Hugging Face's logo

nerottt
/
lc_repeat_unk_as_pad_token

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
nerottt commited on
Commit
efe8bf5
•
1 Parent(s): 56dd901

End of training

Browse files
Files changed (1) hide show
  1. README.md +110 -0
README.md ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mistral-7B-v0.1
9
+ model-index:
10
+ - name: lc_repeat_unk_as_pad_token
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
+ # lc_repeat_unk_as_pad_token
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.0279
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: 1
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 50
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | 1.4374 | 1.0 | 90 | 1.4046 |
53
+ | 1.2546 | 2.0 | 180 | 1.3617 |
54
+ | 1.3413 | 3.0 | 270 | 1.3468 |
55
+ | 1.2581 | 4.0 | 360 | 1.3482 |
56
+ | 1.2393 | 5.0 | 450 | 1.3575 |
57
+ | 1.1919 | 6.0 | 540 | 1.3651 |
58
+ | 1.1748 | 7.0 | 630 | 1.3817 |
59
+ | 1.0457 | 8.0 | 720 | 1.4023 |
60
+ | 0.986 | 9.0 | 810 | 1.4315 |
61
+ | 1.1143 | 10.0 | 900 | 1.4428 |
62
+ | 0.9689 | 11.0 | 990 | 1.4557 |
63
+ | 0.9452 | 12.0 | 1080 | 1.5132 |
64
+ | 0.9422 | 13.0 | 1170 | 1.5219 |
65
+ | 1.0653 | 14.0 | 1260 | 1.5547 |
66
+ | 1.0175 | 15.0 | 1350 | 1.6080 |
67
+ | 0.8469 | 16.0 | 1440 | 1.6143 |
68
+ | 0.8679 | 17.0 | 1530 | 1.6090 |
69
+ | 0.8854 | 18.0 | 1620 | 1.6813 |
70
+ | 0.789 | 19.0 | 1710 | 1.7044 |
71
+ | 0.8143 | 20.0 | 1800 | 1.7180 |
72
+ | 0.6346 | 21.0 | 1890 | 1.7688 |
73
+ | 0.509 | 22.0 | 1980 | 1.8638 |
74
+ | 0.7174 | 23.0 | 2070 | 1.8140 |
75
+ | 0.6996 | 24.0 | 2160 | 1.8360 |
76
+ | 0.5699 | 25.0 | 2250 | 1.8854 |
77
+ | 0.667 | 26.0 | 2340 | 1.9072 |
78
+ | 0.657 | 27.0 | 2430 | 1.9244 |
79
+ | 0.5345 | 28.0 | 2520 | 1.9389 |
80
+ | 0.5607 | 29.0 | 2610 | 1.9305 |
81
+ | 0.5528 | 30.0 | 2700 | 1.9472 |
82
+ | 0.5348 | 31.0 | 2790 | 1.9645 |
83
+ | 0.5597 | 32.0 | 2880 | 1.9925 |
84
+ | 0.4532 | 33.0 | 2970 | 1.9802 |
85
+ | 0.5005 | 34.0 | 3060 | 1.9918 |
86
+ | 0.6786 | 35.0 | 3150 | 2.0009 |
87
+ | 0.7536 | 36.0 | 3240 | 2.0051 |
88
+ | 0.6406 | 37.0 | 3330 | 2.0132 |
89
+ | 0.5569 | 38.0 | 3420 | 2.0159 |
90
+ | 0.5349 | 39.0 | 3510 | 2.0256 |
91
+ | 0.5433 | 40.0 | 3600 | 2.0228 |
92
+ | 0.5307 | 41.0 | 3690 | 2.0267 |
93
+ | 0.491 | 42.0 | 3780 | 2.0255 |
94
+ | 0.6112 | 43.0 | 3870 | 2.0256 |
95
+ | 0.5487 | 44.0 | 3960 | 2.0260 |
96
+ | 0.4791 | 45.0 | 4050 | 2.0265 |
97
+ | 0.3844 | 46.0 | 4140 | 2.0265 |
98
+ | 0.4253 | 47.0 | 4230 | 2.0265 |
99
+ | 0.4563 | 48.0 | 4320 | 2.0278 |
100
+ | 0.6504 | 49.0 | 4410 | 2.0290 |
101
+ | 0.4971 | 50.0 | 4500 | 2.0279 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - PEFT 0.11.1
107
+ - Transformers 4.41.2
108
+ - Pytorch 2.1.0+cu118
109
+ - Datasets 2.19.2
110
+ - Tokenizers 0.19.1