Training in progress, epoch 1
Browse files- README.md +76 -0
- all_results.json +12 -0
- config.json +0 -0
- eval_results.json +8 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- train_results.json +7 -0
- trainer_state.json +1105 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swinv2-base-patch4-window12-192-22k
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- vision
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
metrics:
|
| 9 |
+
- accuracy
|
| 10 |
+
model-index:
|
| 11 |
+
- name: SWIN_finetuned_frozen_v4
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# SWIN_finetuned_frozen_v4
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-base-patch4-window12-192-22k) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 2.0700
|
| 23 |
+
- Accuracy: 0.7085
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0001
|
| 43 |
+
- train_batch_size: 128
|
| 44 |
+
- eval_batch_size: 128
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 15.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:--------:|:---------------:|
|
| 54 |
+
| 1.3057 | 1.0 | 5249 | 0.5822 | 2.0464 |
|
| 55 |
+
| 1.1387 | 2.0 | 10498 | 0.6084 | 1.9457 |
|
| 56 |
+
| 0.988 | 3.0 | 15747 | 0.6124 | 1.9650 |
|
| 57 |
+
| 0.8653 | 4.0 | 20996 | 0.6344 | 1.9381 |
|
| 58 |
+
| 0.7662 | 5.0 | 26245 | 0.6335 | 1.9391 |
|
| 59 |
+
| 0.6882 | 6.0 | 31494 | 0.6444 | 1.9591 |
|
| 60 |
+
| 0.601 | 7.0 | 36743 | 0.6510 | 1.9506 |
|
| 61 |
+
| 0.5363 | 8.0 | 41992 | 0.6617 | 1.9556 |
|
| 62 |
+
| 0.4871 | 9.0 | 47241 | 0.6741 | 1.9037 |
|
| 63 |
+
| 0.4338 | 10.0 | 52490 | 0.6806 | 1.9794 |
|
| 64 |
+
| 0.3738 | 11.0 | 57739 | 0.6849 | 2.0053 |
|
| 65 |
+
| 0.3338 | 12.0 | 62988 | 0.6955 | 2.0140 |
|
| 66 |
+
| 0.2989 | 13.0 | 68237 | 0.6974 | 2.0830 |
|
| 67 |
+
| 0.267 | 14.0 | 73486 | 0.7041 | 2.0824 |
|
| 68 |
+
| 0.236 | 15.0 | 78735 | 0.7085 | 2.0700 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.33.3
|
| 74 |
+
- Pytorch 2.1.2
|
| 75 |
+
- Datasets 2.16.1
|
| 76 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.708475484504778,
|
| 4 |
+
"eval_loss": 2.0700302124023438,
|
| 5 |
+
"eval_runtime": 2917.685,
|
| 6 |
+
"eval_samples_per_second": 57.564,
|
| 7 |
+
"eval_steps_per_second": 0.45,
|
| 8 |
+
"train_loss": 0.0,
|
| 9 |
+
"train_runtime": 39.8476,
|
| 10 |
+
"train_samples_per_second": 252894.596,
|
| 11 |
+
"train_steps_per_second": 1975.901
|
| 12 |
+
}
|
config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.708475484504778,
|
| 4 |
+
"eval_loss": 2.0700302124023438,
|
| 5 |
+
"eval_runtime": 2917.685,
|
| 6 |
+
"eval_samples_per_second": 57.564,
|
| 7 |
+
"eval_steps_per_second": 0.45
|
| 8 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.485,
|
| 7 |
+
0.456,
|
| 8 |
+
0.406
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"resample": 3,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 192,
|
| 20 |
+
"width": 192
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4b48098f453c5268b23dcef0ffbf1ecea4f9b5f4c0acb1800a4df0628bd0ab9
|
| 3 |
+
size 411298414
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"train_loss": 0.0,
|
| 4 |
+
"train_runtime": 39.8476,
|
| 5 |
+
"train_samples_per_second": 252894.596,
|
| 6 |
+
"train_steps_per_second": 1975.901
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 78735,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1,
|
| 13 |
+
"learning_rate": 0.0009936495840477551,
|
| 14 |
+
"loss": 1.2096,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.19,
|
| 19 |
+
"learning_rate": 0.0009872991680955102,
|
| 20 |
+
"loss": 1.2958,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.29,
|
| 25 |
+
"learning_rate": 0.0009809487521432654,
|
| 26 |
+
"loss": 1.3278,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.38,
|
| 31 |
+
"learning_rate": 0.0009745983361910206,
|
| 32 |
+
"loss": 1.3214,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.48,
|
| 37 |
+
"learning_rate": 0.0009682479202387756,
|
| 38 |
+
"loss": 1.3299,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.57,
|
| 43 |
+
"learning_rate": 0.0009618975042865308,
|
| 44 |
+
"loss": 1.3244,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.67,
|
| 49 |
+
"learning_rate": 0.0009555470883342859,
|
| 50 |
+
"loss": 1.3279,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.76,
