Model save
Browse files- README.md +91 -71
- all_results.json +38 -17
- eval_results.json +32 -11
- model.safetensors +1 -1
- runs/Jul26_04-39-00_66bdfda16dc0/events.out.tfevents.1721970107.66bdfda16dc0.1806.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +372 -101
README.md
CHANGED
|
@@ -1,71 +1,91 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
base_model: distilbert-base-uncased
|
| 4 |
-
tags:
|
| 5 |
-
- generated_from_trainer
|
| 6 |
-
model-index:
|
| 7 |
-
- name: distilbert-base-uncased-pii-200
|
| 8 |
-
results: []
|
| 9 |
-
---
|
| 10 |
-
|
| 11 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
-
|
| 14 |
-
# distilbert-base-uncased-pii-200
|
| 15 |
-
|
| 16 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 17 |
-
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss:
|
| 19 |
-
- Overall Precision: 0.
|
| 20 |
-
- Overall Recall: 0.
|
| 21 |
-
- Overall F1: 0.
|
| 22 |
-
- Overall Accuracy: 0.
|
| 23 |
-
- 0 F1: 0.
|
| 24 |
-
-
|
| 25 |
-
-
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
|
| 44 |
-
-
|
| 45 |
-
-
|
| 46 |
-
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
| 67 |
-
|
| 68 |
-
-
|
| 69 |
-
-
|
| 70 |
-
-
|
| 71 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: distilbert/distilbert-base-uncased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: distilbert-base-uncased-pii-200
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# distilbert-base-uncased-pii-200
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.0786
|
| 19 |
+
- Overall Precision: 0.9472
|
| 20 |
+
- Overall Recall: 0.9567
|
| 21 |
+
- Overall F1: 0.9519
|
| 22 |
+
- Overall Accuracy: 0.9678
|
| 23 |
+
- 0 F1: 0.8918
|
| 24 |
+
- 00 F1: 0.9351
|
| 25 |
+
- 01 F1: 0.2727
|
| 26 |
+
- 02 F1: 0.3439
|
| 27 |
+
- 03 F1: 0.9481
|
| 28 |
+
- 04 F1: 0.8169
|
| 29 |
+
- 05 F1: 0.8037
|
| 30 |
+
- 06 F1: 0.8732
|
| 31 |
+
- 07 F1: 0.8910
|
| 32 |
+
- 08 F1: 0.9636
|
| 33 |
+
- 09 F1: 0.9077
|
| 34 |
+
- 1 F1: 0.9461
|
| 35 |
+
- 10 F1: 0.0
|
| 36 |
+
- 100 F1: 0.9788
|
| 37 |
+
- 2 F1: 0.9052
|
| 38 |
+
- 3 F1: 0.9488
|
| 39 |
+
- 4 F1: 0.9129
|
| 40 |
+
- 5 F1: 0.9431
|
| 41 |
+
- 6 F1: 0.9765
|
| 42 |
+
- 7 F1: 0.9618
|
| 43 |
+
- 8 F1: 0.9574
|
| 44 |
+
- 9 F1: 0.9131
|
| 45 |
+
- F1: 0.9659
|
| 46 |
+
|
| 47 |
+
## Model description
|
| 48 |
+
|
| 49 |
+
More information needed
|
| 50 |
+
|
| 51 |
+
## Intended uses & limitations
|
| 52 |
+
|
| 53 |
+
More information needed
|
| 54 |
+
|
| 55 |
+
## Training and evaluation data
|
| 56 |
+
|
| 57 |
+
More information needed
|
| 58 |
+
|
| 59 |
+
## Training procedure
|
| 60 |
+
|
| 61 |
+
### Training hyperparameters
|
| 62 |
+
|
| 63 |
+
The following hyperparameters were used during training:
|
| 64 |
+
- learning_rate: 5e-05
|
| 65 |
+
- train_batch_size: 32
|
| 66 |
+
- eval_batch_size: 32
|
| 67 |
+
- seed: 42
|
| 68 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 69 |
+
- lr_scheduler_type: linear
|
| 70 |
+
- lr_scheduler_warmup_ratio: 0.2
|
| 71 |
+
- num_epochs: 7
|
| 72 |
+
|
| 73 |
+
### Training results
|
| 74 |
+
|
| 75 |
+
| Training Loss | Epoch | Step | Validation Loss | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | 0 F1 | 00 F1 | 01 F1 | 02 F1 | 03 F1 | 04 F1 | 05 F1 | 06 F1 | 07 F1 | 08 F1 | 09 F1 | 1 F1 | 10 F1 | 100 F1 | 2 F1 | 3 F1 | 4 F1 | 5 F1 | 6 F1 | 7 F1 | 8 F1 | 9 F1 | F1 |
|
| 76 |
+
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:----------------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:-----:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|:------:|
