Hugging Face's logo

irenewds
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
Metrics Community
irenewds commited on
Commit
e564cce
·
verified ·
1 Parent(s): b5c8565

irenewds/shawgpt-ft

Browse files
Files changed (6) hide show
  1. README.md +17 -16
  2. runs/Oct24_19-57-58_1f4e1c060daf/events.out.tfevents.1729799881.1f4e1c060daf.20197.3 +2 -2
  3. runs/Oct24_20-04-57_1f4e1c060daf/events.out.tfevents.1729800298.1f4e1c060daf.27105.0 +3 -0
  4. runs/Oct24_20-05-56_1f4e1c060daf/events.out.tfevents.1729800359.1f4e1c060daf.27105.1 +3 -0
  5. runs/Oct24_20-10-11_1f4e1c060daf/events.out.tfevents.1729800612.1f4e1c060daf.28754.0 +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-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: 1.4702
20
 
21
  ## Model description
22
 
@@ -44,27 +44,28 @@ 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: 15
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 4.6066 | 0.9231 | 3 | 4.0380 |
55
- | 4.1814 | 1.8462 | 6 | 3.6234 |
56
- | 3.6918 | 2.7692 | 9 | 3.2210 |
57
- | 2.4376 | 4.0 | 13 | 2.7762 |
58
- | 2.9041 | 4.9231 | 16 | 2.5057 |
59
- | 2.567 | 5.8462 | 19 | 2.2873 |
60
- | 2.2697 | 6.7692 | 22 | 2.0482 |
61
- | 1.5183 | 8.0 | 26 | 1.8319 |
62
- | 1.8501 | 8.9231 | 29 | 1.7312 |
63
- | 1.7079 | 9.8462 | 32 | 1.6417 |
64
- | 1.6319 | 10.7692 | 35 | 1.5687 |
65
- | 1.1374 | 12.0 | 39 | 1.5067 |
66
- | 1.493 | 12.9231 | 42 | 1.4801 |
67
- | 1.2311 | 13.8462 | 45 | 1.4702 |
 
68
 
69
 
70
  ### 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: 1.4187
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: 16
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.6052 | 0.9231 | 3 | 4.0324 |
55
+ | 4.1734 | 1.8462 | 6 | 3.6130 |
56
+ | 3.6811 | 2.7692 | 9 | 3.2101 |
57
+ | 2.429 | 4.0 | 13 | 2.7565 |
58
+ | 2.8731 | 4.9231 | 16 | 2.4814 |
59
+ | 2.5127 | 5.8462 | 19 | 2.2241 |
60
+ | 2.2188 | 6.7692 | 22 | 2.0188 |
61
+ | 1.4844 | 8.0 | 26 | 1.7915 |
62
+ | 1.7939 | 8.9231 | 29 | 1.6741 |
63
+ | 1.6437 | 9.8462 | 32 | 1.5920 |
64
+ | 1.5781 | 10.7692 | 35 | 1.5269 |
65
+ | 1.1047 | 12.0 | 39 | 1.4688 |
66
+ | 1.4528 | 12.9231 | 42 | 1.4402 |
67
+ | 1.3984 | 13.8462 | 45 | 1.4243 |
68
+ | 1.0591 | 14.7692 | 48 | 1.4187 |
69
 
70
 
71
  ### Framework versions
runs/Oct24_19-57-58_1f4e1c060daf/events.out.tfevents.1729799881.1f4e1c060daf.20197.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c390cc7d873f51a24e93f1bae524bedf1e10ae40f5479f41e8a054a0601314f
3
- size 4184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d58e3d3fb9939c9a9f3e20e4d71141d9a7f19f27b86766fb2bbab0136bea10c
3
+ size 5583
runs/Oct24_20-04-57_1f4e1c060daf/events.out.tfevents.1729800298.1f4e1c060daf.27105.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36982f6704d9b5322c3d32af12b939c923eca4491a345cafa626532fb1d0a85c
3
+ size 5790
runs/Oct24_20-05-56_1f4e1c060daf/events.out.tfevents.1729800359.1f4e1c060daf.27105.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7286857e63681665e4f949b6a9fbe8df7a2589826618a1a978fac7fcb940e553
3
+ size 6056
runs/Oct24_20-10-11_1f4e1c060daf/events.out.tfevents.1729800612.1f4e1c060daf.28754.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dffc2d30a4ff7c3bb390e9a8ac97a575eb072092c907fdc2f69b3a4678a0293
3
+ size 13026
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e21c1964116ccc6f0282deda805e64a933e7c77472bd3593bd8b1399a0f911ee
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5714a42d2cf70813f049beecb9fafe25fb0ee6d41bffc02e440edf728fc52f4e
3
  size 5176