santis2 commited on
Commit
4f1b531
1 Parent(s): 57f47e6

End of training

Browse files
Files changed (4) hide show
  1. README.md +10 -10
  2. adapter_config.json +1 -1
  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 [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 1.6566
19
 
20
  ## Model description
21
 
@@ -47,15 +47,15 @@ The following hyperparameters were used during training:
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
- | 2.1138 | 0.11 | 1000 | 1.7761 |
51
- | 1.8565 | 0.22 | 2000 | 1.7291 |
52
- | 1.8133 | 0.33 | 3000 | 1.7039 |
53
- | 1.8198 | 0.44 | 4000 | 1.6900 |
54
- | 1.8024 | 0.55 | 5000 | 1.6771 |
55
- | 1.7781 | 0.66 | 6000 | 1.6691 |
56
- | 1.7742 | 0.77 | 7000 | 1.6626 |
57
- | 1.7517 | 0.88 | 8000 | 1.6577 |
58
- | 1.7566 | 0.99 | 9000 | 1.6566 |
59
 
60
 
61
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 1.6981
19
 
20
  ## Model description
21
 
 
47
 
48
  | Training Loss | Epoch | Step | Validation Loss |
49
  |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.118 | 0.11 | 1000 | 1.7807 |
51
+ | 1.8878 | 0.22 | 2000 | 1.7477 |
52
+ | 1.8609 | 0.33 | 3000 | 1.7318 |
53
+ | 1.8489 | 0.44 | 4000 | 1.7207 |
54
+ | 1.8416 | 0.55 | 5000 | 1.7134 |
55
+ | 1.8181 | 0.66 | 6000 | 1.7082 |
56
+ | 1.8144 | 0.77 | 7000 | 1.7021 |
57
+ | 1.816 | 0.88 | 8000 | 1.6987 |
58
+ | 1.7825 | 0.99 | 9000 | 1.6981 |
59
 
60
 
61
  ### Framework versions
adapter_config.json CHANGED
@@ -11,7 +11,7 @@
11
  "lora_dropout": 0.05,
12
  "modules_to_save": null,
13
  "peft_type": "LORA",
14
- "r": 16,
15
  "revision": null,
16
  "target_modules": [
17
  "c_attn",
 
11
  "lora_dropout": 0.05,
12
  "modules_to_save": null,
13
  "peft_type": "LORA",
14
+ "r": 2,
15
  "revision": null,
16
  "target_modules": [
17
  "c_attn",
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9f352df4e69658cd91e6c60af2576a5dc8b84064ffc61851b0704d78f84f2d8
3
- size 6513289
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d0f208eb91a5401bc33aea3bf3acacdd75f0a6f12af7c7b26a1c75f0798b97
3
+ size 836233
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60a43c9a70949f8b830037486d91e5e77ccaa62aaedc01ce811aff505e38a6d9
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa37a1b2633f76e2d008cd2e07f89b0c7672d79bf41e03d5e7d9f8cb3b7a9e0d
3
  size 4091