Commit
•
eb05fde
1
Parent(s):
e03bbf1
End of training
Browse files- README.md +87 -0
- all_results.json +8 -0
- config.json +24 -0
- model.safetensors +3 -0
- preprocessor_config.json +36 -0
- runs/Jul12_09-58-17_d5ffb3757aea/events.out.tfevents.1720778368.d5ffb3757aea.195.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +1069 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- imagefolder
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: Tb_Dataset
|
| 12 |
+
results:
|
| 13 |
+
- task:
|
| 14 |
+
name: Image Classification
|
| 15 |
+
type: image-classification
|
| 16 |
+
dataset:
|
| 17 |
+
name: imagefolder
|
| 18 |
+
type: imagefolder
|
| 19 |
+
config: default
|
| 20 |
+
split: validation
|
| 21 |
+
args: default
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.875
|
| 26 |
+
---
|
| 27 |
+
|
| 28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
+
|
| 31 |
+
# Tb_Dataset
|
| 32 |
+
|
| 33 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4037
|
| 36 |
+
- Accuracy: 0.875
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 0.0002
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 8
|
| 58 |
+
- seed: 42
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 4
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
| 67 |
+
| 0.0996 | 0.3067 | 100 | 1.0429 | 0.5625 |
|
| 68 |
+
| 0.0481 | 0.6135 | 200 | 0.5665 | 0.8125 |
|
| 69 |
+
| 0.0391 | 0.9202 | 300 | 1.0037 | 0.6875 |
|
| 70 |
+
| 0.0711 | 1.2270 | 400 | 0.5200 | 0.875 |
|
| 71 |
+
| 0.0258 | 1.5337 | 500 | 0.3818 | 0.9375 |
|
| 72 |
+
| 0.0547 | 1.8405 | 600 | 0.3415 | 0.9375 |
|
| 73 |
+
| 0.0029 | 2.1472 | 700 | 0.0637 | 0.9375 |
|
| 74 |
+
| 0.0543 | 2.4540 | 800 | 0.7362 | 0.8125 |
|
| 75 |
+
| 0.0265 | 2.7607 | 900 | 1.0917 | 0.75 |
|
| 76 |
+
| 0.0017 | 3.0675 | 1000 | 0.0030 | 1.0 |
|
| 77 |
+
| 0.0054 | 3.3742 | 1100 | 0.0364 | 1.0 |
|
| 78 |
+
| 0.0234 | 3.6810 | 1200 | 0.2310 | 0.875 |
|
| 79 |
+
| 0.0076 | 3.9877 | 1300 | 0.4037 | 0.875 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.41.2
|
| 85 |
+
- Pytorch 2.3.0+cu121
|
| 86 |
+
- Datasets 2.20.0
|
| 87 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.6167928713188475e+18,
|
| 4 |
+
"train_loss": 0.04957773063711799,
|
| 5 |
+
"train_runtime": 1223.9715,
|
| 6 |
+
"train_samples_per_second": 17.046,
|
| 7 |
+
"train_steps_per_second": 1.065
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"image_size": 224,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"model_type": "vit",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_channels": 3,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"problem_type": "single_label_classification",
|
| 21 |
+
"qkv_bias": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.41.2"
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c000d83dacd9d1c86d4db5fe15c77b65deb78f7e66f525ea8c4f647e18844f76
|
| 3 |
+
size 343223968
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format"
|
| 15 |
+
],
|
| 16 |
+
"do_normalize": true,
|
| 17 |
+
"do_rescale": true,
|
| 18 |
+
"do_resize": true,
|
| 19 |
+
"image_mean": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 25 |
+
"image_std": [
|
| 26 |
+
0.5,
|
| 27 |
+
0.5,
|
| 28 |
+
0.5
|
| 29 |
+
],
|
| 30 |
+
"resample": 2,
|
| 31 |
+
"rescale_factor": 0.00392156862745098,
|
| 32 |
+
"size": {
|
| 33 |
+
"height": 224,
|
| 34 |
+
"width": 224
|
| 35 |
+
}
|
| 36 |
+
}
|
runs/Jul12_09-58-17_d5ffb3757aea/events.out.tfevents.1720778368.d5ffb3757aea.195.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d1b38c488d13ca2dda4bd1ac303a0ce1fe46fb89480abaa746b7fc7e0ca0339
|
| 3 |
+
size 36601
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 1.6167928713188475e+18,
|
| 4 |
+
"train_loss": 0.04957773063711799,
|
| 5 |
+
"train_runtime": 1223.9715,
|
| 6 |
+
"train_samples_per_second": 17.046,
|
| 7 |
+
"train_steps_per_second": 1.065
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1069 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.0030439873225986958,
|
| 3 |
+
"best_model_checkpoint": "./Tb_Dataset/checkpoint-1000",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1304,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03067484662576687,
|
| 13 |
+
"grad_norm": 1.666305661201477,
|
| 14 |
+
"learning_rate": 0.00019846625766871168,
|
| 15 |
+
"loss": 0.4847,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06134969325153374,
