Hugging Face's logo

Katochh
/
GenAI-task2-ModelB

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Katochh commited on
Commit
8fc4309
·
verified ·
1 Parent(s): c388dea

End of training

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: petals-team/falcon-rw-1b
9
+ model-index:
10
+ - name: GenAI-task2-ModelB
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # GenAI-task2-ModelB
18
+
19
+ This model is a fine-tuned version of [petals-team/falcon-rw-1b](https://huggingface.co/petals-team/falcon-rw-1b) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.0712
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 4
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.01
49
+ - num_epochs: 2
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | 1.4819 | 0.05 | 20 | 1.5761 |
56
+ | 1.6396 | 0.1 | 40 | 1.4181 |
57
+ | 1.4715 | 0.15 | 60 | 1.3053 |
58
+ | 1.2372 | 0.2 | 80 | 1.2440 |
59
+ | 1.3006 | 0.25 | 100 | 1.2091 |
60
+ | 1.117 | 0.3 | 120 | 1.1826 |
61
+ | 1.1284 | 0.35 | 140 | 1.1691 |
62
+ | 1.1199 | 0.4 | 160 | 1.1582 |
63
+ | 1.1853 | 0.45 | 180 | 1.1457 |
64
+ | 1.1308 | 0.5 | 200 | 1.1411 |
65
+ | 1.0031 | 0.55 | 220 | 1.1288 |
66
+ | 1.1332 | 0.6 | 240 | 1.1233 |
67
+ | 1.1182 | 0.65 | 260 | 1.1185 |
68
+ | 1.0737 | 0.7 | 280 | 1.1131 |
69
+ | 1.1858 | 0.75 | 300 | 1.1078 |
70
+ | 1.0432 | 0.8 | 320 | 1.1026 |
71
+ | 1.0895 | 0.85 | 340 | 1.0983 |
72
+ | 1.1091 | 0.9 | 360 | 1.0949 |
73
+ | 1.0866 | 0.95 | 380 | 1.0927 |
74
+ | 1.1613 | 1.0 | 400 | 1.0955 |
75
+ | 1.0328 | 1.05 | 420 | 1.0861 |
76
+ | 1.0603 | 1.1 | 440 | 1.0842 |
77
+ | 1.0627 | 1.15 | 460 | 1.0826 |
78
+ | 0.9571 | 1.2 | 480 | 1.0802 |
79
+ | 1.0478 | 1.25 | 500 | 1.0808 |
80
+ | 1.0482 | 1.3 | 520 | 1.0777 |
81
+ | 1.0552 | 1.35 | 540 | 1.0770 |
82
+ | 1.0545 | 1.4 | 560 | 1.0778 |
83
+ | 0.9966 | 1.45 | 580 | 1.0750 |
84
+ | 1.0967 | 1.5 | 600 | 1.0747 |
85
+ | 1.0334 | 1.55 | 620 | 1.0736 |
86
+ | 1.0981 | 1.6 | 640 | 1.0726 |
87
+ | 1.016 | 1.65 | 660 | 1.0726 |
88
+ | 1.0358 | 1.7 | 680 | 1.0718 |
89
+ | 1.0838 | 1.75 | 700 | 1.0718 |
90
+ | 1.0066 | 1.8 | 720 | 1.0715 |
91
+ | 1.1167 | 1.85 | 740 | 1.0713 |
92
+ | 1.0809 | 1.9 | 760 | 1.0713 |
93
+ | 1.0526 | 1.95 | 780 | 1.0712 |
94
+ | 1.1084 | 2.0 | 800 | 1.0712 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - PEFT 0.10.0
100
+ - Transformers 4.40.0
101
+ - Pytorch 2.2.1+cu121
102
+ - Datasets 2.19.0
103
+ - Tokenizers 0.19.1