|
| 77 |
+
| 0.2545 | 1.0 | 1088 | 0.1255 | 0.9224 | 0.9142 | 0.9182 | 0.9575 | 0.8578 | 0.9054 | 0.0 | 0.0 | 0.7402 | 0.6939 | 0.6694 | 0.3099 | 0.1647 | 0.0 | 0.9048 | 0.9171 | 0.0 | 0.9609 | 0.9003 | 0.9280 | 0.8847 | 0.9121 | 0.9371 | 0.9085 | 0.8524 | 0.8536 | 0.9117 |
|
| 78 |
+
| 0.092 | 2.0 | 2176 | 0.0819 | 0.9439 | 0.9521 | 0.9480 | 0.9657 | 0.8955 | 0.9548 | 0.4305 | 0.4601 | 0.9635 | 0.7525 | 0.5925 | 0.8138 | 0.8468 | 0.9455 | 0.9291 | 0.9426 | 0.0 | 0.9756 | 0.9291 | 0.9466 | 0.9122 | 0.9362 | 0.9687 | 0.9532 | 0.9446 | 0.9067 | 0.9623 |
|
| 79 |
+
| 0.0716 | 3.0 | 3264 | 0.0786 | 0.9472 | 0.9567 | 0.9519 | 0.9678 | 0.8918 | 0.9351 | 0.2727 | 0.3439 | 0.9481 | 0.8169 | 0.8037 | 0.8732 | 0.8910 | 0.9636 | 0.9077 | 0.9461 | 0.0 | 0.9788 | 0.9052 | 0.9488 | 0.9129 | 0.9431 | 0.9765 | 0.9618 | 0.9574 | 0.9131 | 0.9659 |
|
| 80 |
+
| 0.0575 | 4.0 | 4352 | 0.0808 | 0.9501 | 0.9577 | 0.9539 | 0.9673 | 0.8882 | 0.9751 | 0.4669 | 0.3951 | 0.9781 | 0.8206 | 0.8034 | 0.8941 | 0.9196 | 0.9550 | 0.9508 | 0.9438 | 0.0 | 0.9800 | 0.9068 | 0.9545 | 0.9235 | 0.9503 | 0.9744 | 0.9626 | 0.9624 | 0.9086 | 0.9674 |
|
| 81 |
+
| 0.0463 | 5.0 | 5440 | 0.0801 | 0.9559 | 0.9604 | 0.9581 | 0.9693 | 0.9050 | 0.9634 | 0.4693 | 0.4950 | 0.9781 | 0.8 | 0.7726 | 0.9006 | 0.9211 | 0.9636 | 0.9291 | 0.9506 | 0.0 | 0.9814 | 0.9328 | 0.9549 | 0.9278 | 0.9548 | 0.9766 | 0.9647 | 0.9624 | 0.9176 | 0.9707 |
|
| 82 |
+
| 0.0325 | 6.0 | 6528 | 0.1021 | 0.9559 | 0.9611 | 0.9585 | 0.9690 | 0.9019 | 0.9667 | 0.4477 | 0.4275 | 0.9781 | 0.7926 | 0.7870 | 0.9080 | 0.9457 | 0.9541 | 0.9431 | 0.9516 | 0.0 | 0.9820 | 0.9276 | 0.9583 | 0.9298 | 0.9577 | 0.9769 | 0.9654 | 0.9642 | 0.9196 | 0.9695 |
|
| 83 |
+
| 0.0159 | 7.0 | 7616 | 0.1300 | 0.9543 | 0.9601 | 0.9572 | 0.9673 | 0.8968 | 0.9642 | 0.4610 | 0.4408 | 0.9781 | 0.7788 | 0.7702 | 0.9096 | 0.9236 | 0.9550 | 0.9516 | 0.9484 | 0.0 | 0.9823 | 0.9185 | 0.9569 | 0.9273 | 0.9573 | 0.9774 | 0.9652 | 0.9667 | 0.9157 | 0.9706 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.42.4
|
| 89 |
+
- Pytorch 2.3.1+cu121
|
| 90 |
+
- Datasets 2.20.0
|
| 91 |
+
- Tokenizers 0.19.1
|
all_results.json
CHANGED
|
@@ -1,20 +1,41 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 7.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 7.0,
|
| 3 |
+
"eval_00_f1": 0.9351351351351351,
|
| 4 |
+
"eval_01_f1": 0.2727272727272727,
|
| 5 |
+
"eval_02_f1": 0.3438914027149321,
|
| 6 |
+
"eval_03_f1": 0.9481481481481482,
|
| 7 |
+
"eval_04_f1": 0.8168701442841289,
|
| 8 |
+
"eval_05_f1": 0.8036951501154733,
|
| 9 |
+
"eval_06_f1": 0.8732394366197183,
|
| 10 |
+
"eval_07_f1": 0.8909657320872275,
|
| 11 |
+
"eval_08_f1": 0.9636363636363636,
|
| 12 |
+
"eval_09_f1": 0.9076923076923077,
|
| 13 |
+
"eval_0_f1": 0.8918362091166624,
|
| 14 |
+
"eval_100_f1": 0.9787716689913094,
|
| 15 |
+
"eval_10_f1": 0.0,
|
| 16 |
+
"eval_1_f1": 0.9460573633891765,
|
| 17 |
+
"eval_2_f1": 0.9052096569250319,
|
| 18 |
+
"eval_3_f1": 0.9488174195970466,
|
| 19 |
+
"eval_4_f1": 0.9129169464965301,
|
| 20 |
+
"eval_5_f1": 0.9431066419687748,
|
| 21 |
+
"eval_6_f1": 0.9764898851831602,
|
| 22 |
+
"eval_7_f1": 0.9617969579059075,
|
| 23 |
+
"eval_8_f1": 0.9573971403559964,
|
| 24 |
+
"eval_9_f1": 0.9131222981453074,
|
| 25 |
+
"eval___f1": 0.965883121123082,
|
| 26 |
+
"eval_loss": 0.07855656743049622,
|
| 27 |
+
"eval_overall_accuracy": 0.9678325102233014,
|
| 28 |
+
