Hugging Face's logo

RajuEEE
/
RewardModel_RobertaBase

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
RajuEEE commited on
Commit
c6511d9
·
verified ·
1 Parent(s): 654ac9c

RajuEEE/Paper_RewardModel_RobertaBase

Browse files
Files changed (6) hide show
  1. README.md +10 -15
  2. config.json +2 -4
  3. model.safetensors +2 -2
  4. runs/Jul16_20-53-27_6f833c65d347/events.out.tfevents.1721163210.6f833c65d347.209.0 +3 -0
  5. runs/Jul16_20-53-27_6f833c65d347/events.out.tfevents.1721164167.6f833c65d347.209.1 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -18,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1047
22
- - F1: 0.9722
23
- - Roc Auc: 0.9792
24
- - Accuracy: 0.9722
25
 
26
  ## Model description
27
 
@@ -46,22 +46,17 @@ The following hyperparameters were used during training:
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
55
- | No log | 1.0 | 15 | 0.6256 | 0.0 | 0.5 | 0.0 |
56
- | No log | 2.0 | 30 | 0.5210 | 0.3448 | 0.6042 | 0.2083 |
57
- | No log | 3.0 | 45 | 0.3479 | 0.8143 | 0.8576 | 0.7639 |
58
- | No log | 4.0 | 60 | 0.2431 | 0.9241 | 0.9444 | 0.9167 |
59
- | No log | 5.0 | 75 | 0.1917 | 0.9315 | 0.9514 | 0.9167 |
60
- | No log | 6.0 | 90 | 0.1364 | 0.9655 | 0.9757 | 0.9583 |
61
- | 0.3628 | 7.0 | 105 | 0.1120 | 0.9583 | 0.9688 | 0.9583 |
62
- | 0.3628 | 8.0 | 120 | 0.0967 | 0.9655 | 0.9757 | 0.9583 |
63
- | 0.3628 | 9.0 | 135 | 0.1047 | 0.9722 | 0.9792 | 0.9722 |
64
- | 0.3628 | 10.0 | 150 | 0.0928 | 0.9722 | 0.9792 | 0.9722 |
65
 
66
 
67
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5050
22
+ - F1: 0.7522
23
+ - Roc Auc: 0.7526
24
+ - Accuracy: 0.7509
25
 
26
  ## Model description
27
 
 
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 5
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
55
+ | 0.6464 | 1.0 | 100 | 0.6186 | 0.6772 | 0.6772 | 0.6737 |
56
+ | 0.5776 | 2.0 | 200 | 0.5439 | 0.7298 | 0.7298 | 0.7298 |
57
+ | 0.4806 | 3.0 | 300 | 0.5050 | 0.7522 | 0.7526 | 0.7509 |
58
+ | 0.3909 | 4.0 | 400 | 0.8594 | 0.6690 | 0.6684 | 0.6667 |
59
+ | 0.331 | 5.0 | 500 | 0.7766 | 0.7206 | 0.7211 | 0.7193 |
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
config.json CHANGED
@@ -12,15 +12,13 @@
12
  "hidden_size": 768,
13
  "id2label": {
14
  "0": "Bad",
15
- "1": "Average",
16
- "2": "Good"
17
  },
18
  "initializer_range": 0.02,
19
  "intermediate_size": 3072,
20
  "label2id": {
21
- "Average": 1,
22
  "Bad": 0,
23
- "Good": 2
24
  },
25
  "layer_norm_eps": 1e-05,
26
  "max_position_embeddings": 514,
 
12
  "hidden_size": 768,
13
  "id2label": {
14
  "0": "Bad",
15
+ "1": "Good"
 
16
  },
17
  "initializer_range": 0.02,
18
  "intermediate_size": 3072,
19
  "label2id": {
 
20
  "Bad": 0,
21
+ "Good": 1
22
  },
23
  "layer_norm_eps": 1e-05,
24
  "max_position_embeddings": 514,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea3da063902d706260f2b9ae6ccc0dd54f70b774ae06cb0645d5953581e3773d
3
- size 498615900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61dc313b9b0cb871020ca02bab5b800d6b72a310ca90a2e670d097c505503af5
3
+ size 498612824
runs/Jul16_20-53-27_6f833c65d347/events.out.tfevents.1721163210.6f833c65d347.209.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a461c3cdafcafc2bac11e6083941cfdc961e8523c323fd48d967ad7b05af87e
3
+ size 8477
runs/Jul16_20-53-27_6f833c65d347/events.out.tfevents.1721164167.6f833c65d347.209.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f34a441a1cf6dce382147f8d6655f877efe622bb93d7efeffd39fd632877020
3
+ size 508
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:098e46c5a702d34bdec66651e59afcacd001f2ed02dd90e9c149968cd82803f1
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c32164d7d1fbb4be5ff1def9ff4334ea1b25181842232dbc60d27fe502bc651
3
  size 5112