Hugging Face's logo

dafrimi
/
starcoderbase7b_2048_context_length_lr_0.0005

Safetensors
gpt_bigcode
Generated from Trainer
Model card Files Community
dafrimi commited on
Commit
e1873da
·
verified ·
1 Parent(s): 60d9922

End of training

Browse files
Files changed (2) hide show
  1. README.md +84 -24
  2. generation_config.json +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bigcode/starcoderbase-7b](https://huggingface.co/bigcode/starcoderbase-7b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.8933
19
 
20
  ## Model description
21
 
@@ -50,33 +50,93 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Validation Loss |
54
- |:-------------:|:-----:|:----:|:---------------:|
55
- | 0.7067 | 0.05 | 100 | 0.7675 |
56
- | 0.4933 | 0.1 | 200 | 0.6368 |
57
- | 0.3121 | 0.15 | 300 | 0.6059 |
58
- | 0.2769 | 0.2 | 400 | 0.6548 |
59
- | 0.206 | 0.25 | 500 | 0.7635 |
60
- | 0.1528 | 0.3 | 600 | 0.6882 |
61
- | 0.1119 | 0.35 | 700 | 0.6780 |
62
- | 0.1059 | 0.4 | 800 | 0.7212 |
63
- | 0.0933 | 0.45 | 900 | 0.6975 |
64
- | 0.0652 | 0.5 | 1000 | 0.7074 |
65
- | 0.0556 | 0.55 | 1100 | 0.7506 |
66
- | 0.0432 | 0.6 | 1200 | 0.7520 |
67
- | 0.0414 | 0.65 | 1300 | 0.7630 |
68
- | 0.0475 | 0.7 | 1400 | 0.7558 |
69
- | 0.0332 | 0.75 | 1500 | 0.8318 |
70
- | 0.0307 | 0.8 | 1600 | 0.8102 |
71
- | 0.0283 | 0.85 | 1700 | 0.8601 |
72
- | 0.0267 | 0.9 | 1800 | 0.8806 |
73
- | 0.0269 | 0.95 | 1900 | 0.8876 |
74
- | 0.0272 | 1.0 | 2000 | 0.8933 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.43.3
80
  - Pytorch 2.4.0a0+07cecf4168.nv24.05
81
  - Datasets 2.20.0
82
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [bigcode/starcoderbase-7b](https://huggingface.co/bigcode/starcoderbase-7b) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.0501
19
 