"eval_overall_f1": 0.9519101855680437,
|
| 29 |
+
"eval_overall_precision": 0.9471512280264306,
|
| 30 |
+
"eval_overall_recall": 0.9567172073342737,
|
| 31 |
+
"eval_runtime": 31.7972,
|
| 32 |
+
"eval_samples": 8700,
|
| 33 |
+
"eval_samples_per_second": 273.609,
|
| 34 |
+
"eval_steps_per_second": 8.554,
|
| 35 |
+
"total_flos": 6493939017778920.0,
|
| 36 |
+
"train_loss": 0.18183875429843152,
|
| 37 |
+
"train_runtime": 1332.3436,
|
| 38 |
+
"train_samples": 34796,
|
| 39 |
+
"train_samples_per_second": 182.815,
|
| 40 |
+
"train_steps_per_second": 5.716
|
| 41 |
}
|
eval_results.json
CHANGED
|
@@ -1,14 +1,35 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 7.0,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 7.0,
|
| 3 |
+
"eval_00_f1": 0.9351351351351351,
|
| 4 |
+
"eval_01_f1": 0.2727272727272727,
|
| 5 |
+
"eval_02_f1": 0.3438914027149321,
|
| 6 |
+
"eval_03_f1": 0.9481481481481482,
|
| 7 |
+
"eval_04_f1": 0.8168701442841289,
|
| 8 |
+
"eval_05_f1": 0.8036951501154733,
|
| 9 |
+
"eval_06_f1": 0.8732394366197183,
|
| 10 |
+
"eval_07_f1": 0.8909657320872275,
|
| 11 |
+
"eval_08_f1": 0.9636363636363636,
|
| 12 |
+
"eval_09_f1": 0.9076923076923077,
|
| 13 |
+
"eval_0_f1": 0.8918362091166624,
|
| 14 |
+
"eval_100_f1": 0.9787716689913094,
|
| 15 |
+
"eval_10_f1": 0.0,
|
| 16 |
+
"eval_1_f1": 0.9460573633891765,
|
| 17 |
+
"eval_2_f1": 0.9052096569250319,
|
| 18 |
+
"eval_3_f1": 0.9488174195970466,
|
| 19 |
+
"eval_4_f1": 0.9129169464965301,
|
| 20 |
+
"eval_5_f1": 0.9431066419687748,
|
| 21 |
+
"eval_6_f1": 0.9764898851831602,
|
| 22 |
+
"eval_7_f1": 0.9617969579059075,
|
| 23 |
+
"eval_8_f1": 0.9573971403559964,
|
| 24 |
+
"eval_9_f1": 0.9131222981453074,
|
| 25 |
+
"eval___f1": 0.965883121123082,
|
| 26 |
+
"eval_loss": 0.07855656743049622,
|
| 27 |
+
"eval_overall_accuracy": 0.9678325102233014,
|
| 28 |
+
"eval_overall_f1": 0.9519101855680437,
|
| 29 |
+
"eval_overall_precision": 0.9471512280264306,
|
| 30 |
+
"eval_overall_recall": 0.9567172073342737,
|
| 31 |
+
"eval_runtime": 31.7972,
|
| 32 |
+
"eval_samples": 8700,
|
| 33 |
+
"eval_samples_per_second": 273.609,
|
| 34 |
+
"eval_steps_per_second": 8.554
|
| 35 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 265811460
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6374688a8ff2e3bc6d4ee78fc7b6058429092d7ea3d1296f9bb1bd5d8e85b184
|
| 3 |
size 265811460
|
runs/Jul26_04-39-00_66bdfda16dc0/events.out.tfevents.1721970107.66bdfda16dc0.1806.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13d13aebe76c04d8f2085983386d9f15afca04ca9d168c085d4e987cfd22813b
|
| 3 |
+
size 1709
|
train_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 7.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples":
|
| 7 |
-
"train_samples_per_second":
|
| 8 |
-
"train_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 7.0,
|
| 3 |
+
"total_flos": 6493939017778920.0,
|
| 4 |
+
"train_loss": 0.18183875429843152,
|
| 5 |
+
"train_runtime": 1332.3436,
|
| 6 |
+
"train_samples": 34796,
|
| 7 |
+
"train_samples_per_second": 182.815,
|
| 8 |
+
"train_steps_per_second": 5.716
|
| 9 |
}
|
trainer_state.json
CHANGED
|
@@ -1,139 +1,410 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "data/outputs/distilbert-base-uncased-pii-200/checkpoint-
|
| 4 |
"epoch": 7.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
"
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"
|
| 39 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 3.0,
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"
