Commit
•
3422368
1
Parent(s):
4522d7b
Upload 6 files
Browse files- README.md +96 -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 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- audio-classification
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
- precision
|
| 8 |
+
- f1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: wavlm-large
|
| 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 |
+
# wavlm-large
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [microsoft/wavlm-large](https://huggingface.co/microsoft/wavlm-large) on the galsenai/waxal_dataset dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5936
|
| 22 |
+
- Accuracy: 0.8950
|
| 23 |
+
- Precision: 0.9789
|
| 24 |
+
- F1: 0.9334
|
| 25 |
+
|
| 26 |
+
## Model description
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Intended uses & limitations
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training and evaluation data
|
| 35 |
+
|
| 36 |
+
More information needed
|
| 37 |
+
|
| 38 |
+
## Training procedure
|
| 39 |
+
|
| 40 |
+
### Training hyperparameters
|
| 41 |
+
|
| 42 |
+
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 3e-05
|
| 44 |
+
- train_batch_size: 12
|
| 45 |
+
- eval_batch_size: 12
|
| 46 |
+
- seed: 0
|
| 47 |
+
- gradient_accumulation_steps: 4
|
| 48 |
+
- total_train_batch_size: 48
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 32.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | F1 |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|
|
| 58 |
+
| 4.7405 | 1.01 | 500 | 5.1525 | 0.0 | 0.0 | 0.0 |
|
| 59 |
+
| 4.4299 | 2.02 | 1000 | 5.8969 | 0.0 | 0.0 | 0.0 |
|
| 60 |
+
| 4.2868 | 3.04 | 1500 | 4.9304 | 0.0019 | 0.0031 | 0.0023 |
|
| 61 |
+
| 3.6242 | 4.05 | 2000 | 4.3396 | 0.0409 | 0.0224 | 0.0237 |
|
| 62 |
+
| 2.686 | 5.06 | 2500 | 3.9399 | 0.0549 | 0.0320 | 0.0308 |
|
| 63 |
+
| 1.9284 | 6.07 | 3000 | 3.7736 | 0.0500 | 0.0779 | 0.0442 |
|
| 64 |
+
| 1.3936 | 7.08 | 3500 | 3.5380 | 0.0947 | 0.1381 | 0.0916 |
|
| 65 |
+
| 1.0764 | 8.1 | 4000 | 3.3281 | 0.1584 | 0.3514 | 0.1839 |
|
| 66 |
+
| 0.872 | 9.11 | 4500 | 2.9592 | 0.2755 | 0.6027 | 0.3315 |
|
| 67 |
+
| 0.7026 | 10.12 | 5000 | 2.5049 | 0.3971 | 0.6971 | 0.4587 |
|
| 68 |
+
| 0.603 | 11.13 | 5500 | 2.1485 | 0.5479 | 0.8074 | 0.6129 |
|
| 69 |
+
| 0.5042 | 12.15 | 6000 | 1.6532 | 0.7014 | 0.8604 | 0.7544 |
|
| 70 |
+
| 0.4542 | 13.16 | 6500 | 1.4057 | 0.7435 | 0.8941 | 0.7990 |
|
| 71 |
+
| 0.388 | 14.17 | 7000 | 1.2338 | 0.7802 | 0.9219 | 0.8332 |
|
| 72 |
+
| 0.3515 | 15.18 | 7500 | 0.9898 | 0.8170 | 0.9433 | 0.8681 |
|
| 73 |
+
| 0.3195 | 16.19 | 8000 | 1.1404 | 0.8067 | 0.9523 | 0.8635 |
|
| 74 |
+
| 0.2882 | 17.21 | 8500 | 0.9811 | 0.8177 | 0.9540 | 0.8746 |
|
| 75 |
+
| 0.2695 | 18.22 | 9000 | 0.9483 | 0.8318 | 0.9616 | 0.8878 |
|
| 76 |
+
| 0.2535 | 19.23 | 9500 | 0.6694 | 0.8844 | 0.9692 | 0.9198 |
|
| 77 |
+
| 0.2437 | 20.24 | 10000 | 0.7546 | 0.8700 | 0.9656 | 0.9125 |
|
| 78 |
+
| 0.2376 | 21.25 | 10500 | 0.6698 | 0.8810 | 0.9695 | 0.9202 |
|
| 79 |
+
| 0.2214 | 22.27 | 11000 | 0.7156 | 0.8727 | 0.9726 | 0.9174 |
|
| 80 |
+
| 0.2148 | 23.28 | 11500 | 0.5982 | 0.8931 | 0.9711 | 0.9286 |
|
| 81 |
+
| 0.2087 | 24.29 | 12000 | 0.7109 | 0.8814 | 0.9757 | 0.9243 |
|
| 82 |
+
| 0.2039 | 25.3 | 12500 | 0.6577 | 0.8897 | 0.9799 | 0.9306 |
