Hugging Face's logo

imdatta0
/
Meta-Llama-3-8B_magiccoder_default

PEFT
Safetensors
unsloth
Generated from Trainer
Model card Files
xet
Community
imdatta0 commited on
Commit
6ceff86
·
verified ·
1 Parent(s): 6e2d47c

End of training

Browse files
Files changed (2) hide show
  1. README.md +42 -42
  2. adapter_model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- base_model: unsloth/llama-3-8b-bnb-4bit
3
  library_name: peft
4
  license: llama3
5
  tags:
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # Meta-Llama-3-8B_magiccoder_default
17
 
18
- This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.2364
21
 
22
  ## Model description
23
 
@@ -36,7 +36,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 0.0001
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
@@ -51,44 +51,44 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 1.3123 | 0.0259 | 4 | 1.4459 |
55
- | 1.3773 | 0.0518 | 8 | 1.3830 |
56
- | 1.3126 | 0.0777 | 12 | 1.3384 |
57
- | 1.3342 | 0.1036 | 16 | 1.3304 |
58
- | 1.3395 | 0.1296 | 20 | 1.3152 |
59
- | 1.238 | 0.1555 | 24 | 1.3039 |
60
- | 1.2922 | 0.1814 | 28 | 1.2958 |
61
- | 1.2613 | 0.2073 | 32 | 1.2857 |
62
- | 1.2744 | 0.2332 | 36 | 1.2727 |
63
- | 1.3175 | 0.2591 | 40 | 1.2619 |
64
- | 1.2728 | 0.2850 | 44 | 1.2570 |
65
- | 1.1929 | 0.3109 | 48 | 1.2556 |
66
- | 1.2508 | 0.3368 | 52 | 1.2539 |
67
- | 1.29 | 0.3628 | 56 | 1.2504 |
68
- | 1.2648 | 0.3887 | 60 | 1.2506 |
69
- | 1.3289 | 0.4146 | 64 | 1.2486 |
70
- | 1.1775 | 0.4405 | 68 | 1.2479 |
71
- | 1.2501 | 0.4664 | 72 | 1.2447 |
72
- | 1.192 | 0.4923 | 76 | 1.2443 |
73
- | 1.2792 | 0.5182 | 80 | 1.2432 |
74
- | 1.205 | 0.5441 | 84 | 1.2402 |
75
- | 1.2449 | 0.5700 | 88 | 1.2405 |
76
- | 1.3454 | 0.5960 | 92 | 1.2390 |
77
- | 1.1549 | 0.6219 | 96 | 1.2390 |
78
- | 1.2483 | 0.6478 | 100 | 1.2395 |
79
- | 1.1643 | 0.6737 | 104 | 1.2395 |
80
- | 1.1872 | 0.6996 | 108 | 1.2393 |
81
- | 1.1994 | 0.7255 | 112 | 1.2391 |
82
- | 1.2578 | 0.7514 | 116 | 1.2388 |
83
- | 1.2391 | 0.7773 | 120 | 1.2382 |
84
- | 1.2605 | 0.8032 | 124 | 1.2376 |
85
- | 1.2528 | 0.8291 | 128 | 1.2371 |
86
- | 1.2524 | 0.8551 | 132 | 1.2367 |
87
- | 1.2054 | 0.8810 | 136 | 1.2365 |
88
- | 1.2068 | 0.9069 | 140 | 1.2366 |
89
- | 1.1916 | 0.9328 | 144 | 1.2365 |
90
- | 1.2172 | 0.9587 | 148 | 1.2364 |
91
- | 1.1899 | 0.9846 | 152 | 1.2364 |
92
 
93
 
94
  ### Framework versions
 
1
  ---
2
+ base_model: unsloth/llama-3-8b
3
  library_name: peft
4
  license: llama3
5
  tags:
 
15
 
16
  # Meta-Llama-3-8B_magiccoder_default
17
 
18
+ This model is a fine-tuned version of [unsloth/llama-3-8b](https://huggingface.co/unsloth/llama-3-8b) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.2697
21
 
22
  ## Model description
23
 
 
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
+ - learning_rate: 0.0003
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.2592 | 0.0259 | 4 | 1.4263 |
55
+ | 1.4281 | 0.0518 | 8 | 1.4063 |
56
+ | 1.3795 | 0.0777 | 12 | 1.3824 |
57
+ | 1.3751 | 0.1036 | 16 | 1.3937 |
58
+ | 1.4053 | 0.1296 | 20 | 1.3523 |
59
+ | 1.2927 | 0.1555 | 24 | 1.3474 |
60
+ | 1.3619 | 0.1814 | 28 | 1.3529 |
61
+ | 1.3533 | 0.2073 | 32 | 1.3629 |
62
+ | 1.3627 | 0.2332 | 36 | 1.3636 |
63
+ | 1.4408 | 0.2591 | 40 | 1.3531 |
64
+ | 1.3744 | 0.2850 | 44 | 1.3395 |
65
+ | 1.2658 | 0.3109 | 48 | 1.3364 |
66
+ | 1.3364 | 0.3368 | 52 | 1.3400 |
67
+ | 1.3765 | 0.3628 | 56 | 1.3391 |
68
+ | 1.3427 | 0.3887 | 60 | 1.3370 |
69
+ | 1.3975 | 0.4146 | 64 | 1.3329 |
70
+ | 1.2595 | 0.4405 | 68 | 1.3325 |
71
+ | 1.3291 | 0.4664 | 72 | 1.3312 |
72
+ | 1.2702 | 0.4923 | 76 | 1.3323 |
73
+ | 1.3527 | 0.5182 | 80 | 1.3213 |
74
+ | 1.2799 | 0.5441 | 84 | 1.3154 |
75
+ | 1.3082 | 0.5700 | 88 | 1.3099 |
76
+ | 1.4042 | 0.5960 | 92 | 1.3089 |
77
+ | 1.2221 | 0.6219 | 96 | 1.3048 |
78
+ | 1.3079 | 0.6478 | 100 | 1.3017 |
79
+ | 1.2165 | 0.6737 | 104 | 1.2970 |
80
+ | 1.239 | 0.6996 | 108 | 1.2941 |
81
+ | 1.2528 | 0.7255 | 112 | 1.2877 |
82
+ | 1.2932 | 0.7514 | 116 | 1.2859 |
83
+ | 1.2762 | 0.7773 | 120 | 1.2804 |
84
+ | 1.2914 | 0.8032 | 124 | 1.2791 |
85
+ | 1.2835 | 0.8291 | 128 | 1.2755 |
86
+ | 1.2735 | 0.8551 | 132 | 1.2731 |
87
+ | 1.2264 | 0.8810 | 136 | 1.2722 |
88
+ | 1.2637 | 0.9069 | 140 | 1.2713 |
89
+ | 1.2133 | 0.9328 | 144 | 1.2704 |
90
+ | 1.2379 | 0.9587 | 148 | 1.2699 |
91
+ | 1.2131 | 0.9846 | 152 | 1.2697 |
92
 
93
 
94
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37ed734062ded528972c7206ed4746f726c92e4bdde134063471aea08d53da54
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c19c8ee4fafd4dbf2eebeb359cd25e8436333e8a5aa3d300aa148e31ca8dc5
3
  size 83945296