Commit
•
e551c7a
1
Parent(s):
a412f63
Upload 6 files
Browse files- README.md +97 -0
- all_results.json +14 -0
- eval_results.json +10 -0
- train_results.json +7 -0
- trainer_state.json +552 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- audio-classification
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
- precision
|
| 9 |
+
- f1
|
| 10 |
+
model-index:
|
| 11 |
+
- name: hubert-large-ls960-ft
|
| 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 |
+
# hubert-large-ls960-ft
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [facebook/hubert-large-ls960-ft](https://huggingface.co/facebook/hubert-large-ls960-ft) on the galsenai/waxal_dataset dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3272
|
| 23 |
+
- Accuracy: 0.9413
|
| 24 |
+
- Precision: 0.9865
|
| 25 |
+
- F1: 0.9628
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 3e-05
|
| 45 |
+
- train_batch_size: 12
|
| 46 |
+
- eval_batch_size: 12
|
| 47 |
+
- seed: 0
|
| 48 |
+
- gradient_accumulation_steps: 4
|
| 49 |
+
- total_train_batch_size: 48
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 32.0
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1 |
|
| 58 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|
|
| 59 |
+
| 4.7142 | 1.01 | 500 | 5.2765 | 0.0 | 0.0 | 0.0 |
|
| 60 |
+
| 4.396 | 2.02 | 1000 | 5.4145 | 0.0 | 0.0 | 0.0 |
|
| 61 |
+
| 3.8883 | 3.04 | 1500 | 4.4336 | 0.0474 | 0.0408 | 0.0104 |
|
| 62 |
+
| 2.7848 | 4.05 | 2000 | 3.9772 | 0.1300 | 0.1281 | 0.0964 |
|
| 63 |
+
| 1.8649 | 5.06 | 2500 | 3.4482 | 0.1576 | 0.3339 | 0.1547 |
|
| 64 |
+
| 1.3084 | 6.07 | 3000 | 2.9703 | 0.3081 | 0.5296 | 0.3402 |
|
| 65 |
+
| 0.9868 | 7.08 | 3500 | 2.3985 | 0.4687 | 0.8032 | 0.5353 |
|
| 66 |
+
| 0.7679 | 8.1 | 4000 | 1.7937 | 0.6521 | 0.8389 | 0.7095 |
|
| 67 |
+
| 0.6232 | 9.11 | 4500 | 1.4768 | 0.7389 | 0.8698 | 0.7847 |
|
| 68 |
+
| 0.5126 | 10.12 | 5000 | 1.0542 | 0.8287 | 0.9443 | 0.8763 |
|
| 69 |
+
| 0.4453 | 11.13 | 5500 | 0.9050 | 0.8518 | 0.9511 | 0.8960 |
|
| 70 |
+
| 0.3775 | 12.15 | 6000 | 0.6996 | 0.8928 | 0.9662 | 0.9266 |
|
| 71 |
+
| 0.3568 | 13.16 | 6500 | 0.6157 | 0.8958 | 0.9743 | 0.9285 |
|
| 72 |
+
| 0.3165 | 14.17 | 7000 | 0.4925 | 0.9151 | 0.9764 | 0.9436 |
|
| 73 |
+
| 0.2951 | 15.18 | 7500 | 0.4992 | 0.9038 | 0.9773 | 0.9369 |
|
| 74 |
+
| 0.2763 | 16.19 | 8000 | 0.5212 | 0.9072 | 0.9821 | 0.9404 |
|
| 75 |
+
| 0.2634 | 17.21 | 8500 | 0.5201 | 0.9087 | 0.9817 | 0.9418 |
|
| 76 |
+
| 0.2422 | 18.22 | 9000 | 0.4504 | 0.9235 | 0.9840 | 0.9514 |
|
| 77 |
+
| 0.236 | 19.23 | 9500 | 0.3829 | 0.9257 | 0.9825 | 0.9518 |
|
| 78 |
+
| 0.2272 | 20.24 | 10000 | 0.4632 | 0.9155 | 0.9822 | 0.9451 |
|
| 79 |
+
| 0.226 | 21.25 | 10500 | 0.4731 | 0.9159 | 0.9837 | 0.9470 |
|
| 80 |
+
| 0.2129 | 22.27 | 11000 | 0.3814 | 0.9299 | 0.9832 | 0.9549 |
|
| 81 |
+
| 0.2009 | 23.28 | 11500 | 0.4119 | 0.9257 | 0.9814 | 0.9515 |
|
| 82 |
+
| 0.1973 | 24.29 | 12000 | 0.4310 | 0.9216 | 0.9843 | 0.9493 |
|
| 83 |
+
| 0.1965 | 25.3 | 12500 | 0.3272 | 0.9413 | 0.9865 | 0.9628 |
|
| 84 |
+
| 0.1989 | 26.32 | 13000 | 0.4231 | 0.9242 | 0.9878 | 0.9528 |
|
| 85 |
+
| 0.1916 | 27.33 | 13500 | 0.3978 | 0.9284 | 0.9876 | 0.9559 |
|
| 86 |
+
| 0.1849 | 28.34 | 14000 | 0.4529 | 0.9216 | 0.9865 | 0.9507 |
|
| 87 |
+