|
| 83 |
+
| 0.1997 | 26.32 | 13000 | 0.7307 | 0.8746 | 0.9774 | 0.9203 |
|
| 84 |
+
| 0.1896 | 27.33 | 13500 | 0.6143 | 0.8905 | 0.9748 | 0.9290 |
|
| 85 |
+
| 0.1869 | 28.34 | 14000 | 0.6380 | 0.8909 | 0.9739 | 0.9287 |
|
| 86 |
+
| 0.185 | 29.35 | 14500 | 0.6932 | 0.8871 | 0.9791 | 0.9289 |
|
| 87 |
+
| 0.1813 | 30.36 | 15000 | 0.5936 | 0.8950 | 0.9789 | 0.9334 |
|
| 88 |
+
| 0.1801 | 31.38 | 15500 | 0.6150 | 0.8947 | 0.9801 | 0.9334 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- Transformers 4.27.0.dev0
|
| 94 |
+
- Pytorch 1.11.0+cu113
|
| 95 |
+
- Datasets 2.9.1.dev0
|
| 96 |
+
- Tokenizers 0.13.2
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"eval_accuracy": 0.8950359984842744,
|
| 4 |
+
"eval_f1": 0.9333589015381497,
|
| 5 |
+
"eval_loss": 0.5935563445091248,
|
| 6 |
+
"eval_precision": 0.9789140060741345,
|
| 7 |
+
"eval_runtime": 230.8033,
|
| 8 |
+
"eval_samples_per_second": 11.434,
|
| 9 |
+
"eval_steps_per_second": 0.953,
|
| 10 |
+
"train_loss": 1.0038429288729,
|
| 11 |
+
"train_runtime": 86553.4289,
|
| 12 |
+
"train_samples_per_second": 8.78,
|
| 13 |
+
"train_steps_per_second": 0.183
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"eval_accuracy": 0.8950359984842744,
|
| 4 |
+
"eval_f1": 0.9333589015381497,
|
| 5 |
+
"eval_loss": 0.5935563445091248,
|
| 6 |
+
"eval_precision": 0.9789140060741345,
|
| 7 |
+
"eval_runtime": 230.8033,
|
| 8 |
+
"eval_samples_per_second": 11.434,
|
| 9 |
+
"eval_steps_per_second": 0.953
|
| 10 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 32.0,
|
| 3 |
+
"train_loss": 1.0038429288729,
|
| 4 |
+
"train_runtime": 86553.4289,
|
| 5 |
+
"train_samples_per_second": 8.78,
|
| 6 |
+
"train_steps_per_second": 0.183
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,552 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8950359984842744,
|
| 3 |
+
"best_model_checkpoint": "wavlm-large/checkpoint-15000",
|
| 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": 4.7405,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.01,
|
| 18 |
+
"eval_accuracy": 0.0,
|
| 19 |
+
"eval_f1": 0.0,
|
| 20 |
+
"eval_loss": 5.152532577514648,
|
| 21 |
+
"eval_precision": 0.0,
|
| 22 |
+
"eval_runtime": 231.7392,
|
| 23 |
+
"eval_samples_per_second": 11.388,
|
| 24 |
+
"eval_steps_per_second": 0.949,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.02,
|
| 29 |
+
"learning_rate": 1.8975332068311197e-05,
|
| 30 |
+
"loss": 4.4299,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.02,
|
| 35 |
+
"eval_accuracy": 0.0,
|
| 36 |
+
"eval_f1": 0.0,
|
| 37 |
+
"eval_loss": 5.896852016448975,
|
| 38 |
+
"eval_precision": 0.0,
|
| 39 |
+
"eval_runtime": 229.527,
|
| 40 |
+
"eval_samples_per_second": 11.498,
|
| 41 |
+
"eval_steps_per_second": 0.958,
|
| 42 |
+
"step": 1000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.04,
|
| 46 |
+
"learning_rate": 2.846299810246679e-05,
|
| 47 |
+
"loss": 4.2868,
|
| 48 |
+
"step": 1500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.04,
|
| 52 |
+
"eval_accuracy": 0.0018946570670708603,
|
| 53 |
+
"eval_f1": 0.002260186233515175,
|
| 54 |
+
"eval_loss": 4.930444717407227,
|
| 55 |
+
"eval_precision": 0.0030713084224438304,
|
| 56 |
+
"eval_runtime": 224.9204,
|
| 57 |
+
"eval_samples_per_second": 11.733,
|
| 58 |