|
| 20 |
+
"grad_norm": 1.4896280765533447,
|
| 21 |
+
"learning_rate": 0.00019693251533742332,
|
| 22 |
+
"loss": 0.278,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09202453987730061,
|
| 27 |
+
"grad_norm": 1.3254238367080688,
|
| 28 |
+
"learning_rate": 0.000195398773006135,
|
| 29 |
+
"loss": 0.2401,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12269938650306748,
|
| 34 |
+
"grad_norm": 1.1399273872375488,
|
| 35 |
+
"learning_rate": 0.00019386503067484663,
|
| 36 |
+
"loss": 0.188,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15337423312883436,
|
| 41 |
+
"grad_norm": 2.320486307144165,
|
| 42 |
+
"learning_rate": 0.0001923312883435583,
|
| 43 |
+
"loss": 0.1944,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18404907975460122,
|
| 48 |
+
"grad_norm": 0.24434129893779755,
|
| 49 |
+
"learning_rate": 0.00019079754601226997,
|
| 50 |
+
"loss": 0.0738,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2147239263803681,
|
| 55 |
+
"grad_norm": 0.7523425221443176,
|
| 56 |
+
"learning_rate": 0.0001892638036809816,
|
| 57 |
+
"loss": 0.171,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24539877300613497,
|
| 62 |
+
"grad_norm": 3.6861462593078613,
|
| 63 |
+
"learning_rate": 0.00018773006134969328,
|
| 64 |
+
"loss": 0.178,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.27607361963190186,
|
| 69 |
+
"grad_norm": 2.111417770385742,
|
| 70 |
+
"learning_rate": 0.00018619631901840492,
|
| 71 |
+
"loss": 0.2488,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3067484662576687,
|
| 76 |
+
"grad_norm": 0.8211548328399658,
|
| 77 |
+
"learning_rate": 0.00018466257668711656,
|
| 78 |
+
"loss": 0.0996,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3067484662576687,
|
| 83 |
+
"eval_accuracy": 0.5625,
|
| 84 |
+
"eval_loss": 1.0429491996765137,
|
| 85 |
+
"eval_runtime": 0.6744,
|
| 86 |
+
"eval_samples_per_second": 23.723,
|
| 87 |
+
"eval_steps_per_second": 2.965,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.3374233128834356,
|
| 92 |
+
"grad_norm": 0.12294389307498932,
|
| 93 |
+
"learning_rate": 0.00018312883435582823,
|
| 94 |
+
"loss": 0.1403,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.36809815950920244,
|
| 99 |
+
"grad_norm": 1.0773956775665283,
|
| 100 |
+
"learning_rate": 0.00018159509202453987,
|
| 101 |
+
"loss": 0.0801,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.3987730061349693,
|
| 106 |
+
"grad_norm": 1.2252161502838135,
|
| 107 |
+
"learning_rate": 0.00018006134969325154,
|
| 108 |
+
"loss": 0.1667,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.4294478527607362,
|
| 113 |
+
"grad_norm": 0.3200875520706177,
|
| 114 |
+
"learning_rate": 0.00017852760736196318,
|
| 115 |
+
"loss": 0.1365,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.4601226993865031,
|
| 120 |
+
"grad_norm": 0.4385143518447876,
|
| 121 |
+
"learning_rate": 0.00017699386503067485,
|
| 122 |
+
"loss": 0.1371,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.49079754601226994,
|
| 127 |
+
"grad_norm": 0.11226026713848114,
|
| 128 |
+
"learning_rate": 0.00017546012269938652,
|
| 129 |
+
"loss": 0.042,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.5214723926380368,
|
| 134 |
+
"grad_norm": 1.9924014806747437,
|
| 135 |
+
"learning_rate": 0.00017392638036809816,
|
| 136 |
+
"loss": 0.1138,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5521472392638037,
|
| 141 |
+
"grad_norm": 2.601227045059204,
|
| 142 |
+
"learning_rate": 0.00017239263803680983,
|
| 143 |
+
"loss": 0.1729,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.5828220858895705,
|
| 148 |
+
"grad_norm": 5.278203964233398,
|
| 149 |
+
"learning_rate": 0.00017085889570552147,
|
| 150 |
+
"loss": 0.1036,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.6134969325153374,
|
| 155 |
+
"grad_norm": 1.20023512840271,
|
| 156 |
+
"learning_rate": 0.00016932515337423314,
|
| 157 |
+
"loss": 0.0481,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.6134969325153374,
|
| 162 |
+
"eval_accuracy": 0.8125,
|
| 163 |
+
"eval_loss": 0.5665359497070312,
|
| 164 |
+
"eval_runtime": 0.4807,
|
| 165 |
+
"eval_samples_per_second": 33.285,
|
| 166 |
+
"eval_steps_per_second": 4.161,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.6441717791411042,
|
| 171 |
+
"grad_norm": 0.7395023107528687,
|
| 172 |
+
"learning_rate": 0.0001677914110429448,
|
| 173 |
+
