Hugging Face's logo

coinplusfire
/
coinplusfire_llm_2

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
coinplusfire commited on
Commit
77e2c82
·
verified ·
1 Parent(s): f7d960a

coinplusfire/coinplusfire_llm_2

Browse files
Files changed (3) hide show
  1. README.md +22 -12
  2. runs/Apr17_02-10-11_2cf8682266e1/events.out.tfevents.1713319812.2cf8682266e1.709.0 +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: 1.3706
20
 
21
  ## Model description
22
 
@@ -44,23 +44,33 @@ 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
- | 2.2985 | 0.99 | 51 | 1.8297 |
55
- | 1.6179 | 1.99 | 103 | 1.6461 |
56
- | 1.4812 | 3.0 | 155 | 1.5621 |
57
- | 1.3993 | 4.0 | 207 | 1.5078 |
58
- | 1.3646 | 4.99 | 258 | 1.4690 |
59
- | 1.2914 | 5.99 | 310 | 1.4270 |
60
- | 1.2542 | 7.0 | 362 | 1.4022 |
61
- | 1.2263 | 8.0 | 414 | 1.3832 |
62
- | 1.2279 | 8.99 | 465 | 1.3720 |
63
- | 1.1812 | 9.86 | 510 | 1.3706 |
 
 
 
 
 
 
 
 
 
 
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: 1.1450
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: 20
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 2.2919 | 0.99 | 51 | 1.8319 |
55
+ | 1.6082 | 1.99 | 103 | 1.6426 |
56
+ | 1.4689 | 3.0 | 155 | 1.5522 |
57
+ | 1.3821 | 4.0 | 207 | 1.4883 |
58
+ | 1.3406 | 4.99 | 258 | 1.4421 |
59
+ | 1.2592 | 5.99 | 310 | 1.3900 |
60
+ | 1.2115 | 7.0 | 362 | 1.3508 |
61
+ | 1.1705 | 8.0 | 414 | 1.3213 |
62
+ | 1.1555 | 8.99 | 465 | 1.2913 |
63
+ | 1.1031 | 9.99 | 517 | 1.2629 |
64
+ | 1.0727 | 11.0 | 569 | 1.2418 |
65
+ | 1.0481 | 12.0 | 621 | 1.2208 |
66
+ | 1.0466 | 12.99 | 672 | 1.1971 |
67
+ | 1.006 | 13.99 | 724 | 1.1864 |
68
+ | 0.989 | 15.0 | 776 | 1.1732 |
69
+ | 0.9719 | 16.0 | 828 | 1.1589 |
70
+ | 0.979 | 16.99 | 879 | 1.1535 |
71
+ | 0.9494 | 17.99 | 931 | 1.1469 |
72
+ | 0.9401 | 19.0 | 983 | 1.1449 |
73
+ | 0.9302 | 19.71 | 1020 | 1.1450 |
74
 
75
 
76
  ### Framework versions
runs/Apr17_02-10-11_2cf8682266e1/events.out.tfevents.1713319812.2cf8682266e1.709.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0e4e5deabc2788c0fc3e5e5c234c110cff73ec0dd9d510bb48e89afeea0e2f
3
+ size 15207
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:449d1160346d35d092c056d4ce219dab2f49067dc87dce42020a43fa8d3bf98a
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c8bbbdaafc013ef0e09284808f7a446e06bfb5403b766b09d22327cfc345f2
3
  size 4920