|
| 52 |
-
"
|
| 53 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 4.0,
|
| 57 |
-
"
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
},
|
| 69 |
{
|
| 70 |
"epoch": 5.0,
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.0,
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 7.0,
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
"
|
| 104 |
-
"
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"
|
| 108 |
-
"
|
| 109 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 7.0,
|
| 113 |
-
"step":
|
| 114 |
-
"total_flos":
|
| 115 |
-
"train_loss":
|
| 116 |
-
"train_runtime":
|
| 117 |
-
"train_samples_per_second":
|
| 118 |
-
"train_steps_per_second":
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 7.0,
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"
|
| 130 |
-
"
|
| 131 |
-
"
|
| 132 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 133 |
}
|
| 134 |
],
|
| 135 |
"logging_steps": 500,
|
| 136 |
-
"max_steps":
|
| 137 |
"num_input_tokens_seen": 0,
|
| 138 |
"num_train_epochs": 7,
|
| 139 |
"save_steps": 500,
|
|
@@ -149,7 +420,7 @@
|
|
| 149 |
"attributes": {}
|
| 150 |
}
|
| 151 |
},
|
| 152 |
-
"total_flos":
|
| 153 |
"train_batch_size": 32,
|
| 154 |
"trial_name": null,
|
| 155 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.07855656743049622,
|
| 3 |
+
"best_model_checkpoint": "data/outputs/distilbert-base-uncased-pii-200/checkpoint-3264",
|
| 4 |
"epoch": 7.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7616,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.45955882352941174,
|
| 13 |
+
"grad_norm": 1.3934886455535889,
|
| 14 |
+
"learning_rate": 1.6404199475065617e-05,
|
| 15 |
+
"loss": 1.7881,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9191176470588235,
|
| 20 |
+
"grad_norm": 0.784841775894165,
|
| 21 |
+
"learning_rate": 3.280839895013123e-05,
|
| 22 |
+
"loss": 0.2545,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
{
|
| 26 |
"epoch": 1.0,
|
| 27 |
+
"eval_00_f1": 0.9054441260744985,
|
| 28 |
+
"eval_01_f1": 0.0,
|
| 29 |
+
"eval_02_f1": 0.0,
|
| 30 |
+
"eval_03_f1": 0.7401574803149606,
|
| 31 |
+
"eval_04_f1": 0.6938775510204082,
|
| 32 |
+
"eval_05_f1": 0.6694045174537987,
|
| 33 |
+
"eval_06_f1": 0.30985915492957744,
|
| 34 |
+
"eval_07_f1": 0.16470588235294117,
|
| 35 |
+
"eval_08_f1": 0.0,
|
| 36 |
+
"eval_09_f1": 0.9047619047619048,
|
| 37 |
+
"eval_0_f1": 0.8577833823735463,
|
| 38 |
+
"eval_100_f1": 0.9608561749307052,
|
| 39 |
+
"eval_10_f1": 0.0,
|
| 40 |
+
"eval_1_f1": 0.9170798427081553,
|
| 41 |
+
"eval_2_f1": 0.9002621395581076,
|
| 42 |
+
"eval_3_f1": 0.9280289330922241,
|
| 43 |
+
"eval_4_f1": 0.8847179031541538,
|
| 44 |
+
"eval_5_f1": 0.9121113162004828,
|
| 45 |
+
"eval_6_f1": 0.9370610480821178,
|
| 46 |
+
"eval_7_f1": 0.9085239085239085,
|
| 47 |
+
"eval_8_f1": 0.8524124881740777,
|
| 48 |
+
"eval_9_f1": 0.8535798122065729,
|
| 49 |
+
"eval___f1": 0.9117056318791676,
|
| 50 |
+
"eval_loss": 0.12546201050281525,
|
| 51 |
+
"eval_overall_accuracy": 0.9575080375008431,
|
| 52 |
+
"eval_overall_f1": 0.918246790209348,
|
| 53 |
+
"eval_overall_precision": 0.9223653782623059,
|
| 54 |
+
"eval_overall_recall": 0.9141648196655249,
|
| 55 |
+
"eval_runtime": 33.5549,
|
| 56 |
+
"eval_samples_per_second": 259.277,
|
| 57 |
+
"eval_steps_per_second": 8.106,
|
| 58 |
+
"step": 1088
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.3786764705882353,
|
| 62 |
+
"grad_norm": 0.5563145279884338,
|
| 63 |
+
