Commit
•
00adc38
1
Parent(s):
29de752
Supreeta03/vit-base-patch16-224-MelSpecImages
Browse files- README.md +74 -0
- all_results.json +13 -0
- config.json +40 -0
- eval_results.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Apr03_12-20-17_2d0e4f99d01d/events.out.tfevents.1712146851.2d0e4f99d01d.166.6 +3 -0
- runs/Apr03_12-20-17_2d0e4f99d01d/events.out.tfevents.1712147850.2d0e4f99d01d.166.7 +3 -0
- train_results.json +8 -0
- trainer_state.json +1064 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: vit-base-melSpecImagesCREMA
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# vit-base-melSpecImagesCREMA
|
| 18 |
+
|
| 19 |
+
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 Supreeta03/CREMA-melSpecImages dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.1416
|
| 22 |
+
- Accuracy: 0.5808
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0002
|
| 42 |
+
- train_batch_size: 32
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 10
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 1.5606 | 0.76 | 100 | 1.4424 | 0.4079 |
|
| 55 |
+
| 1.2841 | 1.53 | 200 | 1.4981 | 0.3695 |
|
| 56 |
+
| 1.0159 | 2.29 | 300 | 1.1693 | 0.5518 |
|
| 57 |
+
| 0.9868 | 3.05 | 400 | 1.0969 | 0.5931 |
|
| 58 |
+
| 0.8477 | 3.82 | 500 | 1.1719 | 0.5797 |
|
| 59 |
+
| 0.5495 | 4.58 | 600 | 1.2348 | 0.5806 |
|
| 60 |
+
| 0.2671 | 5.34 | 700 | 1.3457 | 0.5854 |
|
| 61 |
+
| 0.1388 | 6.11 | 800 | 1.3891 | 0.5787 |
|
| 62 |
+
| 0.1548 | 6.87 | 900 | 1.4216 | 0.5979 |
|
| 63 |
+
| 0.0906 | 7.63 | 1000 | 1.6401 | 0.5643 |
|
| 64 |
+
| 0.1047 | 8.4 | 1100 | 1.6780 | 0.5873 |
|
| 65 |
+
| 0.0583 | 9.16 | 1200 | 1.6795 | 0.5768 |
|
| 66 |
+
| 0.0228 | 9.92 | 1300 | 1.6926 | 0.5883 |
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
### Framework versions
|
| 70 |
+
|
| 71 |
+
- Transformers 4.38.2
|
| 72 |
+
- Pytorch 2.2.1+cu121
|
| 73 |
+
- Datasets 2.18.0
|
| 74 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.580832960143305,
|
| 4 |
+
"eval_loss": 1.141593098640442,
|
| 5 |
+
"eval_runtime": 29.7231,
|
| 6 |
+
"eval_samples_per_second": 75.127,
|
| 7 |
+
"eval_steps_per_second": 9.42,
|
| 8 |
+
"total_flos": 3.229206972532531e+18,
|
| 9 |
+
"train_loss": 0.583979975267221,
|
| 10 |
+
"train_runtime": 954.0647,
|
| 11 |
+
"train_samples_per_second": 43.676,
|
| 12 |
+
"train_steps_per_second": 1.373
|
| 13 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"id2label": {
|
| 12 |
+
"0": "Anger",
|
| 13 |
+
"1": "Happy",
|
| 14 |
+
"2": "Fear",
|
| 15 |
+
"3": "Sad",
|
| 16 |
+
"4": "Disgust",
|
| 17 |
+
"5": "Neutral"
|
| 18 |
+
},
|
| 19 |
+
"image_size": 224,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"Anger": 0,
|
| 24 |
+
"Disgust": 4,
|
| 25 |
+
"Fear": 2,
|
| 26 |
+
"Happy": 1,
|
| 27 |
+
"Neutral": 5,
|
| 28 |
+
"Sad": 3
|
| 29 |
+
},
|
| 30 |
+
"layer_norm_eps": 1e-12,
|
| 31 |
+
"model_type": "vit",
|
| 32 |
+
"num_attention_heads": 12,
|
| 33 |
+
"num_channels": 3,
|
| 34 |
+
"num_hidden_layers": 12,
|
| 35 |
+
"patch_size": 16,
|
| 36 |
+
"problem_type": "single_label_classification",
|
| 37 |
+
"qkv_bias": true,
|
| 38 |
+
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.38.2"
|
| 40 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.580832960143305,
|
| 4 |
+
"eval_loss": 1.141593098640442,
|
| 5 |
+
"eval_runtime": 29.7231,
|
| 6 |
+
"eval_samples_per_second": 75.127,
|
| 7 |
+
"eval_steps_per_second": 9.42
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c550c0f973ee1cd11782ce7af763358581ee6c54d715aa995365a859796c362c
|
| 3 |
+
size 343236280
|
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 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
runs/Apr03_12-20-17_2d0e4f99d01d/events.out.tfevents.1712146851.2d0e4f99d01d.166.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2230d36814c9d34621ff2df24dad388d89dcd0cb1657fd2f44df058fb8cb3493
|
| 3 |
+
size 36863
|
runs/Apr03_12-20-17_2d0e4f99d01d/events.out.tfevents.1712147850.2d0e4f99d01d.166.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1336a75bbcccf7dc750ac88a8573abd8a852865a07063452fb3364df947fc74
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 3.229206972532531e+18,
|
| 4 |
+
"train_loss": 0.583979975267221,
|
| 5 |
+
"train_runtime": 954.0647,
|
| 6 |
+
"train_samples_per_second": 43.676,
|
| 7 |
+
"train_steps_per_second": 1.373
