"step": 2310
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.8336327703916637,
|
| 1631 |
+
"grad_norm": 5.9594926834106445,
|
| 1632 |
+
"learning_rate": 3.334531081566655e-06,
|
| 1633 |
+
"loss": 0.6994,
|
| 1634 |
+
"step": 2320
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.8372260150916278,
|
| 1638 |
+
"grad_norm": 3.9269344806671143,
|
| 1639 |
+
"learning_rate": 3.2626661875673735e-06,
|
| 1640 |
+
"loss": 0.5302,
|
| 1641 |
+
"step": 2330
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.8408192597915918,
|
| 1645 |
+
"grad_norm": 6.650905609130859,
|
| 1646 |
+
"learning_rate": 3.1908012935680922e-06,
|
| 1647 |
+
"loss": 0.8061,
|
| 1648 |
+
"step": 2340
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.8444125044915559,
|
| 1652 |
+
"grad_norm": 6.4028449058532715,
|
| 1653 |
+
"learning_rate": 3.118936399568811e-06,
|
| 1654 |
+
"loss": 0.6817,
|
| 1655 |
+
"step": 2350
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.8480057491915199,
|
| 1659 |
+
"grad_norm": 6.031358242034912,
|
| 1660 |
+
"learning_rate": 3.047071505569529e-06,
|
| 1661 |
+
"loss": 0.7775,
|
| 1662 |
+
"step": 2360
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.851598993891484,
|
| 1666 |
+
"grad_norm": 8.679971694946289,
|
| 1667 |
+
"learning_rate": 2.9752066115702483e-06,
|
| 1668 |
+
"loss": 0.9736,
|
| 1669 |
+
"step": 2370
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.8551922385914481,
|
| 1673 |
+
"grad_norm": 9.925468444824219,
|
| 1674 |
+
"learning_rate": 2.9033417175709665e-06,
|
| 1675 |
+
"loss": 0.6576,
|
| 1676 |
+
"step": 2380
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.8587854832914121,
|
| 1680 |
+
"grad_norm": 6.079770565032959,
|
| 1681 |
+
"learning_rate": 2.8314768235716856e-06,
|
| 1682 |
+
"loss": 0.9628,
|
| 1683 |
+
"step": 2390
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.8623787279913762,
|
| 1687 |
+
"grad_norm": 5.954907417297363,
|
| 1688 |
+
"learning_rate": 2.759611929572404e-06,
|
| 1689 |
+
"loss": 0.7555,
|
| 1690 |
+
"step": 2400
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.8659719726913403,
|
| 1694 |
+
"grad_norm": 5.5433783531188965,
|
| 1695 |
+
"learning_rate": 2.687747035573123e-06,
|
| 1696 |
+
"loss": 0.5379,
|
| 1697 |
+
"step": 2410
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.8695652173913043,
|
| 1701 |
+
"grad_norm": 9.579656600952148,
|
| 1702 |
+
"learning_rate": 2.6158821415738412e-06,
|
| 1703 |
+
"loss": 0.6478,
|
| 1704 |
+
"step": 2420
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.8731584620912685,
|
| 1708 |
+
"grad_norm": 5.076817035675049,
|
| 1709 |
+
"learning_rate": 2.54401724757456e-06,
|
| 1710 |
+
"loss": 0.6276,
|
| 1711 |
+
"step": 2430
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.8767517067912325,
|
| 1715 |
+
"grad_norm": 8.012504577636719,
|
| 1716 |
+
"learning_rate": 2.4721523535752786e-06,
|
| 1717 |
+
"loss": 0.6421,
|
| 1718 |
+
"step": 2440
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.8803449514911965,
|
| 1722 |
+
"grad_norm": 7.541149139404297,
|
| 1723 |
+
"learning_rate": 2.4002874595759973e-06,
|
| 1724 |
+
"loss": 0.6516,
|
| 1725 |
+
"step": 2450
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.8839381961911607,
|
| 1729 |
+
"grad_norm": 6.304592132568359,
|
| 1730 |
+
"learning_rate": 2.328422565576716e-06,
|
| 1731 |
+
"loss": 0.6013,
|
| 1732 |
+
"step": 2460
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.8875314408911247,
|
| 1736 |
+
"grad_norm": 4.353475570678711,
|
| 1737 |
+
"learning_rate": 2.2565576715774346e-06,
|
| 1738 |
+
"loss": 0.8041,
|
| 1739 |
+
"step": 2470
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.8911246855910887,
|
| 1743 |
+
"grad_norm": 7.181800365447998,
|
| 1744 |
+
"learning_rate": 2.1846927775781533e-06,
|
| 1745 |
+
"loss": 0.8463,
|
| 1746 |
+
"step": 2480
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.8947179302910528,
|
| 1750 |
+
"grad_norm": 3.317331552505493,
|
| 1751 |
+
"learning_rate": 2.112827883578872e-06,
|
| 1752 |
