End of training
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -50,170 +50,165 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:------:|:-----:|:---------------:|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
-
| 0.
|
93 |
-
| 0.
|
94 |
-
| 0.
|
95 |
-
| 0.
|
96 |
-
| 0.
|
97 |
-
| 0.
|
98 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
-
| 0.
|
106 |
-
| 0.
|
107 |
-
| 0.
|
108 |
-
| 0.
|
109 |
-
| 0.
|
110 |
-
| 0.
|
111 |
-
| 0.
|
112 |
-
| 0.
|
113 |
-
| 0.
|
114 |
-
| 0.
|
115 |
-
| 0.
|
116 |
-
| 0.
|
117 |
-
| 0.
|
118 |
-
| 0.
|
119 |
-
| 0.
|
120 |
-
| 0.
|
121 |
-
| 0.
|
122 |
-
| 0.
|
123 |
-
| 0.
|
124 |
-
| 0.
|
125 |
-
| 0.
|
126 |
-
| 0.
|
127 |
-
| 0.
|
128 |
-
| 0.
|
129 |
-
| 0.
|
130 |
-
| 0.
|
131 |
-
| 0.
|
132 |
-
| 0.
|
133 |
-
| 0.
|
134 |
-
| 0.
|
135 |
-
| 0.
|
136 |
-
| 0.
|
137 |
-
| 0.
|
138 |
-
| 0.
|
139 |
-
| 0.
|
140 |
-
| 0.
|
141 |
-
| 0.
|
142 |
-
| 0.
|
143 |
-
| 0.
|
144 |
-
| 0.
|
145 |
-
| 0.
|
146 |
-
| 0.
|
147 |
-
| 0.
|
148 |
-
| 0.
|
149 |
-
| 0.
|
150 |
-
| 0.
|
151 |
-
| 0.
|
152 |
-
| 0.
|
153 |
-
| 0.
|
154 |
-
| 0.
|
155 |
-
| 0.
|
156 |
-
| 0.
|
157 |
-
| 0.
|
158 |
-
| 0.
|
159 |
-
| 0.
|
160 |
-
| 0.
|
161 |
-
| 0.
|
162 |
-
| 0.
|
163 |
-
| 0.
|
164 |
-
| 0.
|
165 |
-
| 0.
|
166 |
-
| 0.
|
167 |
-
| 0.
|
168 |
-
| 0.
|
169 |
-
| 0.
|
170 |
-
| 0.
|
171 |
-
| 0.
|
172 |
-
| 0.
|
173 |
-
| 0.
|
174 |
-
| 0.
|
175 |
-
| 0.
|
176 |
-
| 0.
|
177 |
-
| 0.
|
178 |
-
| 0.
|
179 |
-
| 0.
|
180 |
-
| 0.
|
181 |
-
| 0.
|
182 |
-
| 0.
|
183 |
-
| 0.
|
184 |
-
| 0.
|
185 |
-
| 0.
|
186 |
-
| 0.
|
187 |
-
| 0.
|
188 |
-
| 0.
|
189 |
-
| 0.
|
190 |
-
| 0.
|
191 |
-
| 0.
|
192 |
-
| 0.
|
193 |
-
| 0.
|
194 |
-
| 0.
|
195 |
-
| 0.
|
196 |
-
| 0.
|
197 |
-
| 0.
|
198 |
-
| 0.
|
199 |
-
| 0.
|
200 |
-
| 0.
|
201 |
-
| 0.
|
202 |
-
| 0.
|
203 |
-
| 0.
|
204 |
-
| 0.
|
205 |
-
| 0.
|
206 |
-
| 0.1116 | 3.9577 | 22650 | 0.2963 |
|
207 |
-
| 0.1176 | 3.9665 | 22700 | 0.2963 |
|
208 |
-
| 0.117 | 3.9752 | 22750 | 0.2961 |
|
209 |
-
| 0.1287 | 3.9839 | 22800 | 0.2962 |
|
210 |
-
| 0.1162 | 3.9927 | 22850 | 0.2962 |
|
211 |
|
212 |
|
213 |
### Framework versions
|
214 |
|
215 |
-
- PEFT 0.
