Hugging Face's logo

Anixyz
/
fine_tune_e2e

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Metrics Community
Anixyz commited on
Commit
04bd5c9
·
verified ·
1 Parent(s): 6d765c2

End of training

Browse files
Files changed (5) hide show
  1. README.md +4 -9
  2. adapter_model.safetensors +1 -1
  3. runs/Oct07_08-24-29_7cb473712ebb/events.out.tfevents.1759825483.7cb473712ebb.8026.0 +3 -0
  4. runs/Oct07_08-33-19_7cb473712ebb/events.out.tfevents.1759826001.7cb473712ebb.8026.1 +3 -0
  5. 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 [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.3306
24
 
25
  ## Model description
26
 
@@ -39,7 +39,7 @@ More information needed
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
- - learning_rate: 0.0005
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
@@ -51,12 +51,7 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 1.4488 | 0.3333 | 10 | 1.3641 |
55
- | 1.3617 | 0.6667 | 20 | 1.3351 |
56
- | 1.2343 | 1.0 | 30 | 1.3294 |
57
- | 1.2651 | 1.3333 | 40 | 1.3317 |
58
- | 1.1214 | 1.6667 | 50 | 1.3311 |
59
- | 1.1861 | 2.0 | 60 | 1.3306 |
60
 
61
 
62
  ### Framework versions
@@ -64,5 +59,5 @@ The following hyperparameters were used during training:
64
  - PEFT 0.11.1
65
  - Transformers 4.40.1
66
  - Pytorch 2.3.1+cu121
67
- - Datasets 4.0.0
68
  - Tokenizers 0.19.1
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.2867
24
 
25
  ## Model description
26
 
 
39
  ### Training hyperparameters
40
 
41
  The following hyperparameters were used during training:
42
+ - learning_rate: 2e-05
43
  - train_batch_size: 8
44
  - eval_batch_size: 8
45
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.3323 | 1.8519 | 200 | 1.2867 |
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
 
59
  - PEFT 0.11.1
60
  - Transformers 4.40.1
61
  - Pytorch 2.3.1+cu121
62
+ - Datasets 4.1.1
63
  - Tokenizers 0.19.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42826e48bf001b2293f2c5c72981e86ba008602cf4571a1419762bfaa445406d
3
  size 13648432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131e9879d6649fa607d512256e9a8d6ca401da1dabf00eb0e82c50fda0a56296
3
  size 13648432
runs/Oct07_08-24-29_7cb473712ebb/events.out.tfevents.1759825483.7cb473712ebb.8026.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b1213480b27cd038916ca4df19746f3dbfd9841ef052fe7e3f4bc70d01e8a60
3
+ size 5433
runs/Oct07_08-33-19_7cb473712ebb/events.out.tfevents.1759826001.7cb473712ebb.8026.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06fe415713b9fda84c30a68c43b2c420b6de90ce8b64a1adb3ab51cd59dfdfa1
3
+ size 6269
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6f5ca2da79a90712e6af5e470e79f62bab71f9101fce7e065c6734966efd395
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57960b4403e8409c0e89eb7cc0577ce4b7cf0841edeb44ee2b5fa7b9a44a91e
3
  size 5240