Hugging Face's logo

richychn
/
uplimit-project-3-phi-1.5

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
richychn commited on
Commit
60175c6
•
1 Parent(s): 56cadf8

End of training

Browse files
Files changed (8) hide show
  1. README.md +10 -10
  2. adapter_config.json +2 -2
  3. adapter_model.bin +2 -2
  4. adapter_model.safetensors +2 -2
  5. runs/Nov04_22-39-20_3e84e73cd1f0/events.out.tfevents.1699137584.3e84e73cd1f0.14417.0 +3 -0
  6. runs/Nov04_22-50-37_3e84e73cd1f0/events.out.tfevents.1699138240.3e84e73cd1f0.14417.1 +3 -0
  7. tokenizer.json +1 -6
  8. training_args.bin +1 -1
README.md CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the scitldr dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 2.6008
21
 
22
  ## Model description
23
 
@@ -48,15 +48,15 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 2.5528 | 0.1 | 200 | 2.6505 |
52
- | 2.5753 | 0.2 | 400 | 2.6454 |
53
- | 2.5339 | 0.3 | 600 | 2.6385 |
54
- | 2.587 | 0.4 | 800 | 2.6245 |
55
- | 2.5421 | 0.5 | 1000 | 2.6231 |
56
- | 2.5775 | 0.6 | 1200 | 2.6156 |
57
- | 2.5478 | 0.7 | 1400 | 2.6096 |
58
- | 2.5278 | 0.8 | 1600 | 2.6047 |
59
- | 2.5759 | 0.9 | 1800 | 2.6008 |
60
 
61
 
62
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the scitldr dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 2.6005
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 2.5714 | 0.1 | 200 | 2.6784 |
52
+ | 2.5921 | 0.2 | 400 | 2.6719 |
53
+ | 2.5493 | 0.3 | 600 | 2.6583 |
54
+ | 2.602 | 0.4 | 800 | 2.6390 |
55
+ | 2.5574 | 0.5 | 1000 | 2.6373 |
56
+ | 2.5859 | 0.6 | 1200 | 2.6265 |
57
+ | 2.552 | 0.7 | 1400 | 2.6172 |
58
+ | 2.5306 | 0.8 | 1600 | 2.6099 |
59
+ | 2.5827 | 0.9 | 1800 | 2.6005 |
60
 
61
 
62
  ### Framework versions
adapter_config.json CHANGED
@@ -8,11 +8,11 @@
8
  "init_lora_weights": true,
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
- "lora_alpha": 16,
12
  "lora_dropout": 0.05,
13
  "modules_to_save": null,
14
  "peft_type": "LORA",
15
- "r": 8,
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
8
  "init_lora_weights": true,
9
  "layers_pattern": null,
10
  "layers_to_transform": null,
11
+ "lora_alpha": 32,
12
  "lora_dropout": 0.05,
13
  "modules_to_save": null,
14
  "peft_type": "LORA",
15
+ "r": 16,
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b24a5d5cfa96ef70f2f73203c2776201934d151eabc056a03ffd1f7c82ec1838
3
- size 6308286
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526069d6801c5beaf27f157493f6e01cee94ac32615669415ffc6956d03c057e
3
+ size 12599806
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9447960bdcf9a89f859cb32b4579dc387699a4fee4f4c9884a4578b8d4c0b408
3
- size 6297216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef3ec3f30e9d9b500ad2ea7335e917c1f098aa0d652d803a3d36eb61beb9f77
3
+ size 12588752
runs/Nov04_22-39-20_3e84e73cd1f0/events.out.tfevents.1699137584.3e84e73cd1f0.14417.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea43b0f3a988d9a11fd7065499f1f07a6fe66f70c52fbf314ff8356d8774a61
3
+ size 6223
runs/Nov04_22-50-37_3e84e73cd1f0/events.out.tfevents.1699138240.3e84e73cd1f0.14417.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d53e012fc96978f33ba2f3c486bf4a542bded983026598bfe339e6f17c25b9f
3
+ size 13341
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eb4b89f4fb3a2fe0515074bfa11ffd53a3915b2cf98629cd786978daed2b592
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69eac68f90d9ff24f28e26e0aa5e233f559abc076ee8cf115802a3bf058799d
3
  size 4600