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0969369411468506,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-melSpecImagesCREMA/checkpoint-400",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1310,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 1.503008246421814,
|
| 14 |
+
"learning_rate": 0.0001984732824427481,
|
| 15 |
+
"loss": 1.7751,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.15,
|
| 20 |
+
"grad_norm": 1.1629976034164429,
|
| 21 |
+
"learning_rate": 0.0001969465648854962,
|
| 22 |
+
"loss": 1.6558,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.23,
|
| 27 |
+
"grad_norm": 1.205520749092102,
|
| 28 |
+
"learning_rate": 0.00019541984732824428,
|
| 29 |
+
"loss": 1.6062,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.31,
|
| 34 |
+
"grad_norm": 1.4008492231369019,
|
| 35 |
+
"learning_rate": 0.00019389312977099237,
|
| 36 |
+
"loss": 1.6114,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.38,
|
| 41 |
+
"grad_norm": 1.3961032629013062,
|
| 42 |
+
"learning_rate": 0.00019236641221374049,
|
| 43 |
+
"loss": 1.5886,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.46,
|
| 48 |
+
"grad_norm": 1.31687331199646,
|
| 49 |
+
"learning_rate": 0.00019083969465648857,
|
| 50 |
+
"loss": 1.544,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.53,
|
| 55 |
+
"grad_norm": 1.3430259227752686,
|
| 56 |
+
"learning_rate": 0.00018931297709923666,
|
| 57 |
+
"loss": 1.493,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.61,
|
| 62 |
+
"grad_norm": 2.1518867015838623,
|
| 63 |
+
"learning_rate": 0.00018778625954198475,
|
| 64 |
+
"loss": 1.5494,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.69,
|
| 69 |
+
"grad_norm": 1.066909909248352,
|
| 70 |
+
"learning_rate": 0.00018625954198473284,
|
| 71 |
+
"loss": 1.4324,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.76,
|
| 76 |
+
"grad_norm": 1.1103651523590088,
|
| 77 |
+
"learning_rate": 0.00018473282442748093,
|
| 78 |
+
"loss": 1.5606,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.76,
|
| 83 |
+
"eval_accuracy": 0.40786948176583493,
|
| 84 |
+
"eval_loss": 1.4423701763153076,
|
| 85 |
+
"eval_runtime": 10.9463,
|
| 86 |
+
"eval_samples_per_second": 95.192,
|
| 87 |
+
"eval_steps_per_second": 11.967,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.84,
|
| 92 |
+
"grad_norm": 1.20200777053833,
|
| 93 |
+
"learning_rate": 0.00018320610687022902,
|
| 94 |
+
"loss": 1.429,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.92,
|
| 99 |
+
"grad_norm": 1.1876991987228394,
|
| 100 |
+
"learning_rate": 0.0001816793893129771,
|
| 101 |
+
"loss": 1.4265,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.99,
|
| 106 |
+
"grad_norm": 1.1246036291122437,
|
| 107 |
+
"learning_rate": 0.00018015267175572518,
|
| 108 |
+
"loss": 1.4526,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.07,
|
| 113 |
+
"grad_norm": 1.8578764200210571,
|
| 114 |
+
"learning_rate": 0.0001786259541984733,
|
| 115 |
+
"loss": 1.349,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.15,
|
| 120 |
+
"grad_norm": 1.8486779928207397,
|
| 121 |
+
"learning_rate": 0.00017709923664122138,
|
| 122 |
+
"loss": 1.3172,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.22,
|
| 127 |
+
"grad_norm": 1.775232195854187,
|
| 128 |
+
"learning_rate": 0.00017557251908396947,
|
| 129 |
+
"loss": 1.2735,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.3,
|
| 134 |
+
"grad_norm": 1.7306294441223145,
|
| 135 |
+
"learning_rate": 0.00017404580152671756,
|
| 136 |
+
"loss": 1.3665,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.37,
|
| 141 |
+
"grad_norm": 1.8813070058822632,
|
| 142 |
+
"learning_rate": 0.00017251908396946565,
|
| 143 |
+
"loss": 1.322,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.45,
|
| 148 |
+
"grad_norm": 1.4844669103622437,
|
| 149 |
+
"learning_rate": 0.00017099236641221374,
|
| 150 |
+
"loss": 1.324,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.53,
|
| 155 |
+
"grad_norm": 2.489121913909912,
|
| 156 |
+
"learning_rate": 0.00016946564885496183,
|
| 157 |
+
"loss": 1.2841,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.53,
|
| 162 |
+
"eval_accuracy": 0.3694817658349328,
|
| 163 |
+
"eval_loss": 1.498081088066101,
|
| 164 |
+
"eval_runtime": 11.2582,
|
| 165 |
+
"eval_samples_per_second": 92.555,
|
| 166 |
+
