End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: gokuls/model_v1_complete_training_wt_init_48_mini_freeze_new
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- massive
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: hbertv1-massive-logit_KD-mini
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Text Classification
|
| 14 |
+
type: text-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: massive
|
| 17 |
+
type: massive
|
| 18 |
+
config: en-US
|
| 19 |
+
split: validation
|
| 20 |
+
args: en-US
|
| 21 |
+
metrics:
|
| 22 |
+
- name: Accuracy
|
| 23 |
+
type: accuracy
|
| 24 |
+
value: 0.8598130841121495
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 28 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 29 |
+
|
| 30 |
+
# hbertv1-massive-logit_KD-mini
|
| 31 |
+
|
| 32 |
+
This model is a fine-tuned version of [gokuls/model_v1_complete_training_wt_init_48_mini_freeze_new](https://huggingface.co/gokuls/model_v1_complete_training_wt_init_48_mini_freeze_new) on the massive dataset.
|
| 33 |
+
It achieves the following results on the evaluation set:
|
| 34 |
+
- Loss: 0.4640
|
| 35 |
+
- Accuracy: 0.8598
|
| 36 |
+
|
| 37 |
+
## Model description
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Intended uses & limitations
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training and evaluation data
|
| 46 |
+
|
| 47 |
+
More information needed
|
| 48 |
+
|
| 49 |
+
## Training procedure
|
| 50 |
+
|
| 51 |
+
### Training hyperparameters
|
| 52 |
+
|
| 53 |
+
The following hyperparameters were used during training:
|
| 54 |
+
- learning_rate: 5e-05
|
| 55 |
+
- train_batch_size: 64
|
| 56 |
+
- eval_batch_size: 64
|
| 57 |
+
- seed: 33
|
| 58 |
+
- distributed_type: multi-GPU
|
| 59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
+
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 50
|
| 62 |
+
|
| 63 |
+
### Training results
|
| 64 |
+
|
| 65 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 66 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 67 |
+
| 3.5547 | 1.0 | 180 | 2.3028 | 0.4481 |
|
| 68 |
+
| 1.9374 | 2.0 | 360 | 1.2686 | 0.6513 |
|
| 69 |
+
| 1.2845 | 3.0 | 540 | 0.9328 | 0.7324 |
|
| 70 |
+
| 0.9981 | 4.0 | 720 | 0.7684 | 0.7836 |
|
| 71 |
+
| 0.8273 | 5.0 | 900 | 0.6834 | 0.7998 |
|
| 72 |
+
| 0.7068 | 6.0 | 1080 | 0.6369 | 0.8062 |
|
| 73 |
+
| 0.6043 | 7.0 | 1260 | 0.5804 | 0.8205 |
|
| 74 |
+
| 0.535 | 8.0 | 1440 | 0.5475 | 0.8396 |
|
| 75 |
+
| 0.4763 | 9.0 | 1620 | 0.5247 | 0.8396 |
|
| 76 |
+
| 0.4245 | 10.0 | 1800 | 0.5122 | 0.8470 |
|
| 77 |
+
| 0.3794 | 11.0 | 1980 | 0.5038 | 0.8460 |
|
| 78 |
+
| 0.3424 | 12.0 | 2160 | 0.5057 | 0.8465 |
|
| 79 |
+
| 0.3194 | 13.0 | 2340 | 0.4977 | 0.8485 |
|
| 80 |
+
| 0.2897 | 14.0 | 2520 | 0.4973 | 0.8534 |
|
| 81 |
+
| 0.2688 | 15.0 | 2700 | 0.4714 | 0.8574 |
|
| 82 |
+
| 0.255 | 16.0 | 2880 | 0.4763 | 0.8480 |
|
| 83 |
+
| 0.2401 | 17.0 | 3060 | 0.4856 | 0.8510 |
|
| 84 |
+
| 0.2286 | 18.0 | 3240 | 0.4713 | 0.8578 |
|
| 85 |
+
| 0.2138 | 19.0 | 3420 | 0.4753 | 0.8500 |
|
| 86 |
+
| 0.2022 | 20.0 | 3600 | 0.4641 | 0.8544 |
|
| 87 |
+
| 0.1937 | 21.0 | 3780 | 0.4640 | 0.8598 |
|
| 88 |
+
| 0.1802 | 22.0 | 3960 | 0.4788 | 0.8505 |
|
| 89 |
+
| 0.1719 | 23.0 | 4140 | 0.4520 | 0.8593 |
|
| 90 |
+
| 0.17 | 24.0 | 4320 | 0.4703 | 0.8564 |
|
| 91 |
+
| 0.159 | 25.0 | 4500 | 0.4620 | 0.8554 |
|
| 92 |
+
| 0.1566 | 26.0 | 4680 | 0.4825 | 0.8549 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.35.2
|
| 98 |
+
- Pytorch 1.14.0a0+410ce96
|
| 99 |
+
- Datasets 2.15.0
|
| 100 |
+
- Tokenizers 0.15.0
|
logs/events.out.tfevents.1700962445.serv-3318.864794.10
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1214c0faa922d5e0382b692f36c01b46956a41b0296a67e3316522d5b03070c5
|
| 3 |
+
size 20310
|
logs/events.out.tfevents.1700962621.serv-3318.864794.11
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd5990cbdf82be966fae3cf79f425450925cb1db5002ae25d35d59ba1e192e2e
|
| 3 |
+
size 363
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 46360656
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:731a4cf2595e0a1539957dde5f6c4687287353081563e59a4daf9eaec26ee3a3
|
| 3 |
size 46360656
|