Hugging Face's logo

sv469
/
final-checkpoint

PEFT
Safetensors
Generated from Trainer
Model card Files Community
sv469 commited on
Commit
ea025c4
•
1 Parent(s): 59d15df

sv469/phi-2_finetuned

Browse files
Files changed (4) hide show
  1. README.md +9 -13
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3177
20
 
21
  ## Model description
22
 
@@ -44,28 +44,24 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
- - training_steps: 500
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-------:|:----:|:---------------:|
53
- | 1.2127 | 2.5641 | 50 | 0.5753 |
54
- | 0.5175 | 5.1282 | 100 | 0.4192 |
55
- | 0.3604 | 7.6923 | 150 | 0.3369 |
56
- | 0.2555 | 10.2564 | 200 | 0.3104 |
57
- | 0.1953 | 12.8205 | 250 | 0.3153 |
58
- | 0.1453 | 15.3846 | 300 | 0.3106 |
59
- | 0.1237 | 17.9487 | 350 | 0.3059 |
60
- | 0.0965 | 20.5128 | 400 | 0.3080 |
61
- | 0.0842 | 23.0769 | 450 | 0.3207 |
62
- | 0.0751 | 25.6410 | 500 | 0.3177 |
63
 
64
 
65
  ### Framework versions
66
 
67
  - PEFT 0.11.1
68
- - Transformers 4.42.3
69
  - Pytorch 2.1.2
70
  - Datasets 2.20.0
71
  - Tokenizers 0.19.1
 
16
 
17
  This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.1627
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
+ - training_steps: 300
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-------:|:----:|:---------------:|
53
+ | 0.92 | 4.6512 | 50 | 0.3772 |
54
+ | 0.2534 | 9.3023 | 100 | 0.2253 |
55
+ | 0.1327 | 13.9535 | 150 | 0.1858 |
56
+ | 0.0795 | 18.6047 | 200 | 0.1676 |
57
+ | 0.0601 | 23.2558 | 250 | 0.1641 |
58
+ | 0.0483 | 27.9070 | 300 | 0.1627 |
 
 
 
 
59
 
60
 
61
  ### Framework versions
62
 
63
  - PEFT 0.11.1
64
+ - Transformers 4.42.4
65
  - Pytorch 2.1.2
66
  - Datasets 2.20.0
67
  - Tokenizers 0.19.1
adapter_config.json CHANGED
@@ -20,10 +20,10 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
  "q_proj",
25
- "dense",
26
- "k_proj"
 
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "q_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "dense"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a34793be02fbd4f2282497a6888db4174dbfeaa36ed557e84eafb2b155ac02cf
3
  size 83920464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87917607e271e584fc3b86415fdfd0cab6ace7f7d2be189e9eb9f91ddf1967f0
3
  size 83920464
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c464dbc10d45536d440e8620e6d50fe8f5f796add6364694cef349c0e3c281d
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99b3219f11780e86b2f5401e3c4473722529a744a068013da9406cb4ef7d065
3
  size 5112