|
| 55 |
+
"learning_rate": 0.000949196672382041,
|
| 56 |
+
"loss": 1.3269,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.86,
|
| 61 |
+
"learning_rate": 0.0009428462564297961,
|
| 62 |
+
"loss": 1.3179,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.95,
|
| 67 |
+
"learning_rate": 0.0009364958404775514,
|
| 68 |
+
"loss": 1.3057,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.0,
|
| 73 |
+
"eval_accuracy": 0.58219165847995,
|
| 74 |
+
"eval_loss": 2.046381950378418,
|
| 75 |
+
"eval_runtime": 1873.4069,
|
| 76 |
+
"eval_samples_per_second": 89.652,
|
| 77 |
+
"eval_steps_per_second": 0.701,
|
| 78 |
+
"step": 5249
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.05,
|
| 82 |
+
"learning_rate": 0.0009301454245253064,
|
| 83 |
+
"loss": 1.1726,
|
| 84 |
+
"step": 5500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.14,
|
| 88 |
+
"learning_rate": 0.0009237950085730616,
|
| 89 |
+
"loss": 1.0732,
|
| 90 |
+
"step": 6000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.24,
|
| 94 |
+
"learning_rate": 0.0009174445926208167,
|
| 95 |
+
"loss": 1.0922,
|
| 96 |
+
"step": 6500
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.33,
|
| 100 |
+
"learning_rate": 0.0009110941766685719,
|
| 101 |
+
"loss": 1.1075,
|
| 102 |
+
"step": 7000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.43,
|
| 106 |
+
"learning_rate": 0.0009047437607163269,
|
| 107 |
+
"loss": 1.112,
|
| 108 |
+
"step": 7500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.52,
|
| 112 |
+
"learning_rate": 0.0008983933447640821,
|
| 113 |
+
"loss": 1.1417,
|
| 114 |
+
"step": 8000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.62,
|
| 118 |
+
"learning_rate": 0.0008920429288118372,
|
| 119 |
+
"loss": 1.1343,
|
| 120 |
+
"step": 8500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.71,
|
| 124 |
+
"learning_rate": 0.0008856925128595922,
|
| 125 |
+
"loss": 1.1319,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.81,
|
| 130 |
+
"learning_rate": 0.0008793420969073475,
|
| 131 |
+
"loss": 1.1326,
|
| 132 |
+
"step": 9500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.91,
|
| 136 |
+
"learning_rate": 0.0008729916809551026,
|
| 137 |
+
"loss": 1.1387,
|
| 138 |
+
"step": 10000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.0,
|
| 142 |
+
"eval_accuracy": 0.6084486916138251,
|
| 143 |
+
"eval_loss": 1.9456982612609863,
|
| 144 |
+
"eval_runtime": 4861.9841,
|
| 145 |
+
"eval_samples_per_second": 34.545,
|
| 146 |
+
"eval_steps_per_second": 0.27,
|
| 147 |
+
"step": 10498
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.0,
|
| 151 |
+
"learning_rate": 0.0008666412650028577,
|
| 152 |
+
"loss": 1.124,
|
| 153 |
+
"step": 10500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.1,
|
| 157 |
+
"learning_rate": 0.0008602908490506128,
|
| 158 |
+
"loss": 0.9,
|
| 159 |
+
"step": 11000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.19,
|
| 163 |
+
"learning_rate": 0.000853940433098368,
|
| 164 |
+
"loss": 0.9401,
|
| 165 |
+
"step": 11500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.29,
|
| 169 |
+
"learning_rate": 0.000847590017146123,
|
| 170 |
+
"loss": 0.967,
|
| 171 |
+
"step": 12000
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.38,
|
| 175 |
+
"learning_rate": 0.0008412396011938782,
|
| 176 |
+
"loss": 0.9734,
|
| 177 |
+
"step": 12500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.48,
|
| 181 |
+
"learning_rate": 0.0008348891852416333,
|
| 182 |
+
"loss": 0.9657,
|
| 183 |
+
"step": 13000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.57,
|
| 187 |
+
"learning_rate": 0.0008285387692893885,
|
| 188 |
+
"loss": 0.9883,
|
| 189 |
+
"step": 13500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.67,
|
| 193 |
+
"learning_rate": 0.0008221883533371436,
|
| 194 |
+
"loss": 0.9781,
|
| 195 |
+
"step": 14000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.76,
|
| 199 |
+
"learning_rate": 0.0008158379373848988,
|
| 200 |
+
"loss": 0.9822,
|
| 201 |
+
"step": 14500
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.86,
|
| 205 |
+
"learning_rate": 0.0008094875214326538,
|
| 206 |
+
"loss": 0.992,
|
| 207 |
+
"step": 15000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.95,
|
| 211 |
+
"learning_rate": 0.000803137105480409,