"learning_rate": 4.9212598425196856e-05,
|
| 64 |
+
"loss": 0.1199,
|
| 65 |
+
"step": 1500
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.8382352941176472,
|
| 69 |
+
"grad_norm": 0.48911386728286743,
|
| 70 |
+
"learning_rate": 4.609323703217334e-05,
|
| 71 |
+
"loss": 0.092,
|
| 72 |
+
"step": 2000
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 2.0,
|
| 76 |
+
"eval_00_f1": 0.9548022598870056,
|
| 77 |
+
"eval_01_f1": 0.4304635761589404,
|
| 78 |
+
"eval_02_f1": 0.46009389671361506,
|
| 79 |
+
"eval_03_f1": 0.9635036496350365,
|
| 80 |
+
"eval_04_f1": 0.7525252525252526,
|
| 81 |
+
"eval_05_f1": 0.5924812030075188,
|
| 82 |
+
"eval_06_f1": 0.8138297872340425,
|
| 83 |
+
"eval_07_f1": 0.8468468468468469,
|
| 84 |
+
"eval_08_f1": 0.9454545454545454,
|
| 85 |
+
"eval_09_f1": 0.9291338582677166,
|
| 86 |
+
"eval_0_f1": 0.8954570333880678,
|
| 87 |
+
"eval_100_f1": 0.975552255713914,
|
| 88 |
+
"eval_10_f1": 0.0,
|
| 89 |
+
"eval_1_f1": 0.9426179998274226,
|
| 90 |
+
"eval_2_f1": 0.9290612143124298,
|
| 91 |
+
"eval_3_f1": 0.9465685683271017,
|
| 92 |
+
"eval_4_f1": 0.9122260540660807,
|
| 93 |
+
"eval_5_f1": 0.9362116991643455,
|
| 94 |
+
"eval_6_f1": 0.9686864579097194,
|
| 95 |
+
"eval_7_f1": 0.953225525995479,
|
| 96 |
+
"eval_8_f1": 0.9446140427387701,
|
| 97 |
+
"eval_9_f1": 0.9067169592340055,
|
| 98 |
+
"eval___f1": 0.9622872037142625,
|
| 99 |
+
"eval_loss": 0.08186369389295578,
|
| 100 |
+
"eval_overall_accuracy": 0.9657341417048245,
|
| 101 |
+
"eval_overall_f1": 0.9479689782509201,
|
| 102 |
+
"eval_overall_precision": 0.9439151985816489,
|
| 103 |
+
"eval_overall_recall": 0.9520577271811405,
|
| 104 |
+
"eval_runtime": 31.5004,
|
| 105 |
+
"eval_samples_per_second": 276.187,
|
| 106 |
+
"eval_steps_per_second": 8.635,
|
| 107 |
+
"step": 2176
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.297794117647059,
|
| 111 |
+
"grad_norm": 1.011751413345337,
|
| 112 |
+
"learning_rate": 4.198949441891005e-05,
|
| 113 |
+
"loss": 0.0772,
|
| 114 |
+
"step": 2500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.7573529411764706,
|
| 118 |
+
"grad_norm": 0.7153874635696411,
|
| 119 |
+
"learning_rate": 3.788575180564675e-05,
|
| 120 |
+
"loss": 0.0716,
|
| 121 |
+
"step": 3000
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 3.0,
|
| 125 |
+
"eval_00_f1": 0.9351351351351351,
|
| 126 |
+
"eval_01_f1": 0.2727272727272727,
|
| 127 |
+
"eval_02_f1": 0.3438914027149321,
|
| 128 |
+
"eval_03_f1": 0.9481481481481482,
|
| 129 |
+
"eval_04_f1": 0.8168701442841289,
|
| 130 |
+
"eval_05_f1": 0.8036951501154733,
|
| 131 |
+
"eval_06_f1": 0.8732394366197183,
|
| 132 |
+
"eval_07_f1": 0.8909657320872275,
|
| 133 |
+
"eval_08_f1": 0.9636363636363636,
|
| 134 |
+
"eval_09_f1": 0.9076923076923077,
|
| 135 |
+
"eval_0_f1": 0.8918362091166624,
|
| 136 |
+
"eval_100_f1": 0.9787716689913094,
|
| 137 |
+
"eval_10_f1": 0.0,
|
| 138 |
+
"eval_1_f1": 0.9460573633891765,
|
| 139 |
+
"eval_2_f1": 0.9052096569250319,
|
| 140 |
+
"eval_3_f1": 0.9488174195970466,
|
| 141 |
+
"eval_4_f1": 0.9129169464965301,
|
| 142 |
+
"eval_5_f1": 0.9431066419687748,
|
| 143 |
+
"eval_6_f1": 0.9764898851831602,
|
| 144 |
+
"eval_7_f1": 0.9617969579059075,
|
| 145 |
+
"eval_8_f1": 0.9573971403559964,
|
| 146 |
+
"eval_9_f1": 0.9131222981453074,
|
| 147 |
+
"eval___f1": 0.965883121123082,
|
| 148 |
+
"eval_loss": 0.07855656743049622,
|
| 149 |
+
"eval_overall_accuracy": 0.9678325102233014,
|
| 150 |
+
"eval_overall_f1": 0.9519101855680437,
|
| 151 |
+
