Hugging Face's logo

oneonlee
/
flan-t5-small-qclassifier_new_0.6-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
a1e0d8d
•
1 Parent(s): 421ea0d

End of training

Browse files
Files changed (7) hide show
  1. README.md +14 -15
  2. all_results.json +14 -14
  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 +6 -6
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: 0.5707
23
- - Precision: 0.7422
24
- - Recall: 0.9965
25
- - F1: 0.8507
26
 
27
  ## Model description
28
 
@@ -54,17 +54,16 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
57
- | 0.5969 | 1.0 | 193 | 0.5841 | 0.7395 | 1.0 | 0.8502 |
58
- | 0.5863 | 2.0 | 386 | 0.5784 | 0.7395 | 1.0 | 0.8502 |
59
- | 0.5784 | 3.0 | 579 | 0.5759 | 0.7395 | 1.0 | 0.8502 |
60
- | 0.5747 | 4.0 | 772 | 0.5752 | 0.7395 | 1.0 | 0.8502 |
61
- | 0.5716 | 5.0 | 965 | 0.5720 | 0.7399 | 0.9974 | 0.8496 |
62
- | 0.5702 | 6.0 | 1158 | 0.5707 | 0.7422 | 0.9965 | 0.8507 |
63
- | 0.5669 | 7.0 | 1351 | 0.5709 | 0.7428 | 0.9947 | 0.8505 |
64
- | 0.565 | 8.0 | 1544 | 0.5705 | 0.7460 | 0.9886 | 0.8504 |
65
- | 0.5632 | 9.0 | 1737 | 0.5710 | 0.7462 | 0.9842 | 0.8488 |
66
- | 0.5613 | 10.0 | 1930 | 0.5704 | 0.7495 | 0.9702 | 0.8457 |
67
- | 0.5622 | 11.0 | 2123 | 0.5712 | 0.75 | 0.9702 | 0.8460 |
68
 
69
 
70
  ### 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: 0.5694
23
+ - Precision: 0.7409
24
+ - Recall: 1.0
25
+ - F1: 0.8512
26
 
27
  ## Model description
28
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
57
+ | 0.6201 | 1.0 | 193 | 0.5847 | 0.7395 | 1.0 | 0.8502 |
58
+ | 0.5868 | 2.0 | 386 | 0.5770 | 0.7395 | 1.0 | 0.8502 |
59
+ | 0.5791 | 3.0 | 579 | 0.5728 | 0.7395 | 1.0 | 0.8502 |
60
+ | 0.5736 | 4.0 | 772 | 0.5746 | 0.7395 | 1.0 | 0.8502 |
61
+ | 0.5713 | 5.0 | 965 | 0.5694 | 0.7409 | 1.0 | 0.8512 |
62
+ | 0.5678 | 6.0 | 1158 | 0.5697 | 0.7404 | 0.9947 | 0.8489 |
63
+ | 0.5664 | 7.0 | 1351 | 0.5694 | 0.7413 | 0.9869 | 0.8466 |
64
+ | 0.5639 | 8.0 | 1544 | 0.5693 | 0.7409 | 0.9798 | 0.8438 |
65
+ | 0.5623 | 9.0 | 1737 | 0.5707 | 0.7428 | 0.9772 | 0.8441 |
66
+ | 0.5602 | 10.0 | 1930 | 0.5700 | 0.7470 | 0.9702 | 0.8441 |
 
67
 
68
 
69
  ### Framework versions
all_results.json CHANGED
@@ -1,17 +1,17 @@
1
  {
2
- "epoch": 11.0,
3
- "eval_f1": 0.8507295173961841,
4
- "eval_loss": 0.5706504583358765,
5
- "eval_precision": 0.7421671018276762,
6
- "eval_recall": 0.9964943032427696,
7
- "eval_runtime": 8.1326,
8
- "eval_samples_per_second": 189.731,
9
- "eval_steps_per_second": 3.074,
10
- "test_f1": 0.8412757973733583,
11
- "test_loss": 0.5738372206687927,
12
- "test_precision": 0.7260362694300518,
13
  "test_recall": 1.0,
14
- "test_runtime": 8.1726,
15
- "test_samples_per_second": 188.924,
16
- "test_steps_per_second": 3.059
17
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "eval_f1": 0.8511749347258486,
4
+ "eval_loss": 0.5693770051002502,
5
+ "eval_precision": 0.740909090909091,
6
+ "eval_recall": 1.0,
7
+ "eval_runtime": 8.5586,
8
+ "eval_samples_per_second": 180.287,
9
+ "eval_steps_per_second": 2.921,
10
+ "test_f1": 0.8419076229815997,
11
+ "test_loss": 0.5764256715774536,
12
+ "test_precision": 0.7269779507133592,
13
  "test_recall": 1.0,
14
+ "test_runtime": 8.5139,
15
+ "test_samples_per_second": 181.35,
16
+ "test_steps_per_second": 2.936
17
  }
eval_results.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "epoch": 11.0,
3
- "eval_f1": 0.8507295173961841,
4
- "eval_loss": 0.5706504583358765,
5
- "eval_precision": 0.7421671018276762,
6
- "eval_recall": 0.9964943032427696,
7
- "eval_runtime": 8.1326,
8
- "eval_samples_per_second": 189.731,
9
- "eval_steps_per_second": 3.074
10
  }
 
1
  {
2
+ "epoch": 10.0,
3
+ "eval_f1": 0.8511749347258486,
4
+ "eval_loss": 0.5693770051002502,
5
+ "eval_precision": 0.740909090909091,
6
+ "eval_recall": 1.0,
7
+ "eval_runtime": 8.5586,
8
+ "eval_samples_per_second": 180.287,
9
+ "eval_steps_per_second": 2.921
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 sha256:5d3e9f4b0da44454ae4a169e5a55ef0bf8acf9caca12f6010369a552d39ff706
3
  size 243126200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb23abd621cc8a48913c61a1ebb790a46436634723a5b12f8c3bf5c2c0ebe1d
3
  size 243126200
test_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "test_f1": 0.8412757973733583,
3
- "test_loss": 0.5738372206687927,
4
- "test_precision": 0.7260362694300518,
5
  "test_recall": 1.0,
6
- "test_runtime": 8.1726,
7
- "test_samples_per_second": 188.924,
8
- "test_steps_per_second": 3.059
9
  }
 
1
  {
2
+ "test_f1": 0.8419076229815997,
3
+ "test_loss": 0.5764256715774536,
4
+ "test_precision": 0.7269779507133592,
5
  "test_recall": 1.0,
6
+ "test_runtime": 8.5139,
7
+ "test_samples_per_second": 181.35,
8
+ "test_steps_per_second": 2.936
9
  }