| 0.1844 | 29.35 | 14500 | 0.3854 | 0.9314 | 0.9864 | 0.9566 |
|
| 88 |
+
| 0.1831 | 30.36 | 15000 | 0.4178 | 0.9257 | 0.9853 | 0.9528 |
|
| 89 |
+
| 0.1778 | 31.38 | 15500 | 0.3737 | 0.9360 | 0.9884 | 0.9606 |
|
| 90 |
+
|
| 91 |
+
|
| 92 |
+
### Framework versions
|
| 93 |
+
|
| 94 |
+
- Transformers 4.27.0.dev0
|
| 95 |
+
- Pytorch 1.11.0+cu113
|
| 96 |
+
- Datasets 2.9.1.dev0
|
| 97 |
+
- Tokenizers 0.13.2
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"eval_accuracy": 0.9412656309208033,
|
| 4 |
+
"eval_f1": 0.9627712250405202,
|
| 5 |
+
"eval_loss": 0.327240914106369,
|
| 6 |
+
"eval_precision": 0.9865248931670977,
|
| 7 |
+
"eval_runtime": 205.0233,
|
| 8 |
+
"eval_samples_per_second": 12.872,
|
| 9 |
+
"eval_steps_per_second": 1.073,
|
| 10 |
+
"train_loss": 0.858633176759187,
|
| 11 |
+
"train_runtime": 80385.1912,
|
| 12 |
+
"train_samples_per_second": 9.454,
|
| 13 |
+
"train_steps_per_second": 0.197
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"eval_accuracy": 0.9412656309208033,
|
| 4 |
+
"eval_f1": 0.9627712250405202,
|
| 5 |
+
"eval_loss": 0.327240914106369,
|
| 6 |
+
"eval_precision": 0.9865248931670977,
|
| 7 |
+
"eval_runtime": 205.0233,
|
| 8 |
+
"eval_samples_per_second": 12.872,
|
| 9 |
+
"eval_steps_per_second": 1.073
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"train_loss": 0.858633176759187,
|
| 4 |
+
"train_runtime": 80385.1912,
|
| 5 |
+
"train_samples_per_second": 9.454,
|
| 6 |
+
"train_steps_per_second": 0.197
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,552 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9412656309208033,
|
| 3 |
+
"best_model_checkpoint": "hubert-large-ls960-ft/checkpoint-12500",
|
| 4 |
+
"epoch": 31.998484082870135,
|
| 5 |
+
"global_step": 15808,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.01,
|
| 12 |
+
"learning_rate": 9.487666034155598e-06,
|
| 13 |
+
"loss": 4.7142,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.01,
|
| 18 |
+
"eval_accuracy": 0.0,
|
| 19 |
+
"eval_f1": 0.0,
|
| 20 |
+
"eval_loss": 5.276514053344727,
|
| 21 |
+
"eval_precision": 0.0,
|
| 22 |
+
"eval_runtime": 207.9912,
|
| 23 |
+
"eval_samples_per_second": 12.688,
|
| 24 |
+
"eval_steps_per_second": 1.058,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.02,
|
| 29 |
+
"learning_rate": 1.8975332068311197e-05,
|
| 30 |
+
"loss": 4.396,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.02,
|
| 35 |
+
"eval_accuracy": 0.0,
|
| 36 |
+
"eval_f1": 0.0,
|
| 37 |
+
"eval_loss": 5.414546012878418,
|
| 38 |
+
"eval_precision": 0.0,
|
| 39 |
+
"eval_runtime": 211.3332,
|
| 40 |
+
"eval_samples_per_second": 12.487,
|
| 41 |
+
"eval_steps_per_second": 1.041,
|
| 42 |
+
"step": 1000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.04,
|
| 46 |
+
"learning_rate": 2.846299810246679e-05,
|
| 47 |
+
"loss": 3.8883,
|
| 48 |
+
"step": 1500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.04,
|
| 52 |
+
"eval_accuracy": 0.0473664266767715,
|
| 53 |
+
"eval_f1": 0.010399469379098707,
|
| 54 |
+
"eval_loss": 4.433555603027344,
|
| 55 |
+
"eval_precision": 0.04084585694141838,
|
| 56 |
+
"eval_runtime": 206.03,
|
| 57 |
+
"eval_samples_per_second": 12.809,
|
| 58 |
+
"eval_steps_per_second": 1.068,
|
| 59 |
+
"step": 1500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.05,