"eval_steps_per_second": 11.636,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.6,
|
| 171 |
+
"grad_norm": 1.9091380834579468,
|
| 172 |
+
"learning_rate": 0.00016793893129770992,
|
| 173 |
+
"loss": 1.2919,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.68,
|
| 178 |
+
"grad_norm": 1.8453233242034912,
|
| 179 |
+
"learning_rate": 0.00016641221374045804,
|
| 180 |
+
"loss": 1.2998,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.76,
|
| 185 |
+
"grad_norm": 2.699350595474243,
|
| 186 |
+
"learning_rate": 0.00016488549618320613,
|
| 187 |
+
"loss": 1.3153,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.83,
|
| 192 |
+
"grad_norm": 2.409592628479004,
|
| 193 |
+
"learning_rate": 0.00016335877862595422,
|
| 194 |
+
"loss": 1.1943,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.91,
|
| 199 |
+
"grad_norm": 1.59845769405365,
|
| 200 |
+
"learning_rate": 0.0001618320610687023,
|
| 201 |
+
"loss": 1.2302,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.98,
|
| 206 |
+
"grad_norm": 2.2508938312530518,
|
| 207 |
+
"learning_rate": 0.0001603053435114504,
|
| 208 |
+
"loss": 1.4177,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.06,
|
| 213 |
+
"grad_norm": 1.6891452074050903,
|
| 214 |
+
"learning_rate": 0.00015877862595419848,
|
| 215 |
+
"loss": 1.0828,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.14,
|
| 220 |
+
"grad_norm": 3.317949056625366,
|
| 221 |
+
"learning_rate": 0.00015725190839694657,
|
| 222 |
+
"loss": 1.1312,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.21,
|
| 227 |
+
"grad_norm": 3.0603318214416504,
|
| 228 |
+
"learning_rate": 0.00015572519083969466,
|
| 229 |
+
"loss": 1.0713,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.29,
|
| 234 |
+
"grad_norm": 2.0383269786834717,
|
| 235 |
+
"learning_rate": 0.00015419847328244275,
|
| 236 |
+
"loss": 1.0159,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.29,
|
| 241 |
+
"eval_accuracy": 0.5518234165067178,
|
| 242 |
+
"eval_loss": 1.1692744493484497,
|
| 243 |
+
"eval_runtime": 11.2045,
|
| 244 |
+
"eval_samples_per_second": 92.998,
|
| 245 |
+
"eval_steps_per_second": 11.692,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.37,
|
| 250 |
+
"grad_norm": 1.9367152452468872,
|
| 251 |
+
"learning_rate": 0.00015267175572519084,
|
| 252 |
+
"loss": 0.9986,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.44,
|
| 257 |
+
"grad_norm": 2.3003132343292236,
|
| 258 |
+
"learning_rate": 0.00015114503816793893,
|
| 259 |
+
"loss": 1.0508,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.52,
|
| 264 |
+
"grad_norm": 3.84384822845459,
|
| 265 |
+
"learning_rate": 0.00014961832061068702,
|
| 266 |
+
"loss": 1.0623,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.6,
|
| 271 |
+
"grad_norm": 1.7760237455368042,
|
| 272 |
+
"learning_rate": 0.0001480916030534351,
|
| 273 |
+
"loss": 1.0425,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.67,
|
| 278 |
+
"grad_norm": 2.6222035884857178,
|
| 279 |
+
"learning_rate": 0.0001465648854961832,
|
| 280 |
+
"loss": 1.0366,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.75,
|
| 285 |
+
"grad_norm": 2.4612748622894287,
|
| 286 |
+
"learning_rate": 0.0001450381679389313,
|
| 287 |
+
"loss": 1.0451,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.82,
|
| 292 |
+
"grad_norm": 2.3277204036712646,
|
| 293 |
+
"learning_rate": 0.00014351145038167938,
|
| 294 |
+
"loss": 1.1176,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.9,
|
| 299 |
+
"grad_norm": 2.187209129333496,
|
| 300 |
+
"learning_rate": 0.00014198473282442747,
|
| 301 |
+
"loss": 0.9908,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.98,
|
| 306 |
+
"grad_norm": 3.229308843612671,
|
| 307 |
+
"learning_rate": 0.00014045801526717556,
|
| 308 |
+
"loss": 1.0181,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.05,
|
| 313 |
+
"grad_norm": 1.847447156906128,
|
| 314 |
+
"learning_rate": 0.00013893129770992368,
|
| 315 |
+
"loss": 0.9868,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 3.05,
|
| 320 |
+
"eval_accuracy": 0.5930902111324377,
|
| 321 |
+
"eval_loss": 1.0969369411468506,
|
| 322 |
+
"eval_runtime": 11.1277,
|
| 323 |
+
"eval_samples_per_second": 93.64,
|
| 324 |
+
"eval_steps_per_second": 11.772,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 3.13,
|
| 329 |
+
"grad_norm": 2.6871042251586914,
