Hugging Face's logo

cnatale
/
Mistral-7B-Instruct-v0.1-Txt-2-Presto-SQL

PEFT
TensorBoard
Safetensors
mistral
trl
sft
Generated from Trainer
Model card Files Metrics Community
1
cnatale commited on
Commit
1adf9e6
·
1 Parent(s): b4fdf66

cnatale/Mistral-7B-Instruct-v0.1-Txt-2-Presto-SQL

Browse files
Files changed (4) hide show
  1. README.md +10 -8
  2. adapter_model.safetensors +1 -1
  3. runs/Jan03_14-00-56_4f0560a2c54d/events.out.tfevents.1704290457.4f0560a2c54d.546.0 +3 -0
  4. training_args.bin +2 -2
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: 1.1460
24
 
25
  ## Model description
26
 
@@ -46,19 +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: 360
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
- | 0.6522 | 4.29 | 60 | 0.6580 |
57
- | 0.4675 | 8.57 | 120 | 0.6740 |
58
- | 0.3553 | 12.86 | 180 | 0.7585 |
59
- | 0.2772 | 17.14 | 240 | 0.9292 |
60
- | 0.1834 | 21.43 | 300 | 0.9867 |
61
- | 0.1106 | 25.71 | 360 | 1.1460 |
 
 
62
 
63
 
64
  ### 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: 0.6471
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: 80
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:-----:|:----:|:---------------:|
56
+ | 1.3628 | 0.71 | 10 | 1.1096 |
57
+ | 1.0411 | 1.43 | 20 | 0.8938 |
58
+ | 0.8678 | 2.14 | 30 | 0.7808 |
59
+ | 0.7681 | 2.86 | 40 | 0.7271 |
60
+ | 0.7108 | 3.57 | 50 | 0.6852 |
61
+ | 0.6521 | 4.29 | 60 | 0.6573 |
62
+ | 0.618 | 5.0 | 70 | 0.6484 |
63
+ | 0.5824 | 5.71 | 80 | 0.6471 |
64
 
65
 
66
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d3aa3afe439448066a0c875491447f5ff08add2e4fe03befe06a51f1889301d
3
  size 109069176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe8691b1102078f937971822f5cc62eca6d3097db1654526406ee418899a7cf1
3
  size 109069176
runs/Jan03_14-00-56_4f0560a2c54d/events.out.tfevents.1704290457.4f0560a2c54d.546.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d610adc042c198f81dd48321274908b75faa30a2f4d4c190d19867ebba37e6
3
+ size 8532
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc0de5108669b4a832a1cffb7f7205c77efdaa907833f0028753d180b0d0ab78
3
- size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20b802012751011814220a7752f34eb25bf361f603f3335f89d9c39ad3052d41
3
+ size 4728