williamplacroix commited on
Commit
c1015dc
·
verified ·
1 Parent(s): 4eaecb0

Finished 2-12 grades: evens pretraining

Browse files
README.md CHANGED
@@ -13,11 +13,12 @@ model-index:
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uds/Graded%20text%20simplification%20training/runs/4mf11grk)
 
16
  # text-simplification
17
 
18
  This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.9922
21
 
22
  ## Model description
23
 
@@ -48,11 +49,11 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:-----:|:---------------:|
51
- | 1.4054 | 1.0 | 4932 | 1.0352 |
52
- | 1.0639 | 2.0 | 9864 | 0.9727 |
53
- | 1.0374 | 3.0 | 14796 | 0.9790 |
54
- | 1.0411 | 4.0 | 19728 | 0.9888 |
55
- | 1.045 | 5.0 | 24660 | 0.9922 |
56
 
57
 
58
  ### Framework versions
 
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
  [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uds/Graded%20text%20simplification%20training/runs/4mf11grk)
16
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/uds/Graded%20text%20simplification%20training/runs/fkl8in2e)
17
  # text-simplification
18
 
19
  This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.9653
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:-----:|:---------------:|
52
+ | 1.5549 | 1.0 | 3022 | 1.1338 |
53
+ | 1.1431 | 2.0 | 6044 | 1.0146 |
54
+ | 1.0544 | 3.0 | 9066 | 0.9736 |
55
+ | 1.0264 | 4.0 | 12088 | 0.9658 |
56
+ | 1.0198 | 5.0 | 15110 | 0.9653 |
57
 
58
 
59
  ### Framework versions
gpt2-2-12-evens/adapter_config.json CHANGED
@@ -20,9 +20,9 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "c_attn",
24
- "lm_head",
25
  "c_proj",
 
 
26
  "c_fc"
27
  ],
28
  "task_type": "CAUSAL_LM",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "c_proj",
24
+ "lm_head",
25
+ "c_attn",
26
  "c_fc"
27
  ],
28
  "task_type": "CAUSAL_LM",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:217e787aeb17eef1d198a3c8bd355116d8291b4cb6d37c82e41558de313bb402
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc7b4f548f7a8ddfaae09ebd46c749bb4b4075519657c8289da7a5e250e9167a
3
  size 5240