|
| 330 |
+
"learning_rate": 0.00013740458015267177,
|
| 331 |
+
"loss": 0.8034,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.21,
|
| 336 |
+
"grad_norm": 3.8769664764404297,
|
| 337 |
+
"learning_rate": 0.00013587786259541986,
|
| 338 |
+
"loss": 0.8141,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.28,
|
| 343 |
+
"grad_norm": 2.8785126209259033,
|
| 344 |
+
"learning_rate": 0.00013435114503816795,
|
| 345 |
+
"loss": 0.7343,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 3.36,
|
| 350 |
+
"grad_norm": 2.4167301654815674,
|
| 351 |
+
"learning_rate": 0.00013282442748091604,
|
| 352 |
+
"loss": 0.8251,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.44,
|
| 357 |
+
"grad_norm": 2.921082019805908,
|
| 358 |
+
"learning_rate": 0.00013129770992366413,
|
| 359 |
+
"loss": 0.7511,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.51,
|
| 364 |
+
"grad_norm": 2.847332000732422,
|
| 365 |
+
"learning_rate": 0.00012977099236641222,
|
| 366 |
+
"loss": 0.7392,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.59,
|
| 371 |
+
"grad_norm": 3.5761501789093018,
|
| 372 |
+
"learning_rate": 0.0001282442748091603,
|
| 373 |
+
"loss": 0.6463,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.66,
|
| 378 |
+
"grad_norm": 3.0666024684906006,
|
| 379 |
+
"learning_rate": 0.0001267175572519084,
|
| 380 |
+
"loss": 0.7027,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.74,
|
| 385 |
+
"grad_norm": 1.9951330423355103,
|
| 386 |
+
"learning_rate": 0.0001251908396946565,
|
| 387 |
+
"loss": 0.7666,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.82,
|
| 392 |
+
"grad_norm": 3.5129895210266113,
|
| 393 |
+
"learning_rate": 0.0001236641221374046,
|
| 394 |
+
"loss": 0.8477,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.82,
|
| 399 |
+
"eval_accuracy": 0.5796545105566219,
|
| 400 |
+
"eval_loss": 1.1718865633010864,
|
| 401 |
+
"eval_runtime": 11.143,
|
| 402 |
+
"eval_samples_per_second": 93.511,
|
| 403 |
+
"eval_steps_per_second": 11.756,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.89,
|
| 408 |
+
"grad_norm": 2.490349054336548,
|
| 409 |
+
"learning_rate": 0.0001221374045801527,
|
| 410 |
+
"loss": 0.6279,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.97,
|
| 415 |
+
"grad_norm": 4.751981258392334,
|
| 416 |
+
"learning_rate": 0.00012061068702290077,
|
| 417 |
+
"loss": 0.6861,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 4.05,
|
| 422 |
+
"grad_norm": 1.843367338180542,
|
| 423 |
+
"learning_rate": 0.00011908396946564886,
|
| 424 |
+
"loss": 0.6348,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.12,
|
| 429 |
+
"grad_norm": 3.823432445526123,
|
| 430 |
+
"learning_rate": 0.00011755725190839695,
|
| 431 |
+
"loss": 0.4487,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 4.2,
|
| 436 |
+
"grad_norm": 1.805336833000183,
|
| 437 |
+
"learning_rate": 0.00011603053435114504,
|
| 438 |
+
"loss": 0.4393,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 4.27,
|
| 443 |
+
"grad_norm": 2.604633331298828,
|
| 444 |
+
"learning_rate": 0.00011450381679389313,
|
| 445 |
+
"loss": 0.4098,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.35,
|
| 450 |
+
"grad_norm": 3.3479952812194824,
|
| 451 |
+
"learning_rate": 0.00011297709923664124,
|
| 452 |
+
"loss": 0.5057,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.43,
|
| 457 |
+
"grad_norm": 2.961186408996582,
|
| 458 |
+
"learning_rate": 0.00011145038167938933,
|
| 459 |
+
"loss": 0.5446,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 4.5,
|
| 464 |
+
"grad_norm": 4.528743267059326,
|
| 465 |
+
"learning_rate": 0.00010992366412213742,
|
| 466 |
+
"loss": 0.5032,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.58,
|
| 471 |
+
"grad_norm": 3.593770742416382,
|
| 472 |
+
"learning_rate": 0.0001083969465648855,
|
| 473 |
+
"loss": 0.5495,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 4.58,
|
| 478 |
+
"eval_accuracy": 0.5806142034548945,
|
| 479 |
+
"eval_loss": 1.234790563583374,
|
| 480 |
+
"eval_runtime": 11.1508,
|
| 481 |
+
"eval_samples_per_second": 93.446,
|
| 482 |
+
"eval_steps_per_second": 11.748,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.66,
|
| 487 |
+
"grad_norm": 2.7948455810546875,
|
| 488 |
+
"learning_rate": 0.00010687022900763359,
|
| 489 |
+
