Hugging Face's logo

Shivprasad17
/
mistral_instruct_generation

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Shivprasad17 commited on
Commit
f99c20c
•
1 Parent(s): a1d3015

Promptengineering/mistral-instruct-generation_updated

Browse files
Files changed (6) hide show
  1. README.md +11 -12
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +2 -2
  4. runs/Feb11_20-21-19_ab6695f28bb2/events.out.tfevents.1707682894.ab6695f28bb2.1842.0 +3 -0
  5. runs/Feb11_20-30-25_ab6695f28bb2/events.out.tfevents.1707683432.ab6695f28bb2.1842.1 +3 -0
  6. 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-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1519
24
 
25
  ## Model description
26
 
@@ -46,22 +46,21 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_steps: 0.03
49
- - training_steps: 200
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 1.1307 | 1.11 | 20 | 1.0842 |
56
- | 0.6826 | 2.22 | 40 | 0.6897 |
57
- | 0.4163 | 3.33 | 60 | 0.3940 |
58
- | 0.2125 | 4.44 | 80 | 0.2545 |
59
- | 0.1186 | 5.56 | 100 | 0.1905 |
60
- | 0.085 | 6.67 | 120 | 0.1641 |
61
- | 0.0693 | 7.78 | 140 | 0.1562 |
62
- | 0.0604 | 8.89 | 160 | 0.1516 |
63
- | 0.0516 | 10.0 | 180 | 0.1436 |
64
- | 0.044 | 11.11 | 200 | 0.1519 |
65
 
66
 
67
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.7713
24
 
25
  ## Model description
26
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_steps: 0.03
49
+ - training_steps: 180
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.7443 | 1.11 | 20 | 0.7713 |
56
+ | 0.7413 | 2.22 | 40 | 0.7713 |
57
+ | 0.7476 | 3.33 | 60 | 0.7713 |
58
+ | 0.753 | 4.44 | 80 | 0.7713 |
59
+ | 0.7514 | 5.56 | 100 | 0.7713 |
60
+ | 0.7383 | 6.67 | 120 | 0.7713 |
61
+ | 0.7434 | 7.78 | 140 | 0.7713 |
62
+ | 0.7497 | 8.89 | 160 | 0.7713 |
63
+ | 0.7644 | 10.0 | 180 | 0.7713 |
 
64
 
65
 
66
  ### Framework versions
adapter_config.json CHANGED
@@ -19,8 +19,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
- "v_proj"
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "v_proj",
23
+ "q_proj"
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7522f58b71980000b6dc878762ca1909d145175d4adbb5019ed870aa7c874856
3
- size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
3
+ size 48
runs/Feb11_20-21-19_ab6695f28bb2/events.out.tfevents.1707682894.ab6695f28bb2.1842.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feb065ac8b33f4a20333f322485a8da33904ac0ada7dc8235a5c75a40a22e24c
3
+ size 8001
runs/Feb11_20-30-25_ab6695f28bb2/events.out.tfevents.1707683432.ab6695f28bb2.1842.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae23d4086ae985c16acc64b667af40979657f845ab7e42ca86d201cbf9770be
3
+ size 10336
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:869689526706ca2d6ec02fc679c66aa0b1768a5077f1208ea0270d568579b091
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f621554be607a891ff3f8d52ab2b5608c0ac5dadb6bce7262c9d4952a0629489
3
  size 4728