Hugging Face's logo

zorooo
/
MathLlama-7b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
zorooo commited on
Commit
35a9645
·
verified ·
1 Parent(s): 9dbd9ac

End of training

Browse files
Files changed (2) hide show
  1. README.md +19 -19
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -96,7 +96,7 @@ special_tokens:
96
 
97
  This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
98
  It achieves the following results on the evaluation set:
99
- - Loss: 0.1580
100
 
101
  ## Model description
102
 
@@ -130,24 +130,24 @@ The following hyperparameters were used during training:
130
 
131
  | Training Loss | Epoch | Step | Validation Loss |
132
  |:-------------:|:-----:|:----:|:---------------:|
133
- | 0.952 | 0.04 | 1 | 0.9490 |
134
- | 0.9351 | 0.27 | 7 | 0.9474 |
135
- | 0.9431 | 0.54 | 14 | 0.9181 |
136
- | 0.8078 | 0.82 | 21 | 0.7671 |
137
- | 0.5693 | 1.06 | 28 | 0.5249 |
138
- | 0.309 | 1.33 | 35 | 0.3288 |
139
- | 0.2752 | 1.6 | 42 | 0.2607 |
140
- | 0.2406 | 1.87 | 49 | 0.2267 |
141
- | 0.2241 | 2.12 | 56 | 0.2068 |
142
- | 0.2212 | 2.39 | 63 | 0.1932 |
143
- | 0.1991 | 2.66 | 70 | 0.1842 |
144
- | 0.173 | 2.93 | 77 | 0.1738 |
145
- | 0.162 | 3.18 | 84 | 0.1711 |
146
- | 0.1357 | 3.46 | 91 | 0.1681 |
147
- | 0.15 | 3.73 | 98 | 0.1664 |
148
- | 0.1553 | 4.0 | 105 | 0.1610 |
149
- | 0.1263 | 4.25 | 112 | 0.1613 |
150
- | 0.132 | 4.52 | 119 | 0.1580 |
151
 
152
 
153
  ### Framework versions
 
96
 
97
  This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
98
  It achieves the following results on the evaluation set:
99
+ - Loss: 0.1702
100
 
101
  ## Model description
102
 
 
130
 
131
  | Training Loss | Epoch | Step | Validation Loss |
132
  |:-------------:|:-----:|:----:|:---------------:|
133
+ | 0.1242 | 0.04 | 1 | 0.1574 |
134
+ | 0.1265 | 0.27 | 7 | 0.1573 |
135
+ | 0.1644 | 0.54 | 14 | 0.1574 |
136
+ | 0.1213 | 0.82 | 21 | 0.1566 |
137
+ | 0.1219 | 1.06 | 28 | 0.1560 |
138
+ | 0.111 | 1.33 | 35 | 0.1577 |
139
+ | 0.1289 | 1.6 | 42 | 0.1562 |
140
+ | 0.1241 | 1.87 | 49 | 0.1551 |
141
+ | 0.1254 | 2.12 | 56 | 0.1592 |
142
+ | 0.1376 | 2.39 | 63 | 0.1646 |
143
+ | 0.132 | 2.66 | 70 | 0.1611 |
144
+ | 0.1165 | 2.93 | 77 | 0.1568 |
145
+ | 0.1047 | 3.18 | 84 | 0.1698 |
146
+ | 0.0918 | 3.46 | 91 | 0.1717 |
147
+ | 0.1022 | 3.73 | 98 | 0.1677 |
148
+ | 0.1136 | 4.0 | 105 | 0.1661 |
149
+ | 0.0856 | 4.25 | 112 | 0.1733 |
150
+ | 0.0834 | 4.52 | 119 | 0.1702 |
151
 
152
 
153
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86bec5f50e37d656eb95c891a2db9c1b17734b0a7a88522e1175d69ea92f8372
3
  size 319977229
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac440d689373674d45738935fe284133dfd4ccc6aa7baf2b8097abb7efb4dc8
3
  size 319977229