Hugging Face's logo

LineLS
/
shawgpt-ft

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
LineLS commited on
Commit
1e62a8f
·
verified ·
1 Parent(s): 743d064

LineLS/shawgpt-ftV2

Browse files
Files changed (7) hide show
  1. README.md +24 -15
  2. adapter_config.json +2 -2
  3. adapter_model.safetensors +2 -2
  4. runs/Oct13_11-56-56_bc68b11829bc/events.out.tfevents.1728821649.bc68b11829bc.3705.1 +3 -0
  5. runs/Oct13_13-04-02_bc68b11829bc/events.out.tfevents.1728824651.bc68b11829bc.3705.2 +3 -0
  6. runs/Oct13_13-04-02_bc68b11829bc/events.out.tfevents.1728826131.bc68b11829bc.3705.3 +3 -0
  7. 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: 1.7259
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0002
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
@@ -44,23 +44,32 @@ 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
- | 4.5932 | 0.9231 | 3 | 3.9725 |
55
- | 4.0532 | 1.8462 | 6 | 3.4547 |
56
- | 3.4704 | 2.7692 | 9 | 2.9927 |
57
- | 2.2395 | 4.0 | 13 | 2.5308 |
58
- | 2.6051 | 4.9231 | 16 | 2.2441 |
59
- | 2.2545 | 5.8462 | 19 | 2.0362 |
60
- | 2.0136 | 6.7692 | 22 | 1.8869 |
61
- | 1.4182 | 8.0 | 26 | 1.7714 |
62
- | 1.8025 | 8.9231 | 29 | 1.7306 |
63
- | 1.2552 | 9.2308 | 30 | 1.7259 |
 
 
 
 
 
 
 
 
 
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: 1.3086
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0003
39
  - train_batch_size: 4
40
  - eval_batch_size: 4
41
  - seed: 42
 
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
+ | 4.562 | 0.9231 | 3 | 3.8136 |
55
+ | 3.7584 | 1.8462 | 6 | 3.0439 |
56
+ | 2.9884 | 2.7692 | 9 | 2.5154 |
57
+ | 1.8103 | 4.0 | 13 | 1.9763 |
58
+ | 1.9109 | 4.9231 | 16 | 1.6535 |
59
+ | 1.543 | 5.8462 | 19 | 1.4627 |
60
+ | 1.352 | 6.7692 | 22 | 1.3896 |
61
+ | 0.9888 | 8.0 | 26 | 1.3458 |
62
+ | 1.2644 | 8.9231 | 29 | 1.3269 |
63
+ | 1.2035 | 9.8462 | 32 | 1.3169 |
64
+ | 1.198 | 10.7692 | 35 | 1.3156 |
65
+ | 0.8476 | 12.0 | 39 | 1.3114 |
66
+ | 1.1265 | 12.9231 | 42 | 1.3086 |
67
+ | 1.0791 | 13.8462 | 45 | 1.3138 |
68
+ | 1.0711 | 14.7692 | 48 | 1.3207 |
69
+ | 0.7968 | 16.0 | 52 | 1.3141 |
70
+ | 1.0279 | 16.9231 | 55 | 1.3216 |
71
+ | 1.0094 | 17.8462 | 58 | 1.3262 |
72
+ | 0.7129 | 18.4615 | 60 | 1.3255 |
73
 
74
 
75
  ### Framework versions
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -16,7 +16,7 @@
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
18
  "peft_type": "LORA",
19
- "r": 8,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": null,
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
18
  "peft_type": "LORA",
19
+ "r": 16,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a0b08f5d6246e777f2e54dc03d715ec001af5f28f7f6d6d0dd5981bcb6b9708
3
- size 8397056
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85a09d508b0e378143f60dbcdda2f4742ce3ae1a5e0276ab89a10ad18f5fe552
3
+ size 16786880
runs/Oct13_11-56-56_bc68b11829bc/events.out.tfevents.1728821649.bc68b11829bc.3705.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee39184a716e7ed55e1ce73ca0ba4b7bf468ea77a20950c9d76f837130b1098b
3
+ size 354
runs/Oct13_13-04-02_bc68b11829bc/events.out.tfevents.1728824651.bc68b11829bc.3705.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f56925f4cefaab758e6d06cc758db3d51e74763d0c936de8ab366e0c443bed4
3
+ size 14905
runs/Oct13_13-04-02_bc68b11829bc/events.out.tfevents.1728826131.bc68b11829bc.3705.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db49c04d7aa45aee004b9d8feaace6c96c1c19449da48308390e4c0deec31f4
3
+ size 354
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0af5f42eb06c9715607ce2f751f94bb5963f86272e684f9d9f815a2912e2403
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea165663aed45dffb895c53d611a4e7e5b39fb6a8e8427b7fa97da0d2adad9c7
3
  size 5176