Hugging Face's logo

jd0g
/
mistral-7b-nli_cot

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
jd0g commited on
Commit
4344510
·
verified ·
1 Parent(s): 83b6d56

jd0g/Mistral-7B-NLI-v0.1

Browse files
Files changed (6) hide show
  1. README.md +14 -7
  2. adapter_model.safetensors +1 -1
  3. runs/Apr25_13-03-59_8ce629014f90/events.out.tfevents.1714050239.8ce629014f90.284.0 +3 -0
  4. runs/Apr25_13-04-30_8ce629014f90/events.out.tfevents.1714050271.8ce629014f90.284.1 +3 -0
  5. runs/Apr25_13-05-49_8ce629014f90/events.out.tfevents.1714050349.8ce629014f90.3864.0 +3 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3549
20
 
21
  ## Model description
22
 
@@ -44,16 +44,23 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
- - num_epochs: 3
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:-----:|:----:|:---------------:|
54
- | 0.7334 | 0.992 | 31 | 0.3914 |
55
- | 0.3755 | 1.984 | 62 | 0.3592 |
56
- | 0.348 | 2.976 | 93 | 0.3549 |
 
 
 
 
 
 
 
57
 
58
 
59
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-v0.1-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-v0.1-GPTQ) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6735
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
+ - num_epochs: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.8799 | 0.9231 | 3 | 1.6354 |
55
+ | 1.6206 | 1.8462 | 6 | 1.3630 |
56
+ | 1.3224 | 2.7692 | 9 | 1.1313 |
57
+ | 0.8177 | 4.0 | 13 | 0.9223 |
58
+ | 0.9144 | 4.9231 | 16 | 0.8115 |
59
+ | 0.801 | 5.8462 | 19 | 0.7444 |
60
+ | 0.7393 | 6.7692 | 22 | 0.7097 |
61
+ | 0.5279 | 8.0 | 26 | 0.6836 |
62
+ | 0.6872 | 8.9231 | 29 | 0.6745 |
63
+ | 0.4589 | 9.2308 | 30 | 0.6735 |
64
 
65
 
66
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60bcd217837893d8bc57b929d3816e0d2ce1552f7dc581097bd9c7f2b9e833e8
3
  size 4203824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:186a8f496eea24fe331caa52f969f5ce4ee60952d14104dc3c4e38fbb66e5026
3
  size 4203824
runs/Apr25_13-03-59_8ce629014f90/events.out.tfevents.1714050239.8ce629014f90.284.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:729fb2458cb87f4d0c1251e3a75ca1dacc79e36fe3fb37258b7376f43aec97d1
3
+ size 5330
runs/Apr25_13-04-30_8ce629014f90/events.out.tfevents.1714050271.8ce629014f90.284.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56b50b400d5366d38d61dde62a2fa8b41025d47baf3db01ab2c85147878c8e0
3
+ size 5330
runs/Apr25_13-05-49_8ce629014f90/events.out.tfevents.1714050349.8ce629014f90.3864.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbf8abfdf2669a2cab51716cb761fd992dfe5e837a52353757d3f7c1c5e7d47
3
+ size 10408
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de351c59c2e0a2e4cdcf07e7ba361eb5e866e4c5848eb10e3e5be204d4502329
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccb48c341715f03da45d6376940a73d2f4b4ac536ed63d81b2b56365c52b7f6
3
  size 4984