Hugging Face's logo

sezing
/
mistral_instruct_generation_tr

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
sezing commited on
Commit
03f16df
•
1 Parent(s): e083ca0

mistralai/mistral-instruct-generation_tr

Browse files
Files changed (4) hide show
  1. README.md +11 -11
  2. adapter_model.safetensors +1 -1
  3. runs/Jun04_06-09-57_fa8cd0496e5c/events.out.tfevents.1717481409.fa8cd0496e5c.1084.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [malhajar/Mistral-7B-Instruct-v0.2-turkish](https://huggingface.co/malhajar/Mistral-7B-Instruct-v0.2-turkish) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0179
24
 
25
  ## Model description
26
 
@@ -40,7 +40,7 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0002
43
- - train_batch_size: 4
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -51,19 +51,19 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss |
55
- |:-------------:|:------:|:----:|:---------------:|
56
- | 0.3552 | 0.2740 | 20 | 0.1361 |
57
- | 0.036 | 0.5479 | 40 | 0.0302 |
58
- | 0.022 | 0.8219 | 60 | 0.0218 |
59
- | 0.019 | 1.0959 | 80 | 0.0192 |
60
- | 0.017 | 1.3699 | 100 | 0.0179 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - PEFT 0.11.1
66
- - Transformers 4.41.1
67
  - Pytorch 2.3.0+cu121
68
- - Datasets 2.19.1
69
  - Tokenizers 0.19.1
 
20
 
21
  This model is a fine-tuned version of [malhajar/Mistral-7B-Instruct-v0.2-turkish](https://huggingface.co/malhajar/Mistral-7B-Instruct-v0.2-turkish) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0029
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 0.0002
43
+ - train_batch_size: 2
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:-------:|:----:|:---------------:|
56
+ | 0.2758 | 6.6667 | 20 | 0.0672 |
57
+ | 0.0115 | 13.3333 | 40 | 0.0068 |
58
+ | 0.0044 | 20.0 | 60 | 0.0036 |
59
+ | 0.0032 | 26.6667 | 80 | 0.0032 |
60
+ | 0.0029 | 33.3333 | 100 | 0.0029 |
61
 
62
 
63
  ### Framework versions
64
 
65
  - PEFT 0.11.1
66
+ - Transformers 4.41.2
67
  - Pytorch 2.3.0+cu121
68
+ - Datasets 2.19.2
69
  - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb99b89bac657f60e7c22028f33b846c83afd6c1fa3f23ed10987379ef3381d1
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b579eb72b16fa77c7036f259c8c0fbfd14345e4efc9c8175e6cd2a41fb5240
3
  size 27280152
runs/Jun04_06-09-57_fa8cd0496e5c/events.out.tfevents.1717481409.fa8cd0496e5c.1084.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61942353a21a909b2ac7e624a2d0e53f98bc7e533928f0510a76753533742e93
3
+ size 9105
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:566628469a9183342e9ace373ba43e1b3b7e4767d7162a7c947ef60cd4404fa0
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4475dba96e0697c8e679b803e40c8293518ef1b4fd671c811a1a83473696e51
3
  size 5112