Hugging Face's logo

vincentyandex
/
ft-output

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
vincentyandex commited on
Commit
6c6ae2c
·
verified ·
1 Parent(s): af37625

vincentyandex/ch-to-en-novel-ft

Browse files
Files changed (5) hide show
  1. README.md +6 -13
  2. adapter_model.safetensors +1 -1
  3. runs/Mar14_05-59-30_16e9007ae1d4/events.out.tfevents.1710395975.16e9007ae1d4.1252.0 +3 -0
  4. runs/Mar14_07-04-08_16e9007ae1d4/events.out.tfevents.1710399854.16e9007ae1d4.1252.1 +3 -0
  5. 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 [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 2.0465
20
 
21
  ## Model description
22
 
@@ -44,29 +44,22 @@ 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
- - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 2.5009 | 0.99 | 25 | 2.3047 |
55
- | 2.2382 | 1.98 | 50 | 2.1932 |
56
- | 2.1235 | 2.97 | 75 | 2.1300 |
57
- | 1.965 | 4.0 | 101 | 2.0837 |
58
- | 1.9833 | 4.99 | 126 | 2.0611 |
59
- | 1.9385 | 5.98 | 151 | 2.0519 |
60
- | 1.9041 | 6.97 | 176 | 2.0469 |
61
- | 1.8035 | 8.0 | 202 | 2.0451 |
62
- | 1.854 | 8.99 | 227 | 2.0466 |
63
- | 1.8044 | 9.9 | 250 | 2.0465 |
64
 
65
 
66
  ### Framework versions
67
 
68
  - PEFT 0.9.0
69
  - Transformers 4.38.2
70
- - Pytorch 2.1.0+cu121
71
  - Datasets 2.18.0
72
  - Tokenizers 0.15.2
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 2.1164
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
+ - num_epochs: 3
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 2.289 | 1.0 | 173 | 2.1528 |
55
+ | 2.0978 | 2.0 | 347 | 2.1227 |
56
+ | 2.0557 | 2.99 | 519 | 2.1164 |
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
60
 
61
  - PEFT 0.9.0
62
  - Transformers 4.38.2
63
+ - Pytorch 2.2.1+cu121
64
  - Datasets 2.18.0
65
  - Tokenizers 0.15.2
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ba2e880765eb3aced48881904368487f1b7944e9347c82b043eee61810eff24
3
  size 8397056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f51a3604e8ec609f8173adcc4ed49eb8fc3c582ccbad4144716cb5dd032bba39
3
  size 8397056
runs/Mar14_05-59-30_16e9007ae1d4/events.out.tfevents.1710395975.16e9007ae1d4.1252.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55cc81264e61aa4b16c433666f0a06ec583d89f1e6f2abc6d13962dd6b1ddd3
3
+ size 8096
runs/Mar14_07-04-08_16e9007ae1d4/events.out.tfevents.1710399854.16e9007ae1d4.1252.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb311af4f303534d47c306dcd9d35a8f0b1c554bfe62413d553072e896febf1
3
+ size 7003
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f5aad7708367565db140373b8559c2418c11f1b09fbcf6d73b8e196ebc969de
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81ad4cd6eb0e10b57b51edae3d751b05eb9f656da2134fddb052c063091bd66f
3
  size 4856