"loss": 0.519,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.73,
|
| 494 |
+
"grad_norm": 5.143344879150391,
|
| 495 |
+
"learning_rate": 0.00010534351145038168,
|
| 496 |
+
"loss": 0.5493,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.81,
|
| 501 |
+
"grad_norm": 4.292489528656006,
|
| 502 |
+
"learning_rate": 0.00010381679389312977,
|
| 503 |
+
"loss": 0.5947,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 4.89,
|
| 508 |
+
"grad_norm": 3.135993480682373,
|
| 509 |
+
"learning_rate": 0.00010229007633587786,
|
| 510 |
+
"loss": 0.4873,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 4.96,
|
| 515 |
+
"grad_norm": 2.5363755226135254,
|
| 516 |
+
"learning_rate": 0.00010076335877862595,
|
| 517 |
+
"loss": 0.4813,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.04,
|
| 522 |
+
"grad_norm": 2.4878172874450684,
|
| 523 |
+
"learning_rate": 9.923664122137405e-05,
|
| 524 |
+
"loss": 0.4249,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 5.11,
|
| 529 |
+
"grad_norm": 2.6882851123809814,
|
| 530 |
+
"learning_rate": 9.770992366412214e-05,
|
| 531 |
+
"loss": 0.2691,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.19,
|
| 536 |
+
"grad_norm": 2.534364700317383,
|
| 537 |
+
"learning_rate": 9.618320610687024e-05,
|
| 538 |
+
"loss": 0.3055,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.27,
|
| 543 |
+
"grad_norm": 4.340401649475098,
|
| 544 |
+
"learning_rate": 9.465648854961833e-05,
|
| 545 |
+
"loss": 0.2444,
|
| 546 |
+
"step": 690
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 5.34,
|
| 550 |
+
"grad_norm": 5.553411483764648,
|
| 551 |
+
"learning_rate": 9.312977099236642e-05,
|
| 552 |
+
"loss": 0.2671,
|
| 553 |
+
"step": 700
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 5.34,
|
| 557 |
+
"eval_accuracy": 0.5854126679462572,
|
| 558 |
+
"eval_loss": 1.3457223176956177,
|
| 559 |
+
"eval_runtime": 11.154,
|
| 560 |
+
"eval_samples_per_second": 93.419,
|
| 561 |
+
"eval_steps_per_second": 11.745,
|
| 562 |
+
"step": 700
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 5.42,
|
| 566 |
+
"grad_norm": 2.335097551345825,
|
| 567 |
+
"learning_rate": 9.160305343511451e-05,
|
| 568 |
+
"loss": 0.3027,
|
| 569 |
+
"step": 710
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.5,
|
| 573 |
+
"grad_norm": 6.312303066253662,
|
| 574 |
+
"learning_rate": 9.007633587786259e-05,
|
| 575 |
+
"loss": 0.3205,
|
| 576 |
+
"step": 720
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 5.57,
|
| 580 |
+
"grad_norm": 7.102092266082764,
|
| 581 |
+
"learning_rate": 8.854961832061069e-05,
|
| 582 |
+
"loss": 0.2796,
|
| 583 |
+
"step": 730
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 5.65,
|
| 587 |
+
"grad_norm": 4.718852996826172,
|
| 588 |
+
"learning_rate": 8.702290076335878e-05,
|
| 589 |
+
"loss": 0.3254,
|
| 590 |
+
"step": 740
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 5.73,
|
| 594 |
+
"grad_norm": 5.368557453155518,
|
| 595 |
+
"learning_rate": 8.549618320610687e-05,
|
| 596 |
+
"loss": 0.329,
|
| 597 |
+
"step": 750
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 5.8,
|
| 601 |
+
"grad_norm": 1.7768850326538086,
|
| 602 |
+
"learning_rate": 8.396946564885496e-05,
|
| 603 |
+
"loss": 0.2239,
|
| 604 |
+
"step": 760
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 5.88,
|
| 608 |
+
"grad_norm": 1.6067969799041748,
|
| 609 |
+
"learning_rate": 8.244274809160306e-05,
|
| 610 |
+
"loss": 0.2289,
|
| 611 |
+
"step": 770
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.95,
|
| 615 |
+
"grad_norm": 0.8688230514526367,
|
| 616 |
+
"learning_rate": 8.091603053435115e-05,
|
| 617 |
+
"loss": 0.2715,
|
| 618 |
+
"step": 780
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 6.03,
|
| 622 |
+
"grad_norm": 2.5685417652130127,
|
| 623 |
+
"learning_rate": 7.938931297709924e-05,
|
| 624 |
+
"loss": 0.2098,
|
| 625 |
+
"step": 790
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 6.11,
|
| 629 |
+
"grad_norm": 1.9992344379425049,
|
| 630 |
+
"learning_rate": 7.786259541984733e-05,
|
| 631 |
+
"loss": 0.1388,
|
| 632 |
+
"step": 800
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.11,
|
| 636 |
+
"eval_accuracy": 0.5786948176583493,
|
| 637 |
+
"eval_loss": 1.389073371887207,
|
| 638 |
+
"eval_runtime": 11.1211,
|
| 639 |
+
"eval_samples_per_second": 93.696,
|
| 640 |
+
