End of training
Browse files- README.md +100 -0
- adapter_model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/llama-3-8b-bnb-4bit
|
3 |
+
library_name: peft
|
4 |
+
license: llama3
|
5 |
+
tags:
|
6 |
+
- unsloth
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: Meta-Llama-3-8B_magiccoder_ortho
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# Meta-Llama-3-8B_magiccoder_ortho
|
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: 1.2979
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
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
|
43 |
+
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 64
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: cosine
|
47 |
+
- lr_scheduler_warmup_ratio: 0.02
|
48 |
+
- num_epochs: 1
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
54 |
+
| 1.3729 | 0.0259 | 4 | 1.4553 |
|
55 |
+
| 1.4282 | 0.0518 | 8 | 1.4025 |
|
56 |
+
| 1.3582 | 0.0777 | 12 | 1.3661 |
|
57 |
+
| 1.3765 | 0.1036 | 16 | 1.3732 |
|
58 |
+
| 1.412 | 0.1296 | 20 | 1.3709 |
|
59 |
+
| 1.3139 | 0.1555 | 24 | 1.3703 |
|
60 |
+
| 1.3527 | 0.1814 | 28 | 1.3569 |
|
61 |
+
| 1.3366 | 0.2073 | 32 | 1.3696 |
|
62 |
+
| 1.3585 | 0.2332 | 36 | 1.3574 |
|
63 |
+
| 1.4341 | 0.2591 | 40 | 1.3561 |
|
64 |
+
| 1.3608 | 0.2850 | 44 | 1.3471 |
|
65 |
+
| 1.2669 | 0.3109 | 48 | 1.3583 |
|
66 |
+
| 1.3432 | 0.3368 | 52 | 1.3500 |
|
67 |
+
| 1.3825 | 0.3628 | 56 | 1.3465 |
|
68 |
+
| 1.3424 | 0.3887 | 60 | 1.3365 |
|
69 |
+
| 1.3974 | 0.4146 | 64 | 1.3424 |
|
70 |
+
| 1.2641 | 0.4405 | 68 | 1.3373 |
|
71 |
+
| 1.3123 | 0.4664 | 72 | 1.3308 |
|
72 |
+
| 1.2767 | 0.4923 | 76 | 1.3429 |
|
73 |
+
| 1.3543 | 0.5182 | 80 | 1.3270 |
|
74 |
+
| 1.3019 | 0.5441 | 84 | 1.3380 |
|
75 |
+
| 1.3383 | 0.5700 | 88 | 1.3378 |
|
76 |
+
| 1.4165 | 0.5960 | 92 | 1.3250 |
|
77 |
+
| 1.2437 | 0.6219 | 96 | 1.3246 |
|
78 |
+
| 1.32 | 0.6478 | 100 | 1.3234 |
|
79 |
+
| 1.2362 | 0.6737 | 104 | 1.3309 |
|
80 |
+
| 1.2529 | 0.6996 | 108 | 1.3166 |
|
81 |
+
| 1.2605 | 0.7255 | 112 | 1.3099 |
|
82 |
+
| 1.3089 | 0.7514 | 116 | 1.3075 |
|
83 |
+
| 1.2937 | 0.7773 | 120 | 1.3063 |
|
84 |
+
| 1.3127 | 0.8032 | 124 | 1.3017 |
|
85 |
+
| 1.308 | 0.8291 | 128 | 1.3033 |
|
86 |
+
| 1.2962 | 0.8551 | 132 | 1.3026 |
|
87 |
+
| 1.2542 | 0.8810 | 136 | 1.3004 |
|
88 |
+
| 1.2808 | 0.9069 | 140 | 1.2992 |
|
89 |
+
| 1.242 | 0.9328 | 144 | 1.2967 |
|
90 |
+
| 1.265 | 0.9587 | 148 | 1.2990 |
|
91 |
+
| 1.2364 | 0.9846 | 152 | 1.2979 |
|
92 |
+
|
93 |
+
|
94 |
+
### Framework versions
|
95 |
+
|
96 |
+
- PEFT 0.12.0
|
97 |
+
- Transformers 4.44.0
|
98 |
+
- Pytorch 2.4.0+cu121
|
99 |
+
- Datasets 2.20.0
|
100 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f34ff1cc5825f37906eb38080fd30f61e53e05b91cae182e78dee6b688c04b5
|
3 |
size 83945296
|