|
216 |
-
- Transformers 4.
|
217 |
- Pytorch 2.3.1+cu121
|
218 |
- Datasets 2.20.0
|
219 |
- Tokenizers 0.19.1
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2781
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:------:|:-----:|:---------------:|
|
53 |
+
| 0.1903 | 2.5238 | 13000 | 0.2652 |
|
54 |
+
| 0.1723 | 2.5335 | 13050 | 0.2645 |
|
55 |
+
| 0.17 | 2.5432 | 13100 | 0.2640 |
|
56 |
+
| 0.1681 | 2.5529 | 13150 | 0.2656 |
|
57 |
+
| 0.1865 | 2.5626 | 13200 | 0.2655 |
|
58 |
+
| 0.1855 | 2.5723 | 13250 | 0.2640 |
|
59 |
+
| 0.1657 | 2.5820 | 13300 | 0.2664 |
|
60 |
+
| 0.197 | 2.5917 | 13350 | 0.2621 |
|
61 |
+
| 0.1912 | 2.6014 | 13400 | 0.2645 |
|
62 |
+
| 0.1787 | 2.6111 | 13450 | 0.2605 |
|
63 |
+
| 0.2003 | 2.6209 | 13500 | 0.2609 |
|
64 |
+
| 0.1812 | 2.6306 | 13550 | 0.2631 |
|
65 |
+
| 0.1964 | 2.6403 | 13600 | 0.2630 |
|
66 |
+
| 0.1774 | 2.6500 | 13650 | 0.2626 |
|
67 |
+
| 0.1907 | 2.6597 | 13700 | 0.2615 |
|
68 |
+
| 0.1835 | 2.6694 | 13750 | 0.2610 |
|
69 |
+
| 0.1812 | 2.6791 | 13800 | 0.2620 |
|
70 |
+
| 0.1778 | 2.6888 | 13850 | 0.2636 |
|
71 |
+
| 0.1738 | 2.6985 | 13900 | 0.2624 |
|
72 |
+
| 0.1795 | 2.7082 | 13950 | 0.2644 |
|
73 |
+
| 0.1773 | 2.7179 | 14000 | 0.2619 |
|
74 |
+
| 0.1951 | 2.7276 | 14050 | 0.2594 |
|
75 |
+
| 0.178 | 2.7373 | 14100 | 0.2609 |
|
76 |
+
| 0.1711 | 2.7470 | 14150 | 0.2620 |
|
77 |
+
| 0.1712 | 2.7567 | 14200 | 0.2617 |
|
78 |
+
| 0.1762 | 2.7665 | 14250 | 0.2620 |
|
79 |
+
| 0.1893 | 2.7762 | 14300 | 0.2612 |
|
80 |
+
| 0.1715 | 2.7859 | 14350 | 0.2625 |
|
81 |
+
| 0.166 | 2.7956 | 14400 | 0.2615 |
|
82 |
+
| 0.1771 | 2.8053 | 14450 | 0.2618 |
|
83 |
+
| 0.16 | 2.8150 | 14500 | 0.2614 |
|
84 |
+
| 0.1754 | 2.8247 | 14550 | 0.2603 |
|
85 |
+
| 0.1677 | 2.8344 | 14600 | 0.2610 |
|
86 |
+
| 0.1828 | 2.8441 | 14650 | 0.2610 |
|
87 |
+
| 0.1708 | 2.8538 | 14700 | 0.2606 |
|
88 |
+
| 0.1853 | 2.8635 | 14750 | 0.2582 |
|
89 |
+
| 0.1823 | 2.8732 | 14800 | 0.2601 |
|
90 |
+
| 0.1863 | 2.8829 | 14850 | 0.2601 |
|
91 |
+
| 0.182 | 2.8926 | 14900 | 0.2598 |
|
92 |
+
| 0.1874 | 2.9023 | 14950 | 0.2590 |
|
93 |
+