"eval_steps_per_second": 11.779,
|
| 641 |
+
"step": 800
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 6.18,
|
| 645 |
+
"grad_norm": 2.335876703262329,
|
| 646 |
+
"learning_rate": 7.633587786259542e-05,
|
| 647 |
+
"loss": 0.1762,
|
| 648 |
+
"step": 810
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 6.26,
|
| 652 |
+
"grad_norm": 4.345489025115967,
|
| 653 |
+
"learning_rate": 7.480916030534351e-05,
|
| 654 |
+
"loss": 0.1829,
|
| 655 |
+
"step": 820
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 6.34,
|
| 659 |
+
"grad_norm": 1.5818490982055664,
|
| 660 |
+
"learning_rate": 7.32824427480916e-05,
|
| 661 |
+
"loss": 0.2543,
|
| 662 |
+
"step": 830
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 6.41,
|
| 666 |
+
"grad_norm": 2.3892974853515625,
|
| 667 |
+
"learning_rate": 7.175572519083969e-05,
|
| 668 |
+
"loss": 0.2035,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 6.49,
|
| 673 |
+
"grad_norm": 0.9355500936508179,
|
| 674 |
+
"learning_rate": 7.022900763358778e-05,
|
| 675 |
+
"loss": 0.2287,
|
| 676 |
+
"step": 850
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 6.56,
|
| 680 |
+
"grad_norm": 3.3484275341033936,
|
| 681 |
+
"learning_rate": 6.870229007633588e-05,
|
| 682 |
+
"loss": 0.1433,
|
| 683 |
+
"step": 860
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 6.64,
|
| 687 |
+
"grad_norm": 1.1796901226043701,
|
| 688 |
+
"learning_rate": 6.717557251908397e-05,
|
| 689 |
+
"loss": 0.1943,
|
| 690 |
+
"step": 870
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 6.72,
|
| 694 |
+
"grad_norm": 3.2419047355651855,
|
| 695 |
+
"learning_rate": 6.564885496183206e-05,
|
| 696 |
+
"loss": 0.2079,
|
| 697 |
+
"step": 880
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 6.79,
|
| 701 |
+
"grad_norm": 5.841382026672363,
|
| 702 |
+
"learning_rate": 6.412213740458015e-05,
|
| 703 |
+
"loss": 0.2108,
|
| 704 |
+
"step": 890
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.87,
|
| 708 |
+
"grad_norm": 1.1594499349594116,
|
| 709 |
+
"learning_rate": 6.259541984732826e-05,
|
| 710 |
+
"loss": 0.1548,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 6.87,
|
| 715 |
+
"eval_accuracy": 0.5978886756238004,
|
| 716 |
+
"eval_loss": 1.4216477870941162,
|
| 717 |
+
"eval_runtime": 11.0828,
|
| 718 |
+
"eval_samples_per_second": 94.019,
|
| 719 |
+
"eval_steps_per_second": 11.82,
|
| 720 |
+
"step": 900
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 6.95,
|
| 724 |
+
"grad_norm": 1.131686806678772,
|
| 725 |
+
"learning_rate": 6.106870229007635e-05,
|
| 726 |
+
"loss": 0.1264,
|
| 727 |
+
"step": 910
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 7.02,
|
| 731 |
+
"grad_norm": 0.8231382966041565,
|
| 732 |
+
"learning_rate": 5.954198473282443e-05,
|
| 733 |
+
"loss": 0.1726,
|
| 734 |
+
"step": 920
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 7.1,
|
| 738 |
+
"grad_norm": 0.48267778754234314,
|
| 739 |
+
"learning_rate": 5.801526717557252e-05,
|
| 740 |
+
"loss": 0.1198,
|
| 741 |
+
"step": 930
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 7.18,
|
| 745 |
+
"grad_norm": 2.5278027057647705,
|
| 746 |
+
"learning_rate": 5.648854961832062e-05,
|
| 747 |
+
"loss": 0.1702,
|
| 748 |
+
"step": 940
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 7.25,
|
| 752 |
+
"grad_norm": 2.183692455291748,
|
| 753 |
+
"learning_rate": 5.496183206106871e-05,
|
| 754 |
+
"loss": 0.0854,
|
| 755 |
+
"step": 950
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 7.33,
|
| 759 |
+
"grad_norm": 0.40628916025161743,
|
| 760 |
+
"learning_rate": 5.3435114503816794e-05,
|
| 761 |
+
"loss": 0.1078,
|
| 762 |
+
"step": 960
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 7.4,
|
| 766 |
+
"grad_norm": 0.19366604089736938,
|
| 767 |
+
"learning_rate": 5.1908396946564884e-05,
|
| 768 |
+
"loss": 0.0979,
|
| 769 |
+
"step": 970
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 7.48,
|
| 773 |
+
"grad_norm": 0.4136432707309723,
|
| 774 |
+
"learning_rate": 5.038167938931297e-05,
|
| 775 |
+
"loss": 0.0954,
|
| 776 |
+
"step": 980
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 7.56,
|
| 780 |
+
"grad_norm": 0.17071671783924103,
|
| 781 |
+
"learning_rate": 4.885496183206107e-05,
|
| 782 |
+
"loss": 0.0432,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 7.63,
|
| 787 |
+