+
"loss": 0.6592,
|
| 1753 |
+
"step": 2490
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.8983111749910169,
|
| 1757 |
+
"grad_norm": 5.976993083953857,
|
| 1758 |
+
"learning_rate": 2.0409629895795903e-06,
|
| 1759 |
+
"loss": 0.701,
|
| 1760 |
+
"step": 2500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.901904419690981,
|
| 1764 |
+
"grad_norm": 5.5971832275390625,
|
| 1765 |
+
"learning_rate": 1.969098095580309e-06,
|
| 1766 |
+
"loss": 0.7341,
|
| 1767 |
+
"step": 2510
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.905497664390945,
|
| 1771 |
+
"grad_norm": 10.143183708190918,
|
| 1772 |
+
"learning_rate": 1.8972332015810276e-06,
|
| 1773 |
+
"loss": 0.8767,
|
| 1774 |
+
"step": 2520
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.9090909090909091,
|
| 1778 |
+
"grad_norm": 7.039025783538818,
|
| 1779 |
+
"learning_rate": 1.8253683075817465e-06,
|
| 1780 |
+
"loss": 0.6021,
|
| 1781 |
+
"step": 2530
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.9126841537908732,
|
| 1785 |
+
"grad_norm": 5.272881984710693,
|
| 1786 |
+
"learning_rate": 1.7535034135824652e-06,
|
| 1787 |
+
"loss": 0.7078,
|
| 1788 |
+
"step": 2540
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.9162773984908372,
|
| 1792 |
+
"grad_norm": 6.3512349128723145,
|
| 1793 |
+
"learning_rate": 1.6816385195831839e-06,
|
| 1794 |
+
"loss": 0.8479,
|
| 1795 |
+
"step": 2550
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.9198706431908013,
|
| 1799 |
+
"grad_norm": 5.514537811279297,
|
| 1800 |
+
"learning_rate": 1.6097736255839025e-06,
|
| 1801 |
+
"loss": 0.7474,
|
| 1802 |
+
"step": 2560
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.9234638878907654,
|
| 1806 |
+
"grad_norm": 7.537227630615234,
|
| 1807 |
+
"learning_rate": 1.537908731584621e-06,
|
| 1808 |
+
"loss": 0.7484,
|
| 1809 |
+
"step": 2570
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.9270571325907294,
|
| 1813 |
+
"grad_norm": 6.216177940368652,
|
| 1814 |
+
"learning_rate": 1.4660438375853397e-06,
|
| 1815 |
+
"loss": 0.7374,
|
| 1816 |
+
"step": 2580
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.9306503772906934,
|
| 1820 |
+
"grad_norm": 5.915536403656006,
|
| 1821 |
+
"learning_rate": 1.3941789435860584e-06,
|
| 1822 |
+
"loss": 0.7044,
|
| 1823 |
+
"step": 2590
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.9342436219906576,
|
| 1827 |
+
"grad_norm": 7.503188133239746,
|
| 1828 |
+
"learning_rate": 1.322314049586777e-06,
|
| 1829 |
+
"loss": 0.7071,
|
| 1830 |
+
"step": 2600
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.9378368666906216,
|
| 1834 |
+
"grad_norm": 6.930708408355713,
|
| 1835 |
+
"learning_rate": 1.2504491555874957e-06,
|
| 1836 |
+
"loss": 0.8625,
|
| 1837 |
+
"step": 2610
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.9414301113905857,
|
| 1841 |
+
"grad_norm": 7.8779296875,
|
| 1842 |
+
"learning_rate": 1.1785842615882142e-06,
|
| 1843 |
+
"loss": 0.614,
|
| 1844 |
+
"step": 2620
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.9450233560905498,
|
| 1848 |
+
"grad_norm": 6.569777488708496,
|
| 1849 |
+
"learning_rate": 1.1067193675889329e-06,
|
| 1850 |
+
"loss": 0.6891,
|
| 1851 |
+
"step": 2630
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.9486166007905138,
|
| 1855 |
+
"grad_norm": 6.492995738983154,
|
| 1856 |
+
"learning_rate": 1.0348544735896516e-06,
|
| 1857 |
+
"loss": 0.7514,
|
| 1858 |
+
"step": 2640
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.9522098454904779,
|
| 1862 |
+
"grad_norm": 5.516550540924072,
|
| 1863 |
+
"learning_rate": 9.629895795903702e-07,
|
| 1864 |
+
"loss": 0.6322,
|
| 1865 |
+
"step": 2650
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.955803090190442,
|
| 1869 |
+
"grad_norm": 8.970290184020996,
|
| 1870 |
+
"learning_rate": 8.911246855910888e-07,
|
| 1871 |
+
"loss": 0.8457,
|
| 1872 |
+
"step": 2660
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.959396334890406,
|
| 1876 |
+
"grad_norm": 7.239262580871582,
|
| 1877 |
+
"learning_rate": 8.192597915918074e-07,