"loss": 0.1225,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.6748466257668712,
|
| 178 |
+
"grad_norm": 0.05845380574464798,
|
| 179 |
+
"learning_rate": 0.00016625766871165645,
|
| 180 |
+
"loss": 0.1034,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.7055214723926381,
|
| 185 |
+
"grad_norm": 2.7569024562835693,
|
| 186 |
+
"learning_rate": 0.00016472392638036812,
|
| 187 |
+
"loss": 0.0538,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.7361963190184049,
|
| 192 |
+
"grad_norm": 0.06222417205572128,
|
| 193 |
+
"learning_rate": 0.00016319018404907976,
|
| 194 |
+
"loss": 0.0958,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.7668711656441718,
|
| 199 |
+
"grad_norm": 1.9317396879196167,
|
| 200 |
+
"learning_rate": 0.00016165644171779143,
|
| 201 |
+
"loss": 0.09,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.7975460122699386,
|
| 206 |
+
"grad_norm": 3.952806234359741,
|
| 207 |
+
"learning_rate": 0.0001601226993865031,
|
| 208 |
+
"loss": 0.0878,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.8282208588957055,
|
| 213 |
+
"grad_norm": 1.5617386102676392,
|
| 214 |
+
"learning_rate": 0.00015858895705521474,
|
| 215 |
+
"loss": 0.1304,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.8588957055214724,
|
| 220 |
+
"grad_norm": 0.32101425528526306,
|
| 221 |
+
"learning_rate": 0.0001570552147239264,
|
| 222 |
+
"loss": 0.0684,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.8895705521472392,
|
| 227 |
+
"grad_norm": 0.6578021049499512,
|
| 228 |
+
"learning_rate": 0.00015552147239263805,
|
| 229 |
+
"loss": 0.0917,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.9202453987730062,
|
| 234 |
+
"grad_norm": 0.03468528762459755,
|
| 235 |
+
"learning_rate": 0.0001539877300613497,
|
| 236 |
+
"loss": 0.0391,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.9202453987730062,
|
| 241 |
+
"eval_accuracy": 0.6875,
|
| 242 |
+
"eval_loss": 1.0036612749099731,
|
| 243 |
+
"eval_runtime": 0.4639,
|
| 244 |
+
"eval_samples_per_second": 34.488,
|
| 245 |
+
"eval_steps_per_second": 4.311,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.950920245398773,
|
| 250 |
+
"grad_norm": 0.04961508885025978,
|
| 251 |
+
"learning_rate": 0.00015245398773006136,
|
| 252 |
+
"loss": 0.0435,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.9815950920245399,
|
| 257 |
+
"grad_norm": 0.7167016863822937,
|
| 258 |
+
"learning_rate": 0.000150920245398773,
|
| 259 |
+
"loss": 0.0667,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.0122699386503067,
|
| 264 |
+
"grad_norm": 0.3984834551811218,
|
| 265 |
+
"learning_rate": 0.00014938650306748467,
|
| 266 |
+
"loss": 0.1054,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.0429447852760736,
|
| 271 |
+
"grad_norm": 0.09521777182817459,
|
| 272 |
+
"learning_rate": 0.0001478527607361963,
|
| 273 |
+
"loss": 0.0565,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.0736196319018405,
|
| 278 |
+
"grad_norm": 3.836611032485962,
|
| 279 |
+
"learning_rate": 0.00014631901840490798,
|
| 280 |
+
"loss": 0.0498,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.1042944785276074,
|
| 285 |
+
"grad_norm": 0.6689714789390564,
|
| 286 |
+
"learning_rate": 0.00014478527607361964,
|
| 287 |
+
"loss": 0.0693,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.1349693251533743,
|
| 292 |
+
"grad_norm": 0.42697030305862427,
|
| 293 |
+
"learning_rate": 0.00014325153374233129,
|
| 294 |
+
"loss": 0.1017,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.165644171779141,
|
| 299 |
+
"grad_norm": 0.28322863578796387,
|
| 300 |
+
"learning_rate": 0.00014171779141104295,
|
| 301 |
+
"loss": 0.0072,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.196319018404908,
|
| 306 |
+
"grad_norm": 0.02922147326171398,
|
| 307 |
+
"learning_rate": 0.0001401840490797546,
|
| 308 |
+
"loss": 0.0355,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.2269938650306749,
|
| 313 |
+
"grad_norm": 0.4956642687320709,
|
| 314 |
+
"learning_rate": 0.00013865030674846626,
|
| 315 |
+
"loss": 0.0711,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.2269938650306749,
|
| 320 |
+
"eval_accuracy": 0.875,
|
| 321 |
+
"eval_loss": 0.5200170874595642,
|
| 322 |
+
"eval_runtime": 0.4602,
|
| 323 |
+
"eval_samples_per_second": 34.769,
|
| 324 |
+
"eval_steps_per_second": 4.346,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.2576687116564418,