"grad_norm": 0.9517059326171875,
|
| 788 |
+
"learning_rate": 4.7328244274809166e-05,
|
| 789 |
+
"loss": 0.0906,
|
| 790 |
+
"step": 1000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 7.63,
|
| 794 |
+
"eval_accuracy": 0.564299424184261,
|
| 795 |
+
"eval_loss": 1.640116810798645,
|
| 796 |
+
"eval_runtime": 11.0958,
|
| 797 |
+
"eval_samples_per_second": 93.91,
|
| 798 |
+
"eval_steps_per_second": 11.806,
|
| 799 |
+
"step": 1000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 7.71,
|
| 803 |
+
"grad_norm": 0.1622392237186432,
|
| 804 |
+
"learning_rate": 4.5801526717557256e-05,
|
| 805 |
+
"loss": 0.1284,
|
| 806 |
+
"step": 1010
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 7.79,
|
| 810 |
+
"grad_norm": 6.343606948852539,
|
| 811 |
+
"learning_rate": 4.4274809160305345e-05,
|
| 812 |
+
"loss": 0.0985,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 7.86,
|
| 817 |
+
"grad_norm": 0.7874533534049988,
|
| 818 |
+
"learning_rate": 4.2748091603053435e-05,
|
| 819 |
+
"loss": 0.1168,
|
| 820 |
+
"step": 1030
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 7.94,
|
| 824 |
+
"grad_norm": 0.31581443548202515,
|
| 825 |
+
"learning_rate": 4.122137404580153e-05,
|
| 826 |
+
"loss": 0.1668,
|
| 827 |
+
"step": 1040
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 8.02,
|
| 831 |
+
"grad_norm": 0.3773091435432434,
|
| 832 |
+
"learning_rate": 3.969465648854962e-05,
|
| 833 |
+
"loss": 0.1027,
|
| 834 |
+
"step": 1050
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 8.09,
|
| 838 |
+
"grad_norm": 0.09075737744569778,
|
| 839 |
+
"learning_rate": 3.816793893129771e-05,
|
| 840 |
+
"loss": 0.0301,
|
| 841 |
+
"step": 1060
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 8.17,
|
| 845 |
+
"grad_norm": 0.1646617352962494,
|
| 846 |
+
"learning_rate": 3.66412213740458e-05,
|
| 847 |
+
"loss": 0.077,
|
| 848 |
+
"step": 1070
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 8.24,
|
| 852 |
+
"grad_norm": 1.9873558282852173,
|
| 853 |
+
"learning_rate": 3.511450381679389e-05,
|
| 854 |
+
"loss": 0.0443,
|
| 855 |
+
"step": 1080
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 8.32,
|
| 859 |
+
"grad_norm": 0.13392330706119537,
|
| 860 |
+
"learning_rate": 3.358778625954199e-05,
|
| 861 |
+
"loss": 0.0823,
|
| 862 |
+
"step": 1090
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 8.4,
|
| 866 |
+
"grad_norm": 1.0865620374679565,
|
| 867 |
+
"learning_rate": 3.2061068702290076e-05,
|
| 868 |
+
"loss": 0.1047,
|
| 869 |
+
"step": 1100
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 8.4,
|
| 873 |
+
"eval_accuracy": 0.5873320537428023,
|
| 874 |
+
"eval_loss": 1.6780017614364624,
|
| 875 |
+
"eval_runtime": 11.1335,
|
| 876 |
+
"eval_samples_per_second": 93.591,
|
| 877 |
+
"eval_steps_per_second": 11.766,
|
| 878 |
+
"step": 1100
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 8.47,
|
| 882 |
+
"grad_norm": 0.10025681555271149,
|
| 883 |
+
"learning_rate": 3.053435114503817e-05,
|
| 884 |
+
"loss": 0.0592,
|
| 885 |
+
"step": 1110
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 8.55,
|
| 889 |
+
"grad_norm": 0.14586412906646729,
|
| 890 |
+
"learning_rate": 2.900763358778626e-05,
|
| 891 |
+
"loss": 0.0393,
|
| 892 |
+
"step": 1120
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 8.63,
|
| 896 |
+
"grad_norm": 0.5182372331619263,
|
| 897 |
+
"learning_rate": 2.7480916030534355e-05,
|
| 898 |
+
"loss": 0.0802,
|
| 899 |
+
"step": 1130
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 8.7,
|
| 903 |
+
"grad_norm": 0.3386911153793335,
|
| 904 |
+
"learning_rate": 2.5954198473282442e-05,
|
| 905 |
+
"loss": 0.0748,
|
| 906 |
+
"step": 1140
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 8.78,
|
| 910 |
+
"grad_norm": 0.10998167097568512,
|
| 911 |
+
"learning_rate": 2.4427480916030535e-05,
|
| 912 |
+
"loss": 0.0366,
|
| 913 |
+
"step": 1150
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 8.85,
|
| 917 |
+
"grad_norm": 0.12017246335744858,
|
| 918 |
+
"learning_rate": 2.2900763358778628e-05,
|
| 919 |
+
"loss": 0.0461,
|
| 920 |
+
"step": 1160
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 8.93,
|
| 924 |
+
"grad_norm": 0.09363219887018204,
|
| 925 |
+
"learning_rate": 2.1374045801526718e-05,
|
| 926 |
+
"loss": 0.056,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 9.01,