+
"eval_steps_per_second": 0.978,
|
| 59 |
+
"step": 1500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.05,
|
| 63 |
+
"learning_rate": 2.9116468686300697e-05,
|
| 64 |
+
"loss": 3.6242,
|
| 65 |
+
"step": 2000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.05,
|
| 69 |
+
"eval_accuracy": 0.04092459264873058,
|
| 70 |
+
"eval_f1": 0.023734423060596616,
|
| 71 |
+
"eval_loss": 4.339611053466797,
|
| 72 |
+
"eval_precision": 0.02235030209371723,
|
| 73 |
+
"eval_runtime": 231.3364,
|
| 74 |
+
"eval_samples_per_second": 11.408,
|
| 75 |
+
"eval_steps_per_second": 0.951,
|
| 76 |
+
"step": 2000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 5.06,
|
| 80 |
+
"learning_rate": 2.8062135376396992e-05,
|
| 81 |
+
"loss": 2.686,
|
| 82 |
+
"step": 2500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 5.06,
|
| 86 |
+
"eval_accuracy": 0.054945054945054944,
|
| 87 |
+
"eval_f1": 0.030815499275931264,
|
| 88 |
+
"eval_loss": 3.9399423599243164,
|
| 89 |
+
"eval_precision": 0.03198760556742773,
|
| 90 |
+
"eval_runtime": 229.8015,
|
| 91 |
+
"eval_samples_per_second": 11.484,
|
| 92 |
+
"eval_steps_per_second": 0.957,
|
| 93 |
+
"step": 2500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 6.07,
|
| 97 |
+
"learning_rate": 2.700780206649329e-05,
|
| 98 |
+
"loss": 1.9284,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.07,
|
| 103 |
+
"eval_accuracy": 0.05001894657067071,
|
| 104 |
+
"eval_f1": 0.044225493965773466,
|
| 105 |
+
"eval_loss": 3.7735581398010254,
|
| 106 |
+
"eval_precision": 0.07786075378351333,
|
| 107 |
+
"eval_runtime": 229.6709,
|
| 108 |
+
"eval_samples_per_second": 11.49,
|
| 109 |
+
"eval_steps_per_second": 0.958,
|
| 110 |
+
"step": 3000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.08,
|
| 114 |
+
"learning_rate": 2.5953468756589585e-05,
|
| 115 |
+
"loss": 1.3936,
|
| 116 |
+
"step": 3500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.08,
|
| 120 |
+
"eval_accuracy": 0.094732853353543,
|
| 121 |
+
"eval_f1": 0.09155559566994678,
|
| 122 |
+
"eval_loss": 3.537994146347046,
|
| 123 |
+
"eval_precision": 0.13805010974816684,
|
| 124 |
+
"eval_runtime": 222.7345,
|
| 125 |
+
"eval_samples_per_second": 11.848,
|
| 126 |
+
"eval_steps_per_second": 0.988,
|
| 127 |
+
"step": 3500
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 8.1,
|
| 131 |
+
"learning_rate": 2.489913544668588e-05,
|
| 132 |
+
"loss": 1.0764,
|
| 133 |
+
"step": 4000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 8.1,
|
| 137 |
+
"eval_accuracy": 0.15839333080712392,
|
| 138 |
+
"eval_f1": 0.1838779712805326,
|
| 139 |
+
"eval_loss": 3.328141689300537,
|
| 140 |
+
"eval_precision": 0.35144388335355753,
|
| 141 |
+
"eval_runtime": 231.5928,
|
| 142 |
+
"eval_samples_per_second": 11.395,
|
| 143 |
+
"eval_steps_per_second": 0.95,
|
| 144 |
+
"step": 4000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.11,
|
| 148 |
+
"learning_rate": 2.3844802136782175e-05,
|
| 149 |
+
"loss": 0.872,
|
| 150 |
+
"step": 4500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 9.11,
|
| 154 |
+
"eval_accuracy": 0.2754831375521031,
|
| 155 |
+
"eval_f1": 0.33153761364278084,
|
| 156 |
+
"eval_loss": 2.959165096282959,
|
| 157 |
+
"eval_precision": 0.6026709651704474,
|
| 158 |
+
"eval_runtime": 229.3101,
|
| 159 |
