lesso commited on
Commit
6624cd3
·
verified ·
1 Parent(s): 8904c5c

Добавление обновлённого README.md без блоков <details>

Browse files
Files changed (1) hide show
  1. README.md +73 -0
README.md ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ base_model: katuni4ka/tiny-random-falcon-40b
4
+ tags:
5
+ - axolotl
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: f4c4980f-94f4-4e51-85d8-5b8c432eda0f
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
16
+ <br>
17
+
18
+ # f4c4980f-94f4-4e51-85d8-5b8c432eda0f
19
+
20
+ This model is a fine-tuned version of [katuni4ka/tiny-random-falcon-40b](https://huggingface.co/katuni4ka/tiny-random-falcon-40b) on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 10.7234
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.000214
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 128
47
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: constant
49
+ - lr_scheduler_warmup_steps: 50
50
+ - training_steps: 400
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | No log | 0.0016 | 1 | 11.1055 |
57
+ | 43.6515 | 0.0793 | 50 | 10.8410 |
58
+ | 43.3002 | 0.1587 | 100 | 10.8140 |
59
+ | 43.2285 | 0.2380 | 150 | 10.7995 |
60
+ | 43.1918 | 0.3173 | 200 | 10.7876 |
61
+ | 43.1369 | 0.3967 | 250 | 10.7752 |
62
+ | 43.1038 | 0.4760 | 300 | 10.7642 |
63
+ | 43.0364 | 0.5553 | 350 | 10.7495 |
64
+ | 42.9207 | 0.6347 | 400 | 10.7234 |
65
+
66
+
67
+ ### Framework versions
68
+
69
+ - PEFT 0.13.2
70
+ - Transformers 4.46.0
71
+ - Pytorch 2.5.0+cu124
72
+ - Datasets 3.0.1
73
+ - Tokenizers 0.20.1