Hugging Face's logo

SudiptoPramanik
/
RewardModelSmallerQuestionWithTwoLabelsLengthJustified

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
SudiptoPramanik commited on
Commit
0f01265
·
1 Parent(s): 11256a8

SudiptoPramanik/RewardModelSmallerQuestionWithTwoLabelsLengthJustified

Browse files
Files changed (15) hide show
  1. README.md +40 -11
  2. adapter_config.json +23 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Dec04_09-04-32_1f3b4092150b/events.out.tfevents.1701680684.1f3b4092150b.952.0 +3 -0
  5. runs/Dec04_09-15-29_1f3b4092150b/events.out.tfevents.1701681335.1f3b4092150b.952.1 +3 -0
  6. runs/Dec04_09-15-29_1f3b4092150b/events.out.tfevents.1701681615.1f3b4092150b.952.2 +3 -0
  7. runs/Dec04_09-21-43_1f3b4092150b/events.out.tfevents.1701681708.1f3b4092150b.952.3 +3 -0
  8. runs/Dec04_09-21-43_1f3b4092150b/events.out.tfevents.1701682531.1f3b4092150b.952.4 +3 -0
  9. runs/Dec04_09-43-11_1f3b4092150b/events.out.tfevents.1701683008.1f3b4092150b.952.5 +3 -0
  10. runs/Dec04_09-46-36_1f3b4092150b/events.out.tfevents.1701683212.1f3b4092150b.952.6 +3 -0
  11. runs/Dec04_09-50-59_1f3b4092150b/events.out.tfevents.1701683483.1f3b4092150b.17971.0 +3 -0
  12. runs/Dec04_09-50-59_1f3b4092150b/events.out.tfevents.1701688189.1f3b4092150b.17971.1 +3 -0
  13. tokenizer.json +2 -2
  14. tokenizer_config.json +1 -1
  15. training_args.bin +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: mit
3
- base_model: roberta-base
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -16,12 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # RewardModelSmallerQuestionWithTwoLabelsLengthJustified
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: 0.5538
22
- - F1: 0.7190
23
- - Roc Auc: 0.7190
24
- - Accuracy: 0.7190
25
 
26
  ## Model description
27
 
@@ -40,20 +40,49 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 2e-05
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
- - lr_scheduler_type: linear
49
- - num_epochs: 2
 
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
55
- | 0.6271 | 1.0 | 200 | 0.5978 | 0.6942 | 0.6942 | 0.6915 |
56
- | 0.5383 | 2.0 | 400 | 0.5538 | 0.7190 | 0.7190 | 0.7190 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: roberta-large
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
16
 
17
  # RewardModelSmallerQuestionWithTwoLabelsLengthJustified
18
 
19
+ This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.5248
22
+ - F1: 0.7539
23
+ - Roc Auc: 0.7508
24
+ - Accuracy: 0.7380
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 0.0001
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: constant
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 30
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
56
+ | 0.7105 | 1.0 | 145 | 0.6814 | 0.5260 | 0.5192 | 0.5048 |
57
+ | 0.6899 | 2.0 | 290 | 0.6530 | 0.6090 | 0.6102 | 0.6038 |
58
+ | 0.6703 | 3.0 | 435 | 0.6318 | 0.6387 | 0.6565 | 0.6070 |
59
+ | 0.6432 | 4.0 | 580 | 0.6098 | 0.6961 | 0.7029 | 0.6805 |
60
+ | 0.6273 | 5.0 | 725 | 0.5909 | 0.7118 | 0.7141 | 0.7061 |
61
+ | 0.64 | 6.0 | 870 | 0.5837 | 0.7038 | 0.7029 | 0.6965 |
62
+ | 0.6178 | 7.0 | 1015 | 0.5829 | 0.7005 | 0.6981 | 0.6869 |
63
+ | 0.6342 | 8.0 | 1160 | 0.5855 | 0.6785 | 0.6805 | 0.6741 |
64
+ | 0.583 | 9.0 | 1305 | 0.5549 | 0.7310 | 0.7284 | 0.7188 |
65
+ | 0.5801 | 10.0 | 1450 | 0.5805 | 0.6710 | 0.6773 | 0.6581 |
66
+ | 0.6279 | 11.0 | 1595 | 0.6581 | 0.6003 | 0.6022 | 0.5974 |
67
+ | 0.6112 | 12.0 | 1740 | 0.5382 | 0.7372 | 0.7380 | 0.7348 |
68
+ | 0.5967 | 13.0 | 1885 | 0.6305 | 0.6443 | 0.6438 | 0.6422 |
69
+ | 0.5927 | 14.0 | 2030 | 0.6144 | 0.6613 | 0.6645 | 0.6550 |
70
+ | 0.5968 | 15.0 | 2175 | 0.5825 | 0.6901 | 0.6901 | 0.6901 |
71
+ | 0.6122 | 16.0 | 2320 | 0.5858 | 0.6815 | 0.6805 | 0.6773 |
72
+ | 0.5941 | 17.0 | 2465 | 0.5719 | 0.6979 | 0.7013 | 0.6901 |
73
+ | 0.5977 | 18.0 | 2610 | 0.6043 | 0.6699 | 0.6709 | 0.6677 |
74
+ | 0.59 | 19.0 | 2755 | 0.5465 | 0.7203 | 0.7220 | 0.7157 |
75
+ | 0.5871 | 20.0 | 2900 | 0.6474 | 0.6262 | 0.6262 | 0.6262 |
76
+ | 0.5932 | 21.0 | 3045 | 0.5701 | 0.6945 | 0.6965 | 0.6901 |
77
+ | 0.5966 | 22.0 | 3190 | 0.5281 | 0.7387 | 0.7412 | 0.7316 |
78
+ | 0.6006 | 23.0 | 3335 | 0.5713 | 0.6945 | 0.6965 | 0.6869 |
79
+ | 0.5696 | 24.0 | 3480 | 0.6498 | 0.6242 | 0.6230 | 0.6198 |
80
+ | 0.5921 | 25.0 | 3625 | 0.6453 | 0.6359 | 0.6342 | 0.6294 |
81
+ | 0.5761 | 26.0 | 3770 | 0.5226 | 0.7528 | 0.7524 | 0.7508 |
82
+ | 0.5504 | 27.0 | 3915 | 0.5793 | 0.6751 | 0.6725 | 0.6645 |
83
+ | 0.5891 | 28.0 | 4060 | 0.5248 | 0.7539 | 0.7508 | 0.7380 |
84
+ | 0.5757 | 29.0 | 4205 | 0.5983 | 0.6699 | 0.6693 | 0.6677 |
85
+ | 0.5631 | 30.0 | 4350 | 0.6187 | 0.6454 | 0.6454 | 0.6454 |
86
 