"eval_overall_precision": 0.9471512280264306,
|
| 152 |
+
"eval_overall_recall": 0.9567172073342737,
|
| 153 |
+
"eval_runtime": 31.5113,
|
| 154 |
+
"eval_samples_per_second": 276.091,
|
| 155 |
+
"eval_steps_per_second": 8.632,
|
| 156 |
+
"step": 3264
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.2169117647058822,
|
| 160 |
+
"grad_norm": 0.566089928150177,
|
| 161 |
+
"learning_rate": 3.378200919238346e-05,
|
| 162 |
+
"loss": 0.064,
|
| 163 |
+
"step": 3500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.6764705882352944,
|
| 167 |
+
"grad_norm": 0.5392144322395325,
|
| 168 |
+
"learning_rate": 2.9678266579120157e-05,
|
| 169 |
+
"loss": 0.0575,
|
| 170 |
+
"step": 4000
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 4.0,
|
| 174 |
+
"eval_00_f1": 0.9750692520775622,
|
| 175 |
+
"eval_01_f1": 0.46692607003891046,
|
| 176 |
+
"eval_02_f1": 0.39506172839506176,
|
| 177 |
+
"eval_03_f1": 0.9781021897810219,
|
| 178 |
+
"eval_04_f1": 0.8205741626794257,
|
| 179 |
+
"eval_05_f1": 0.8033573141486811,
|
| 180 |
+
"eval_06_f1": 0.8941176470588235,
|
| 181 |
+
"eval_07_f1": 0.9196141479099678,
|
| 182 |
+
"eval_08_f1": 0.9549549549549549,
|
| 183 |
+
"eval_09_f1": 0.9508196721311476,
|
| 184 |
+
"eval_0_f1": 0.8882090503505418,
|
| 185 |
+
"eval_100_f1": 0.9800042935565983,
|
| 186 |
+
"eval_10_f1": 0.0,
|
| 187 |
+
"eval_1_f1": 0.9437605172261093,
|
| 188 |
+
"eval_2_f1": 0.9068274144935132,
|
| 189 |
+
"eval_3_f1": 0.9544898458527037,
|
| 190 |
+
"eval_4_f1": 0.9235419232060899,
|
| 191 |
+
"eval_5_f1": 0.9502912095354191,
|
| 192 |
+
"eval_6_f1": 0.974421768707483,
|
| 193 |
+
"eval_7_f1": 0.9625987708516243,
|
| 194 |
+
"eval_8_f1": 0.9623994147768837,
|
| 195 |
+
"eval_9_f1": 0.9085659287776707,
|
| 196 |
+
"eval___f1": 0.9674214041374817,
|
| 197 |
+
"eval_loss": 0.08075448125600815,
|
| 198 |
+
"eval_overall_accuracy": 0.9673478870178436,
|
| 199 |
+
"eval_overall_f1": 0.9538741337681478,
|
| 200 |
+
"eval_overall_precision": 0.9500668357340063,
|
| 201 |
+
"eval_overall_recall": 0.9577120693129155,
|
| 202 |
+
"eval_runtime": 31.7082,
|
| 203 |
+
"eval_samples_per_second": 274.377,
|
| 204 |
+
"eval_steps_per_second": 8.578,
|
| 205 |
+
"step": 4352
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.136029411764706,
|
| 209 |
+
"grad_norm": 0.993366003036499,
|
| 210 |
+
"learning_rate": 2.557452396585686e-05,
|
| 211 |
+
"loss": 0.052,
|
| 212 |
+
"step": 4500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.595588235294118,
|
| 216 |
+
"grad_norm": 0.6269740462303162,
|
| 217 |
+
"learning_rate": 2.1470781352593567e-05,
|
| 218 |
+
"loss": 0.0463,
|
| 219 |
+
"step": 5000
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 5.0,
|
| 223 |
+
"eval_00_f1": 0.9633802816901408,
|
| 224 |
+
"eval_01_f1": 0.4693140794223827,
|
| 225 |
+
"eval_02_f1": 0.49504950495049505,
|
| 226 |
+
"eval_03_f1": 0.9781021897810219,
|
| 227 |
+
"eval_04_f1": 0.8,
|
| 228 |
+
"eval_05_f1": 0.772609819121447,
|
| 229 |
+
"eval_06_f1": 0.9005847953216374,
|
| 230 |
+
"eval_07_f1": 0.9211356466876972,
|
| 231 |
+
"eval_08_f1": 0.9636363636363636,
|
| 232 |
+
"eval_09_f1": 0.9291338582677166,
|
| 233 |
+
"eval_0_f1": 0.9050072664817017,
|
| 234 |
+
"eval_100_f1": 0.9814164045116244,
|
| 235 |
+
"eval_10_f1": 0.0,
|
| 236 |
+
"eval_1_f1": 0.9505915100904663,
|
| 237 |
+
"eval_2_f1": 0.932791259052217,
|
| 238 |
+
"eval_3_f1": 0.9548890514508657,
|
| 239 |
+
"eval_4_f1": 0.9277958132766148,
|
| 240 |
+
"eval_5_f1": 0.954789061426412,
