trungvo commited on
Commit
a99879f
1 Parent(s): b1cd957

End of training

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -1,11 +1,11 @@
1
  ---
2
- license: apache-2.0
3
  library_name: peft
 
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
- base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
9
  model-index:
10
  - name: Mixtral-8x7B-Instruct-v0.1-finetuned-PubMedQA
11
  results: []
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
- - training_steps: 5000
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
51
  ### Framework versions
52
 
53
  - PEFT 0.11.1
54
- - Transformers 4.41.1
55
  - Pytorch 2.3.0+cu121
56
  - Datasets 2.19.1
57
  - Tokenizers 0.19.1
 
1
  ---
2
+ base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
3
  library_name: peft
4
+ license: apache-2.0
5
  tags:
6
  - trl
7
  - sft
8
  - generated_from_trainer
 
9
  model-index:
10
  - name: Mixtral-8x7B-Instruct-v0.1-finetuned-PubMedQA
11
  results: []
 
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
+ - num_epochs: 8
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
 
51
  ### Framework versions
52
 
53
  - PEFT 0.11.1
54
+ - Transformers 4.42.3
55
  - Pytorch 2.3.0+cu121
56
  - Datasets 2.19.1
57
  - Tokenizers 0.19.1