87
 
88
  ### Framework versions
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "roberta-large",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.1,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 2,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "query",
20
+ "value"
21
+ ],
22
+ "task_type": "SEQ_CLS"
23
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:138b66bdbcf6f7c9196c3fdb6fc1d4d6c2e1a5c1cd2decfc6f6895976f39fcac
3
+ size 5007376
runs/Dec04_09-04-32_1f3b4092150b/events.out.tfevents.1701680684.1f3b4092150b.952.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e1ba9594798004d01f6fd1ab30c2f7b368a4d6dfb6efcfccffe22139796b41
3
+ size 9170
runs/Dec04_09-15-29_1f3b4092150b/events.out.tfevents.1701681335.1f3b4092150b.952.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51e069d684e99621f8a79f7059e14e326a22ccf0f1b1e60c356ced48f9898913
3
+ size 8025
runs/Dec04_09-15-29_1f3b4092150b/events.out.tfevents.1701681615.1f3b4092150b.952.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:006af2a2ae3fa0d98a19d33423538928e15e6fb19a4f09a5f714d6d5d4b4b31a
3
+ size 508
runs/Dec04_09-21-43_1f3b4092150b/events.out.tfevents.1701681708.1f3b4092150b.952.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084cbf7cd27f88f2083a9cf3857bba69ea1b93aca8a24a6dc9fdc26b7433f1e3
3
+ size 14424
runs/Dec04_09-21-43_1f3b4092150b/events.out.tfevents.1701682531.1f3b4092150b.952.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7cf00578d38e26ff24d107e7221f9ff72b9ab67dba467920bb331fec99f4d1
3
+ size 508
runs/Dec04_09-43-11_1f3b4092150b/events.out.tfevents.1701683008.1f3b4092150b.952.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a12b7220cab1b3be39b68b32969166cb755e6a477c3ff360f27b8dbcbe6e134e
3
+ size 4632
runs/Dec04_09-46-36_1f3b4092150b/events.out.tfevents.1701683212.1f3b4092150b.952.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:790b8a1f54a9481d92939c9032c5c1f0bb7577d411f52323d0c18afee590d12e
3
+ size 5052
runs/Dec04_09-50-59_1f3b4092150b/events.out.tfevents.1701683483.1f3b4092150b.17971.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0727cb90a14885349a784c0cfe4cd68119761506a0890acd1808dd5a0f10c6ae
3
+ size 24180
runs/Dec04_09-50-59_1f3b4092150b/events.out.tfevents.1701688189.1f3b4092150b.17971.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cf9bb25e24cb05951fe00bf678be0b3b680f8b1cad5501eb1a2f734578ab727
3
+ size 508
tokenizer.json CHANGED
@@ -52,7 +52,7 @@
52
  "normalizer": null,
53
  "pre_tokenizer": {
54
  "type": "ByteLevel",
55
- "add_prefix_space": false,
56
  "trim_offsets": true,
57
  "use_regex": true
58
  },
@@ -67,7 +67,7 @@
67
  0
68
  ],
69
  "trim_offsets": true,
70
- "add_prefix_space": false
71
  },
72
  "decoder": {
73
  "type": "ByteLevel",
 
52
  "normalizer": null,
53
  "pre_tokenizer": {
54
  "type": "ByteLevel",
55
+ "add_prefix_space": true,
56
  "trim_offsets": true,
57
  "use_regex": true
58
  },
 
67
  0
68
  ],
69
  "trim_offsets": true,
70
+ "add_prefix_space": true
71
  },
72
  "decoder": {
73
  "type": "ByteLevel",
tokenizer_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<s>",
 
1
  {
2
+ "add_prefix_space": true,
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<s>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fed2c501e8b3b49c41e04c00e9020a112dfab965fbe0521ed08a7fc4442b9872
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d62dbe25d65322a60e61f30a77228e0a9971a13a3d8a0bc906eea153d6b820f9
3
  size 4664