Hugging Face's logo

Inc44
/
myBit-Llama2-jp-127M-3

Text Generation
Transformers
Safetensors
bit_llama
Generated from Trainer
custom_code
Model card Files Community
Inc44 commited on
Commit
5bba740
•
1 Parent(s): 632dc6d

End of training

Browse files
Files changed (1) hide show
  1. README.md +87 -6
README.md CHANGED
@@ -13,12 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - eval_loss: 14.1081
17
- - eval_runtime: 0.0886
18
- - eval_samples_per_second: 237.106
19
- - eval_steps_per_second: 11.291
20
- - epoch: 50.0
21
- - step: 400
22
 
23
  ## Model description
24
 
@@ -45,6 +40,92 @@ The following hyperparameters were used during training:
45
  - lr_scheduler_type: polynomial
46
  - num_epochs: 100
47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - Transformers 4.39.1
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 13.0221
 
 
 
 
 
17
 
18
  ## Model description
19
 
 
40
  - lr_scheduler_type: polynomial
41
  - num_epochs: 100
42
 
43
+ ### Training results
44
+
45
+ | Training Loss | Epoch | Step | Validation Loss |
46
+ |:-------------:|:-----:|:----:|:---------------:|
47
+ | 7.8184 | 1.25 | 10 | 8.3355 |
48
+ | 5.4327 | 2.5 | 20 | 7.6000 |
49
+ | 5.0861 | 3.75 | 30 | 7.8126 |
50
+ | 4.7586 | 5.0 | 40 | 7.5748 |
51
+ | 4.4392 | 6.25 | 50 | 7.4509 |
52
+ | 4.1938 | 7.5 | 60 | 7.3834 |
53
+ | 4.0095 | 8.75 | 70 | 7.2750 |
54
+ | 3.905 | 10.0 | 80 | 7.3800 |
55
+ | 3.6536 | 11.25 | 90 | 7.4560 |
56
+ | 3.3187 | 12.5 | 100 | 7.6310 |
57
+ | 3.3315 | 13.75 | 110 | 8.0397 |
58
+ | 2.9308 | 15.0 | 120 | 8.3902 |
59
+ | 2.679 | 16.25 | 130 | 9.0364 |
60
+ | 2.2896 | 17.5 | 140 | 9.8766 |
61
+ | 1.8407 | 18.75 | 150 | 10.7682 |
62
+ | 1.5081 | 20.0 | 160 | 11.7175 |
63
+ | 0.9778 | 21.25 | 170 | 12.8239 |
64
+ | 0.6572 | 22.5 | 180 | 13.6506 |
65
+ | 0.5411 | 23.75 | 190 | 14.2579 |
66
+ | 0.44 | 25.0 | 200 | 14.5732 |
67
+ | 0.3283 | 26.25 | 210 | 15.1087 |
68
+ | 0.2507 | 27.5 | 220 | 15.0569 |
69
+ | 0.2044 | 28.75 | 230 | 15.1893 |
70
+ | 0.1838 | 30.0 | 240 | 15.6291 |
71
+ | 0.1626 | 31.25 | 250 | 15.4617 |
72
+ | 0.1124 | 32.5 | 260 | 15.2738 |
73
+ | 0.1011 | 33.75 | 270 | 15.2130 |
74
+ | 0.0845 | 35.0 | 280 | 15.2749 |
75
+ | 0.0852 | 36.25 | 290 | 15.3292 |
76
+ | 0.1025 | 37.5 | 300 | 15.1574 |
77
+ | 0.1075 | 38.75 | 310 | 15.1100 |
78
+ | 0.079 | 40.0 | 320 | 14.8177 |
79
+ | 0.0857 | 41.25 | 330 | 14.8609 |
80
+ | 0.0629 | 42.5 | 340 | 14.6443 |
81
+ | 0.0713 | 43.75 | 350 | 14.5514 |
82
+ | 0.0594 | 45.0 | 360 | 14.6032 |
83
+ | 0.0557 | 46.25 | 370 | 14.3489 |
84
+ | 0.0554 | 47.5 | 380 | 14.3289 |
85
+ | 0.0548 | 48.75 | 390 | 14.1991 |
86
+ | 0.0528 | 50.0 | 400 | 14.1350 |
87
+ | 0.0515 | 51.25 | 410 | 13.9952 |
88
+ | 0.0529 | 52.5 | 420 | 13.9788 |
89
+ | 0.0516 | 53.75 | 430 | 13.9438 |
90
+ | 0.0506 | 55.0 | 440 | 13.8746 |
91
+ | 0.049 | 56.25 | 450 | 13.7564 |
92
+ | 0.0491 | 57.5 | 460 | 13.7900 |
93
+ | 0.0493 | 58.75 | 470 | 13.6992 |
94
+ | 0.0491 | 60.0 | 480 | 13.6421 |
95
+ | 0.0497 | 61.25 | 490 | 13.6419 |
96
+ | 0.0489 | 62.5 | 500 | 13.5448 |
97
+ | 0.0504 | 63.75 | 510 | 13.5048 |
98
+ | 0.0508 | 65.0 | 520 | 13.5077 |
99
+ | 0.0488 | 66.25 | 530 | 13.5045 |
100
+ | 0.0485 | 67.5 | 540 | 13.4404 |
101
+ | 0.0493 | 68.75 | 550 | 13.4167 |
102
+ | 0.0507 | 70.0 | 560 | 13.3758 |
103
+ | 0.0491 | 71.25 | 570 | 13.3239 |
104
+ | 0.0484 | 72.5 | 580 | 13.3139 |
105
+ | 0.0472 | 73.75 | 590 | 13.2933 |
106
+ | 0.0493 | 75.0 | 600 | 13.3105 |
107
+ | 0.0475 | 76.25 | 610 | 13.2306 |
108
+ | 0.0465 | 77.5 | 620 | 13.2378 |
109
+ | 0.0474 | 78.75 | 630 | 13.2074 |
110
+ | 0.0468 | 80.0 | 640 | 13.1871 |
111
+ | 0.0466 | 81.25 | 650 | 13.2055 |
112
+ | 0.0459 | 82.5 | 660 | 13.1327 |
113
+ | 0.0466 | 83.75 | 670 | 13.1801 |
114
+ | 0.0485 | 85.0 | 680 | 13.1610 |
115
+ | 0.046 | 86.25 | 690 | 13.1439 |
116
+ | 0.0467 | 87.5 | 700 | 13.1114 |
117
+ | 0.0455 | 88.75 | 710 | 13.1123 |
118
+ | 0.0456 | 90.0 | 720 | 13.0635 |
119
+ | 0.0447 | 91.25 | 730 | 13.0997 |
120
+ | 0.0449 | 92.5 | 740 | 13.0704 |
121
+ | 0.0453 | 93.75 | 750 | 13.0531 |
122
+ | 0.0451 | 95.0 | 760 | 13.0432 |
123
+ | 0.0442 | 96.25 | 770 | 13.0311 |
124
+ | 0.0444 | 97.5 | 780 | 13.0329 |
125
+ | 0.0432 | 98.75 | 790 | 13.0491 |
126
+ | 0.0442 | 100.0 | 800 | 13.0221 |
127
+
128
+
129
  ### Framework versions
130
 
131
  - Transformers 4.39.1