Hugging Face's logo

oneonlee
/
flan-t5-small-qclassifier_new_avg-droprob_0.2-smooth_0.1-lr_1e-5-dcy_0.1

Safetensors
t5
Generated from Trainer
Model card Files Community
oneonlee commited on
Commit
fd96fb5
•
1 Parent(s): 95a8c7d

End of training

Browse files
Files changed (7) hide show
  1. README.md +12 -13
  2. all_results.json +15 -15
  3. eval_results.json +8 -8
  4. f1_scores.png +0 -0
  5. losses.png +0 -0
  6. model.safetensors +1 -1
  7. test_results.json +7 -7
README.md CHANGED
@@ -19,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.5931
23
- - Precision: 0.7189
24
- - Recall: 0.9946
25
- - F1: 0.8345
26
 
27
  ## Model description
28
 
@@ -54,15 +54,14 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
57
- | 0.7094 | 1.0 | 193 | 0.6088 | 0.7148 | 1.0 | 0.8337 |
58
- | 0.605 | 2.0 | 386 | 0.5990 | 0.7148 | 1.0 | 0.8337 |
59
- | 0.5966 | 3.0 | 579 | 0.5934 | 0.7147 | 0.9991 | 0.8333 |
60
- | 0.5904 | 4.0 | 772 | 0.5931 | 0.7189 | 0.9946 | 0.8345 |
61
- | 0.5871 | 5.0 | 965 | 0.5910 | 0.7222 | 0.9665 | 0.8267 |
62
- | 0.5843 | 6.0 | 1158 | 0.5905 | 0.7247 | 0.9619 | 0.8266 |
63
- | 0.5824 | 7.0 | 1351 | 0.5914 | 0.7275 | 0.9510 | 0.8244 |
64
- | 0.58 | 8.0 | 1544 | 0.5911 | 0.7295 | 0.9510 | 0.8257 |
65
- | 0.5791 | 9.0 | 1737 | 0.5909 | 0.7311 | 0.9492 | 0.8260 |
66
 
67
 
68
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.5940
23
+ - Precision: 0.7153
24
+ - Recall: 1.0
25
+ - F1: 0.8340
26
 
27
  ## Model description
28
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
57
+ | 0.612 | 1.0 | 193 | 0.6055 | 0.7148 | 1.0 | 0.8337 |
58
+ | 0.6046 | 2.0 | 386 | 0.5983 | 0.7148 | 1.0 | 0.8337 |
59
+ | 0.596 | 3.0 | 579 | 0.5940 | 0.7153 | 1.0 | 0.8340 |
60
+ | 0.5907 | 4.0 | 772 | 0.5939 | 0.7181 | 0.9909 | 0.8328 |
61
+ | 0.5883 | 5.0 | 965 | 0.5916 | 0.7233 | 0.9692 | 0.8284 |
62
+ | 0.5868 | 6.0 | 1158 | 0.5906 | 0.7243 | 0.9692 | 0.8290 |
63
+ | 0.5834 | 7.0 | 1351 | 0.5907 | 0.7260 | 0.9583 | 0.8261 |
64
+ | 0.581 | 8.0 | 1544 | 0.5905 | 0.7273 | 0.9529 | 0.8250 |
 
65
 
66
 
67
  ### Framework versions
all_results.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
- "epoch": 9.0,
3
- "eval_f1": 0.8345378470901483,
4
- "eval_loss": 0.5931139588356018,
5
- "eval_precision": 0.718872870249017,
6
- "eval_recall": 0.9945602901178604,
7
- "eval_runtime": 8.1012,
8
- "eval_samples_per_second": 190.467,
9
- "eval_steps_per_second": 3.086,
10
- "test_f1": 0.8258212375859435,
11
- "test_loss": 0.5932575464248657,
12
- "test_precision": 0.7060744611365121,
13
- "test_recall": 0.9944802207911684,
14
- "test_runtime": 8.1169,
15
- "test_samples_per_second": 190.22,
16
- "test_steps_per_second": 3.08
17
  }
 
1
  {
2
+ "epoch": 8.0,
3
+ "eval_f1": 0.8340264650283554,
4
+ "eval_loss": 0.5939932465553284,
5
+ "eval_precision": 0.7153047989623865,
6
+ "eval_recall": 1.0,
7
+ "eval_runtime": 8.5988,
8
+ "eval_samples_per_second": 179.444,
9
+ "eval_steps_per_second": 2.907,
10
+ "test_f1": 0.8263017863930064,
11
+ "test_loss": 0.5939090847969055,
12
+ "test_precision": 0.7040155440414507,
13
+ "test_recall": 1.0,
14
+ "test_runtime": 8.4879,
15
+ "test_samples_per_second": 181.905,
16
+ "test_steps_per_second": 2.945
17
  }
eval_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "epoch": 9.0,
3
- "eval_f1": 0.8345378470901483,
4
- "eval_loss": 0.5931139588356018,
5
- "eval_precision": 0.718872870249017,
6
- "eval_recall": 0.9945602901178604,
7
- "eval_runtime": 8.1012,
8
- "eval_samples_per_second": 190.467,
9
- "eval_steps_per_second": 3.086
10
  }
 
1
  {
2
+ "epoch": 8.0,
3
+ "eval_f1": 0.8340264650283554,
4
+ "eval_loss": 0.5939932465553284,
5
+ "eval_precision": 0.7153047989623865,
6
+ "eval_recall": 1.0,
7
+ "eval_runtime": 8.5988,
8
+ "eval_samples_per_second": 179.444,
9
+ "eval_steps_per_second": 2.907
10
  }
f1_scores.png CHANGED
losses.png CHANGED
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11b99f05e1604d689129f85c40b356e44ebd1b23b7ee804d16654566c49672a7
3
  size 243126200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f69aa7ddfe243e8f0d853285ea8098235a9e9052c10985f0117b1117711f768
3
  size 243126200
test_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "test_f1": 0.8258212375859435,
3
- "test_loss": 0.5932575464248657,
4
- "test_precision": 0.7060744611365121,
5
- "test_recall": 0.9944802207911684,
6
- "test_runtime": 8.1169,
7
- "test_samples_per_second": 190.22,
8
- "test_steps_per_second": 3.08
9
  }
 
1
  {
2
+ "test_f1": 0.8263017863930064,
3
+ "test_loss": 0.5939090847969055,
4
+ "test_precision": 0.7040155440414507,
5
+ "test_recall": 1.0,
6
+ "test_runtime": 8.4879,
7
+ "test_samples_per_second": 181.905,
8
+ "test_steps_per_second": 2.945
9
  }