|
| 212 |
+
"loss": 0.988,
|
| 213 |
+
"step": 15500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 3.0,
|
| 217 |
+
"eval_accuracy": 0.6124319014021613,
|
| 218 |
+
"eval_loss": 1.965035319328308,
|
| 219 |
+
"eval_runtime": 4587.2857,
|
| 220 |
+
"eval_samples_per_second": 36.613,
|
| 221 |
+
"eval_steps_per_second": 0.286,
|
| 222 |
+
"step": 15747
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.05,
|
| 226 |
+
"learning_rate": 0.0007967866895281641,
|
| 227 |
+
"loss": 0.8822,
|
| 228 |
+
"step": 16000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.14,
|
| 232 |
+
"learning_rate": 0.0007904362735759192,
|
| 233 |
+
"loss": 0.8149,
|
| 234 |
+
"step": 16500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.24,
|
| 238 |
+
"learning_rate": 0.0007840858576236743,
|
| 239 |
+
"loss": 0.8325,
|
| 240 |
+
"step": 17000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.33,
|
| 244 |
+
"learning_rate": 0.0007777354416714295,
|
| 245 |
+
"loss": 0.8412,
|
| 246 |
+
"step": 17500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.43,
|
| 250 |
+
"learning_rate": 0.0007713850257191847,
|
| 251 |
+
"loss": 0.8421,
|
| 252 |
+
"step": 18000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.52,
|
| 256 |
+
"learning_rate": 0.0007650346097669397,
|
| 257 |
+
"loss": 0.8487,
|
| 258 |
+
"step": 18500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.62,
|
| 262 |
+
"learning_rate": 0.0007586841938146949,
|
| 263 |
+
"loss": 0.855,
|
| 264 |
+
"step": 19000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.71,
|
| 268 |
+
"learning_rate": 0.00075233377786245,
|
| 269 |
+
"loss": 0.8623,
|
| 270 |
+
"step": 19500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.81,
|
| 274 |
+
"learning_rate": 0.0007459833619102051,
|
| 275 |
+
"loss": 0.8668,
|
| 276 |
+
"step": 20000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.91,
|
| 280 |
+
"learning_rate": 0.0007396329459579602,
|
| 281 |
+
"loss": 0.8653,
|
| 282 |
+
"step": 20500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 4.0,
|
| 286 |
+
"eval_accuracy": 0.634402071983567,
|
| 287 |
+
"eval_loss": 1.9380866289138794,
|
| 288 |
+
"eval_runtime": 1885.7719,
|
| 289 |
+
"eval_samples_per_second": 89.064,
|
| 290 |
+
"eval_steps_per_second": 0.696,
|
| 291 |
+
"step": 20996
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 4.0,
|
| 295 |
+
"learning_rate": 0.0007332825300057155,
|
| 296 |
+
"loss": 0.864,
|
| 297 |
+
"step": 21000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.1,
|
| 301 |
+
"learning_rate": 0.0007269321140534705,
|
| 302 |
+
"loss": 0.7073,
|
| 303 |
+
"step": 21500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.19,
|
| 307 |
+
"learning_rate": 0.0007205816981012257,
|
| 308 |
+
"loss": 0.7257,
|
| 309 |
+
"step": 22000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 4.29,
|
| 313 |
+
"learning_rate": 0.0007142312821489808,
|
| 314 |
+
"loss": 0.7415,
|
| 315 |
+
"step": 22500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.38,
|
| 319 |
+
"learning_rate": 0.0007078808661967359,
|
| 320 |
+
"loss": 0.7397,
|
| 321 |
+
"step": 23000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.48,
|
| 325 |
+
"learning_rate": 0.000701530450244491,
|
| 326 |
+
"loss": 0.7635,
|
| 327 |
+
"step": 23500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 4.57,
|
| 331 |
+
"learning_rate": 0.0006951800342922462,
|
| 332 |
+
"loss": 0.7736,
|
| 333 |
+
"step": 24000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.67,
|
| 337 |
+
"learning_rate": 0.0006888296183400012,
|
| 338 |
+
"loss": 0.7694,
|
| 339 |
+
"step": 24500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.76,
|
| 343 |
+
"learning_rate": 0.0006824792023877565,
|
| 344 |
+
"loss": 0.759,
|
| 345 |
+
"step": 25000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.86,
|
| 349 |
+
"learning_rate": 0.0006761287864355116,
|
| 350 |
+
"loss": 0.7728,
|
| 351 |
+
"step": 25500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.95,
|
| 355 |
+
"learning_rate": 0.0006697783704832666,
|
| 356 |
+
"loss": 0.7662,
|
| 357 |
+
"step": 26000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 5.0,
|
| 361 |
+
"eval_accuracy": 0.6335327915215385,
|
| 362 |
+
"eval_loss": 1.9391114711761475,
|
| 363 |
+
"eval_runtime": 1717.5004,
