Hugging Face's logo

imdatta0
/
qwen_cnn_dailymail

Generated from Trainer
Model card Files Community
imdatta0 commited on
Commit
ca17263
•
1 Parent(s): 0a62236

qwen-final-cnn_dailymail

Browse files
Files changed (1) hide show
  1. README.md +110 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Qwen/Qwen-14B
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - cnn_dailymail
7
+ model-index:
8
+ - name: final_cnn_dailymail
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
+ # final_cnn_dailymail
16
+
17
+ This model is a fine-tuned version of [Qwen/Qwen-14B](https://huggingface.co/Qwen/Qwen-14B) on the cnn_dailymail dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.2127
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 16
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_steps: 0.01
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:-----:|:----:|:---------------:|
53
+ | 1.9757 | 0.02 | 100 | 1.9261 |
54
+ | 1.9258 | 0.04 | 200 | 1.8833 |
55
+ | 1.8977 | 0.06 | 300 | 1.8657 |
56
+ | 1.8903 | 0.08 | 400 | 1.8630 |
57
+ | 1.8858 | 0.1 | 500 | 1.8638 |
58
+ | 1.89 | 0.12 | 600 | 1.8636 |
59
+ | 1.873 | 0.14 | 700 | 1.8637 |
60
+ | 1.8908 | 0.16 | 800 | 1.8637 |
61
+ | 1.8791 | 0.18 | 900 | 1.8626 |
62
+ | 1.8851 | 0.2 | 1000 | 1.8634 |
63
+ | 1.89 | 0.22 | 1100 | 1.8651 |
64
+ | 1.8889 | 0.24 | 1200 | 1.8681 |
65
+ | 1.8896 | 0.26 | 1300 | 1.8708 |
66
+ | 1.8817 | 0.28 | 1400 | 1.8739 |
67
+ | 1.9003 | 0.3 | 1500 | 1.8791 |
68
+ | 1.9005 | 0.32 | 1600 | 1.8825 |
69
+ | 1.9024 | 0.34 | 1700 | 1.8864 |
70
+ | 1.9204 | 0.36 | 1800 | 1.8929 |
71
+ | 1.9182 | 0.38 | 1900 | 1.8955 |
72
+ | 1.9289 | 0.4 | 2000 | 1.9035 |
73
+ | 1.9348 | 0.42 | 2100 | 1.9157 |
74
+ | 1.9453 | 0.44 | 2200 | 1.9277 |
75
+ | 1.9689 | 0.46 | 2300 | 1.9457 |
76
+ | 1.9829 | 0.48 | 2400 | 1.9596 |
77
+ | 1.9874 | 0.5 | 2500 | 1.9803 |
78
+ | 2.0148 | 0.52 | 2600 | 1.9991 |
79
+ | 2.0391 | 0.54 | 2700 | 2.0249 |
80
+ | 2.0619 | 0.56 | 2800 | 2.0477 |
81
+ | 2.0736 | 0.58 | 2900 | 2.0678 |
82
+ | 2.0957 | 0.6 | 3000 | 2.0825 |
83
+ | 2.1223 | 0.62 | 3100 | 2.1097 |
84
+ | 2.1357 | 0.64 | 3200 | 2.1164 |
85
+ | 2.1759 | 0.66 | 3300 | 2.1524 |
86
+ | 2.168 | 0.68 | 3400 | 2.1650 |
87
+ | 2.1842 | 0.7 | 3500 | 2.1637 |
88
+ | 2.1956 | 0.72 | 3600 | 2.1775 |
89
+ | 2.2131 | 0.74 | 3700 | 2.1888 |
90
+ | 2.198 | 0.76 | 3800 | 2.1953 |
91
+ | 2.2231 | 0.78 | 3900 | 2.1994 |
92
+ | 2.2292 | 0.8 | 4000 | 2.2080 |
93
+ | 2.2343 | 0.82 | 4100 | 2.2093 |
94
+ | 2.2261 | 0.84 | 4200 | 2.2009 |
95
+ | 2.2104 | 0.86 | 4300 | 2.2015 |
96
+ | 2.2255 | 0.88 | 4400 | 2.2077 |
97
+ | 2.2299 | 0.9 | 4500 | 2.2099 |
98
+ | 2.2253 | 0.92 | 4600 | 2.2100 |
99
+ | 2.2239 | 0.94 | 4700 | 2.2116 |
100
+ | 2.2322 | 0.96 | 4800 | 2.2122 |
101
+ | 2.2457 | 0.98 | 4900 | 2.2127 |
102
+ | 2.2325 | 1.0 | 5000 | 2.2127 |
103
+
104
+
105
+ ### Framework versions
106
+
107
+ - Transformers 4.32.0
108
+ - Pytorch 2.1.0
109
+ - Datasets 2.14.7
110
+ - Tokenizers 0.13.3