|
| 241 |
+
"eval_6_f1": 0.9766105867870333,
|
| 242 |
+
"eval_7_f1": 0.964676792652773,
|
| 243 |
+
"eval_8_f1": 0.9624082232011747,
|
| 244 |
+
"eval_9_f1": 0.9176204606471668,
|
| 245 |
+
"eval___f1": 0.9707106143428246,
|
| 246 |
+
"eval_loss": 0.08005847036838531,
|
| 247 |
+
"eval_overall_accuracy": 0.9692788856663944,
|
| 248 |
+
"eval_overall_f1": 0.9581124205342111,
|
| 249 |
+
"eval_overall_precision": 0.9558786663324141,
|
| 250 |
+
"eval_overall_recall": 0.9603566391295587,
|
| 251 |
+
"eval_runtime": 31.5692,
|
| 252 |
+
"eval_samples_per_second": 275.585,
|
| 253 |
+
"eval_steps_per_second": 8.616,
|
| 254 |
+
"step": 5440
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.055147058823529,
|
| 258 |
+
"grad_norm": 0.6535865068435669,
|
| 259 |
+
"learning_rate": 1.736703873933027e-05,
|
| 260 |
+
"loss": 0.0429,
|
| 261 |
+
"step": 5500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.514705882352941,
|
| 265 |
+
"grad_norm": 0.42540472745895386,
|
| 266 |
+
"learning_rate": 1.3263296126066974e-05,
|
| 267 |
+
"loss": 0.0321,
|
| 268 |
+
"step": 6000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 5.974264705882353,
|
| 272 |
+
"grad_norm": 0.3176397979259491,
|
| 273 |
+
"learning_rate": 9.159553512803678e-06,
|
| 274 |
+
"loss": 0.0325,
|
| 275 |
+
"step": 6500
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 6.0,
|
| 279 |
+
"eval_00_f1": 0.9666666666666666,
|
| 280 |
+
"eval_01_f1": 0.4476534296028881,
|
| 281 |
+
"eval_02_f1": 0.4275362318840579,
|
| 282 |
+
"eval_03_f1": 0.9781021897810219,
|
| 283 |
+
"eval_04_f1": 0.7926380368098158,
|
| 284 |
+
"eval_05_f1": 0.7869674185463661,
|
| 285 |
+
"eval_06_f1": 0.9080459770114941,
|
| 286 |
+
"eval_07_f1": 0.9456869009584665,
|
| 287 |
+
"eval_08_f1": 0.9541284403669724,
|
| 288 |
+
"eval_09_f1": 0.943089430894309,
|
| 289 |
+
"eval_0_f1": 0.9018794556059624,
|
| 290 |
+
"eval_100_f1": 0.9819615302021658,
|
| 291 |
+
"eval_10_f1": 0.0,
|
| 292 |
+
"eval_1_f1": 0.9515930293962331,
|
| 293 |
+
"eval_2_f1": 0.9276000518067608,
|
| 294 |
+
"eval_3_f1": 0.9582514734774068,
|
| 295 |
+
"eval_4_f1": 0.9297636384003585,
|
| 296 |
+
"eval_5_f1": 0.9576626538617611,
|
| 297 |
+
"eval_6_f1": 0.9769031023643571,
|
| 298 |
+
"eval_7_f1": 0.9654320987654321,
|
| 299 |
+
"eval_8_f1": 0.9641913707073672,
|
| 300 |
+
"eval_9_f1": 0.9196490739451331,
|
| 301 |
+
"eval___f1": 0.9694843342036553,
|
| 302 |
+
"eval_loss": 0.10214365273714066,
|
| 303 |
+
"eval_overall_accuracy": 0.9690265818326251,
|
| 304 |
+
"eval_overall_f1": 0.9584994756704824,
|
| 305 |
+
"eval_overall_precision": 0.9558884310459276,
|
| 306 |
+
"eval_overall_recall": 0.9611248236953456,
|
| 307 |
+
"eval_runtime": 31.5742,
|
| 308 |
+
"eval_samples_per_second": 275.541,
|
| 309 |
+
"eval_steps_per_second": 8.615,
|
| 310 |
+
"step": 6528
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 6.4338235294117645,
|
| 314 |
+
"grad_norm": 1.4613324403762817,
|
| 315 |
+
"learning_rate": 5.0558108995403805e-06,
|
| 316 |
+
"loss": 0.0193,
|
| 317 |
+
"step": 7000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 6.893382352941177,
|
| 321 |
+
"grad_norm": 0.6644862294197083,
|
| 322 |
+
"learning_rate": 9.520682862770847e-07,
|
| 323 |
+
"loss": 0.0159,
|
| 324 |
+
"step": 7500
|
| 325 |
},
|
| 326 |
{
|
| 327 |
"epoch": 7.0,
|
| 328 |
+
"eval_00_f1": 0.9641873278236915,
|
| 329 |
+
"eval_01_f1": 0.461038961038961,
|
| 330 |
+
"eval_02_f1": 0.4407894736842105,
|
| 331 |
+
