Hugging Face's logo

minh21
/
flan-t5-large-prompt-tuning-cpgQA

Generated from Trainer
Model card Files Community
minh21 commited on
Commit
8295267
•
1 Parent(s): af10e4d

End of training

Browse files
Files changed (4) hide show
  1. README.md +5 -8
  2. adapter_config.json +3 -3
  3. adapter_model.bin +2 -2
  4. training_args.bin +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.1363
19
 
20
  ## Model description
21
 
@@ -35,22 +35,19 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 3e-05
38
- - train_batch_size: 2
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 5
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | 0.192 | 1.0 | 430 | 0.1363 |
50
- | 0.2402 | 2.0 | 860 | 0.1363 |
51
- | 0.2249 | 3.0 | 1290 | 0.1363 |
52
- | 0.2243 | 4.0 | 1720 | 0.1363 |
53
- | 0.2243 | 5.0 | 2150 | 0.1363 |
54
 
55
 
56
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1314
19
 
20
  ## Model description
21
 
 
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 3e-05
38
+ - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 2
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | 0.2287 | 1.0 | 430 | 0.1314 |
50
+ | 0.2014 | 2.0 | 860 | 0.1314 |
 
 
 
51
 
52
 
53
  ### Framework versions
adapter_config.json CHANGED
@@ -5,10 +5,10 @@
5
  "num_attention_heads": 16,
6
  "num_layers": 24,
7
  "num_transformer_submodules": 2,
8
- "num_virtual_tokens": 20,
9
  "peft_type": "PROMPT_TUNING",
10
- "prompt_tuning_init": "TEXT",
11
- "prompt_tuning_init_text": "Answer this question using the provided context",
12
  "revision": null,
13
  "task_type": "SEQ_2_SEQ_LM",
14
  "token_dim": 1024,
 
5
  "num_attention_heads": 16,
6
  "num_layers": 24,
7
  "num_transformer_submodules": 2,
8
+ "num_virtual_tokens": 8,
9
  "peft_type": "PROMPT_TUNING",
10
+ "prompt_tuning_init": "RANDOM",
11
+ "prompt_tuning_init_text": null,
12
  "revision": null,
13
  "task_type": "SEQ_2_SEQ_LM",
14
  "token_dim": 1024,
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34bd6fbe4ca9710c3217bb88f627333c27861fdf642d2e815636091dee8aecdb
3
- size 164605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353f2f19234d0dc4d54ae03fec116695608b592244b6987b8f887109541e2e11
3
+ size 66301
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f8eb94c1337f4adf82eb85b1ebcdbf245054a02b9da2716bbd86d8e45880b6b
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36ea94b94e9d3e7a936caa6a922bfe5dc8f6f93ac97ef9d562dbec62eb709047
3
  size 4219