+
"eval_samples_per_second": 11.508,
|
| 160 |
+
"eval_steps_per_second": 0.959,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 10.12,
|
| 165 |
+
"learning_rate": 2.279046882687847e-05,
|
| 166 |
+
"loss": 0.7026,
|
| 167 |
+
"step": 5000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 10.12,
|
| 171 |
+
"eval_accuracy": 0.3971201212580523,
|
| 172 |
+
"eval_f1": 0.4587007542105457,
|
| 173 |
+
"eval_loss": 2.504917860031128,
|
| 174 |
+
"eval_precision": 0.6970861611172207,
|
| 175 |
+
"eval_runtime": 229.0193,
|
| 176 |
+
"eval_samples_per_second": 11.523,
|
| 177 |
+
"eval_steps_per_second": 0.961,
|
| 178 |
+
"step": 5000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 11.13,
|
| 182 |
+
"learning_rate": 2.1736135516974768e-05,
|
| 183 |
+
"loss": 0.603,
|
| 184 |
+
"step": 5500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 11.13,
|
| 188 |
+
"eval_accuracy": 0.5479348237968927,
|
| 189 |
+
"eval_f1": 0.6128796045577696,
|
| 190 |
+
"eval_loss": 2.1484670639038086,
|
| 191 |
+
"eval_precision": 0.8073946450067734,
|
| 192 |
+
"eval_runtime": 226.9343,
|
| 193 |
+
"eval_samples_per_second": 11.629,
|
| 194 |
+
"eval_steps_per_second": 0.969,
|
| 195 |
+
"step": 5500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 12.15,
|
| 199 |
+
"learning_rate": 2.0681802207071063e-05,
|
| 200 |
+
"loss": 0.5042,
|
| 201 |
+
"step": 6000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 12.15,
|
| 205 |
+
"eval_accuracy": 0.7014020462296324,
|
| 206 |
+
"eval_f1": 0.7543542303794953,
|
| 207 |
+
"eval_loss": 1.6532080173492432,
|
| 208 |
+
"eval_precision": 0.8604295269195706,
|
| 209 |
+
"eval_runtime": 229.9455,
|
| 210 |
+
"eval_samples_per_second": 11.477,
|
| 211 |
+
"eval_steps_per_second": 0.957,
|
| 212 |
+
"step": 6000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 13.16,
|
| 216 |
+
"learning_rate": 1.9627468897167357e-05,
|
| 217 |
+
"loss": 0.4542,
|
| 218 |
+
"step": 6500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 13.16,
|
| 222 |
+
"eval_accuracy": 0.7434634331186055,
|
| 223 |
+
"eval_f1": 0.7989946253783239,
|
| 224 |
+
"eval_loss": 1.4056562185287476,
|
| 225 |
+
"eval_precision": 0.8941430548214513,
|
| 226 |
+
"eval_runtime": 223.4311,
|
| 227 |
+
"eval_samples_per_second": 11.811,
|
| 228 |
+
"eval_steps_per_second": 0.985,
|
| 229 |
+
"step": 6500
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 14.17,
|
| 233 |
+
"learning_rate": 1.8573135587263652e-05,
|
| 234 |
+
"loss": 0.388,
|
| 235 |
+
"step": 7000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 14.17,
|
| 239 |
+
"eval_accuracy": 0.7802197802197802,
|
| 240 |
+
"eval_f1": 0.8331608145111185,
|
| 241 |
+
"eval_loss": 1.233764410018921,
|
| 242 |
+
"eval_precision": 0.92185981522448,
|
| 243 |
+
"eval_runtime": 231.0616,
|
| 244 |
+
"eval_samples_per_second": 11.421,
|
| 245 |
+
"eval_steps_per_second": 0.952,
|
| 246 |
+
"step": 7000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 15.18,
|
| 250 |
+
"learning_rate": 1.751880227735995e-05,
|
| 251 |
+
"loss": 0.3515,
|
| 252 |
+
"step": 7500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 15.18,
|
| 256 |
+
"eval_accuracy": 0.8169761273209549,
|
| 257 |
+
"eval_f1": 0.8681431492951,
|
| 258 |
+
"eval_loss": 0.9898241758346558,
|
| 259 |
+