| 0.1813 | 2.9121 | 15000 | 0.2587 |
|
94 |
+
| 0.1803 | 2.9218 | 15050 | 0.2577 |
|
95 |
+
| 0.1652 | 2.9315 | 15100 | 0.2596 |
|
96 |
+
| 0.2131 | 2.9412 | 15150 | 0.2586 |
|
97 |
+
| 0.1699 | 2.9509 | 15200 | 0.2579 |
|
98 |
+
| 0.175 | 2.9606 | 15250 | 0.2575 |
|
99 |
+
| 0.1604 | 2.9703 | 15300 | 0.2588 |
|
100 |
+
| 0.191 | 2.9800 | 15350 | 0.2575 |
|
101 |
+
| 0.1911 | 2.9897 | 15400 | 0.2584 |
|
102 |
+
| 0.1945 | 2.9994 | 15450 | 0.2564 |
|
103 |
+
| 0.1149 | 3.0091 | 15500 | 0.2782 |
|
104 |
+
| 0.1198 | 3.0188 | 15550 | 0.2785 |
|
105 |
+
| 0.137 | 3.0285 | 15600 | 0.2770 |
|
106 |
+
| 0.1292 | 3.0382 | 15650 | 0.2778 |
|
107 |
+
| 0.1227 | 3.0480 | 15700 | 0.2814 |
|
108 |
+
| 0.1349 | 3.0577 | 15750 | 0.2810 |
|
109 |
+
| 0.117 | 3.0674 | 15800 | 0.2815 |
|
110 |
+
| 0.13 | 3.0771 | 15850 | 0.2790 |
|
111 |
+
| 0.1297 | 3.0868 | 15900 | 0.2788 |
|
112 |
+
| 0.1238 | 3.0965 | 15950 | 0.2799 |
|
113 |
+
| 0.1303 | 3.1062 | 16000 | 0.2792 |
|
114 |
+
| 0.1259 | 3.1159 | 16050 | 0.2799 |
|
115 |
+
| 0.1217 | 3.1256 | 16100 | 0.2807 |
|
116 |
+
| 0.1268 | 3.1353 | 16150 | 0.2825 |
|
117 |
+
| 0.1201 | 3.1450 | 16200 | 0.2788 |
|
118 |
+
| 0.1363 | 3.1547 | 16250 | 0.2795 |
|
119 |
+
| 0.1108 | 3.1644 | 16300 | 0.2817 |
|
120 |
+
| 0.1227 | 3.1741 | 16350 | 0.2798 |
|
121 |
+
| 0.1397 | 3.1838 | 16400 | 0.2808 |
|
122 |
+
| 0.1193 | 3.1936 | 16450 | 0.2788 |
|
123 |
+
| 0.1257 | 3.2033 | 16500 | 0.2807 |
|
124 |
+
| 0.1279 | 3.2130 | 16550 | 0.2805 |
|
125 |
+
| 0.1148 | 3.2227 | 16600 | 0.2794 |
|
126 |
+
| 0.1323 | 3.2324 | 16650 | 0.2810 |
|
127 |
+
| 0.112 | 3.2421 | 16700 | 0.2802 |
|
128 |
+
| 0.1369 | 3.2518 | 16750 | 0.2799 |
|
129 |
+
| 0.1109 | 3.2615 | 16800 | 0.2823 |
|
130 |
+
| 0.1188 | 3.2712 | 16850 | 0.2813 |
|
131 |
+
| 0.1211 | 3.2809 | 16900 | 0.2804 |
|
132 |
+
| 0.1256 | 3.2906 | 16950 | 0.2820 |
|
133 |
+
| 0.1215 | 3.3003 | 17000 | 0.2819 |
|
134 |
+
| 0.1241 | 3.3100 | 17050 | 0.2804 |
|
135 |
+
| 0.121 | 3.3197 | 17100 | 0.2813 |
|
136 |
+
| 0.1207 | 3.3295 | 17150 | 0.2803 |
|
137 |
+
| 0.1241 | 3.3392 | 17200 | 0.2794 |
|
138 |
+