|
| 1878 |
+
"loss": 0.7673,
|
| 1879 |
+
"step": 2670
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.9629895795903701,
|
| 1883 |
+
"grad_norm": 6.02666711807251,
|
| 1884 |
+
"learning_rate": 7.473948975925262e-07,
|
| 1885 |
+
"loss": 0.619,
|
| 1886 |
+
"step": 2680
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.9665828242903342,
|
| 1890 |
+
"grad_norm": 5.881245136260986,
|
| 1891 |
+
"learning_rate": 6.755300035932449e-07,
|
| 1892 |
+
"loss": 0.7459,
|
| 1893 |
+
"step": 2690
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.9701760689902983,
|
| 1897 |
+
"grad_norm": 6.145602703094482,
|
| 1898 |
+
"learning_rate": 6.036651095939633e-07,
|
| 1899 |
+
"loss": 0.7081,
|
| 1900 |
+
"step": 2700
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.9737693136902623,
|
| 1904 |
+
"grad_norm": 7.62270450592041,
|
| 1905 |
+
"learning_rate": 5.318002155946821e-07,
|
| 1906 |
+
"loss": 0.7145,
|
| 1907 |
+
"step": 2710
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.9773625583902263,
|
| 1911 |
+
"grad_norm": 7.651326656341553,
|
| 1912 |
+
"learning_rate": 4.599353215954007e-07,
|
| 1913 |
+
"loss": 0.6958,
|
| 1914 |
+
"step": 2720
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.9809558030901905,
|
| 1918 |
+
"grad_norm": 5.604285717010498,
|
| 1919 |
+
"learning_rate": 3.880704275961193e-07,
|
| 1920 |
+
"loss": 0.8249,
|
| 1921 |
+
"step": 2730
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.9845490477901545,
|
| 1925 |
+
"grad_norm": 3.623215436935425,
|
| 1926 |
+
"learning_rate": 3.1620553359683794e-07,
|
| 1927 |
+
"loss": 0.5312,
|
| 1928 |
+
"step": 2740
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.9881422924901185,
|
| 1932 |
+
"grad_norm": 4.056583881378174,
|
| 1933 |
+
"learning_rate": 2.443406395975566e-07,
|
| 1934 |
+
"loss": 0.7,
|
| 1935 |
+
"step": 2750
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.9917355371900827,
|
| 1939 |
+
"grad_norm": 6.8995466232299805,
|
| 1940 |
+
"learning_rate": 1.7247574559827524e-07,
|
| 1941 |
+
"loss": 0.6235,
|
| 1942 |
+
"step": 2760
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.9953287818900467,
|
| 1946 |
+
"grad_norm": 5.702864646911621,
|
| 1947 |
+
"learning_rate": 1.0061085159899391e-07,
|
| 1948 |
+
"loss": 0.7579,
|
| 1949 |
+
"step": 2770
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.9989220265900107,
|
| 1953 |
+
"grad_norm": 5.987502574920654,
|
| 1954 |
+
"learning_rate": 2.8745957599712543e-08,
|
| 1955 |
+
"loss": 0.627,
|
| 1956 |
+
"step": 2780
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 1.0,
|
| 1960 |
+
"eval_accuracy": 0.7164420485175202,
|
| 1961 |
+
"eval_loss": 0.7538194060325623,
|
| 1962 |
+
"eval_runtime": 708.1853,
|
| 1963 |
+
"eval_samples_per_second": 7.858,
|
| 1964 |
+
"eval_steps_per_second": 0.983,
|
| 1965 |
+
"step": 2783
|
| 1966 |
+
}
|
| 1967 |
+
],
|
| 1968 |
+
"logging_steps": 10,
|
| 1969 |
+
"max_steps": 2783,
|
| 1970 |
+
"num_input_tokens_seen": 0,
|
| 1971 |
+
"num_train_epochs": 1,
|
| 1972 |
+
"save_steps": 500,
|
| 1973 |
+
"stateful_callbacks": {
|
| 1974 |
+
"TrainerControl": {
|
| 1975 |
+
"args": {
|
| 1976 |
+
"should_epoch_stop": false,
|
| 1977 |
+
"should_evaluate": false,
|
| 1978 |
+
"should_log": false,
|
| 1979 |
+
"should_save": true,
|
| 1980 |
+
"should_training_stop": true
|
| 1981 |
+
},
|
| 1982 |
+
"attributes": {}
|
| 1983 |
+
}
|
| 1984 |
+
},
|
| 1985 |
+
"total_flos": 1.7248939997743964e+18,
|
| 1986 |
+
"train_batch_size": 8,
|
| 1987 |
+
"trial_name": null,
|
| 1988 |
+
"trial_params": null
|
| 1989 |
+
}
|
checkpoint-2783/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94f676490ee54778cdc75d5071936ebf75c31263660fd60ead39f9c07c7b913f
|
| 3 |
+
size 5841
|
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 sha256:30b8401bc059b3af5b58485e1e6e3846cf3c6dcb9c069ca543a25406568021e1
|
| 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 sha256:94f676490ee54778cdc75d5071936ebf75c31263660fd60ead39f9c07c7b913f
|
| 3 |
+
size 5841
|