Commit
•
ab98890
1
Parent(s):
8b09cf9
End of training
Browse files- README.md +80 -0
- eval_results.txt +6 -0
- logs/events.out.tfevents.1649425099.algo-1.599.0 +2 -2
- logs/events.out.tfevents.1649425287.algo-1.599.2 +3 -0
- pytorch_model.bin +1 -1
README.md
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- glue
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: MiniLMv2-L12-H384-sst2
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Text Classification
|
13 |
+
type: text-classification
|
14 |
+
dataset:
|
15 |
+
name: glue
|
16 |
+
type: glue
|
17 |
+
args: sst2
|
18 |
+
metrics:
|
19 |
+
- name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.9208715596330275
|
22 |
+
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# MiniLMv2-L12-H384-sst2
|
28 |
+
|
29 |
+
This model is a fine-tuned version of [nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large](https://huggingface.co/nreimers/MiniLMv2-L12-H384-distilled-from-RoBERTa-Large) on the glue dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 0.2195
|
32 |
+
- Accuracy: 0.9209
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 3e-05
|
52 |
+
- train_batch_size: 32
|
53 |
+
- eval_batch_size: 32
|
54 |
+
- seed: 42
|
55 |
+
- distributed_type: sagemaker_data_parallel
|
56 |
+
- num_devices: 8
|
57 |
+
- total_train_batch_size: 256
|
58 |
+
- total_eval_batch_size: 256
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 500
|
62 |
+
- num_epochs: 4
|
63 |
+
- mixed_precision_training: Native AMP
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
68 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
69 |
+
| 0.5576 | 1.0 | 264 | 0.2690 | 0.8979 |
|
70 |
+
| 0.2854 | 2.0 | 528 | 0.2077 | 0.9117 |
|
71 |
+
| 0.2158 | 3.0 | 792 | 0.2195 | 0.9209 |
|
72 |
+
| 0.1789 | 4.0 | 1056 | 0.2260 | 0.9163 |
|
73 |
+
|
74 |
+
|
75 |
+
### Framework versions
|
76 |
+
|
77 |
+
- Transformers 4.17.0
|
78 |
+
- Pytorch 1.10.2+cu113
|
79 |
+
- Datasets 1.18.4
|
80 |
+
- Tokenizers 0.11.6
|
eval_results.txt
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 4.0
|
2 |
+
eval_accuracy = 0.9208715596330275
|
3 |
+
eval_loss = 0.2195197343826294
|
4 |
+
eval_runtime = 0.5346
|
5 |
+
eval_samples_per_second = 1631.215
|
6 |
+
eval_steps_per_second = 7.483
|
logs/events.out.tfevents.1649425099.algo-1.599.0
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 sha256:8c386781ccc9573ec98fbd62647f69e370b78df36bc2f173f8e669db9f1385ab
|
3 |
+
size 5741
|
logs/events.out.tfevents.1649425287.algo-1.599.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f776549c2f5ef42801d9f452f77bd619101219ae923528fbd7824272e438a86
|
3 |
+
size 363
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 163856237
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf756d3ec95f18b316c90cbecd132539802a7f8e20e152f60ce1185f758641e6
|
3 |
size 163856237
|