"eval_precision": 0.9432737435443141,
|
| 260 |
+
"eval_runtime": 229.2806,
|
| 261 |
+
"eval_samples_per_second": 11.51,
|
| 262 |
+
"eval_steps_per_second": 0.96,
|
| 263 |
+
"step": 7500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 16.19,
|
| 267 |
+
"learning_rate": 1.6464468967456245e-05,
|
| 268 |
+
"loss": 0.3195,
|
| 269 |
+
"step": 8000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 16.19,
|
| 273 |
+
"eval_accuracy": 0.8067449791587723,
|
| 274 |
+
"eval_f1": 0.8635483223798979,
|
| 275 |
+
"eval_loss": 1.1404353380203247,
|
| 276 |
+
"eval_precision": 0.9523356531691418,
|
| 277 |
+
"eval_runtime": 224.231,
|
| 278 |
+
"eval_samples_per_second": 11.769,
|
| 279 |
+
"eval_steps_per_second": 0.981,
|
| 280 |
+
"step": 8000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 17.21,
|
| 284 |
+
"learning_rate": 1.541013565755254e-05,
|
| 285 |
+
"loss": 0.2882,
|
| 286 |
+
"step": 8500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 17.21,
|
| 290 |
+
"eval_accuracy": 0.8177339901477833,
|
| 291 |
+
"eval_f1": 0.8745687675592978,
|
| 292 |
+
"eval_loss": 0.9810923933982849,
|
| 293 |
+
"eval_precision": 0.9540040162889087,
|
| 294 |
+
"eval_runtime": 230.2032,
|
| 295 |
+
"eval_samples_per_second": 11.464,
|
| 296 |
+
"eval_steps_per_second": 0.956,
|
| 297 |
+
"step": 8500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 18.22,
|
| 301 |
+
"learning_rate": 1.4355802347648837e-05,
|
| 302 |
+
"loss": 0.2695,
|
| 303 |
+
"step": 9000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 18.22,
|
| 307 |
+
"eval_accuracy": 0.8317544524441076,
|
| 308 |
+
"eval_f1": 0.8877909926292662,
|
| 309 |
+
"eval_loss": 0.9483387470245361,
|
| 310 |
+
"eval_precision": 0.9615575975196211,
|
| 311 |
+
"eval_runtime": 227.4444,
|
| 312 |
+
"eval_samples_per_second": 11.603,
|
| 313 |
+
"eval_steps_per_second": 0.967,
|
| 314 |
+
"step": 9000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 19.23,
|
| 318 |
+
"learning_rate": 1.3301469037745133e-05,
|
| 319 |
+
"loss": 0.2535,
|
| 320 |
+
"step": 9500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 19.23,
|
| 324 |
+
"eval_accuracy": 0.8844259189086775,
|
| 325 |
+
"eval_f1": 0.9198466869617786,
|
| 326 |
+
"eval_loss": 0.6694388389587402,
|
| 327 |
+
"eval_precision": 0.9692367120798446,
|
| 328 |
+
"eval_runtime": 229.887,
|
| 329 |
+
"eval_samples_per_second": 11.48,
|
| 330 |
+
"eval_steps_per_second": 0.957,
|
| 331 |
+
"step": 9500
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 20.24,
|
| 335 |
+
"learning_rate": 1.2247135727841428e-05,
|
| 336 |
+
"loss": 0.2437,
|
| 337 |
+
"step": 10000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 20.24,
|
| 341 |
+
"eval_accuracy": 0.870026525198939,
|
| 342 |
+
"eval_f1": 0.9124563736238709,
|
| 343 |
+
"eval_loss": 0.7545726299285889,
|
| 344 |
+
"eval_precision": 0.9655808349316077,
|
| 345 |
+
"eval_runtime": 228.7826,
|
| 346 |
+
"eval_samples_per_second": 11.535,
|
| 347 |
+
"eval_steps_per_second": 0.962,
|
| 348 |
+
"step": 10000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 21.25,
|
| 352 |
+
"learning_rate": 1.1192802417937724e-05,
|
| 353 |
+
"loss": 0.2376,
|
| 354 |
+
"step": 10500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 21.25,
|
| 358 |
+
"eval_accuracy": 0.88101553618795,