|
| 364 |
+
"eval_samples_per_second": 97.79,
|
| 365 |
+
"eval_steps_per_second": 0.764,
|
| 366 |
+
"step": 26245
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.05,
|
| 370 |
+
"learning_rate": 0.0006634279545310218,
|
| 371 |
+
"loss": 0.7034,
|
| 372 |
+
"step": 26500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.14,
|
| 376 |
+
"learning_rate": 0.0006570775385787769,
|
| 377 |
+
"loss": 0.6446,
|
| 378 |
+
"step": 27000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 5.24,
|
| 382 |
+
"learning_rate": 0.000650727122626532,
|
| 383 |
+
"loss": 0.6511,
|
| 384 |
+
"step": 27500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 5.33,
|
| 388 |
+
"learning_rate": 0.0006443767066742871,
|
| 389 |
+
"loss": 0.6562,
|
| 390 |
+
"step": 28000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.43,
|
| 394 |
+
"learning_rate": 0.0006380262907220423,
|
| 395 |
+
"loss": 0.6673,
|
| 396 |
+
"step": 28500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.52,
|
| 400 |
+
"learning_rate": 0.0006316758747697975,
|
| 401 |
+
"loss": 0.6719,
|
| 402 |
+
"step": 29000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.62,
|
| 406 |
+
"learning_rate": 0.0006253254588175526,
|
| 407 |
+
"loss": 0.6818,
|
| 408 |
+
"step": 29500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.72,
|
| 412 |
+
"learning_rate": 0.0006189750428653077,
|
| 413 |
+
"loss": 0.6745,
|
| 414 |
+
"step": 30000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 5.81,
|
| 418 |
+
"learning_rate": 0.0006126246269130629,
|
| 419 |
+
"loss": 0.6778,
|
| 420 |
+
"step": 30500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 5.91,
|
| 424 |
+
"learning_rate": 0.0006062742109608179,
|
| 425 |
+
"loss": 0.6882,
|
| 426 |
+
"step": 31000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 6.0,
|
| 430 |
+
"eval_accuracy": 0.6443749813938258,
|
| 431 |
+
"eval_loss": 1.9590805768966675,
|
| 432 |
+
"eval_runtime": 1673.9405,
|
| 433 |
+
"eval_samples_per_second": 100.335,
|
| 434 |
+
"eval_steps_per_second": 0.784,
|
| 435 |
+
"step": 31494
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 6.0,
|
| 439 |
+
"learning_rate": 0.0005999237950085731,
|
| 440 |
+
"loss": 0.6787,
|
| 441 |
+
"step": 31500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 6.1,
|
| 445 |
+
"learning_rate": 0.0005935733790563282,
|
| 446 |
+
"loss": 0.5613,
|
| 447 |
+
"step": 32000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 6.19,
|
| 451 |
+
"learning_rate": 0.0005872229631040833,
|
| 452 |
+
"loss": 0.5867,
|
| 453 |
+
"step": 32500
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 6.29,
|
| 457 |
+
"learning_rate": 0.0005808725471518384,
|
| 458 |
+
"loss": 0.5839,
|
| 459 |
+
"step": 33000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 6.38,
|
| 463 |
+
"learning_rate": 0.0005745221311995937,
|
| 464 |
+
"loss": 0.588,
|
| 465 |
+
"step": 33500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.48,
|
| 469 |
+
"learning_rate": 0.0005681717152473487,
|
| 470 |
+
"loss": 0.6022,
|
| 471 |
+
"step": 34000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.57,
|
| 475 |
+
"learning_rate": 0.0005618212992951039,
|
| 476 |
+
"loss": 0.596,
|
| 477 |
+
"step": 34500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 6.67,
|
| 481 |
+
"learning_rate": 0.000555470883342859,
|
| 482 |
+
"loss": 0.6072,
|
| 483 |
+
"step": 35000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 6.76,
|
| 487 |
+
"learning_rate": 0.000549120467390614,
|
| 488 |
+
"loss": 0.615,
|
| 489 |
+
"step": 35500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 6.86,
|
| 493 |
+
"learning_rate": 0.0005427700514383692,
|
| 494 |
+
"loss": 0.6103,
|
| 495 |
+
"step": 36000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 6.95,
|
| 499 |
+
"learning_rate": 0.0005364196354861243,
|
| 500 |
+
"loss": 0.601,
|
| 501 |
+
"step": 36500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 7.0,
|
| 505 |
+
"eval_accuracy": 0.6510374802774552,
|
| 506 |
+
"eval_loss": 1.9506298303604126,
|
| 507 |
+
"eval_runtime": 4758.5372,
|
| 508 |
+
"eval_samples_per_second": 35.296,
|
| 509 |
+
"eval_steps_per_second": 0.276,
|
| 510 |
+
"step": 36743
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 7.05,
|
| 514 |
+
"learning_rate": 0.0005300692195338794,
