williamplacroix commited on
Commit
2ada86a
·
verified ·
1 Parent(s): ce55f27

Finished finetuning grade 9

Browse files
README.md CHANGED
@@ -12,18 +12,12 @@ model-index:
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
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/gd6mkxtp)
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/s2qn3a6p)
17
- [<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/qz6551rc)
18
- [<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/lm55kzij)
19
- [<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/nifhcrxt)
20
- [<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/ubay9iap)
21
- [<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/7pz1g9ob)
22
  # text-simplification
23
 
24
  This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.5622
27
 
28
  ## Model description
29
 
@@ -54,9 +48,11 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss |
56
  |:-------------:|:-----:|:----:|:---------------:|
57
- | 0.586 | 1.0 | 1326 | 0.5631 |
58
- | 0.581 | 2.0 | 2652 | 0.5587 |
59
- | 0.5778 | 3.0 | 3978 | 0.5622 |
 
 
60
 
61
 
62
  ### Framework versions
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
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/kh94yqwi)
 
 
 
 
 
 
16
  # text-simplification
17
 
18
  This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5755
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.6211 | 1.0 | 898 | 0.5805 |
52
+ | 0.6157 | 2.0 | 1796 | 0.5763 |
53
+ | 0.6128 | 3.0 | 2694 | 0.5742 |
54
+ | 0.6102 | 4.0 | 3592 | 0.5738 |
55
+ | 0.6073 | 5.0 | 4490 | 0.5755 |
56
 
57
 
58
  ### Framework versions
gpt2-grade-9-finetuned/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "openai-community/gpt2",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 32,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.01,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "c_fc",
27
+ "c_attn",
28
+ "c_proj",
29
+ "lm_head"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
gpt2-grade-9-finetuned/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545a6ff0337dc7ea7119011655e3cfe423fce8c0bc2db6acace57a30cc87feba
3
+ size 160776023
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82ea106a506088759161a7bb089e0c98736104247f2e47ddbf2a2725d5c67115
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d556b294403022e0ca243b0dbf1041d9e52799130066df32ede03fd5c34518a4
3
  size 5496