|
| 359 |
+
"eval_f1": 0.9202319275311999,
|
| 360 |
+
"eval_loss": 0.669846773147583,
|
| 361 |
+
"eval_precision": 0.9694585382786844,
|
| 362 |
+
"eval_runtime": 225.8023,
|
| 363 |
+
"eval_samples_per_second": 11.687,
|
| 364 |
+
"eval_steps_per_second": 0.974,
|
| 365 |
+
"step": 10500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 22.27,
|
| 369 |
+
"learning_rate": 1.013846910803402e-05,
|
| 370 |
+
"loss": 0.2214,
|
| 371 |
+
"step": 11000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 22.27,
|
| 375 |
+
"eval_accuracy": 0.8726790450928382,
|
| 376 |
+
"eval_f1": 0.9174460541012326,
|
| 377 |
+
"eval_loss": 0.7156072854995728,
|
| 378 |
+
"eval_precision": 0.972619503520754,
|
| 379 |
+
"eval_runtime": 230.4418,
|
| 380 |
+
"eval_samples_per_second": 11.452,
|
| 381 |
+
"eval_steps_per_second": 0.955,
|
| 382 |
+
"step": 11000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 23.28,
|
| 386 |
+
"learning_rate": 9.084135798130316e-06,
|
| 387 |
+
"loss": 0.2148,
|
| 388 |
+
"step": 11500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 23.28,
|
| 392 |
+
"eval_accuracy": 0.8931413414172035,
|
| 393 |
+
"eval_f1": 0.9285879507962082,
|
| 394 |
+
"eval_loss": 0.5982441902160645,
|
| 395 |
+
"eval_precision": 0.9711102757838663,
|
| 396 |
+
"eval_runtime": 229.8221,
|
| 397 |
+
"eval_samples_per_second": 11.483,
|
| 398 |
+
"eval_steps_per_second": 0.957,
|
| 399 |
+
"step": 11500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 24.29,
|
| 403 |
+
"learning_rate": 8.029802488226612e-06,
|
| 404 |
+
"loss": 0.2087,
|
| 405 |
+
"step": 12000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 24.29,
|
| 409 |
+
"eval_accuracy": 0.8813944676013642,
|
| 410 |
+
"eval_f1": 0.9242728727643769,
|
| 411 |
+
"eval_loss": 0.7108510732650757,
|
| 412 |
+
"eval_precision": 0.975723189780374,
|
| 413 |
+
"eval_runtime": 223.4291,
|
| 414 |
+
"eval_samples_per_second": 11.811,
|
| 415 |
+
"eval_steps_per_second": 0.985,
|
| 416 |
+
"step": 12000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 25.3,
|
| 420 |
+
"learning_rate": 6.975469178322908e-06,
|
| 421 |
+
"loss": 0.2039,
|
| 422 |
+
"step": 12500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 25.3,
|
| 426 |
+
"eval_accuracy": 0.8897309586964759,
|
| 427 |
+
"eval_f1": 0.93059059028571,
|
| 428 |
+
"eval_loss": 0.6577169895172119,
|
| 429 |
+
"eval_precision": 0.9799317453490524,
|
| 430 |
+
"eval_runtime": 229.7405,
|
| 431 |
+
"eval_samples_per_second": 11.487,
|
| 432 |
+
"eval_steps_per_second": 0.958,
|
| 433 |
+
"step": 12500
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 26.32,
|
| 437 |
+
"learning_rate": 5.9211358684192026e-06,
|
| 438 |
+
"loss": 0.1997,
|
| 439 |
+
"step": 13000
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 26.32,
|
| 443 |
+
"eval_accuracy": 0.874573702159909,
|
| 444 |
+
"eval_f1": 0.9203192830080359,
|
| 445 |
+
"eval_loss": 0.7307356595993042,
|
| 446 |
+
"eval_precision": 0.9774472205704657,
|
| 447 |
+
"eval_runtime": 226.7422,
|
| 448 |
+
"eval_samples_per_second": 11.639,
|
| 449 |
+
"eval_steps_per_second": 0.97,
|
| 450 |
+
"step": 13000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 27.33,
|
| 454 |
+
"learning_rate": 4.866802558515498e-06,
|
| 455 |
+
"loss": 0.1896,
|
| 456 |