|
| 329 |
+
"grad_norm": 0.35631048679351807,
|
| 330 |
+
"learning_rate": 0.00013711656441717793,
|
| 331 |
+
"loss": 0.018,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2883435582822087,
|
| 336 |
+
"grad_norm": 0.053142815828323364,
|
| 337 |
+
"learning_rate": 0.00013558282208588957,
|
| 338 |
+
"loss": 0.0114,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.3190184049079754,
|
| 343 |
+
"grad_norm": 3.590878963470459,
|
| 344 |
+
"learning_rate": 0.00013404907975460124,
|
| 345 |
+
"loss": 0.0385,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.3496932515337423,
|
| 350 |
+
"grad_norm": 0.0230648685246706,
|
| 351 |
+
"learning_rate": 0.00013251533742331288,
|
| 352 |
+
"loss": 0.0333,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.3803680981595092,
|
| 357 |
+
"grad_norm": 3.86190128326416,
|
| 358 |
+
"learning_rate": 0.00013098159509202455,
|
| 359 |
+
"loss": 0.0393,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.4110429447852761,
|
| 364 |
+
"grad_norm": 0.9012386798858643,
|
| 365 |
+
"learning_rate": 0.00012944785276073622,
|
| 366 |
+
"loss": 0.0571,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.441717791411043,
|
| 371 |
+
"grad_norm": 0.07151665538549423,
|
| 372 |
+
"learning_rate": 0.00012791411042944786,
|
| 373 |
+
"loss": 0.0104,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.4723926380368098,
|
| 378 |
+
"grad_norm": 0.783393919467926,
|
| 379 |
+
"learning_rate": 0.00012638036809815953,
|
| 380 |
+
"loss": 0.101,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.5030674846625767,
|
| 385 |
+
"grad_norm": 0.11429934948682785,
|
| 386 |
+
"learning_rate": 0.00012484662576687117,
|
| 387 |
+
"loss": 0.0861,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.5337423312883436,
|
| 392 |
+
"grad_norm": 0.22566761076450348,
|
| 393 |
+
"learning_rate": 0.00012331288343558281,
|
| 394 |
+
"loss": 0.0258,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.5337423312883436,
|
| 399 |
+
"eval_accuracy": 0.9375,
|
| 400 |
+
"eval_loss": 0.38183438777923584,
|
| 401 |
+
"eval_runtime": 0.6415,
|
| 402 |
+
"eval_samples_per_second": 24.943,
|
| 403 |
+
"eval_steps_per_second": 3.118,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.5644171779141103,
|
| 408 |
+
"grad_norm": 0.0231198500841856,
|
| 409 |
+
"learning_rate": 0.0001217791411042945,
|
| 410 |
+
"loss": 0.0112,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.5950920245398774,
|
| 415 |
+
"grad_norm": 0.07680622488260269,
|
| 416 |
+
"learning_rate": 0.00012024539877300614,
|
| 417 |
+
"loss": 0.0332,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.6257668711656441,
|
| 422 |
+
"grad_norm": 4.2723798751831055,
|
| 423 |
+
"learning_rate": 0.0001187116564417178,
|
| 424 |
+
"loss": 0.0615,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.656441717791411,
|
| 429 |
+
"grad_norm": 0.020270884037017822,
|
| 430 |
+
"learning_rate": 0.00011717791411042945,
|
| 431 |
+
"loss": 0.0025,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.687116564417178,
|
| 436 |
+
"grad_norm": 0.017487134784460068,
|
| 437 |
+
"learning_rate": 0.0001156441717791411,
|
| 438 |
+
"loss": 0.0032,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.7177914110429446,
|
| 443 |
+
"grad_norm": 3.106546401977539,
|
| 444 |
+
"learning_rate": 0.00011411042944785277,
|
| 445 |
+
"loss": 0.0776,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.7484662576687118,
|
| 450 |
+
"grad_norm": 0.2955380380153656,
|
| 451 |
+
"learning_rate": 0.00011257668711656441,
|
| 452 |
+
"loss": 0.046,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.7791411042944785,
|
| 457 |
+
"grad_norm": 0.03838299587368965,
|
| 458 |
+
"learning_rate": 0.00011104294478527608,
|
| 459 |
+
"loss": 0.0039,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.8098159509202454,
|
| 464 |
+
"grad_norm": 0.02066592499613762,
|
| 465 |
+
"learning_rate": 0.00010950920245398772,
|
| 466 |
+
"loss": 0.0411,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.8404907975460123,
|
| 471 |
+
"grad_norm": 0.029740285128355026,
|
| 472 |
+
"learning_rate": 0.00010797546012269939,
|
| 473 |
+
"loss": 0.0547,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.8404907975460123,
|
| 478 |
+
"eval_accuracy": 0.9375,
|
| 479 |
+
"eval_loss": 0.3414860665798187,
|
| 480 |
+
"eval_runtime": 0.6402,
|
| 481 |
+