|
| 515 |
+
"loss": 0.5518,
|
| 516 |
+
"step": 37000
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 7.14,
|
| 520 |
+
"learning_rate": 0.0005237188035816346,
|
| 521 |
+
"loss": 0.5144,
|
| 522 |
+
"step": 37500
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 7.24,
|
| 526 |
+
"learning_rate": 0.0005173683876293898,
|
| 527 |
+
"loss": 0.5214,
|
| 528 |
+
"step": 38000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 7.33,
|
| 532 |
+
"learning_rate": 0.0005110179716771448,
|
| 533 |
+
"loss": 0.522,
|
| 534 |
+
"step": 38500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.43,
|
| 538 |
+
"learning_rate": 0.0005046675557249,
|
| 539 |
+
"loss": 0.5331,
|
| 540 |
+
"step": 39000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 7.53,
|
| 544 |
+
"learning_rate": 0.0004983171397726551,
|
| 545 |
+
"loss": 0.5357,
|
| 546 |
+
"step": 39500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 7.62,
|
| 550 |
+
"learning_rate": 0.0004919667238204102,
|
| 551 |
+
"loss": 0.53,
|
| 552 |
+
"step": 40000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 7.72,
|
| 556 |
+
"learning_rate": 0.00048561630786816534,
|
| 557 |
+
"loss": 0.5397,
|
| 558 |
+
"step": 40500
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 7.81,
|
| 562 |
+
"learning_rate": 0.0004792658919159205,
|
| 563 |
+
"loss": 0.5319,
|
| 564 |
+
"step": 41000
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 7.91,
|
| 568 |
+
"learning_rate": 0.0004729154759636756,
|
| 569 |
+
"loss": 0.5363,
|
| 570 |
+
"step": 41500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 8.0,
|
| 574 |
+
"eval_accuracy": 0.6616772349736536,
|
| 575 |
+
"eval_loss": 1.9555561542510986,
|
| 576 |
+
"eval_runtime": 4754.1095,
|
| 577 |
+
"eval_samples_per_second": 35.328,
|
| 578 |
+
"eval_steps_per_second": 0.276,
|
| 579 |
+
"step": 41992
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 8.0,
|
| 583 |
+
"learning_rate": 0.0004665650600114307,
|
| 584 |
+
"loss": 0.3811,
|
| 585 |
+
"step": 42000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 8.1,
|
| 589 |
+
"learning_rate": 0.0004602146440591859,
|
| 590 |
+
"loss": 0.4593,
|
| 591 |
+
"step": 42500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 8.19,
|
| 595 |
+
"learning_rate": 0.000453864228106941,
|
| 596 |
+
"loss": 0.4769,
|
| 597 |
+
"step": 43000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.29,
|
| 601 |
+
"learning_rate": 0.00044751381215469617,
|
| 602 |
+
"loss": 0.4676,
|
| 603 |
+
"step": 43500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 8.38,
|
| 607 |
+
"learning_rate": 0.0004411633962024513,
|
| 608 |
+
"loss": 0.4816,
|
| 609 |
+
"step": 44000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 8.48,
|
| 613 |
+
"learning_rate": 0.0004348129802502064,
|
| 614 |
+
"loss": 0.4765,
|
| 615 |
+
"step": 44500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 8.57,
|
| 619 |
+
"learning_rate": 0.00042846256429796155,
|
| 620 |
+
"loss": 0.4835,
|
| 621 |
+
"step": 45000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 8.67,
|
| 625 |
+
"learning_rate": 0.00042211214834571666,
|
| 626 |
+
"loss": 0.4767,
|
| 627 |
+
"step": 45500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 8.76,
|
| 631 |
+
"learning_rate": 0.0004157617323934718,
|
| 632 |
+
"loss": 0.4877,
|
| 633 |
+
"step": 46000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 8.86,
|
| 637 |
+
"learning_rate": 0.00040941131644122694,
|
| 638 |
+
"loss": 0.4706,
|
| 639 |
+
"step": 46500
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 8.95,
|
| 643 |
+
"learning_rate": 0.00040306090048898205,
|
| 644 |
+
"loss": 0.4871,
|
| 645 |
+
"step": 47000
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 9.0,
|
| 649 |
+
"eval_accuracy": 0.6740853204727457,
|
| 650 |
+
"eval_loss": 1.9037331342697144,
|
| 651 |
+
"eval_runtime": 5063.3946,
|
| 652 |
+
"eval_samples_per_second": 33.17,
|
| 653 |
+
"eval_steps_per_second": 0.259,
|
| 654 |
+
"step": 47241
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 9.05,
|
| 658 |
+
"learning_rate": 0.00039671048453673716,
|
| 659 |
+
"loss": 0.4473,
|
| 660 |
+
"step": 47500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 9.14,
|
| 664 |
+
"learning_rate": 0.0003903600685844923,
|
| 665 |
+
