Hugging Face's logo

deboramachadoandrade
/
mistral7binstruct_summarize

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
deboramachadoandrade commited on
Commit
dbbcfc9
•
1 Parent(s): a94c8cc

ai-maker-space/mistral-7binstruct-summary-100s

Browse files
Files changed (5) hide show
  1. README.md +10 -10
  2. adapter_model.safetensors +1 -1
  3. runs/Mar04_16-47-38_acaf5e89fb3f/events.out.tfevents.1709570859.acaf5e89fb3f.2701.1 +3 -0
  4. runs/Mar04_16-51-01_acaf5e89fb3f/events.out.tfevents.1709571063.acaf5e89fb3f.2701.2 +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-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 1.4442
24
 
25
  ## Model description
26
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
- - lr_scheduler_type: cosine
48
  - lr_scheduler_warmup_steps: 3
49
  - training_steps: 200
50
 
@@ -52,14 +52,14 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 1.7037 | 0.22 | 25 | 1.5738 |
56
- | 1.5952 | 0.43 | 50 | 1.4712 |
57
- | 1.5767 | 0.65 | 75 | 1.4572 |
58
- | 1.5413 | 0.86 | 100 | 1.4535 |
59
- | 1.5256 | 1.08 | 125 | 1.4473 |
60
- | 1.4647 | 1.29 | 150 | 1.4462 |
61
- | 1.5195 | 1.51 | 175 | 1.4444 |
62
- | 1.464 | 1.72 | 200 | 1.4442 |
63
 
64
 
65
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 1.5218
24
 
25
  ## Model description
26
 
 
44
  - eval_batch_size: 8
45
  - seed: 42
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: constant
48
  - lr_scheduler_warmup_steps: 3
49
  - training_steps: 200
50
 
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 1.6377 | 0.03 | 25 | 1.6268 |
56
+ | 1.5147 | 0.05 | 50 | 1.5521 |
57
+ | 1.5779 | 0.08 | 75 | 1.5416 |
58
+ | 1.548 | 0.11 | 100 | 1.5338 |
59
+ | 1.421 | 0.13 | 125 | 1.5284 |
60
+ | 1.6 | 0.16 | 150 | 1.5293 |
61
+ | 1.5307 | 0.19 | 175 | 1.5227 |
62
+ | 1.5756 | 0.22 | 200 | 1.5218 |
63
 
64
 
65
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:747dc31a276108f926759d4b7df3f83059f147bffe14c5e2a1cb97214e5ab02f
3
  size 27280152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29e17b2db8445543580835558234c6d73f0409d70794ec7dab921d457811ec97
3
  size 27280152
runs/Mar04_16-47-38_acaf5e89fb3f/events.out.tfevents.1709570859.acaf5e89fb3f.2701.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e634b645b865a43dabb0110e26755be3db6ef06434d981fe8e6280a79e9a45ba
3
+ size 5934
runs/Mar04_16-51-01_acaf5e89fb3f/events.out.tfevents.1709571063.acaf5e89fb3f.2701.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a022b88d20781197eaf563d9a057b308d3734bd4908798828682cb539b6ff6f0
3
+ size 11718
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48aa11c2f77e971eaef61863583c088a558ab7455f0f07001507bdadef4cbb3e
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a57a09de3077eef9d5d6cef2417955d822dd73ae37f93d4184279479d27dcbd
3
  size 4920