Hugging Face's logo

saumitras01
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
saumitras01 commited on
Commit
238a26d
•
1 Parent(s): 883678d

saumitras01/shawgpt-ft

Browse files
Files changed (9) hide show
  1. README.md +13 -14
  2. runs/Mar06_12-53-42_instance-20240306-123153/events.out.tfevents.1709729622.instance-20240306-123153 +3 -0
  3. runs/Mar06_13-33-49_instance-20240306-123153/events.out.tfevents.1709732029.instance-20240306-123153 +3 -0
  4. runs/Mar06_13-35-48_instance-20240306-123153/events.out.tfevents.1709732148.instance-20240306-123153 +3 -0
  5. runs/Mar06_13-41-15_instance-20240306-123153/events.out.tfevents.1709732475.instance-20240306-123153 +3 -0
  6. runs/Mar06_14-20-08_instance-20240306-123153/events.out.tfevents.1709734808.instance-20240306-123153 +3 -0
  7. runs/Mar06_14-21-10_instance-20240306-123153/events.out.tfevents.1709734870.instance-20240306-123153 +3 -0
  8. runs/Mar06_14-24-03_instance-20240306-123153/events.out.tfevents.1709735044.instance-20240306-123153 +3 -0
  9. 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: 1.8899
20
 
21
  ## Model description
22
 
@@ -45,28 +45,27 @@ The following hyperparameters were used during training:
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
- | 4.5947 | 0.92 | 3 | 3.9682 |
55
- | 4.058 | 1.85 | 6 | 3.4521 |
56
- | 3.4874 | 2.77 | 9 | 2.9993 |
57
- | 2.2713 | 4.0 | 13 | 2.5722 |
58
- | 2.698 | 4.92 | 16 | 2.3416 |
59
- | 2.3939 | 5.85 | 19 | 2.1543 |
60
- | 2.187 | 6.77 | 22 | 2.0294 |
61
- | 1.5495 | 8.0 | 26 | 1.9548 |
62
- | 2.0129 | 8.92 | 29 | 1.9055 |
63
- | 1.3924 | 9.23 | 30 | 1.8899 |
64
 
65
 
66
  ### Framework versions
67
 
68
  - PEFT 0.9.0
69
- - Transformers 4.38.1
70
- - Pytorch 2.1.0+cu121
71
  - Datasets 2.18.0
72
  - Tokenizers 0.15.2
 
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: 4.2329
20
 
21
  ## Model description
22
 
 
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 2
47
  - num_epochs: 10
 
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | 4.6496 | 0.92 | 3 | 4.2329 |
54
+ | 4.6271 | 1.85 | 6 | 4.2329 |
55
+ | 4.6451 | 2.77 | 9 | 4.2329 |
56
+ | 3.4785 | 4.0 | 13 | 4.2329 |
57
+ | 4.654 | 4.92 | 16 | 4.2329 |
58
+ | 4.6348 | 5.85 | 19 | 4.2329 |
59
+ | 4.6483 | 6.77 | 22 | 4.2329 |
60
+ | 3.4571 | 8.0 | 26 | 4.2329 |
61
+ | 4.6148 | 8.92 | 29 | 4.2329 |
62
+ | 3.0699 | 9.23 | 30 | 4.2329 |
63
 
64
 
65
  ### Framework versions
66
 
67
  - PEFT 0.9.0
68
+ - Transformers 4.39.0.dev0
69
+ - Pytorch 2.2.1+cu121
70
  - Datasets 2.18.0
71
  - Tokenizers 0.15.2
runs/Mar06_12-53-42_instance-20240306-123153/events.out.tfevents.1709729622.instance-20240306-123153 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9598cac9dfc351c185c56fcb0a4ea497e0463c7b2495d8da27dffda0a1e83726
3
+ size 5172
runs/Mar06_13-33-49_instance-20240306-123153/events.out.tfevents.1709732029.instance-20240306-123153 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1fcf646b81316eaba879a3304e423e95e65a45c258eb078dd9f6b914b8be10
3
+ size 5177
runs/Mar06_13-35-48_instance-20240306-123153/events.out.tfevents.1709732148.instance-20240306-123153 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d836969038fef65c66fdf3e5443f0c2089486f2ce02a2bc98c5f06d190aeb0
3
+ size 5177
runs/Mar06_13-41-15_instance-20240306-123153/events.out.tfevents.1709732475.instance-20240306-123153 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abfbaa90710536115f96b4d195b7626951b8ebdf50265a8cb0a97fdae9e7c78e
3
+ size 5177
runs/Mar06_14-20-08_instance-20240306-123153/events.out.tfevents.1709734808.instance-20240306-123153 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfa05e7fe9194a01f06649eed108554787e5483a19189262a7089b5d919d26b
3
+ size 5204
runs/Mar06_14-21-10_instance-20240306-123153/events.out.tfevents.1709734870.instance-20240306-123153 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c24f64228558951f3d7945e7bafdce67ab01ac8c066b9dc78375db2e46d79369
3
+ size 10283
runs/Mar06_14-24-03_instance-20240306-123153/events.out.tfevents.1709735044.instance-20240306-123153 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecb5b990a8b18562dfb859e2a18bd4053d38e9cee22bdafcdef3e2fe325ef7fa
3
+ size 10283
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05da5d2163f31e7dca961d3c9381b6855f332ba90b26fb5c3225552889bfaa79
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386d01f80bbabdbf45af886bf53a46615012ac954d5eb495ed5e8531725cb2d4
3
  size 4856