"eval_03_f1": 0.9781021897810219,
|
| 332 |
+
"eval_04_f1": 0.7787610619469025,
|
| 333 |
+
"eval_05_f1": 0.7702182284980743,
|
| 334 |
+
"eval_06_f1": 0.9096209912536442,
|
| 335 |
+
"eval_07_f1": 0.9235668789808917,
|
| 336 |
+
"eval_08_f1": 0.9549549549549549,
|
| 337 |
+
"eval_09_f1": 0.9516129032258064,
|
| 338 |
+
"eval_0_f1": 0.8967626816212082,
|
| 339 |
+
"eval_100_f1": 0.9823135095335246,
|
| 340 |
+
"eval_10_f1": 0.0,
|
| 341 |
+
"eval_1_f1": 0.94840600301927,
|
| 342 |
+
"eval_2_f1": 0.9184932405827536,
|
| 343 |
+
"eval_3_f1": 0.9568531038721574,
|
| 344 |
+
"eval_4_f1": 0.927282913165266,
|
| 345 |
+
"eval_5_f1": 0.9573369565217391,
|
| 346 |
+
"eval_6_f1": 0.9773841961852859,
|
| 347 |
+
"eval_7_f1": 0.9652387640449438,
|
| 348 |
+
"eval_8_f1": 0.966681344488478,
|
| 349 |
+
"eval_9_f1": 0.9156825048063718,
|
| 350 |
+
"eval___f1": 0.9706314243759178,
|
| 351 |
+
"eval_loss": 0.1300029456615448,
|
| 352 |
+
"eval_overall_accuracy": 0.9673478870178436,
|
| 353 |
+
"eval_overall_f1": 0.9572067971952467,
|
| 354 |
+
"eval_overall_precision": 0.9543013780931997,
|
| 355 |
+
"eval_overall_recall": 0.9601299617167036,
|
| 356 |
+
"eval_runtime": 31.698,
|
| 357 |
+
"eval_samples_per_second": 274.465,
|
| 358 |
+
"eval_steps_per_second": 8.581,
|
| 359 |
+
"step": 7616
|
| 360 |
},
|
| 361 |
{
|
| 362 |
"epoch": 7.0,
|
| 363 |
+
"step": 7616,
|
| 364 |
+
"total_flos": 6493939017778920.0,
|
| 365 |
+
"train_loss": 0.18183875429843152,
|
| 366 |
+
"train_runtime": 1332.3436,
|
| 367 |
+
"train_samples_per_second": 182.815,
|
| 368 |
+
"train_steps_per_second": 5.716
|
| 369 |
},
|
| 370 |
{
|
| 371 |
"epoch": 7.0,
|
| 372 |
+
"eval_00_f1": 0.9351351351351351,
|
| 373 |
+
"eval_01_f1": 0.2727272727272727,
|
| 374 |
+
"eval_02_f1": 0.3438914027149321,
|
| 375 |
+
"eval_03_f1": 0.9481481481481482,
|
| 376 |
+
"eval_04_f1": 0.8168701442841289,
|
| 377 |
+
"eval_05_f1": 0.8036951501154733,
|
| 378 |
+
"eval_06_f1": 0.8732394366197183,
|
| 379 |
+
"eval_07_f1": 0.8909657320872275,
|
| 380 |
+
"eval_08_f1": 0.9636363636363636,
|
| 381 |
+
"eval_09_f1": 0.9076923076923077,
|
| 382 |
+
"eval_0_f1": 0.8918362091166624,
|
| 383 |
+
"eval_100_f1": 0.9787716689913094,
|
| 384 |
+
"eval_10_f1": 0.0,
|
| 385 |
+
"eval_1_f1": 0.9460573633891765,
|
| 386 |
+
"eval_2_f1": 0.9052096569250319,
|
| 387 |
+
"eval_3_f1": 0.9488174195970466,
|
| 388 |
+
"eval_4_f1": 0.9129169464965301,
|
| 389 |
+
"eval_5_f1": 0.9431066419687748,
|
| 390 |
+
"eval_6_f1": 0.9764898851831602,
|
| 391 |
+
"eval_7_f1": 0.9617969579059075,
|
| 392 |
+
"eval_8_f1": 0.9573971403559964,
|
| 393 |
+
"eval_9_f1": 0.9131222981453074,
|
| 394 |
+
"eval___f1": 0.965883121123082,
|
| 395 |
+
"eval_loss": 0.07855656743049622,
|
| 396 |
+
"eval_overall_accuracy": 0.9678325102233014,
|
| 397 |
+
"eval_overall_f1": 0.9519101855680437,
|
| 398 |
+
"eval_overall_precision": 0.9471512280264306,
|
| 399 |
+
"eval_overall_recall": 0.9567172073342737,
|
| 400 |
+
"eval_runtime": 31.7972,
|
| 401 |
+
"eval_samples_per_second": 273.609,
|
| 402 |
+
"eval_steps_per_second": 8.554,
|
| 403 |
+
"step": 7616
|
| 404 |
}
|
| 405 |
],
|
| 406 |
"logging_steps": 500,
|
| 407 |
+
"max_steps": 7616,
|
| 408 |
"num_input_tokens_seen": 0,
|
| 409 |
"num_train_epochs": 7,
|
| 410 |
"save_steps": 500,
|
|
|
|
| 420 |
"attributes": {}
|
| 421 |
}
|
| 422 |
},
|
| 423 |
+
"total_flos": 6493939017778920.0,
|
| 424 |
"train_batch_size": 32,
|
| 425 |
"trial_name": null,
|
| 426 |
"trial_params": null
|