20
  ## Model description
21
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 0.6244 | 0.0125 | 25 | 0.5402 |
56
+ | 1.0172 | 0.025 | 50 | 1.4486 |
57
+ | 0.9991 | 0.0375 | 75 | 1.0535 |
58
+ | 0.715 | 0.05 | 100 | 1.6262 |
59
+ | 0.6957 | 0.0625 | 125 | 0.6796 |
60
+ | 0.5182 | 0.075 | 150 | 0.6086 |
61
+ | 0.497 | 0.0875 | 175 | 0.5938 |
62
+ | 0.4611 | 0.1 | 200 | 0.6104 |
63
+ | 0.4046 | 0.1125 | 225 | 0.5857 |
64
+ | 0.3753 | 0.125 | 250 | 0.6633 |
65
+ | 0.3517 | 0.1375 | 275 | 0.6479 |
66
+ | 0.2758 | 0.15 | 300 | 0.5788 |
67
+ | 0.2928 | 0.1625 | 325 | 0.6429 |
68
+ | 0.2669 | 0.175 | 350 | 0.5874 |
69
+ | 0.2608 | 0.1875 | 375 | 0.5497 |
70
+ | 0.2049 | 0.2 | 400 | 0.6268 |
71
+ | 0.2006 | 0.2125 | 425 | 0.6265 |
72
+ | 0.197 | 0.225 | 450 | 0.6236 |
73
+ | 0.177 | 0.2375 | 475 | 0.6124 |
74
+ | 0.1774 | 0.25 | 500 | 0.6231 |
75
+ | 0.1509 | 0.2625 | 525 | 0.5864 |
76
+ | 0.1389 | 0.275 | 550 | 0.6161 |
77
+ | 0.8679 | 0.2875 | 575 | 11.4657 |
78
+ | 6.5575 | 0.3 | 600 | 6.4917 |
79
+ | 6.0031 | 0.3125 | 625 | 5.5229 |
80
+ | 5.1391 | 0.325 | 650 | 5.2191 |
81
+ | 4.4917 | 0.3375 | 675 | 4.6562 |
82
+ | 3.9199 | 0.35 | 700 | 4.2153 |
83
+ | 3.855 | 0.3625 | 725 | 4.0902 |
84
+ | 3.5441 | 0.375 | 750 | 4.0601 |
85
+ | 3.3835 | 0.3875 | 775 | 3.8844 |
86
+ | 3.1663 | 0.4 | 800 | 3.8223 |
87
+ | 2.9285 | 0.4125 | 825 | 3.4541 |
88
+ | 3.0088 | 0.425 | 850 | 3.5302 |
89
+ | 2.9083 | 0.4375 | 875 | 3.3347 |
90
+ | 2.8438 | 0.45 | 900 | 3.3962 |
91
+ | 2.663 | 0.4625 | 925 | 3.0955 |
92
+ | 2.5084 | 0.475 | 950 | 3.0454 |
93
+ | 2.5818 | 0.4875 | 975 | 3.0131 |
94
+ | 2.4068 | 0.5 | 1000 | 3.0179 |
95
+ | 2.3994 | 0.5125 | 1025 | 2.8273 |
96
+ | 2.1942 | 0.525 | 1050 | 2.7333 |
97
+ | 2.1041 | 0.5375 | 1075 | 2.6163 |
98
+ | 2.0861 | 0.55 | 1100 | 2.6006 |
99
+ | 1.9868 | 0.5625 | 1125 | 2.5482 |
100
+ | 1.9496 | 0.575 | 1150 | 2.6079 |
101
+ | 1.8099 | 0.5875 | 1175 | 2.3777 |
102
+ | 1.6454 | 0.6 | 1200 | 2.2547 |
103
+ | 1.6484 | 0.6125 | 1225 | 2.3254 |
104
+ | 1.5729 | 0.625 | 1250 | 2.2835 |
105
+ | 1.5635 | 0.6375 | 1275 | 2.2167 |
106
+ | 1.3961 | 0.65 | 1300 | 2.2751 |
107
+ | 1.3495 | 0.6625 | 1325 | 2.1755 |
108
+ | 1.3524 | 0.675 | 1350 | 2.1377 |
109
+ | 1.3116 | 0.6875 | 1375 | 2.1407 |
110
+ | 1.282 | 0.7 | 1400 | 2.0955 |
111
+ | 1.114 | 0.7125 | 1425 | 2.0334 |
112
+ | 1.0985 | 0.725 | 1450 | 2.0133 |
113
+ | 1.1216 | 0.7375 | 1475 | 2.0139 |
114
+ | 1.0544 | 0.75 | 1500 | 2.0464 |
115
+ | 1.0221 | 0.7625 | 1525 | 1.9984 |
116
+ | 0.9368 | 0.775 | 1550 | 2.0069 |
117
+ | 0.8973 | 0.7875 | 1575 | 1.9595 |
118
+ | 0.9332 | 0.8 | 1600 | 1.9372 |
119
+ | 0.9227 | 0.8125 | 1625 | 1.9910 |
120
+ | 0.8507 | 0.825 | 1650 | 2.0251 |
121
+ | 0.8242 | 0.8375 | 1675 | 1.9892 |
122
+ | 0.7571 | 0.85 | 1700 | 2.0327 |
123
+ | 0.7519 | 0.8625 | 1725 | 1.9949 |
124
+ | 0.7209 | 0.875 | 1750 | 2.0050 |
125
+ | 0.7315 | 0.8875 | 1775 | 2.0076 |
126
+ | 0.77 | 0.9 | 1800 | 2.0315 |
127
+ | 0.7719 | 0.9125 | 1825 | 2.0241 |
128
+ | 0.681 | 0.925 | 1850 | 2.0440 |
129
+ | 0.7371 | 0.9375 | 1875 | 2.0380 |
130
+ | 0.6823 | 0.95 | 1900 | 2.0392 |
131
+ | 0.6891 | 0.9625 | 1925 | 2.0563 |
132
+ | 0.7266 | 0.975 | 1950 | 2.0511 |
133
+ | 0.6888 | 0.9875 | 1975 | 2.0501 |
134
+ | 0.6663 | 1.0 | 2000 | 2.0501 |
135
 
136
 
137
  ### Framework versions
138
 
139
+ - Transformers 4.44.0
140
  - Pytorch 2.4.0a0+07cecf4168.nv24.05
141
  - Datasets 2.20.0
142
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
- "transformers_version": "4.43.3"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
+ "transformers_version": "4.44.0"
6
  }