"loss": 0.4062,
|
| 666 |
+
"step": 48000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 9.24,
|
| 670 |
+
"learning_rate": 0.0003840096526322474,
|
| 671 |
+
"loss": 0.4208,
|
| 672 |
+
"step": 48500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 9.34,
|
| 676 |
+
"learning_rate": 0.00037765923668000255,
|
| 677 |
+
"loss": 0.4233,
|
| 678 |
+
"step": 49000
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 9.43,
|
| 682 |
+
"learning_rate": 0.00037130882072775766,
|
| 683 |
+
"loss": 0.4211,
|
| 684 |
+
"step": 49500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 9.53,
|
| 688 |
+
"learning_rate": 0.0003649584047755128,
|
| 689 |
+
"loss": 0.4273,
|
| 690 |
+
"step": 50000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 9.62,
|
| 694 |
+
"learning_rate": 0.00035860798882326794,
|
| 695 |
+
"loss": 0.4259,
|
| 696 |
+
"step": 50500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 9.72,
|
| 700 |
+
"learning_rate": 0.00035225757287102305,
|
| 701 |
+
"loss": 0.4157,
|
| 702 |
+
"step": 51000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 9.81,
|
| 706 |
+
"learning_rate": 0.00034590715691877816,
|
| 707 |
+
"loss": 0.4294,
|
| 708 |
+
"step": 51500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 9.91,
|
| 712 |
+
"learning_rate": 0.00033955674096653333,
|
| 713 |
+
"loss": 0.4338,
|
| 714 |
+
"step": 52000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 10.0,
|
| 718 |
+
"eval_accuracy": 0.6806287398410289,
|
| 719 |
+
"eval_loss": 1.9794013500213623,
|
| 720 |
+
"eval_runtime": 4548.1376,
|
| 721 |
+
"eval_samples_per_second": 36.928,
|
| 722 |
+
"eval_steps_per_second": 0.289,
|
| 723 |
+
"step": 52490
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 10.0,
|
| 727 |
+
"learning_rate": 0.00033320632501428844,
|
| 728 |
+
"loss": 0.4278,
|
| 729 |
+
"step": 52500
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 10.1,
|
| 733 |
+
"learning_rate": 0.00032685590906204355,
|
| 734 |
+
"loss": 0.3655,
|
| 735 |
+
"step": 53000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 10.19,
|
| 739 |
+
"learning_rate": 0.0003205054931097987,
|
| 740 |
+
"loss": 0.3792,
|
| 741 |
+
"step": 53500
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 10.29,
|
| 745 |
+
"learning_rate": 0.00031415507715755383,
|
| 746 |
+
"loss": 0.3765,
|
| 747 |
+
"step": 54000
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 10.38,
|
| 751 |
+
"learning_rate": 0.000307804661205309,
|
| 752 |
+
"loss": 0.3777,
|
| 753 |
+
"step": 54500
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 10.48,
|
| 757 |
+
"learning_rate": 0.0003014542452530641,
|
| 758 |
+
"loss": 0.3766,
|
| 759 |
+
"step": 55000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 10.57,
|
| 763 |
+
"learning_rate": 0.0002951038293008192,
|
| 764 |
+
"loss": 0.3847,
|
| 765 |
+
"step": 55500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 10.67,
|
| 769 |
+
"learning_rate": 0.0002887534133485744,
|
| 770 |
+
"loss": 0.3802,
|
| 771 |
+
"step": 56000
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 10.76,
|
| 775 |
+
"learning_rate": 0.00028240299739632944,
|
| 776 |
+
"loss": 0.3836,
|
| 777 |
+
"step": 56500
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 10.86,
|
| 781 |
+
"learning_rate": 0.00027605258144408455,
|
| 782 |
+
"loss": 0.3696,
|
| 783 |
+
"step": 57000
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 10.95,
|
| 787 |
+
"learning_rate": 0.0002697021654918397,
|
| 788 |
+
"loss": 0.3738,
|
| 789 |
+
"step": 57500
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 11.0,
|
| 793 |
+
"eval_accuracy": 0.6849275103450329,
|
| 794 |
+
"eval_loss": 2.0053181648254395,
|
| 795 |
+
"eval_runtime": 3187.3586,
|
| 796 |
+
"eval_samples_per_second": 52.694,
|
| 797 |
+
"eval_steps_per_second": 0.412,
|
| 798 |
+
"step": 57739
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 11.05,
|
| 802 |
+
"learning_rate": 0.0002633517495395948,
|
| 803 |
+
"loss": 0.3603,
|
| 804 |
+
"step": 58000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 11.14,
|
| 808 |
+
"learning_rate": 0.00025700133358734994,
|
| 809 |
+
"loss": 0.3371,
|
| 810 |
+
"step": 58500
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 11.24,
|
| 814 |
+
"learning_rate": 0.0002506509176351051,
|
| 815 |
+
