Hugging Face's logo

ishikaibm
/
gpt-neo-1.3B_peft_ft

PEFT
Safetensors
Generated from Trainer
Model card Files Community
ishikaibm commited on
Commit
3aef155
•
1 Parent(s): 87e6e5d

Model save

Browse files
Files changed (4) hide show
  1. README.md +7 -7
  2. adapter_1/adapter_config.json +2 -2
  3. adapter_1/adapter_model.safetensors +1 -1
  4. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 7.5890
22
- - Accuracy: 9215.8778
23
 
24
  ## Model description
25
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:----------:|
56
- | No log | 1.0 | 1 | 9.3613 | 12607.3874 |
57
- | No log | 2.0 | 2 | 8.7248 | 11916.9648 |
58
- | No log | 3.0 | 3 | 8.1933 | 8938.1332 |
59
- | No log | 4.0 | 4 | 7.7762 | 9565.8911 |
60
- | No log | 5.0 | 5 | 7.5890 | 9215.8778 |
61
 
62
 
63
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 7.5942
22
+ - Accuracy: 9630.1814
23
 
24
  ## Model description
25
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:----------:|
56
+ | No log | 1.0 | 1 | 9.3535 | 12436.1706 |
57
+ | No log | 2.0 | 2 | 8.6990 | 13080.6173 |
58
+ | No log | 3.0 | 3 | 8.1906 | 9042.9082 |
59
+ | No log | 4.0 | 4 | 7.7776 | 9702.7354 |
60
+ | No log | 5.0 | 5 | 7.5942 | 9630.1814 |
61
 
62
 
63
  ### Framework versions
adapter_1/adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "query",
24
- "value"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "value",
24
+ "query"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
adapter_1/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8911ccd724633ac39e7fdc93d4b10468c592b6ac8217fe7a5c0a05e9ed8771ad
3
  size 9443984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2425d51e367a5b60e73de4f9eff623bec57eda572f1603fde061879271b2f6
3
  size 9443984
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fac978dbee6fa35c91b32dcb50e058c70d9e4fa7bacc2cd7f773bd75e4cda5e2
3
  size 9443984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d390646e378d794d3d66210ee8c07d805347b63c65806c7f7079bc6ee17685ff
3
  size 9443984