+
"step": 13500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 27.33,
|
| 460 |
+
"eval_accuracy": 0.8904888215233043,
|
| 461 |
+
"eval_f1": 0.9289821714067877,
|
| 462 |
+
"eval_loss": 0.614262044429779,
|
| 463 |
+
"eval_precision": 0.9747583516326127,
|
| 464 |
+
"eval_runtime": 226.7104,
|
| 465 |
+
"eval_samples_per_second": 11.64,
|
| 466 |
+
"eval_steps_per_second": 0.97,
|
| 467 |
+
"step": 13500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 28.34,
|
| 471 |
+
"learning_rate": 3.8124692486117947e-06,
|
| 472 |
+
"loss": 0.1869,
|
| 473 |
+
"step": 14000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 28.34,
|
| 477 |
+
"eval_accuracy": 0.8908677529367185,
|
| 478 |
+
"eval_f1": 0.9286976343726923,
|
| 479 |
+
"eval_loss": 0.637986958026886,
|
| 480 |
+
"eval_precision": 0.9738854766344701,
|
| 481 |
+
"eval_runtime": 229.6341,
|
| 482 |
+
"eval_samples_per_second": 11.492,
|
| 483 |
+
"eval_steps_per_second": 0.958,
|
| 484 |
+
"step": 14000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 29.35,
|
| 488 |
+
"learning_rate": 2.7581359387080904e-06,
|
| 489 |
+
"loss": 0.185,
|
| 490 |
+
"step": 14500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 29.35,
|
| 494 |
+
"eval_accuracy": 0.8870784388025768,
|
| 495 |
+
"eval_f1": 0.9288845844124958,
|
| 496 |
+
"eval_loss": 0.6932182908058167,
|
| 497 |
+
"eval_precision": 0.979135119670676,
|
| 498 |
+
"eval_runtime": 223.3771,
|
| 499 |
+
"eval_samples_per_second": 11.814,
|
| 500 |
+
"eval_steps_per_second": 0.985,
|
| 501 |
+
"step": 14500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 30.36,
|
| 505 |
+
"learning_rate": 1.7038026288043862e-06,
|
| 506 |
+
"loss": 0.1813,
|
| 507 |
+
"step": 15000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 30.36,
|
| 511 |
+
"eval_accuracy": 0.8950359984842744,
|
| 512 |
+
"eval_f1": 0.9333589015381497,
|
| 513 |
+
"eval_loss": 0.5935563445091248,
|
| 514 |
+
"eval_precision": 0.9789140060741345,
|
| 515 |
+
"eval_runtime": 231.0332,
|
| 516 |
+
"eval_samples_per_second": 11.423,
|
| 517 |
+
"eval_steps_per_second": 0.952,
|
| 518 |
+
"step": 15000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 31.38,
|
| 522 |
+
"learning_rate": 6.494693189006819e-07,
|
| 523 |
+
"loss": 0.1801,
|
| 524 |
+
"step": 15500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 31.38,
|
| 528 |
+
"eval_accuracy": 0.8946570670708601,
|
| 529 |
+
"eval_f1": 0.9334021717198819,
|
| 530 |
+
"eval_loss": 0.6150190234184265,
|
| 531 |
+
"eval_precision": 0.9800558320669844,
|
| 532 |
+
"eval_runtime": 224.8697,
|
| 533 |
+
"eval_samples_per_second": 11.736,
|
| 534 |
+
"eval_steps_per_second": 0.978,
|
| 535 |
+
"step": 15500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 32.0,
|
| 539 |
+
"step": 15808,
|
| 540 |
+
"total_flos": 1.2697230517064026e+20,
|
| 541 |
+
"train_loss": 1.0038429288729,
|
| 542 |
+
"train_runtime": 86553.4289,
|
| 543 |
+
"train_samples_per_second": 8.78,
|
| 544 |
+
"train_steps_per_second": 0.183
|
| 545 |
+
}
|
| 546 |
+
],
|
| 547 |
+
"max_steps": 15808,
|
| 548 |
+
"num_train_epochs": 32,
|
| 549 |
+
"total_flos": 1.2697230517064026e+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 sha256:09112a064f21bd781296feb9fc4c2a0c7bed628ab5cf47097ca98c038db32a8a
|
| 3 |
+
size 3503
|