"eval_samples_per_second": 24.991,
|
| 482 |
+
"eval_steps_per_second": 3.124,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.871165644171779,
|
| 487 |
+
"grad_norm": 0.06896264851093292,
|
| 488 |
+
"learning_rate": 0.00010644171779141106,
|
| 489 |
+
"loss": 0.0412,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.9018404907975461,
|
| 494 |
+
"grad_norm": 0.17898960411548615,
|
| 495 |
+
"learning_rate": 0.0001049079754601227,
|
| 496 |
+
"loss": 0.0059,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.9325153374233128,
|
| 501 |
+
"grad_norm": 0.02462293580174446,
|
| 502 |
+
"learning_rate": 0.00010337423312883437,
|
| 503 |
+
"loss": 0.0334,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.9631901840490797,
|
| 508 |
+
"grad_norm": 0.15255212783813477,
|
| 509 |
+
"learning_rate": 0.00010184049079754601,
|
| 510 |
+
"loss": 0.0484,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.9938650306748467,
|
| 515 |
+
"grad_norm": 1.2095363140106201,
|
| 516 |
+
"learning_rate": 0.00010030674846625767,
|
| 517 |
+
"loss": 0.0409,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.0245398773006134,
|
| 522 |
+
"grad_norm": 0.05067542567849159,
|
| 523 |
+
"learning_rate": 9.877300613496932e-05,
|
| 524 |
+
"loss": 0.0239,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.0552147239263805,
|
| 529 |
+
"grad_norm": 0.048488594591617584,
|
| 530 |
+
"learning_rate": 9.723926380368099e-05,
|
| 531 |
+
"loss": 0.0092,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.085889570552147,
|
| 536 |
+
"grad_norm": 0.06358503550291061,
|
| 537 |
+
"learning_rate": 9.570552147239264e-05,
|
| 538 |
+
"loss": 0.0284,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.116564417177914,
|
| 543 |
+
"grad_norm": 0.02291274443268776,
|
| 544 |
+
"learning_rate": 9.41717791411043e-05,
|
| 545 |
+
"loss": 0.0312,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.147239263803681,
|
| 550 |
+
"grad_norm": 0.01959369145333767,
|
| 551 |
+
"learning_rate": 9.263803680981595e-05,
|
| 552 |
+
"loss": 0.0029,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 2.147239263803681,
|
| 557 |
+
"eval_accuracy": 0.9375,
|
| 558 |
+
"eval_loss": 0.06373238563537598,
|
| 559 |
+
"eval_runtime": 1.4073,
|
| 560 |
+
"eval_samples_per_second": 11.369,
|
| 561 |
+
"eval_steps_per_second": 1.421,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.1779141104294477,
|
| 566 |
+
"grad_norm": 0.015473265200853348,
|
| 567 |
+
"learning_rate": 9.110429447852761e-05,
|
| 568 |
+
"loss": 0.0052,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.208588957055215,
|
| 573 |
+
"grad_norm": 6.127484321594238,
|
| 574 |
+
"learning_rate": 8.957055214723928e-05,
|
| 575 |
+
"loss": 0.0215,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.2392638036809815,
|
| 580 |
+
"grad_norm": 0.014825492165982723,
|
| 581 |
+
"learning_rate": 8.803680981595093e-05,
|
| 582 |
+
"loss": 0.0051,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 2.2699386503067487,
|
| 587 |
+
"grad_norm": 0.09054987877607346,
|
| 588 |
+
"learning_rate": 8.650306748466259e-05,
|
| 589 |
+
"loss": 0.0089,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.3006134969325154,
|
| 594 |
+
"grad_norm": 0.012495328672230244,
|
| 595 |
+
"learning_rate": 8.496932515337423e-05,
|
| 596 |
+
"loss": 0.0035,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.331288343558282,
|
| 601 |
+
"grad_norm": 0.012604707852005959,
|
| 602 |
+
"learning_rate": 8.343558282208588e-05,
|
| 603 |
+
"loss": 0.0046,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.361963190184049,
|
| 608 |
+
"grad_norm": 0.012834266759455204,
|
| 609 |
+
"learning_rate": 8.190184049079755e-05,
|
| 610 |
+
"loss": 0.0685,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.392638036809816,
|
| 615 |
+
"grad_norm": 1.8484301567077637,
|
| 616 |
+
"learning_rate": 8.036809815950921e-05,
|
| 617 |
+
"loss": 0.0058,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.4233128834355826,
|
| 622 |
+
"grad_norm": 0.01303753349930048,
|
| 623 |
+
"learning_rate": 7.883435582822086e-05,
|
| 624 |
+
"loss": 0.0201,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 2.4539877300613497,
|
| 629 |
+
"grad_norm": 0.011059868149459362,
|
| 630 |
+
"learning_rate": 7.730061349693252e-05,
|
| 631 |
+
"loss": 0.0543,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.4539877300613497,