| 0.1115 | 3.3489 | 17250 | 0.2810 |
|
139 |
+
| 0.1113 | 3.3586 | 17300 | 0.2804 |
|
140 |
+
| 0.13 | 3.3683 | 17350 | 0.2805 |
|
141 |
+
| 0.1202 | 3.3780 | 17400 | 0.2796 |
|
142 |
+
| 0.1322 | 3.3877 | 17450 | 0.2798 |
|
143 |
+
| 0.127 | 3.3974 | 17500 | 0.2793 |
|
144 |
+
| 0.1272 | 3.4071 | 17550 | 0.2783 |
|
145 |
+
| 0.1251 | 3.4168 | 17600 | 0.2811 |
|
146 |
+
| 0.1229 | 3.4265 | 17650 | 0.2814 |
|
147 |
+
| 0.122 | 3.4362 | 17700 | 0.2800 |
|
148 |
+
| 0.1246 | 3.4459 | 17750 | 0.2793 |
|
149 |
+
| 0.1113 | 3.4556 | 17800 | 0.2801 |
|
150 |
+
| 0.1229 | 3.4653 | 17850 | 0.2799 |
|
151 |
+
| 0.1246 | 3.4751 | 17900 | 0.2792 |
|
152 |
+
| 0.1217 | 3.4848 | 17950 | 0.2798 |
|
153 |
+
| 0.1129 | 3.4945 | 18000 | 0.2791 |
|
154 |
+
| 0.1234 | 3.5042 | 18050 | 0.2793 |
|
155 |
+
| 0.1187 | 3.5139 | 18100 | 0.2801 |
|
156 |
+
| 0.1239 | 3.5236 | 18150 | 0.2798 |
|
157 |
+
| 0.1134 | 3.5333 | 18200 | 0.2795 |
|
158 |
+
| 0.1307 | 3.5430 | 18250 | 0.2787 |
|
159 |
+
| 0.1232 | 3.5527 | 18300 | 0.2798 |
|
160 |
+
| 0.1271 | 3.5624 | 18350 | 0.2795 |
|
161 |
+
| 0.1176 | 3.5721 | 18400 | 0.2803 |
|
162 |
+
| 0.1273 | 3.5818 | 18450 | 0.2775 |
|
163 |
+
| 0.1186 | 3.5915 | 18500 | 0.2794 |
|
164 |
+
| 0.1267 | 3.6012 | 18550 | 0.2786 |
|
165 |
+
| 0.1316 | 3.6109 | 18600 | 0.2789 |
|
166 |
+
| 0.1132 | 3.6207 | 18650 | 0.2801 |
|
167 |
+
| 0.1292 | 3.6304 | 18700 | 0.2787 |
|
168 |
+
| 0.1211 | 3.6401 | 18750 | 0.2798 |
|
169 |
+
| 0.126 | 3.6498 | 18800 | 0.2796 |
|
170 |
+
| 0.1074 | 3.6595 | 18850 | 0.2781 |
|
171 |
+
| 0.1399 | 3.6692 | 18900 | 0.2779 |
|
172 |
+
| 0.1216 | 3.6789 | 18950 | 0.2775 |
|
173 |
+
| 0.1232 | 3.6886 | 19000 | 0.2780 |
|
174 |
+
| 0.1357 | 3.6983 | 19050 | 0.2796 |
|
175 |
+
| 0.1174 | 3.7080 | 19100 | 0.2792 |
|
176 |
+
| 0.1312 | 3.7177 | 19150 | 0.2790 |
|
177 |
+
| 0.1213 | 3.7274 | 19200 | 0.2794 |
|
178 |
+
| 0.1233 | 3.7371 | 19250 | 0.2789 |
|
179 |
+
| 0.1156 | 3.7468 | 19300 | 0.2794 |
|
180 |
+
| 0.1074 | 3.7566 | 19350 | 0.2785 |
|
181 |
+
| 0.125 | 3.7663 | 19400 | 0.2784 |
|
182 |
+
| 0.1151 | 3.7760 | 19450 | 0.2785 |
|
183 |
