Hugging Face's logo

nerottt
/
lc_v3

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
nerottt commited on
Commit
5f0f13a
•
1 Parent(s): ce4d8c5

End of training

Browse files
Files changed (4) hide show
  1. README.md +11 -8
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.2938
22
 
23
  ## Model description
24
 
@@ -43,18 +43,21 @@ The following hyperparameters were used during training:
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
- - num_epochs: 6
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 1.3462 | 1.0 | 90 | 1.3466 |
53
- | 1.2444 | 2.0 | 180 | 1.3130 |
54
- | 1.2703 | 3.0 | 270 | 1.2982 |
55
- | 1.3261 | 4.0 | 360 | 1.2945 |
56
- | 1.2466 | 5.0 | 450 | 1.2937 |
57
- | 1.323 | 6.0 | 540 | 1.2938 |
 
 
 
58
 
59
 
60
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.2901
22
 
23
  ## Model description
24
 
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
+ - num_epochs: 9
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.3446 | 1.0 | 90 | 1.3456 |
53
+ | 1.2406 | 2.0 | 180 | 1.3101 |
54
+ | 1.2645 | 3.0 | 270 | 1.2944 |
55
+ | 1.3111 | 4.0 | 360 | 1.2891 |
56
+ | 1.2212 | 5.0 | 450 | 1.2879 |
57
+ | 1.2865 | 6.0 | 540 | 1.2887 |
58
+ | 1.1752 | 7.0 | 630 | 1.2897 |
59
+ | 1.163 | 8.0 | 720 | 1.2901 |
60
+ | 1.2103 | 9.0 | 810 | 1.2901 |
61
 
62
 
63
  ### Framework versions
adapter_config.json CHANGED
@@ -22,8 +22,8 @@
22
  "target_modules": [
23
  "q_proj",
24
  "k_proj",
25
- "o_proj",
26
- "v_proj"
27
  ],
28
  "task_type": "CAUSAL_LM",
29
  "use_dora": false,
 
22
  "target_modules": [
23
  "q_proj",
24
  "k_proj",
25
+ "v_proj",
26
+ "o_proj"
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 sha256:72e82abcbbab9a2a7b918d85d29671ea2042611b8fed5782cbc9f52cda66a8f2
3
  size 109086672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9ed6795e19f1edb3f0551218124e7b8511879fedc7503c8a628b4786e43236c
3
  size 109086672
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce72917cac1a7e28de7f2c7a30e212b5a675ada850552ed5a9f206fc48a91448
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4b77db7f1b27540269648be8df596b0e830b2cbcfb44d5ac431607e330600a
3
  size 5432