|
| 636 |
+
"eval_accuracy": 0.8125,
|
| 637 |
+
"eval_loss": 0.7362374067306519,
|
| 638 |
+
"eval_runtime": 0.6252,
|
| 639 |
+
"eval_samples_per_second": 25.594,
|
| 640 |
+
"eval_steps_per_second": 3.199,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.4846625766871164,
|
| 645 |
+
"grad_norm": 0.013651982881128788,
|
| 646 |
+
"learning_rate": 7.576687116564417e-05,
|
| 647 |
+
"loss": 0.0023,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.5153374233128836,
|
| 652 |
+
"grad_norm": 0.013891194015741348,
|
| 653 |
+
"learning_rate": 7.423312883435584e-05,
|
| 654 |
+
"loss": 0.0035,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.5460122699386503,
|
| 659 |
+
"grad_norm": 0.022767823189496994,
|
| 660 |
+
"learning_rate": 7.26993865030675e-05,
|
| 661 |
+
"loss": 0.0023,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.5766871165644174,
|
| 666 |
+
"grad_norm": 0.01230280939489603,
|
| 667 |
+
"learning_rate": 7.116564417177914e-05,
|
| 668 |
+
"loss": 0.0163,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.607361963190184,
|
| 673 |
+
"grad_norm": 0.01010560616850853,
|
| 674 |
+
"learning_rate": 6.963190184049079e-05,
|
| 675 |
+
"loss": 0.0016,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.638036809815951,
|
| 680 |
+
"grad_norm": 0.010164570063352585,
|
| 681 |
+
"learning_rate": 6.809815950920245e-05,
|
| 682 |
+
"loss": 0.0287,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.668711656441718,
|
| 687 |
+
"grad_norm": 0.010293642990291119,
|
| 688 |
+
"learning_rate": 6.656441717791412e-05,
|
| 689 |
+
"loss": 0.0307,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.6993865030674846,
|
| 694 |
+
"grad_norm": 0.01078992523252964,
|
| 695 |
+
"learning_rate": 6.503067484662577e-05,
|
| 696 |
+
"loss": 0.0106,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.7300613496932513,
|
| 701 |
+
"grad_norm": 0.01032053492963314,
|
| 702 |
+
"learning_rate": 6.349693251533743e-05,
|
| 703 |
+
"loss": 0.0014,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.7607361963190185,
|
| 708 |
+
"grad_norm": 0.009690840728580952,
|
| 709 |
+
"learning_rate": 6.196319018404908e-05,
|
| 710 |
+
"loss": 0.0265,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.7607361963190185,
|
| 715 |
+
"eval_accuracy": 0.75,
|
| 716 |
+
"eval_loss": 1.0916930437088013,
|
| 717 |
+
"eval_runtime": 0.4595,
|
| 718 |
+
"eval_samples_per_second": 34.82,
|
| 719 |
+
"eval_steps_per_second": 4.352,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.791411042944785,
|
| 724 |
+
"grad_norm": 0.014224858023226261,
|
| 725 |
+
"learning_rate": 6.0429447852760736e-05,
|
| 726 |
+
"loss": 0.0622,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 2.8220858895705523,
|
| 731 |
+
"grad_norm": 0.013891954906284809,
|
| 732 |
+
"learning_rate": 5.88957055214724e-05,
|
| 733 |
+
"loss": 0.0153,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.852760736196319,
|
| 738 |
+
"grad_norm": 0.0167331974953413,
|
| 739 |
+
"learning_rate": 5.736196319018405e-05,
|
| 740 |
+
"loss": 0.0026,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.883435582822086,
|
| 745 |
+
"grad_norm": 0.03341999277472496,
|
| 746 |
+
"learning_rate": 5.582822085889571e-05,
|
| 747 |
+
"loss": 0.0119,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.914110429447853,
|
| 752 |
+
"grad_norm": 0.012064835987985134,
|
| 753 |
+
"learning_rate": 5.429447852760736e-05,
|
| 754 |
+
"loss": 0.0149,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 2.9447852760736195,
|
| 759 |
+
"grad_norm": 0.012997813522815704,
|
| 760 |
+
"learning_rate": 5.276073619631902e-05,
|
| 761 |
+
"loss": 0.0034,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.9754601226993866,
|
| 766 |
+
"grad_norm": 0.014833126217126846,
|
| 767 |
+
"learning_rate": 5.122699386503068e-05,
|
| 768 |
+
"loss": 0.0209,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 3.0061349693251533,
|
| 773 |
+
"grad_norm": 0.010445049963891506,
|
| 774 |
+
"learning_rate": 4.9693251533742335e-05,
|
| 775 |
+
"loss": 0.0434,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 3.03680981595092,
|
| 780 |
+
"grad_norm": 0.012170241214334965,
|
| 781 |
+
"learning_rate": 4.815950920245399e-05,
|
| 782 |
+
"loss": 0.0058,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 3.067484662576687,
|
| 787 |
+
"grad_norm": 0.010554679669439793,
|
| 788 |
