Hugging Face's logo

robinsmits
/
Mistral-Instruct-7B-v0.2-ChatAlpacaV2

Text Generation
PEFT
TensorBoard
Safetensors
English
Generated from Trainer
unsloth
chatalpaca
mistral
conversational
Model card Files Metrics Community
robinsmits commited on
Commit
90b09af
•
1 Parent(s): d2e515b

End of training

Browse files
Files changed (3) hide show
  1. README.md +7 -13
  2. adapter_model.safetensors +1 -1
  3. runs/Feb11_15-29-18_DS10/events.out.tfevents.1707661759.DS10.684074.0 +2 -2
README.md CHANGED
@@ -2,7 +2,6 @@
2
  library_name: peft
3
  tags:
4
  - generated_from_trainer
5
- - unsloth
6
  base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
7
  model-index:
8
  - name: Mistral-Instruct-7B-v0.2-ChatAlpacaV2
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.8225
20
 
21
  ## Model description
22
 
@@ -44,22 +43,17 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_ratio: 0.05
47
- - num_epochs: 2
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | 0.8873 | 0.2 | 120 | 0.8803 |
54
- | 0.8507 | 0.39 | 240 | 0.8559 |
55
- | 0.8502 | 0.59 | 360 | 0.8462 |
56
- | 0.8275 | 0.78 | 480 | 0.8406 |
57
- | 0.8452 | 0.98 | 600 | 0.8299 |
58
- | 0.8296 | 1.18 | 720 | 0.8259 |
59
- | 0.8243 | 1.37 | 840 | 0.8242 |
60
- | 0.8133 | 1.57 | 960 | 0.8232 |
61
- | 0.8265 | 1.76 | 1080 | 0.8227 |
62
- | 0.8194 | 1.96 | 1200 | 0.8225 |
63
 
64
 
65
  ### Framework versions
 
2
  library_name: peft
3
  tags:
4
  - generated_from_trainer
 
5
  base_model: unsloth/mistral-7b-instruct-v0.2-bnb-4bit
6
  model-index:
7
  - name: Mistral-Instruct-7B-v0.2-ChatAlpacaV2
 
15
 
16
  This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2-bnb-4bit) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.8439
19
 
20
  ## Model description
21
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_ratio: 0.05
46
+ - num_epochs: 1
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 0.8801 | 0.2 | 120 | 0.8756 |
53
+ | 0.8498 | 0.39 | 240 | 0.8553 |
54
+ | 0.8515 | 0.59 | 360 | 0.8475 |
55
+ | 0.8313 | 0.78 | 480 | 0.8445 |
56
+ | 0.857 | 0.98 | 600 | 0.8439 |
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1825bf7e59f15457790daedb498e009e48b0a7fd310d3ec77ef0c979574a0a4f
3
  size 109086416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8667c5cd26654a97cf4eb14d65c636d9424c0d59d6c0f323be9aae34606e073a
3
  size 109086416
runs/Feb11_15-29-18_DS10/events.out.tfevents.1707661759.DS10.684074.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc8ea7d34f478d184aca9f8956a66ede70fb33d05a61fd1ecc71d520baf09790
3
- size 9406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a97969852f73e1a8dc0c228d6855acfdbb2eb4d92776b52ac48621d9419d956
3
+ size 9760