Hugging Face's logo

FrederikKlinkby
/
shawgpt-ft-rank15

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
FrederikKlinkby commited on
Commit
a913600
·
verified ·
1 Parent(s): cd5fedd

shawgpt-ft-rank15

Browse files
Files changed (3) hide show
  1. README.md +16 -14
  2. runs/Oct22_09-18-40_99867d27916d/events.out.tfevents.1729588721.99867d27916d.882.21 +3 -0
  3. 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-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.4008
20
 
21
  ## Model description
22
 
@@ -44,23 +44,25 @@ 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: 10
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:----:|:---------------:|
54
- | 1.1392 | 0.9231 | 3 | 1.3117 |
55
- | 1.0798 | 1.8462 | 6 | 1.3205 |
56
- | 1.0056 | 2.7692 | 9 | 1.3275 |
57
- | 0.7115 | 4.0 | 13 | 1.3498 |
58
- | 0.9418 | 4.9231 | 16 | 1.3680 |
59
- | 0.8846 | 5.8462 | 19 | 1.3849 |
60
- | 0.8429 | 6.7692 | 22 | 1.3786 |
61
- | 0.6394 | 8.0 | 26 | 1.4015 |
62
- | 0.839 | 8.9231 | 29 | 1.4010 |
63
- | 0.6082 | 9.2308 | 30 | 1.4008 |
 
 
64
 
65
 
66
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.5116
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: 12
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 1.0283 | 0.9231 | 3 | 1.3097 |
55
+ | 0.9868 | 1.8462 | 6 | 1.3728 |
56
+ | 0.9174 | 2.7692 | 9 | 1.3527 |
57
+ | 0.6429 | 4.0 | 13 | 1.4026 |
58
+ | 0.8442 | 4.9231 | 16 | 1.4004 |
59
+ | 0.7766 | 5.8462 | 19 | 1.4248 |
60
+ | 0.7289 | 6.7692 | 22 | 1.4474 |
61
+ | 0.543 | 8.0 | 26 | 1.4707 |
62
+ | 0.6976 | 8.9231 | 29 | 1.4967 |
63
+ | 0.6682 | 9.8462 | 32 | 1.5151 |
64
+ | 0.6726 | 10.7692 | 35 | 1.5118 |
65
+ | 0.1014 | 11.0769 | 36 | 1.5116 |
66
 
67
 
68
  ### Framework versions
runs/Oct22_09-18-40_99867d27916d/events.out.tfevents.1729588721.99867d27916d.882.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6ad582d499d90bb028ec4db5a7fc11c410df478ecf7b097d4729519d5ab2eb2
3
+ size 11627
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a55f68d288cfb970f0820ce3e2e26fdf6a5f0779e3f2b13c40d535bd3ee541bf
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdf0306eb9bfdf4a008770af7e841234ee4c6f463c0686303c05e7e1f62aaebe
3
  size 5176