+
"learning_rate": 4.6625766871165645e-05,
|
| 789 |
+
"loss": 0.0017,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 3.067484662576687,
|
| 794 |
+
"eval_accuracy": 1.0,
|
| 795 |
+
"eval_loss": 0.0030439873225986958,
|
| 796 |
+
"eval_runtime": 0.4699,
|
| 797 |
+
"eval_samples_per_second": 34.049,
|
| 798 |
+
"eval_steps_per_second": 4.256,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 3.098159509202454,
|
| 803 |
+
"grad_norm": 0.010963929817080498,
|
| 804 |
+
"learning_rate": 4.5092024539877307e-05,
|
| 805 |
+
"loss": 0.0241,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.128834355828221,
|
| 810 |
+
"grad_norm": 0.010549047961831093,
|
| 811 |
+
"learning_rate": 4.3558282208588955e-05,
|
| 812 |
+
"loss": 0.0015,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 3.1595092024539877,
|
| 817 |
+
"grad_norm": 0.012895047664642334,
|
| 818 |
+
"learning_rate": 4.2024539877300617e-05,
|
| 819 |
+
"loss": 0.0021,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 3.190184049079755,
|
| 824 |
+
"grad_norm": 0.009695703163743019,
|
| 825 |
+
"learning_rate": 4.049079754601227e-05,
|
| 826 |
+
"loss": 0.0013,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 3.2208588957055215,
|
| 831 |
+
"grad_norm": 0.01083831675350666,
|
| 832 |
+
"learning_rate": 3.895705521472393e-05,
|
| 833 |
+
"loss": 0.0018,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.2515337423312882,
|
| 838 |
+
"grad_norm": 0.030923034995794296,
|
| 839 |
+
"learning_rate": 3.742331288343559e-05,
|
| 840 |
+
"loss": 0.0012,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 3.2822085889570554,
|
| 845 |
+
"grad_norm": 0.009053406305611134,
|
| 846 |
+
"learning_rate": 3.5889570552147236e-05,
|
| 847 |
+
"loss": 0.0011,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.312883435582822,
|
| 852 |
+
"grad_norm": 0.009371621534228325,
|
| 853 |
+
"learning_rate": 3.43558282208589e-05,
|
| 854 |
+
"loss": 0.0011,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 3.3435582822085887,
|
| 859 |
+
"grad_norm": 0.009119446389377117,
|
| 860 |
+
"learning_rate": 3.282208588957055e-05,
|
| 861 |
+
"loss": 0.0011,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 3.374233128834356,
|
| 866 |
+
"grad_norm": 0.009182000532746315,
|
| 867 |
+
"learning_rate": 3.1288343558282215e-05,
|
| 868 |
+
"loss": 0.0054,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 3.374233128834356,
|
| 873 |
+
"eval_accuracy": 1.0,
|
| 874 |
+
"eval_loss": 0.036368854343891144,
|
| 875 |
+
"eval_runtime": 0.4537,
|
| 876 |
+
"eval_samples_per_second": 35.267,
|
| 877 |
+
"eval_steps_per_second": 4.408,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.4049079754601226,
|
| 882 |
+
"grad_norm": 0.00895740371197462,
|
| 883 |
+
"learning_rate": 2.9754601226993867e-05,
|
| 884 |
+
"loss": 0.0017,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 3.4355828220858897,
|
| 889 |
+
"grad_norm": 0.20501597225666046,
|
| 890 |
+
"learning_rate": 2.822085889570552e-05,
|
| 891 |
+
"loss": 0.0013,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 3.4662576687116564,
|
| 896 |
+
"grad_norm": 0.009406461380422115,
|
| 897 |
+
"learning_rate": 2.668711656441718e-05,
|
| 898 |
+
"loss": 0.0011,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.4969325153374236,
|
| 903 |
+
"grad_norm": 0.009192903526127338,
|
| 904 |
+
"learning_rate": 2.5153374233128835e-05,
|
| 905 |
+
"loss": 0.0012,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 3.5276073619631902,
|
| 910 |
+
"grad_norm": 0.009342888370156288,
|
| 911 |
+
"learning_rate": 2.361963190184049e-05,
|
| 912 |
+
"loss": 0.0362,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 3.558282208588957,
|
| 917 |
+
"grad_norm": 0.01002499833703041,
|
| 918 |
+
"learning_rate": 2.208588957055215e-05,
|
| 919 |
+
"loss": 0.0011,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.588957055214724,
|
| 924 |
+
"grad_norm": 0.01044855359941721,
|
| 925 |
+
"learning_rate": 2.0552147239263807e-05,
|
| 926 |
+
"loss": 0.0011,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 3.6196319018404908,
|
| 931 |
+
"grad_norm": 0.030983537435531616,
|
| 932 |
+
"learning_rate": 1.9018404907975462e-05,
|
| 933 |
+
"loss": 0.0011,
|
| 934 |
+
"step": 1180
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 3.6503067484662575,
|
| 938 |
+
"grad_norm": 0.009104466997087002,
|