|
| 63 |
+
"learning_rate": 2.9116468686300697e-05,
|
| 64 |
+
"loss": 2.7848,
|
| 65 |
+
"step": 2000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.05,
|
| 69 |
+
"eval_accuracy": 0.129973474801061,
|
| 70 |
+
"eval_f1": 0.09643252305766986,
|
| 71 |
+
"eval_loss": 3.9772207736968994,
|
| 72 |
+
"eval_precision": 0.1280919938791079,
|
| 73 |
+
"eval_runtime": 212.3184,
|
| 74 |
+
"eval_samples_per_second": 12.429,
|
| 75 |
+
"eval_steps_per_second": 1.036,
|
| 76 |
+
"step": 2000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.06,
|
| 80 |
+
"learning_rate": 2.8062135376396992e-05,
|
| 81 |
+
"loss": 1.8649,
|
| 82 |
+
"step": 2500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 5.06,
|
| 86 |
+
"eval_accuracy": 0.15763546798029557,
|
| 87 |
+
"eval_f1": 0.15466013987384877,
|
| 88 |
+
"eval_loss": 3.44816255569458,
|
| 89 |
+
"eval_precision": 0.33391187818919965,
|
| 90 |
+
"eval_runtime": 206.6675,
|
| 91 |
+
"eval_samples_per_second": 12.769,
|
| 92 |
+
"eval_steps_per_second": 1.065,
|
| 93 |
+
"step": 2500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 6.07,
|
| 97 |
+
"learning_rate": 2.700780206649329e-05,
|
| 98 |
+
"loss": 1.3084,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.07,
|
| 103 |
+
"eval_accuracy": 0.3080712391057219,
|
| 104 |
+
"eval_f1": 0.3402390216080642,
|
| 105 |
+
"eval_loss": 2.9702537059783936,
|
| 106 |
+
"eval_precision": 0.5296031035295795,
|
| 107 |
+
"eval_runtime": 212.8576,
|
| 108 |
+
"eval_samples_per_second": 12.398,
|
| 109 |
+
"eval_steps_per_second": 1.034,
|
| 110 |
+
"step": 3000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.08,
|
| 114 |
+
"learning_rate": 2.5953468756589585e-05,
|
| 115 |
+
"loss": 0.9868,
|
| 116 |
+
"step": 3500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.08,
|
| 120 |
+
"eval_accuracy": 0.46873815839333083,
|
| 121 |
+
"eval_f1": 0.5353322629682942,
|
| 122 |
+
"eval_loss": 2.3984930515289307,
|
| 123 |
+
"eval_precision": 0.8031566212997642,
|
| 124 |
+
"eval_runtime": 207.1643,
|
| 125 |
+
"eval_samples_per_second": 12.739,
|
| 126 |
+
"eval_steps_per_second": 1.062,
|
| 127 |
+
"step": 3500
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 8.1,
|
| 131 |
+
"learning_rate": 2.489913544668588e-05,
|
| 132 |
+
"loss": 0.7679,
|
| 133 |
+
"step": 4000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 8.1,
|
| 137 |
+
"eval_accuracy": 0.6521409624857901,
|
| 138 |
+
"eval_f1": 0.7095065774545717,
|
| 139 |
+
"eval_loss": 1.7936781644821167,
|
| 140 |
+
"eval_precision": 0.8388581448735327,
|
| 141 |
+
"eval_runtime": 207.3219,
|
| 142 |
+
"eval_samples_per_second": 12.729,
|
| 143 |
+
"eval_steps_per_second": 1.061,
|
| 144 |
+
"step": 4000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.11,
|
| 148 |
+
"learning_rate": 2.3844802136782175e-05,
|
| 149 |
+
"loss": 0.6232,
|
| 150 |
+
"step": 4500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 9.11,
|
| 154 |
+
"eval_accuracy": 0.7389162561576355,
|
| 155 |
+
"eval_f1": 0.784666736405717,
|
| 156 |
+
"eval_loss": 1.4767512083053589,
|
| 157 |
+
"eval_precision": 0.8697758947640245,
|
| 158 |
+
"eval_runtime": 211.7813,
|
| 159 |
+
"eval_samples_per_second": 12.461,
|
| 160 |
+
"eval_steps_per_second": 1.039,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 10.12,