+
| 0.1237 | 3.7857 | 19500 | 0.2782 |
|
184 |
+
| 0.1158 | 3.7954 | 19550 | 0.2773 |
|
185 |
+
| 0.1193 | 3.8051 | 19600 | 0.2774 |
|
186 |
+
| 0.128 | 3.8148 | 19650 | 0.2770 |
|
187 |
+
| 0.1069 | 3.8245 | 19700 | 0.2775 |
|
188 |
+
| 0.1137 | 3.8342 | 19750 | 0.2778 |
|
189 |
+
| 0.1183 | 3.8439 | 19800 | 0.2784 |
|
190 |
+
| 0.1077 | 3.8536 | 19850 | 0.2780 |
|
191 |
+
| 0.1297 | 3.8633 | 19900 | 0.2775 |
|
192 |
+
| 0.1202 | 3.8730 | 19950 | 0.2776 |
|
193 |
+
| 0.1278 | 3.8827 | 20000 | 0.2772 |
|
194 |
+
| 0.1182 | 3.8924 | 20050 | 0.2769 |
|
195 |
+
| 0.1265 | 3.9022 | 20100 | 0.2772 |
|
196 |
+
| 0.1169 | 3.9119 | 20150 | 0.2774 |
|
197 |
+
| 0.1191 | 3.9216 | 20200 | 0.2776 |
|
198 |
+
| 0.1115 | 3.9313 | 20250 | 0.2777 |
|
199 |
+
| 0.1257 | 3.9410 | 20300 | 0.2777 |
|
200 |
+
| 0.1134 | 3.9507 | 20350 | 0.2781 |
|
201 |
+
| 0.1243 | 3.9604 | 20400 | 0.2780 |
|
202 |
+
| 0.1183 | 3.9701 | 20450 | 0.2781 |
|
203 |
+
| 0.1189 | 3.9798 | 20500 | 0.2781 |
|
204 |
+
| 0.117 | 3.9895 | 20550 | 0.2781 |
|
205 |
+
| 0.1205 | 3.9992 | 20600 | 0.2781 |
|
|
|
|
|
|
|
|
|
|
|
206 |
|
207 |
|
208 |
### Framework versions
|
209 |
|
210 |
+
- PEFT 0.12.0
|
211 |
+
- Transformers 4.43.3
|
212 |
- Pytorch 2.3.1+cu121
|
213 |
- Datasets 2.20.0
|
214 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"up_proj",
|
24 |
-
"v_proj",
|
25 |
-
"q_proj",
|
26 |
"gate_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
"up_proj",
|
|
|
|
|
25 |
"gate_proj",
|
26 |
+
"down_proj",
|
27 |
+
"q_proj",
|
28 |
+
"v_proj",
|
29 |
+
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2332095256
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3b83ee894a2bca96d429a6699918b73f22a461e3c0559612dbad771eaa6185e
|
3 |
size 2332095256
|
runs/Jul31_14-05-10_25b61540014e/events.out.tfevents.1722434716.25b61540014e.8616.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b2483564639e8b3c677468c2d3d14351350754a141cc23472bff30575589e2a
|
3 |
+
size 135360
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49b4f336a6f82a0429db4904b266884f8b7a0df2872893eaff9770497230d52e
|
3 |
+
size 5496
|