"loss": 0.3334,
|
| 816 |
+
"step": 59000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 11.34,
|
| 820 |
+
"learning_rate": 0.0002443005016828602,
|
| 821 |
+
"loss": 0.3342,
|
| 822 |
+
"step": 59500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 11.43,
|
| 826 |
+
"learning_rate": 0.00023795008573061535,
|
| 827 |
+
"loss": 0.3392,
|
| 828 |
+
"step": 60000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 11.53,
|
| 832 |
+
"learning_rate": 0.0002315996697783705,
|
| 833 |
+
"loss": 0.3323,
|
| 834 |
+
"step": 60500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 11.62,
|
| 838 |
+
"learning_rate": 0.00022524925382612563,
|
| 839 |
+
"loss": 0.3444,
|
| 840 |
+
"step": 61000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 11.72,
|
| 844 |
+
"learning_rate": 0.00021889883787388074,
|
| 845 |
+
"loss": 0.3395,
|
| 846 |
+
"step": 61500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 11.81,
|
| 850 |
+
"learning_rate": 0.00021254842192163588,
|
| 851 |
+
"loss": 0.3321,
|
| 852 |
+
"step": 62000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 11.91,
|
| 856 |
+
"learning_rate": 0.00020619800596939102,
|
| 857 |
+
"loss": 0.3338,
|
| 858 |
+
"step": 62500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 12.0,
|
| 862 |
+
"eval_accuracy": 0.6955315411866274,
|
| 863 |
+
"eval_loss": 2.0140492916107178,
|
| 864 |
+
"eval_runtime": 1705.2241,
|
| 865 |
+
"eval_samples_per_second": 98.494,
|
| 866 |
+
"eval_steps_per_second": 0.77,
|
| 867 |
+
"step": 62988
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 12.0,
|
| 871 |
+
"learning_rate": 0.0001998475900171461,
|
| 872 |
+
"loss": 0.3326,
|
| 873 |
+
"step": 63000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 12.1,
|
| 877 |
+
"learning_rate": 0.00019349717406490124,
|
| 878 |
+
"loss": 0.3104,
|
| 879 |
+
"step": 63500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 12.19,
|
| 883 |
+
"learning_rate": 0.00018714675811265638,
|
| 884 |
+
"loss": 0.2943,
|
| 885 |
+
"step": 64000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 12.29,
|
| 889 |
+
"learning_rate": 0.00018079634216041152,
|
| 890 |
+
"loss": 0.3063,
|
| 891 |
+
"step": 64500
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 12.38,
|
| 895 |
+
"learning_rate": 0.00017444592620816663,
|
| 896 |
+
"loss": 0.302,
|
| 897 |
+
"step": 65000
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 12.48,
|
| 901 |
+
"learning_rate": 0.00016809551025592177,
|
| 902 |
+
"loss": 0.295,
|
| 903 |
+
"step": 65500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 12.57,
|
| 907 |
+
"learning_rate": 0.0001617450943036769,
|
| 908 |
+
"loss": 0.2945,
|
| 909 |
+
"step": 66000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 12.67,
|
| 913 |
+
"learning_rate": 0.00015539467835143204,
|
| 914 |
+
"loss": 0.3072,
|
| 915 |
+
"step": 66500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 12.76,
|
| 919 |
+
"learning_rate": 0.00014904426239918715,
|
| 920 |
+
"loss": 0.2913,
|
| 921 |
+
"step": 67000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 12.86,
|
| 925 |
+
"learning_rate": 0.00014269384644694227,
|
| 926 |
+
"loss": 0.3055,
|
| 927 |
+
"step": 67500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 12.95,
|
| 931 |
+
"learning_rate": 0.0001363434304946974,
|
| 932 |
+
"loss": 0.2989,
|
| 933 |
+
"step": 68000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 13.0,
|
| 937 |
+
"eval_accuracy": 0.6974427674079366,
|
| 938 |
+
"eval_loss": 2.083035707473755,
|
| 939 |
+
"eval_runtime": 1683.3073,
|
| 940 |
+
"eval_samples_per_second": 99.777,
|
| 941 |
+
"eval_steps_per_second": 0.78,
|
| 942 |
+
"step": 68237
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 13.05,
|
| 946 |
+
"learning_rate": 0.00012999301454245252,
|
| 947 |
+
"loss": 0.2808,
|
| 948 |
+
"step": 68500
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 13.15,
|
| 952 |
+
"learning_rate": 0.00012364259859020765,
|
| 953 |
+
"loss": 0.2789,
|
| 954 |
+
"step": 69000
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 13.24,
|
| 958 |
+
"learning_rate": 0.00011729218263796279,
|
| 959 |
+
"loss": 0.2743,
|
| 960 |
+
"step": 69500
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 13.34,
|
| 964 |
+
"learning_rate": 0.00011094176668571792,
|
| 965 |