|
| 165 |
+
"learning_rate": 2.279046882687847e-05,
|
| 166 |
+
"loss": 0.5126,
|
| 167 |
+
"step": 5000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 10.12,
|
| 171 |
+
"eval_accuracy": 0.8287230011367942,
|
| 172 |
+
"eval_f1": 0.8762583534303519,
|
| 173 |
+
"eval_loss": 1.054182529449463,
|
| 174 |
+
"eval_precision": 0.9442564310504037,
|
| 175 |
+
"eval_runtime": 210.7585,
|
| 176 |
+
"eval_samples_per_second": 12.521,
|
| 177 |
+
"eval_steps_per_second": 1.044,
|
| 178 |
+
"step": 5000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 11.13,
|
| 182 |
+
"learning_rate": 2.1736135516974768e-05,
|
| 183 |
+
"loss": 0.4453,
|
| 184 |
+
"step": 5500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 11.13,
|
| 188 |
+
"eval_accuracy": 0.8518378173550587,
|
| 189 |
+
"eval_f1": 0.8959895568662314,
|
| 190 |
+
"eval_loss": 0.9049583673477173,
|
| 191 |
+
"eval_precision": 0.9511477433978877,
|
| 192 |
+
"eval_runtime": 205.4589,
|
| 193 |
+
"eval_samples_per_second": 12.844,
|
| 194 |
+
"eval_steps_per_second": 1.071,
|
| 195 |
+
"step": 5500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.15,
|
| 199 |
+
"learning_rate": 2.0681802207071063e-05,
|
| 200 |
+
"loss": 0.3775,
|
| 201 |
+
"step": 6000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.15,
|
| 205 |
+
"eval_accuracy": 0.8927624100037893,
|
| 206 |
+
"eval_f1": 0.9265578308615539,
|
| 207 |
+
"eval_loss": 0.699573278427124,
|
| 208 |
+
"eval_precision": 0.9662252548898577,
|
| 209 |
+
"eval_runtime": 212.4773,
|
| 210 |
+
"eval_samples_per_second": 12.42,
|
| 211 |
+
"eval_steps_per_second": 1.035,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 13.16,
|
| 216 |
+
"learning_rate": 1.9627468897167357e-05,
|
| 217 |
+
"loss": 0.3568,
|
| 218 |
+
"step": 6500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 13.16,
|
| 222 |
+
"eval_accuracy": 0.8957938613111027,
|
| 223 |
+
"eval_f1": 0.9284579551378114,
|
| 224 |
+
"eval_loss": 0.6156648993492126,
|
| 225 |
+
"eval_precision": 0.9743169949637361,
|
| 226 |
+
"eval_runtime": 210.2311,
|
| 227 |
+
"eval_samples_per_second": 12.553,
|
| 228 |
+
"eval_steps_per_second": 1.046,
|
| 229 |
+
"step": 6500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 14.17,
|
| 233 |
+
"learning_rate": 1.8573135587263652e-05,
|
| 234 |
+
"loss": 0.3165,
|
| 235 |
+
"step": 7000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 14.17,
|
| 239 |
+
"eval_accuracy": 0.9151193633952255,
|
| 240 |
+
"eval_f1": 0.943623023847651,
|
| 241 |
+
"eval_loss": 0.4924512505531311,
|
| 242 |
+
"eval_precision": 0.9763736094436646,
|
| 243 |
+
"eval_runtime": 206.0776,
|
| 244 |
+
"eval_samples_per_second": 12.806,
|
| 245 |
+
"eval_steps_per_second": 1.068,
|
| 246 |
+
"step": 7000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.18,
|
| 250 |
+
"learning_rate": 1.751880227735995e-05,
|
| 251 |
+
"loss": 0.2951,
|
| 252 |
+
"step": 7500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 15.18,
|
| 256 |
+
"eval_accuracy": 0.9037514209928003,
|
| 257 |
+
"eval_f1": 0.9368584519497015,
|
| 258 |
+
"eval_loss": 0.49918055534362793,
|
| 259 |
+
"eval_precision": 0.9772932630240506,
|
| 260 |
+
"eval_runtime": 205.4956,
|
| 261 |
+
"eval_samples_per_second": 12.842,
