Hugging Face's logo

lesso02
/
561cc045-d57d-4d40-932e-390287a2eaac

PEFT
Safetensors
falcon
axolotl
Generated from Trainer
custom_code
Model card Files Community
lesso02 commited on
Commit
1c679e3
·
verified ·
1 Parent(s): f0e5175

End of training

Browse files
Files changed (1) hide show
  1. README.md +116 -0
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: mit
4
+ base_model: fxmarty/really-tiny-falcon-testing
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 561cc045-d57d-4d40-932e-390287a2eaac
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
+ [<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)
17
+ <br>
18
+
19
+ # 561cc045-d57d-4d40-932e-390287a2eaac
20
+
21
+ This model is a fine-tuned version of [fxmarty/really-tiny-falcon-testing](https://huggingface.co/fxmarty/really-tiny-falcon-testing) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 10.9172
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 0.000202
43
+ - train_batch_size: 4
44
+ - eval_batch_size: 4
45
+ - seed: 20
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 32
48
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_steps: 100
51
+ - training_steps: 25000
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss |
56
+ |:-------------:|:------:|:-----:|:---------------:|
57
+ | No log | 0.0002 | 1 | 11.0859 |
58
+ | 87.8237 | 0.1129 | 500 | 10.9719 |
59
+ | 87.7348 | 0.2258 | 1000 | 10.9600 |
60
+ | 87.6865 | 0.3386 | 1500 | 10.9512 |
61
+ | 87.6515 | 0.4515 | 2000 | 10.9449 |
62
+ | 87.6171 | 0.5644 | 2500 | 10.9406 |
63
+ | 87.5821 | 0.6773 | 3000 | 10.9366 |
64
+ | 87.5827 | 0.7902 | 3500 | 10.9341 |
65
+ | 87.5556 | 0.9031 | 4000 | 10.9321 |
66
+ | 87.5578 | 1.0159 | 4500 | 10.9300 |
67
+ | 87.5512 | 1.1288 | 5000 | 10.9284 |
68
+ | 87.5338 | 1.2417 | 5500 | 10.9271 |
69
+ | 87.5222 | 1.3546 | 6000 | 10.9265 |
70
+ | 87.5199 | 1.4675 | 6500 | 10.9258 |
71
+ | 87.5171 | 1.5804 | 7000 | 10.9247 |
72
+ | 87.5118 | 1.6932 | 7500 | 10.9238 |
73
+ | 87.5051 | 1.8061 | 8000 | 10.9233 |
74
+ | 87.508 | 1.9190 | 8500 | 10.9228 |
75
+ | 87.4979 | 2.0319 | 9000 | 10.9221 |
76
+ | 87.4973 | 2.1448 | 9500 | 10.9216 |
77
+ | 87.512 | 2.2577 | 10000 | 10.9213 |
78
+ | 87.4823 | 2.3705 | 10500 | 10.9210 |
79
+ | 87.4886 | 2.4834 | 11000 | 10.9207 |
80
+ | 87.4873 | 2.5963 | 11500 | 10.9202 |
81
+ | 87.4897 | 2.7092 | 12000 | 10.9200 |
82
+ | 87.4782 | 2.8221 | 12500 | 10.9196 |
83
+ | 87.4864 | 2.9350 | 13000 | 10.9196 |
84
+ | 87.4777 | 3.0478 | 13500 | 10.9194 |
85
+ | 87.4821 | 3.1607 | 14000 | 10.9189 |
86
+ | 87.479 | 3.2736 | 14500 | 10.9188 |
87
+ | 87.4648 | 3.3865 | 15000 | 10.9185 |
88
+ | 87.4757 | 3.4994 | 15500 | 10.9184 |
89
+ | 87.4546 | 3.6122 | 16000 | 10.9184 |
90
+ | 87.4722 | 3.7251 | 16500 | 10.9183 |
91
+ | 87.4617 | 3.8380 | 17000 | 10.9179 |
92
+ | 87.4607 | 3.9509 | 17500 | 10.9181 |
93
+ | 87.4602 | 4.0638 | 18000 | 10.9178 |
94
+ | 87.4577 | 4.1767 | 18500 | 10.9176 |
95
+ | 87.4592 | 4.2895 | 19000 | 10.9175 |
96
+ | 87.4784 | 4.4024 | 19500 | 10.9174 |
97
+ | 87.4644 | 4.5153 | 20000 | 10.9173 |
98
+ | 87.4677 | 4.6282 | 20500 | 10.9174 |
99
+ | 87.465 | 4.7411 | 21000 | 10.9174 |
100
+ | 87.4606 | 4.8540 | 21500 | 10.9172 |
101
+ | 87.4689 | 4.9668 | 22000 | 10.9173 |
102
+ | 87.4515 | 5.0797 | 22500 | 10.9172 |
103
+ | 87.4637 | 5.1926 | 23000 | 10.9172 |
104
+ | 87.4589 | 5.3055 | 23500 | 10.9172 |
105
+ | 87.4596 | 5.4184 | 24000 | 10.9172 |
106
+ | 87.461 | 5.5313 | 24500 | 10.9173 |
107
+ | 87.4639 | 5.6441 | 25000 | 10.9172 |
108
+
109
+
110
+ ### Framework versions
111
+
112
+ - PEFT 0.13.2
113
+ - Transformers 4.46.0
114
+ - Pytorch 2.5.0+cu124
115
+ - Datasets 3.0.1
116
+ - Tokenizers 0.20.1