+
"loss": 0.2767,
|
| 966 |
+
"step": 70000
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 13.43,
|
| 970 |
+
"learning_rate": 0.00010459135073347304,
|
| 971 |
+
"loss": 0.2648,
|
| 972 |
+
"step": 70500
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 13.53,
|
| 976 |
+
"learning_rate": 9.824093478122817e-05,
|
| 977 |
+
"loss": 0.2724,
|
| 978 |
+
"step": 71000
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 13.62,
|
| 982 |
+
"learning_rate": 9.18905188289833e-05,
|
| 983 |
+
"loss": 0.2753,
|
| 984 |
+
"step": 71500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 13.72,
|
| 988 |
+
"learning_rate": 8.554010287673843e-05,
|
| 989 |
+
"loss": 0.2743,
|
| 990 |
+
"step": 72000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 13.81,
|
| 994 |
+
"learning_rate": 7.918968692449357e-05,
|
| 995 |
+
"loss": 0.2658,
|
| 996 |
+
"step": 72500
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 13.91,
|
| 1000 |
+
"learning_rate": 7.283927097224868e-05,
|
| 1001 |
+
"loss": 0.267,
|
| 1002 |
+
"step": 73000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 14.0,
|
| 1006 |
+
"eval_accuracy": 0.7040516805096603,
|
| 1007 |
+
"eval_loss": 2.0823681354522705,
|
| 1008 |
+
"eval_runtime": 2701.2349,
|
| 1009 |
+
"eval_samples_per_second": 62.177,
|
| 1010 |
+
"eval_steps_per_second": 0.486,
|
| 1011 |
+
"step": 73486
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 14.0,
|
| 1015 |
+
"learning_rate": 6.64888550200038e-05,
|
| 1016 |
+
"loss": 0.2592,
|
| 1017 |
+
"step": 73500
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 14.1,
|
| 1021 |
+
"learning_rate": 6.013843906775894e-05,
|
| 1022 |
+
"loss": 0.2473,
|
| 1023 |
+
"step": 74000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 14.19,
|
| 1027 |
+
"learning_rate": 5.378802311551407e-05,
|
| 1028 |
+
"loss": 0.2471,
|
| 1029 |
+
"step": 74500
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 14.29,
|
| 1033 |
+
"learning_rate": 4.74376071632692e-05,
|
| 1034 |
+
"loss": 0.2592,
|
| 1035 |
+
"step": 75000
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 14.38,
|
| 1039 |
+
"learning_rate": 4.1087191211024324e-05,
|
| 1040 |
+
"loss": 0.2493,
|
| 1041 |
+
"step": 75500
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 14.48,
|
| 1045 |
+
"learning_rate": 3.473677525877945e-05,
|
| 1046 |
+
"loss": 0.2484,
|
| 1047 |
+
"step": 76000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 14.57,
|
| 1051 |
+
"learning_rate": 2.838635930653458e-05,
|
| 1052 |
+
"loss": 0.2468,
|
| 1053 |
+
"step": 76500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 14.67,
|
| 1057 |
+
"learning_rate": 2.203594335428971e-05,
|
| 1058 |
+
"loss": 0.2432,
|
| 1059 |
+
"step": 77000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 14.76,
|
| 1063 |
+
"learning_rate": 1.5685527402044834e-05,
|
| 1064 |
+
"loss": 0.2466,
|
| 1065 |
+
"step": 77500
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 14.86,
|
| 1069 |
+
"learning_rate": 9.335111449799962e-06,
|
| 1070 |
+
"loss": 0.2472,
|
| 1071 |
+
"step": 78000
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 14.96,
|
| 1075 |
+
"learning_rate": 2.98469549755509e-06,
|
| 1076 |
+
"loss": 0.236,
|
| 1077 |
+
"step": 78500
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 15.0,
|
| 1081 |
+
"eval_accuracy": 0.708475484504778,
|
| 1082 |
+
"eval_loss": 2.0700299739837646,
|
| 1083 |
+
"eval_runtime": 1790.1892,
|
| 1084 |
+
"eval_samples_per_second": 93.82,
|
| 1085 |
+
"eval_steps_per_second": 0.733,
|
| 1086 |
+
"step": 78735
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 15.0,
|
| 1090 |
+
"step": 78735,
|
| 1091 |
+
"total_flos": 6.872831806674565e+20,
|
| 1092 |
+
"train_loss": 0.0,
|
| 1093 |
+
"train_runtime": 39.8476,
|
| 1094 |
+
"train_samples_per_second": 252894.596,
|
| 1095 |
+
"train_steps_per_second": 1975.901
|
| 1096 |
+
}
|
| 1097 |
+
],
|
| 1098 |
+
"logging_steps": 500,
|
| 1099 |
+
"max_steps": 78735,
|
| 1100 |
+
"num_train_epochs": 15,
|
| 1101 |
+
"save_steps": 500,
|
| 1102 |
+
"total_flos": 6.872831806674565e+20,
|
| 1103 |
+
"trial_name": null,
|
| 1104 |
+
"trial_params": null
|
| 1105 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d46d7a93871b2bc0c2dd2fca4cac6f649705db85ae3ddb297a86444819a12bfd
|
| 3 |
+
size 4664
|