|
| 931 |
+
"grad_norm": 0.08617076277732849,
|
| 932 |
+
"learning_rate": 1.984732824427481e-05,
|
| 933 |
+
"loss": 0.0407,
|
| 934 |
+
"step": 1180
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 9.08,
|
| 938 |
+
"grad_norm": 0.07992846518754959,
|
| 939 |
+
"learning_rate": 1.83206106870229e-05,
|
| 940 |
+
"loss": 0.0225,
|
| 941 |
+
"step": 1190
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 9.16,
|
| 945 |
+
"grad_norm": 0.5971510410308838,
|
| 946 |
+
"learning_rate": 1.6793893129770993e-05,
|
| 947 |
+
"loss": 0.0583,
|
| 948 |
+
"step": 1200
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 9.16,
|
| 952 |
+
"eval_accuracy": 0.5767754318618042,
|
| 953 |
+
"eval_loss": 1.6794880628585815,
|
| 954 |
+
"eval_runtime": 11.1041,
|
| 955 |
+
"eval_samples_per_second": 93.839,
|
| 956 |
+
"eval_steps_per_second": 11.797,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 9.24,
|
| 961 |
+
"grad_norm": 0.06741204857826233,
|
| 962 |
+
"learning_rate": 1.5267175572519086e-05,
|
| 963 |
+
"loss": 0.0221,
|
| 964 |
+
"step": 1210
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 9.31,
|
| 968 |
+
"grad_norm": 0.08024097234010696,
|
| 969 |
+
"learning_rate": 1.3740458015267178e-05,
|
| 970 |
+
"loss": 0.0357,
|
| 971 |
+
"step": 1220
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 9.39,
|
| 975 |
+
"grad_norm": 0.17311328649520874,
|
| 976 |
+
"learning_rate": 1.2213740458015267e-05,
|
| 977 |
+
"loss": 0.0336,
|
| 978 |
+
"step": 1230
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 9.47,
|
| 982 |
+
"grad_norm": 0.09014473855495453,
|
| 983 |
+
"learning_rate": 1.0687022900763359e-05,
|
| 984 |
+
"loss": 0.0514,
|
| 985 |
+
"step": 1240
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 9.54,
|
| 989 |
+
"grad_norm": 0.07394669950008392,
|
| 990 |
+
"learning_rate": 9.16030534351145e-06,
|
| 991 |
+
"loss": 0.0534,
|
| 992 |
+
"step": 1250
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 9.62,
|
| 996 |
+
"grad_norm": 0.11295180022716522,
|
| 997 |
+
"learning_rate": 7.633587786259543e-06,
|
| 998 |
+
"loss": 0.0254,
|
| 999 |
+
"step": 1260
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 9.69,
|
| 1003 |
+
"grad_norm": 1.9013243913650513,
|
| 1004 |
+
"learning_rate": 6.106870229007634e-06,
|
| 1005 |
+
"loss": 0.0919,
|
| 1006 |
+
"step": 1270
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 9.77,
|
| 1010 |
+
"grad_norm": 0.08759523928165436,
|
| 1011 |
+
"learning_rate": 4.580152671755725e-06,
|
| 1012 |
+
"loss": 0.0476,
|
| 1013 |
+
"step": 1280
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 9.85,
|
| 1017 |
+
"grad_norm": 0.07936747372150421,
|
| 1018 |
+
"learning_rate": 3.053435114503817e-06,
|
| 1019 |
+
"loss": 0.0365,
|
| 1020 |
+
"step": 1290
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 9.92,
|
| 1024 |
+
"grad_norm": 0.13975408673286438,
|
| 1025 |
+
"learning_rate": 1.5267175572519084e-06,
|
| 1026 |
+
"loss": 0.0228,
|
| 1027 |
+
"step": 1300
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 9.92,
|
| 1031 |
+
"eval_accuracy": 0.5882917466410749,
|
| 1032 |
+
"eval_loss": 1.6925907135009766,
|
| 1033 |
+
"eval_runtime": 11.1309,
|
| 1034 |
+
"eval_samples_per_second": 93.613,
|
| 1035 |
+
"eval_steps_per_second": 11.769,
|
| 1036 |
+
"step": 1300
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 10.0,
|
| 1040 |
+
"grad_norm": 0.3255839943885803,
|
| 1041 |
+
"learning_rate": 0.0,
|
| 1042 |
+
"loss": 0.0364,
|
| 1043 |
+
"step": 1310
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 10.0,
|
| 1047 |
+
"step": 1310,
|
| 1048 |
+
"total_flos": 3.229206972532531e+18,
|
| 1049 |
+
"train_loss": 0.583979975267221,
|
| 1050 |
+
"train_runtime": 954.0647,
|
| 1051 |
+
"train_samples_per_second": 43.676,
|
| 1052 |
+
"train_steps_per_second": 1.373
|
| 1053 |
+
}
|
| 1054 |
+
],
|
| 1055 |
+
"logging_steps": 10,
|
| 1056 |
+
"max_steps": 1310,
|
| 1057 |
+
"num_input_tokens_seen": 0,
|
| 1058 |
+
"num_train_epochs": 10,
|
| 1059 |
+
"save_steps": 100,
|
| 1060 |
+
"total_flos": 3.229206972532531e+18,
|
| 1061 |
+
"train_batch_size": 32,
|
| 1062 |
+
"trial_name": null,
|
| 1063 |
+
"trial_params": null
|
| 1064 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3eef633eb9cf5a705913711c5af3d30b3d29beb13aa88bc2c7577189df45835
|
| 3 |
+
size 4920
|