|
| 262 |
+
"eval_steps_per_second": 1.071,
|
| 263 |
+
"step": 7500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 16.19,
|
| 267 |
+
"learning_rate": 1.6464468967456245e-05,
|
| 268 |
+
"loss": 0.2763,
|
| 269 |
+
"step": 8000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 16.19,
|
| 273 |
+
"eval_accuracy": 0.9071618037135278,
|
| 274 |
+
"eval_f1": 0.9403855453166055,
|
| 275 |
+
"eval_loss": 0.5212343335151672,
|
| 276 |
+
"eval_precision": 0.9820562398022753,
|
| 277 |
+
"eval_runtime": 211.5185,
|
| 278 |
+
"eval_samples_per_second": 12.476,
|
| 279 |
+
"eval_steps_per_second": 1.04,
|
| 280 |
+
"step": 8000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 17.21,
|
| 284 |
+
"learning_rate": 1.541013565755254e-05,
|
| 285 |
+
"loss": 0.2634,
|
| 286 |
+
"step": 8500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 17.21,
|
| 290 |
+
"eval_accuracy": 0.9086775293671845,
|
| 291 |
+
"eval_f1": 0.9417778927796274,
|
| 292 |
+
"eval_loss": 0.5201326012611389,
|
| 293 |
+
"eval_precision": 0.9816838665228488,
|
| 294 |
+
"eval_runtime": 205.8774,
|
| 295 |
+
"eval_samples_per_second": 12.818,
|
| 296 |
+
"eval_steps_per_second": 1.069,
|
| 297 |
+
"step": 8500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 18.22,
|
| 301 |
+
"learning_rate": 1.4355802347648837e-05,
|
| 302 |
+
"loss": 0.2422,
|
| 303 |
+
"step": 9000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 18.22,
|
| 307 |
+
"eval_accuracy": 0.9234558544903373,
|
| 308 |
+
"eval_f1": 0.9514314684994079,
|
| 309 |
+
"eval_loss": 0.45036178827285767,
|
| 310 |
+
"eval_precision": 0.9839863223736393,
|
| 311 |
+
"eval_runtime": 211.5273,
|
| 312 |
+
"eval_samples_per_second": 12.476,
|
| 313 |
+
"eval_steps_per_second": 1.04,
|
| 314 |
+
"step": 9000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 19.23,
|
| 318 |
+
"learning_rate": 1.3301469037745133e-05,
|
| 319 |
+
"loss": 0.236,
|
| 320 |
+
"step": 9500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 19.23,
|
| 324 |
+
"eval_accuracy": 0.9257294429708223,
|
| 325 |
+
"eval_f1": 0.9518288569523149,
|
| 326 |
+
"eval_loss": 0.3829096853733063,
|
| 327 |
+
"eval_precision": 0.9824861532841103,
|
| 328 |
+
"eval_runtime": 210.8744,
|
| 329 |
+
"eval_samples_per_second": 12.515,
|
| 330 |
+
"eval_steps_per_second": 1.043,
|
| 331 |
+
"step": 9500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 20.24,
|
| 335 |
+
"learning_rate": 1.2247135727841428e-05,
|
| 336 |
+
"loss": 0.2272,
|
| 337 |
+
"step": 10000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 20.24,
|
| 341 |
+
"eval_accuracy": 0.9154982948086396,
|
| 342 |
+
"eval_f1": 0.9451193658066668,
|
| 343 |
+
"eval_loss": 0.4632132947444916,
|
| 344 |
+
"eval_precision": 0.9822249030180286,
|
| 345 |
+
"eval_runtime": 207.0475,
|
| 346 |
+
"eval_samples_per_second": 12.746,
|
| 347 |
+
"eval_steps_per_second": 1.063,
|
| 348 |
+
"step": 10000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 21.25,
|
| 352 |
+
"learning_rate": 1.1192802417937724e-05,
|
| 353 |
+
"loss": 0.226,
|
| 354 |
+
"step": 10500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 21.25,
|
| 358 |
+
"eval_accuracy": 0.9158772262220538,
|
| 359 |
+
"eval_f1": 0.947028332160647,
|
| 360 |
+
"eval_loss": 0.47312408685684204,
|
| 361 |
