Hugging Face's logo

arche4452
/
minilm-fintuned-emotion

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
arche4452 commited on
Commit
7baa020
•
1 Parent(s): f6f9b5a

Success is guarantded!

Browse files
Files changed (5) hide show
  1. README.md +15 -10
  2. model.safetensors +1 -1
  3. runs/Nov20_05-05-27_4c79db0508a2/events.out.tfevents.1700456783.4c79db0508a2.160.0 +2 -2
  4. runs/Nov20_05-14-38_4c79db0508a2/events.out.tfevents.1700457289.4c79db0508a2.160.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the emotion dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3605
21
 
22
  ## Model description
23
 
@@ -42,23 +42,28 @@ The following hyperparameters were used during training:
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 5
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | No log | 1.0 | 250 | 1.0591 |
53
- | No log | 2.0 | 500 | 0.7041 |
54
- | No log | 3.0 | 750 | 0.4961 |
55
- | No log | 4.0 | 1000 | 0.3879 |
56
- | No log | 5.0 | 1250 | 0.3605 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
- - Transformers 4.35.0
62
  - Pytorch 2.1.0+cu118
63
- - Datasets 2.14.6
64
- - Tokenizers 0.14.1
 
17
 
18
  This model is a fine-tuned version of [microsoft/MiniLM-L12-H384-uncased](https://huggingface.co/microsoft/MiniLM-L12-H384-uncased) on the emotion dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3649
21
 
22
  ## Model description
23
 
 
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - num_epochs: 10
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 1.0 | 250 | 0.2190 |
53
+ | No log | 2.0 | 500 | 0.2935 |
54
+ | No log | 3.0 | 750 | 0.2978 |
55
+ | No log | 4.0 | 1000 | 0.2842 |
56
+ | No log | 5.0 | 1250 | 0.3042 |
57
+ | No log | 6.0 | 1500 | 0.3383 |
58
+ | No log | 7.0 | 1750 | 0.3491 |
59
+ | No log | 8.0 | 2000 | 0.3548 |
60
+ | No log | 9.0 | 2250 | 0.3648 |
61
+ | No log | 10.0 | 2500 | 0.3649 |
62
 
63
 
64
  ### Framework versions
65
 
66
+ - Transformers 4.35.2
67
  - Pytorch 2.1.0+cu118
68
+ - Datasets 2.15.0
69
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71d284c02c8743e72c35df15022a82a84a1dcd6a05e5dbcde01bbd8d4c575695
3
  size 133472536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d67e7f1ad9bdeb52c9ed41bd9707804176843ff9c8727697a24775f316c1dc10
3
  size 133472536
runs/Nov20_05-05-27_4c79db0508a2/events.out.tfevents.1700456783.4c79db0508a2.160.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de01a0986ad64a1f920676f93f3c641607df0b851c4126c957a864ba1ab44cb9
3
- size 8470
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a69d815e670bcf12db761ca8872b153d9b962f5eddf44dff5f03b973feeed9
3
+ size 9283
runs/Nov20_05-14-38_4c79db0508a2/events.out.tfevents.1700457289.4c79db0508a2.160.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390e8cc54d75fc45e818ffa9763c025fdbc369633806a62407c06dd9850a8634
3
+ size 7608
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbf4e8523986e73a4ceba15e50728d54c63957c21c5a158f68be6db23a8d2d68
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200dc859602828db6205be520b69f89fc1812cf925a77ebecbb6267eb4d81e8a
3
  size 4600