| 939 |
+
"learning_rate": 1.7484662576687117e-05,
|
| 940 |
+
"loss": 0.0012,
|
| 941 |
+
"step": 1190
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 3.6809815950920246,
|
| 945 |
+
"grad_norm": 0.009420313872396946,
|
| 946 |
+
"learning_rate": 1.5950920245398772e-05,
|
| 947 |
+
"loss": 0.0234,
|
| 948 |
+
"step": 1200
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.6809815950920246,
|
| 952 |
+
"eval_accuracy": 0.875,
|
| 953 |
+
"eval_loss": 0.23103433847427368,
|
| 954 |
+
"eval_runtime": 0.4704,
|
| 955 |
+
"eval_samples_per_second": 34.012,
|
| 956 |
+
"eval_steps_per_second": 4.252,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 3.7116564417177913,
|
| 961 |
+
"grad_norm": 0.00850239023566246,
|
| 962 |
+
"learning_rate": 1.441717791411043e-05,
|
| 963 |
+
"loss": 0.001,
|
| 964 |
+
"step": 1210
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 3.7423312883435584,
|
| 968 |
+
"grad_norm": 0.008601406589150429,
|
| 969 |
+
"learning_rate": 1.2883435582822087e-05,
|
| 970 |
+
"loss": 0.0013,
|
| 971 |
+
"step": 1220
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.773006134969325,
|
| 975 |
+
"grad_norm": 0.011089220643043518,
|
| 976 |
+
"learning_rate": 1.1349693251533742e-05,
|
| 977 |
+
"loss": 0.0011,
|
| 978 |
+
"step": 1230
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 3.8036809815950923,
|
| 982 |
+
"grad_norm": 0.008406179025769234,
|
| 983 |
+
"learning_rate": 9.8159509202454e-06,
|
| 984 |
+
"loss": 0.001,
|
| 985 |
+
"step": 1240
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.834355828220859,
|
| 989 |
+
"grad_norm": 0.009516136720776558,
|
| 990 |
+
"learning_rate": 8.282208588957055e-06,
|
| 991 |
+
"loss": 0.0012,
|
| 992 |
+
"step": 1250
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.8650306748466257,
|
| 996 |
+
"grad_norm": 0.011050822213292122,
|
| 997 |
+
"learning_rate": 6.748466257668712e-06,
|
| 998 |
+
"loss": 0.0012,
|
| 999 |
+
"step": 1260
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 3.895705521472393,
|
| 1003 |
+
"grad_norm": 0.008980349637567997,
|
| 1004 |
+
"learning_rate": 5.214723926380368e-06,
|
| 1005 |
+
"loss": 0.0012,
|
| 1006 |
+
"step": 1270
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 3.9263803680981595,
|
| 1010 |
+
"grad_norm": 0.00903311651200056,
|
| 1011 |
+
"learning_rate": 3.680981595092025e-06,
|
| 1012 |
+
"loss": 0.0014,
|
| 1013 |
+
"step": 1280
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.957055214723926,
|
| 1017 |
+
"grad_norm": 0.00838613323867321,
|
| 1018 |
+
"learning_rate": 2.147239263803681e-06,
|
| 1019 |
+
"loss": 0.0253,
|
| 1020 |
+
"step": 1290
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 3.9877300613496933,
|
| 1024 |
+
"grad_norm": 0.008292277343571186,
|
| 1025 |
+
"learning_rate": 6.134969325153375e-07,
|
| 1026 |
+
"loss": 0.0076,
|
| 1027 |
+
"step": 1300
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 3.9877300613496933,
|
| 1031 |
+
"eval_accuracy": 0.875,
|
| 1032 |
+
"eval_loss": 0.40373101830482483,
|
| 1033 |
+
"eval_runtime": 0.4908,
|
| 1034 |
+
"eval_samples_per_second": 32.599,
|
| 1035 |
+
"eval_steps_per_second": 4.075,
|
| 1036 |
+
"step": 1300
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 4.0,
|
| 1040 |
+
"step": 1304,
|
| 1041 |
+
"total_flos": 1.6167928713188475e+18,
|
| 1042 |
+
"train_loss": 0.04957773063711799,
|
| 1043 |
+
"train_runtime": 1223.9715,
|
| 1044 |
+
"train_samples_per_second": 17.046,
|
| 1045 |
+
"train_steps_per_second": 1.065
|
| 1046 |
+
}
|
| 1047 |
+
],
|
| 1048 |
+
"logging_steps": 10,
|
| 1049 |
+
"max_steps": 1304,
|
| 1050 |
+
"num_input_tokens_seen": 0,
|
| 1051 |
+
"num_train_epochs": 4,
|
| 1052 |
+
"save_steps": 100,
|
| 1053 |
+
"stateful_callbacks": {
|
| 1054 |
+
"TrainerControl": {
|
| 1055 |
+
"args": {
|
| 1056 |
+
"should_epoch_stop": false,
|
| 1057 |
+
"should_evaluate": false,
|
| 1058 |
+
"should_log": false,
|
| 1059 |
+
"should_save": true,
|
| 1060 |
+
"should_training_stop": false
|
| 1061 |
+
},
|
| 1062 |
+
"attributes": {}
|
| 1063 |
+
}
|
| 1064 |
+
},
|
| 1065 |
+
"total_flos": 1.6167928713188475e+18,
|
| 1066 |
+
"train_batch_size": 16,
|
| 1067 |
+
"trial_name": null,
|
| 1068 |
+
"trial_params": null
|
| 1069 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e1265e8e0fae3dd397db275a1e4bc01e7818b66ee6cc859974880cd008cab48
|
| 3 |
+
size 5112
|