+
"eval_precision": 0.9837188228053231,
|
| 362 |
+
"eval_runtime": 210.5001,
|
| 363 |
+
"eval_samples_per_second": 12.537,
|
| 364 |
+
"eval_steps_per_second": 1.045,
|
| 365 |
+
"step": 10500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 22.27,
|
| 369 |
+
"learning_rate": 1.013846910803402e-05,
|
| 370 |
+
"loss": 0.2129,
|
| 371 |
+
"step": 11000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 22.27,
|
| 375 |
+
"eval_accuracy": 0.9298976885183782,
|
| 376 |
+
"eval_f1": 0.9548846481808738,
|
| 377 |
+
"eval_loss": 0.38141778111457825,
|
| 378 |
+
"eval_precision": 0.983160805693422,
|
| 379 |
+
"eval_runtime": 210.7476,
|
| 380 |
+
"eval_samples_per_second": 12.522,
|
| 381 |
+
"eval_steps_per_second": 1.044,
|
| 382 |
+
"step": 11000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 23.28,
|
| 386 |
+
"learning_rate": 9.084135798130316e-06,
|
| 387 |
+
"loss": 0.2009,
|
| 388 |
+
"step": 11500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 23.28,
|
| 392 |
+
"eval_accuracy": 0.9257294429708223,
|
| 393 |
+
"eval_f1": 0.9514840419100091,
|
| 394 |
+
"eval_loss": 0.4119464159011841,
|
| 395 |
+
"eval_precision": 0.9814366336318854,
|
| 396 |
+
"eval_runtime": 206.3284,
|
| 397 |
+
"eval_samples_per_second": 12.79,
|
| 398 |
+
"eval_steps_per_second": 1.066,
|
| 399 |
+
"step": 11500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 24.29,
|
| 403 |
+
"learning_rate": 8.029802488226612e-06,
|
| 404 |
+
"loss": 0.1973,
|
| 405 |
+
"step": 12000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 24.29,
|
| 409 |
+
"eval_accuracy": 0.9215611974232664,
|
| 410 |
+
"eval_f1": 0.9492716683321308,
|
| 411 |
+
"eval_loss": 0.43100807070732117,
|
| 412 |
+
"eval_precision": 0.98427363081955,
|
| 413 |
+
"eval_runtime": 210.5932,
|
| 414 |
+
"eval_samples_per_second": 12.531,
|
| 415 |
+
"eval_steps_per_second": 1.045,
|
| 416 |
+
"step": 12000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 25.3,
|
| 420 |
+
"learning_rate": 6.975469178322908e-06,
|
| 421 |
+
"loss": 0.1965,
|
| 422 |
+
"step": 12500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 25.3,
|
| 426 |
+
"eval_accuracy": 0.9412656309208033,
|
| 427 |
+
"eval_f1": 0.9627712250405202,
|
| 428 |
+
"eval_loss": 0.327240914106369,
|
| 429 |
+
"eval_precision": 0.9865248931670977,
|
| 430 |
+
"eval_runtime": 207.1296,
|
| 431 |
+
"eval_samples_per_second": 12.741,
|
| 432 |
+
"eval_steps_per_second": 1.062,
|
| 433 |
+
"step": 12500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 26.32,
|
| 437 |
+
"learning_rate": 5.9211358684192026e-06,
|
| 438 |
+
"loss": 0.1989,
|
| 439 |
+
"step": 13000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 26.32,
|
| 443 |
+
"eval_accuracy": 0.9242137173171656,
|
| 444 |
+
"eval_f1": 0.9527761591577618,
|
| 445 |
+
"eval_loss": 0.4231082797050476,
|
| 446 |
+
"eval_precision": 0.9877979282330233,
|
| 447 |
+
"eval_runtime": 212.06,
|
| 448 |
+
"eval_samples_per_second": 12.445,
|
| 449 |
+
"eval_steps_per_second": 1.037,
|
| 450 |
+
"step": 13000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 27.33,
|
| 454 |
+
"learning_rate": 4.866802558515498e-06,
|
| 455 |
+
"loss": 0.1916,
|
| 456 |
+
"step": 13500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 27.33,
|
| 460 |
+
