Hugging Face's logo

deb101
/
mistral-7b-instruct-v0.3-mimic4-adapt-l2r

Transformers
Safetensors
ltr_model
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files
xet
Community
deb101 commited on
Commit
f4efc04
·
verified ·
1 Parent(s): 636d866

Model save

Browse files
Files changed (6) hide show
  1. README.md +8 -7
  2. eval_loss_plot.png +0 -0
  3. eval_ndcg@25_plot.png +0 -0
  4. model.safetensors +1 -1
  5. train_loss_plot.png +0 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: -240602318374661568.0000
20
- - Ndcg: 0.9563
21
- - Ndcg@25: 0.4422
22
- - Precision@25: 0.2214
23
 
24
  ## Model description
25
 
@@ -46,15 +46,16 @@ The following hyperparameters were used during training:
46
  - total_train_batch_size: 4
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
- - num_epochs: 2
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Ndcg | Ndcg@25 | Precision@25 |
55
  |:-------------------------:|:------:|:----:|:------------------------:|:------:|:-------:|:------------:|
56
- | -2330796205703744512.0000 | 1.0 | 44 | -92728505831320080.0000 | 0.9556 | 0.2014 | 0.0400 |
57
- | -98429772131152688.0000 | 1.9711 | 86 | -240602318374661568.0000 | 0.9563 | 0.4422 | 0.2214 |
 
58
 
59
 
60
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: -411510899264896576.0000
20
+ - Ndcg: 0.9569
21
+ - Ndcg@25: 0.7163
22
+ - Precision@25: 0.6126
23
 
24
  ## Model description
25
 
 
46
  - total_train_batch_size: 4
47
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
  - lr_scheduler_type: linear
49
+ - num_epochs: 3
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Ndcg | Ndcg@25 | Precision@25 |
55
  |:-------------------------:|:------:|:----:|:------------------------:|:------:|:-------:|:------------:|
56
+ | -6865760941572830208.0000 | 1.0 | 44 | -240602318374661568.0000 | 0.9563 | 0.4422 | 0.2214 |
57
+ | -170364640055577792.0000 | 2.0 | 88 | -380035817867927296.0000 | 0.9569 | 0.7741 | 0.4871 |
58
+ | -458167182489026560.0000 | 2.9480 | 129 | -411510899264896576.0000 | 0.9569 | 0.7163 | 0.6126 |
59
 
60
 
61
  ### Framework versions
eval_loss_plot.png CHANGED
eval_ndcg@25_plot.png CHANGED
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd5f989c75988e88730d7c9804f1edf50eeb897b1ac5ae913d3e539f87b5beae
3
  size 4323010659
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fbcd969a528ea265d3e0a119126666d4f717cfde9636af938da134a6727a9af
3
  size 4323010659
train_loss_plot.png CHANGED
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b213befbacaa13807e9aba070c28ef3a2e97ec3351f16dc389ae217c7e65988
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb1b273cb582204832674f0fee4f24a66a0b801c988df06f1588d1c029ed3879
3
  size 5905