Hugging Face's logo

Mayilde
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
Mayilde commited on
Commit
b9c303f
•
1 Parent(s): 9f8f1a0

Mayilde/shawgpt-ft

Browse files
Files changed (3) hide show
  1. README.md +27 -13
  2. runs/Oct21_11-55-14_455caaabfdfd/events.out.tfevents.1729511721.455caaabfdfd.2464.0 +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: 1.3485
20
 
21
  ## Model description
22
 
@@ -42,26 +42,40 @@ The following hyperparameters were used during training:
42
  - gradient_accumulation_steps: 4
43
  - total_train_batch_size: 16
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
- - lr_scheduler_type: cosine
46
  - lr_scheduler_warmup_steps: 2
47
- - num_epochs: 5
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:----:|:---------------:|
54
- | 1.1194 | 0.9231 | 3 | 1.3438 |
55
- | 1.1165 | 1.8462 | 6 | 1.3420 |
56
- | 1.0754 | 2.7692 | 9 | 1.3242 |
57
- | 0.7662 | 4.0 | 13 | 1.3482 |
58
- | 0.9215 | 4.6154 | 15 | 1.3485 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
62
 
63
- - PEFT 0.13.0
64
- - Transformers 4.45.1
65
  - Pytorch 2.1.0+cu121
66
  - Datasets 3.0.1
67
- - Tokenizers 0.20.0
 
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: 1.4930
20
 
21
  ## Model description
22
 
 
42
  - gradient_accumulation_steps: 4
43
  - total_train_batch_size: 16
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: 20
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 4.5948 | 0.9231 | 3 | 3.9703 |
55
+ | 4.0516 | 1.8462 | 6 | 3.4377 |
56
+ | 3.4456 | 2.7692 | 9 | 2.9505 |
57
+ | 2.2132 | 4.0 | 13 | 2.4876 |
58
+ | 2.5771 | 4.9231 | 16 | 2.2085 |
59
+ | 2.1985 | 5.8462 | 19 | 1.9655 |
60
+ | 1.9692 | 6.7692 | 22 | 1.8320 |
61
+ | 1.3913 | 8.0 | 26 | 1.7772 |
62
+ | 1.7898 | 8.9231 | 29 | 1.6993 |
63
+ | 1.7076 | 9.8462 | 32 | 1.6772 |
64
+ | 1.7068 | 10.7692 | 35 | 1.6532 |
65
+ | 1.2376 | 12.0 | 39 | 1.6191 |
66
+ | 1.64 | 12.9231 | 42 | 1.5902 |
67
+ | 1.5758 | 13.8462 | 45 | 1.5654 |
68
+ | 1.576 | 14.7692 | 48 | 1.5560 |
69
+ | 1.1826 | 16.0 | 52 | 1.5495 |
70
+ | 1.5448 | 16.9231 | 55 | 1.5249 |
71
+ | 1.499 | 17.8462 | 58 | 1.5051 |
72
+ | 1.0455 | 18.4615 | 60 | 1.4930 |
73
 
74
 
75
  ### Framework versions
76
 
77
+ - PEFT 0.13.2
78
+ - Transformers 4.45.2
79
  - Pytorch 2.1.0+cu121
80
  - Datasets 3.0.1
81
+ - Tokenizers 0.20.1
runs/Oct21_11-55-14_455caaabfdfd/events.out.tfevents.1729511721.455caaabfdfd.2464.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d898e8cd6766c10652d8bf62728347752f454dbeb63e3e235b3a2ff97e2fa7fe
3
+ size 5611
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46331811dd064a064e99e86ac81f5ec6b7e87a5ba66de6c4f0b303193b6be495
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ce4cb54eea19b49f001029c65fc3a426270971c6d6d421b13ec1f596f96b52
3
  size 5176