Hugging Face's logo

salbatarni
/
bert_baseline_prompt_adherence_task3_fold2

TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
salbatarni commited on
Commit
a6b22cf
•
1 Parent(s): d8c6ff8

Training in progress, step 65

Browse files
Files changed (5) hide show
  1. README.md +37 -37
  2. runs/Aug22_09-41-53_b098a78ba869/events.out.tfevents.1724319714.b098a78ba869.24.0 +3 -0
  3. runs/Aug22_09-46-37_b098a78ba869/events.out.tfevents.1724319997.b098a78ba869.24.1 +3 -0
  4. runs/Aug22_09-51-18_b098a78ba869/events.out.tfevents.1724320279.b098a78ba869.24.2 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -4,20 +4,20 @@ base_model: google-bert/bert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
- - name: bert_baseline_prompt_adherence_task3_fold2
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
- # bert_baseline_prompt_adherence_task3_fold2
15
 
16
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.3817
19
- - Qwk: 0.6470
20
- - Mse: 0.3818
21
 
22
  ## Model description
23
 
@@ -48,38 +48,38 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
50
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
51
- | No log | 0.0308 | 2 | 1.5377 | 0.0 | 1.5385 |
52
- | No log | 0.0615 | 4 | 0.9550 | 0.1039 | 0.9553 |
53
- | No log | 0.0923 | 6 | 0.7286 | 0.1294 | 0.7283 |
54
- | No log | 0.1231 | 8 | 0.6242 | 0.0252 | 0.6236 |
55
- | No log | 0.1538 | 10 | 0.6104 | 0.0252 | 0.6097 |
56
- | No log | 0.1846 | 12 | 0.5825 | 0.0638 | 0.5819 |
57
- | No log | 0.2154 | 14 | 0.5472 | 0.0709 | 0.5466 |
58
- | No log | 0.2462 | 16 | 0.4973 | 0.1150 | 0.4968 |
59
- | No log | 0.2769 | 18 | 0.4732 | 0.3908 | 0.4728 |
60
- | No log | 0.3077 | 20 | 0.4665 | 0.5935 | 0.4662 |
61
- | No log | 0.3385 | 22 | 0.4304 | 0.5976 | 0.4304 |
62
- | No log | 0.3692 | 24 | 0.4506 | 0.5795 | 0.4507 |
63
- | No log | 0.4 | 26 | 0.4830 | 0.5936 | 0.4830 |
64
- | No log | 0.4308 | 28 | 0.5284 | 0.4334 | 0.5284 |
65
- | No log | 0.4615 | 30 | 0.5470 | 0.4239 | 0.5469 |
66
- | No log | 0.4923 | 32 | 0.5238 | 0.4711 | 0.5238 |
67
- | No log | 0.5231 | 34 | 0.4764 | 0.5446 | 0.4766 |
68
- | No log | 0.5538 | 36 | 0.4393 | 0.4824 | 0.4396 |
69
- | No log | 0.5846 | 38 | 0.4326 | 0.4425 | 0.4329 |
70
- | No log | 0.6154 | 40 | 0.4139 | 0.4814 | 0.4142 |
71
- | No log | 0.6462 | 42 | 0.4079 | 0.5310 | 0.4081 |
72
- | No log | 0.6769 | 44 | 0.4149 | 0.6150 | 0.4150 |
73
- | No log | 0.7077 | 46 | 0.4218 | 0.6348 | 0.4218 |
74
- | No log | 0.7385 | 48 | 0.4259 | 0.6583 | 0.4259 |
75
- | No log | 0.7692 | 50 | 0.4150 | 0.6611 | 0.4151 |
76
- | No log | 0.8 | 52 | 0.3977 | 0.6481 | 0.3977 |
77
- | No log | 0.8308 | 54 | 0.3910 | 0.6396 | 0.3911 |
78
- | No log | 0.8615 | 56 | 0.3892 | 0.6415 | 0.3892 |
79
- | No log | 0.8923 | 58 | 0.3830 | 0.6405 | 0.3830 |
80
- | No log | 0.9231 | 60 | 0.3792 | 0.6359 | 0.3792 |
81
- | No log | 0.9538 | 62 | 0.3794 | 0.6359 | 0.3794 |
82
- | No log | 0.9846 | 64 | 0.3817 | 0.6470 | 0.3818 |
83
 
84
 
85
  ### Framework versions
 
4
  tags:
5
  - generated_from_trainer
6
  model-index:
7
+ - name: bert_baseline_prompt_adherence_task3_fold1
8
  results: []
9
  ---
10
 
