Hugging Face's logo

sherryzha
/
falcon-rewrite-581-smallset

Generated from Trainer
Model card Files Community
sherryzha commited on
Commit
4a0affd
•
1 Parent(s): d25cda7

End of training

Browse files
Files changed (2) hide show
  1. README.md +97 -0
  2. adapter_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: tiiuae/falcon-7b
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: falcon-rewrite-581-smallset
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # falcon-rewrite-581-smallset
15
+
16
+ This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.8029
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 4
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_ratio: 0.03
44
+ - num_epochs: 4
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 2.4551 | 0.04 | 10 | 2.4085 |
51
+ | 1.4203 | 0.08 | 20 | 2.3957 |
52
+ | 1.6967 | 0.13 | 30 | 2.1396 |
53
+ | 1.5897 | 0.17 | 40 | 2.2547 |
54
+ | 1.4068 | 0.21 | 50 | 2.2484 |
55
+ | 2.4724 | 0.25 | 60 | 2.1803 |
56
+ | 1.6358 | 0.3 | 70 | 2.0363 |
57
+ | 1.7565 | 0.34 | 80 | 2.3048 |
58
+ | 1.9326 | 0.38 | 90 | 2.2237 |
59
+ | 1.4726 | 0.42 | 100 | 1.9666 |
60
+ | 2.6885 | 0.47 | 110 | 2.0889 |
61
+ | 1.7221 | 0.51 | 120 | 2.0868 |
62
+ | 2.7958 | 0.55 | 130 | 2.0033 |
63
+ | 1.6916 | 0.59 | 140 | 2.0824 |
64
+ | 0.9544 | 0.64 | 150 | 2.1048 |
65
+ | 1.8363 | 0.68 | 160 | 1.9306 |
66
+ | 2.2805 | 0.72 | 170 | 2.0956 |
67
+ | 2.2398 | 0.76 | 180 | 2.1049 |
68
+ | 1.0369 | 0.81 | 190 | 2.0348 |
69
+ | 0.9023 | 0.85 | 200 | 1.9050 |
70
+ | 1.1511 | 0.89 | 210 | 2.0645 |
71
+ | 1.1805 | 0.93 | 220 | 1.9241 |
72
+ | 1.0402 | 0.97 | 230 | 2.0542 |
73
+ | 1.1116 | 1.02 | 240 | 1.9184 |
74
+ | 2.2786 | 1.06 | 250 | 2.0039 |
75
+ | 1.5313 | 1.1 | 260 | 1.9232 |
76
+ | 1.0101 | 1.14 | 270 | 1.8365 |
77
+ | 1.3444 | 1.19 | 280 | 1.9812 |
78
+ | 1.9973 | 1.23 | 290 | 2.0105 |
79
+ | 1.001 | 1.27 | 300 | 1.8029 |
80
+ | 1.5717 | 1.31 | 310 | 1.8190 |
81
+ | 1.7842 | 1.36 | 320 | 2.0034 |
82
+ | 0.841 | 1.4 | 330 | 2.0345 |
83
+ | 0.9212 | 1.44 | 340 | 1.9301 |
84
+ | 1.6442 | 1.48 | 350 | 2.0139 |
85
+ | 2.0697 | 1.53 | 360 | 2.1341 |
86
+ | 1.0772 | 1.57 | 370 | 2.0179 |
87
+ | 1.4152 | 1.61 | 380 | 1.8754 |
88
+ | 0.912 | 1.65 | 390 | 1.9178 |
89
+ | 1.7032 | 1.69 | 400 | 1.9235 |
90
+
91
+
92
+ ### Framework versions
93
+
94
+ - Transformers 4.32.1
95
+ - Pytorch 2.0.1
96
+ - Datasets 2.14.5
97
+ - Tokenizers 0.13.3
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5927a8ebb23d39a7fe95a615b837e77d249af904dbab6f13955903426894ace4
3
  size 65978769
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca3a18a634ab68f918dd9588afac501e8a8d4a7d8500e6814aa2fe08465ff23f
3
  size 65978769