"eval_accuracy": 0.9283819628647215,
|
| 461 |
+
"eval_f1": 0.9559474626706007,
|
| 462 |
+
"eval_loss": 0.3977676033973694,
|
| 463 |
+
"eval_precision": 0.9875814057989544,
|
| 464 |
+
"eval_runtime": 205.5092,
|
| 465 |
+
"eval_samples_per_second": 12.841,
|
| 466 |
+
"eval_steps_per_second": 1.071,
|
| 467 |
+
"step": 13500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 28.34,
|
| 471 |
+
"learning_rate": 3.8124692486117947e-06,
|
| 472 |
+
"loss": 0.1849,
|
| 473 |
+
"step": 14000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 28.34,
|
| 477 |
+
"eval_accuracy": 0.9215611974232664,
|
| 478 |
+
"eval_f1": 0.9506673563440831,
|
| 479 |
+
"eval_loss": 0.4528682827949524,
|
| 480 |
+
"eval_precision": 0.9865112585967588,
|
| 481 |
+
"eval_runtime": 212.4387,
|
| 482 |
+
"eval_samples_per_second": 12.422,
|
| 483 |
+
"eval_steps_per_second": 1.036,
|
| 484 |
+
"step": 14000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 29.35,
|
| 488 |
+
"learning_rate": 2.7581359387080904e-06,
|
| 489 |
+
"loss": 0.1844,
|
| 490 |
+
"step": 14500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 29.35,
|
| 494 |
+
"eval_accuracy": 0.9314134141720348,
|
| 495 |
+
"eval_f1": 0.9566213429287339,
|
| 496 |
+
"eval_loss": 0.3853737413883209,
|
| 497 |
+
"eval_precision": 0.9863541882706378,
|
| 498 |
+
"eval_runtime": 205.8351,
|
| 499 |
+
"eval_samples_per_second": 12.821,
|
| 500 |
+
"eval_steps_per_second": 1.069,
|
| 501 |
+
"step": 14500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 30.36,
|
| 505 |
+
"learning_rate": 1.7038026288043862e-06,
|
| 506 |
+
"loss": 0.1831,
|
| 507 |
+
"step": 15000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 30.36,
|
| 511 |
+
"eval_accuracy": 0.9257294429708223,
|
| 512 |
+
"eval_f1": 0.9527879636596958,
|
| 513 |
+
"eval_loss": 0.41776272654533386,
|
| 514 |
+
"eval_precision": 0.9853006909522924,
|
| 515 |
+
"eval_runtime": 210.65,
|
| 516 |
+
"eval_samples_per_second": 12.528,
|
| 517 |
+
"eval_steps_per_second": 1.044,
|
| 518 |
+
"step": 15000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 31.38,
|
| 522 |
+
"learning_rate": 6.494693189006819e-07,
|
| 523 |
+
"loss": 0.1778,
|
| 524 |
+
"step": 15500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 31.38,
|
| 528 |
+
"eval_accuracy": 0.9359605911330049,
|
| 529 |
+
"eval_f1": 0.9606362253618668,
|
| 530 |
+
"eval_loss": 0.37370702624320984,
|
| 531 |
+
"eval_precision": 0.9883638648463977,
|
| 532 |
+
"eval_runtime": 211.0911,
|
| 533 |
+
"eval_samples_per_second": 12.502,
|
| 534 |
+
"eval_steps_per_second": 1.042,
|
| 535 |
+
"step": 15500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 32.0,
|
| 539 |
+
"step": 15808,
|
| 540 |
+
"total_flos": 1.2696857331997786e+20,
|
| 541 |
+
"train_loss": 0.858633176759187,
|
| 542 |
+
"train_runtime": 80385.1912,
|
| 543 |
+
"train_samples_per_second": 9.454,
|
| 544 |
+
"train_steps_per_second": 0.197
|
| 545 |
+
}
|
| 546 |
+
],
|
| 547 |
+
"max_steps": 15808,
|
| 548 |
+
"num_train_epochs": 32,
|
| 549 |
+
"total_flos": 1.2696857331997786e+20,
|
| 550 |
+
"trial_name": null,
|
| 551 |
+
"trial_params": null
|
| 552 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d3e78ce7e6b5357e48fd160a2174336ba6ca6dd12d39d163281dca96d3ddbde
|
| 3 |
+
size 3503
|