11
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
  should probably proofread and complete it, then remove this comment. -->
13
 
14
+ # bert_baseline_prompt_adherence_task3_fold1
15
 
16
  This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.3953
19
+ - Qwk: 0.5713
20
+ - Mse: 0.3957
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Qwk | Mse |
50
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
51
+ | No log | 0.0308 | 2 | 1.5468 | 0.0 | 1.5470 |
52
+ | No log | 0.0615 | 4 | 0.9894 | 0.0062 | 0.9899 |
53
+ | No log | 0.0923 | 6 | 0.7177 | 0.1308 | 0.7184 |
54
+ | No log | 0.1231 | 8 | 0.5962 | 0.0090 | 0.5969 |
55
+ | No log | 0.1538 | 10 | 0.5955 | 0.0030 | 0.5963 |
56
+ | No log | 0.1846 | 12 | 0.5747 | 0.1211 | 0.5755 |
57
+ | No log | 0.2154 | 14 | 0.5424 | 0.0335 | 0.5431 |
58
+ | No log | 0.2462 | 16 | 0.5193 | 0.0423 | 0.5200 |
59
+ | No log | 0.2769 | 18 | 0.4807 | 0.1237 | 0.4815 |
60
+ | No log | 0.3077 | 20 | 0.4729 | 0.2731 | 0.4737 |
61
+ | No log | 0.3385 | 22 | 0.4694 | 0.4293 | 0.4701 |
62
+ | No log | 0.3692 | 24 | 0.4429 | 0.4729 | 0.4436 |
63
+ | No log | 0.4 | 26 | 0.4262 | 0.4577 | 0.4267 |
64
+ | No log | 0.4308 | 28 | 0.4314 | 0.4855 | 0.4319 |
65
+ | No log | 0.4615 | 30 | 0.4305 | 0.5004 | 0.4309 |
66
+ | No log | 0.4923 | 32 | 0.4624 | 0.5260 | 0.4629 |
67
+ | No log | 0.5231 | 34 | 0.4806 | 0.5487 | 0.4811 |
68
+ | No log | 0.5538 | 36 | 0.4851 | 0.5627 | 0.4856 |
69
+ | No log | 0.5846 | 38 | 0.4781 | 0.5647 | 0.4786 |
70
+ | No log | 0.6154 | 40 | 0.4385 | 0.5586 | 0.4390 |
71
+ | No log | 0.6462 | 42 | 0.4008 | 0.4961 | 0.4012 |
72
+ | No log | 0.6769 | 44 | 0.4215 | 0.4424 | 0.4219 |
73
+ | No log | 0.7077 | 46 | 0.4247 | 0.4297 | 0.4251 |
74
+ | No log | 0.7385 | 48 | 0.4050 | 0.4683 | 0.4054 |
75
+ | No log | 0.7692 | 50 | 0.3963 | 0.5180 | 0.3967 |
76
+ | No log | 0.8 | 52 | 0.4101 | 0.5579 | 0.4105 |
77
+ | No log | 0.8308 | 54 | 0.4164 | 0.5675 | 0.4168 |
78
+ | No log | 0.8615 | 56 | 0.4086 | 0.5617 | 0.4090 |
79
+ | No log | 0.8923 | 58 | 0.4033 | 0.5653 | 0.4037 |
80
+ | No log | 0.9231 | 60 | 0.4008 | 0.5653 | 0.4012 |
81
+ | No log | 0.9538 | 62 | 0.3973 | 0.5713 | 0.3977 |
82
+ | No log | 0.9846 | 64 | 0.3953 | 0.5713 | 0.3957 |
83
 
84
 
85
  ### Framework versions
runs/Aug22_09-41-53_b098a78ba869/events.out.tfevents.1724319714.b098a78ba869.24.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dcac9650b5450fbaadc3ad68ba6b6b82ae838a7cafdd92a6b5535dd4d6e9f4b
3
+ size 16732
runs/Aug22_09-46-37_b098a78ba869/events.out.tfevents.1724319997.b098a78ba869.24.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd4d8ff15d7594fdc959841620169c24a65b0c548c6adbd108cc9812cb87616
3
+ size 16732
runs/Aug22_09-51-18_b098a78ba869/events.out.tfevents.1724320279.b098a78ba869.24.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf26d8a0f6ae069f31804c48a0a2dedbf323023d7a090740e3c367f51a258191
3
+ size 16732
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:263a342bf0d5edaa29c754736bbc4869fbca52dd6cbfdf77060c84bac4d40026
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf72ecf215e2333d65306da3c2445d6d8865eda9ad6d5cee399792e87881c61
3
  size 5176